Publications

2022

MoCapAct: A Multi-Task Dataset for Simulated Humanoid Control
Neural Information Processing Systems (NeurIPS) Datasets and Benchmarks Track, 2022
N. Wagener, A. Kolobov, F. V. Frujeri, R. Loynd, C.-A. Cheng, and M. Hausknecht
[TL;DR]  [BibTeX]  [arXiv]  [Website]  [Blog]  [Code]  [Dataset]  [Talk]  [Poster]  [Slides] 

BibTeX

@inproceedings{wagener2022mocapact,
    author = "Wagener, Nolan and Kolobov, Andrey and Frujeri, Felipe Vieira and Loynd, Ricky and Cheng, Ching-An and Hausknecht, Matthew",
    title = "{MoCapAct: A Multi-Task Dataset for Simulated Humanoid Control}",
    booktitle = "Neural Information Processing Systems ({NeurIPS}) Datasets and Benchmarks Track",
    year = "2022"
}

TR;DR

We release a dataset of high-quality experts and their rollouts for tracking 3.5 hours of MoCap data in dm_control. We use this dataset to train policies that can track the entire dataset, efficiently transfer to other tasks, and perform physics-based motion completion.

Motion Policy Networks
Conference on Robot Learning (CoRL), 2022
A. Fishman, A. Murali, C. Eppner, B. Peele, B. Boots, and D. Fox
[BibTeX]  [Website]  [Code] 

BibTeX

@inproceedings{Fishman-CORL-22,
    author = "Fishman, Adam and Murali, Adithyavairavan and Eppner, Clemens and Peele, Bryan and Boots, Byron and Fox, Dieter",
    booktitle = "Conference on Robot Learning ({CoRL})",
    title = "{Motion Policy Networks}",
    year = "2022"
}

TR;DR

Learning Semantics-Aware Locomotion Skills from Human Demonstration
Conference on Robot Learning (CoRL), 2022
Y. Yang, X. Meng, Wenhao, Yu, T. Zhang, J. Tan, and B. Boots
[BibTeX]  [arXiv]  [Website]  [Blog] 

BibTeX

@inproceedings{Yang-CORL-22,
    author = "Yang, Yuxiang and Meng, Xiangyun and Yu, Wenhao, and Zhang, Tingnan and Tan, Jie and Boots, Byron",
    booktitle = "Conference on Robot Learning ({CoRL})",
    title = "{Learning Semantics-Aware Locomotion Skills from Human Demonstration}",
    year = "2022",
    abstract = "The semantics of the environment, such as the terrain type and property, reveals important information for legged robots to adjust their behaviors. In this work, we present a framework that learns semantics-aware locomotion skills from perception for quadrupedal robots, such that the robot can traverse through complex offroad terrains with appropriate speeds and gaits using perception information. Due to the lack of high-fidelity outdoor simulation, our framework needs to be trained directly in the real world, which brings unique challenges in data efficiency and safety. To ensure sample efficiency, we pre-train the perception model with an off-road driving dataset. To avoid the risks of real-world policy exploration, we leverage human demonstration to train a speed policy that selects a desired forward speed from camera image. For maximum traversability, we pair the speed policy with a gait selector, which selects a robust locomotion gait for each forward speed. Using only 40 minutes of human demonstration data, our framework learns to adjust the speed and gait of the robot based on perceived terrain semantics, and enables the robot to walk over 6km without failure at close-to-optimal speed."
}

TR;DR

Learning Sampling Distributions for Model Predictive Control
Conference on Robot Learning (CoRL), 2022
Jacob, Sacks and B. Boots
[BibTeX] 

BibTeX

@inproceedings{Sacks-CORL-22,
    author = "Sacks, Jacob, and Boots, Byron",
    booktitle = "Conference on Robot Learning ({CoRL})",
    title = "{Learning Sampling Distributions for Model Predictive Control}",
    year = "2022"
}

TR;DR

Learning Implicit Priors for Motion Optimization
IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2022
J. Urain, A. T. Le, A. Lambert, G. Chalvatzaki, B. Boots, and J. Peters
[BibTeX] 

BibTeX

@inproceedings{Lambert-IROS-22,
    author = "Urain, Julen and Le, An T. and Lambert, Alexander and Chalvatzaki, Georgia and Boots, Byron and Peters, Jan",
    booktitle = "{IEEE/RSJ} International Conference on Intelligent Robots and Systems ({IROS})",
    title = "{Learning Implicit Priors for Motion Optimization}",
    year = "2022"
}

TR;DR

Learning Semantic-Aware Locomotion Skills from Human Demonstration
Multidisciplinary Conference on Reinforcement Learning and Decision Making (RLDM), 2022
Y. Yang, X. Meng, T. Zhang, J. Tan, and B. Boots
[BibTeX] 

BibTeX

@inproceedings{Yuxiang-RLDM-22,
    author = "Yang, Yuxiang and Meng, Xiangyun and Zhang, Tingnan and Tan, Jie and Boots, Byron",
    booktitle = "Multidisciplinary Conference on Reinforcement Learning and Decision Making ({RLDM})",
    title = "{Learning Semantic-Aware Locomotion Skills from Human Demonstration}",
    year = "2022"
}

TR;DR

Learning Sampling Distributions in Model Predictive Control
Multidisciplinary Conference on Reinforcement Learning and Decision Making (RLDM), 2022
J. Sacks and B. Boots
[BibTeX] 

BibTeX

@inproceedings{Sacks-RLDM-22b,
    author = "Sacks, Jacob and Boots, Byron",
    booktitle = "Multidisciplinary Conference on Reinforcement Learning and Decision Making ({RLDM})",
    title = "{Learning Sampling Distributions in Model Predictive Control}",
    year = "2022"
}

TR;DR

Learning to Optimize in Model Predictive Control
Multidisciplinary Conference on Reinforcement Learning and Decision Making (RLDM), 2022
J. Sacks and B. Boots
[BibTeX] 

BibTeX

@inproceedings{Sacks-RLDM-22a,
    author = "Sacks, Jacob and Boots, Byron",
    booktitle = "Multidisciplinary Conference on Reinforcement Learning and Decision Making ({RLDM})",
    title = "{Learning to Optimize in Model Predictive Control}",
    year = "2022"
}

TR;DR

Motion Policy Networks
Multidisciplinary Conference on Reinforcement Learning and Decision Making (RLDM), 2022
A. Fishman, A. Murali, C. Eppner, B. Peele, B. Boots, and D. Fox
[BibTeX] 

BibTeX

@inproceedings{Fishman-RLDM-22,
    author = "Fishman, Adam and Murali, Adithyavairavan and Eppner, Clemens and Peele, Bryan and Boots, Byron and Fox, Dieter",
    booktitle = "Multidisciplinary Conference on Reinforcement Learning and Decision Making ({RLDM})",
    title = "{Motion Policy Networks}",
    year = "2022"
}

TR;DR

Modular Policy Composition with Policy Centroids
Multidisciplinary Conference on Reinforcement Learning and Decision Making (RLDM), 2022
S. Adhikary and B. Boots
[BibTeX] 

BibTeX

@inproceedings{Adhikary-RLDM-22,
    author = "Adhikary, Sandesh and Boots, Byron",
    booktitle = "Multidisciplinary Conference on Reinforcement Learning and Decision Making ({RLDM})",
    title = "{Modular Policy Composition with Policy Centroids}",
    year = "2022"
}

TR;DR

Adversarial Sampling-Based Motion Planning
IEEE Robotics and Automation Letters (RA-L) (Presented at ICRA), 2022
H. Nichols, M. Jimenez, Z. Goddard, M. Sparapany, M. Boots, and A. Mazumdar
[BibTeX] 

BibTeX

@article{Nichols-RAL-22,
    author = "Nichols, Hayden and Jimenez, Mark and Goddard, Zachary and Sparapany, Michael and Boots, Michael and Mazumdar, Anirban",
    journal = "{IEEE} Robotics and Automation Letters ({RA-L}) (Presented at ICRA)",
    title = "{Adversarial Sampling-Based Motion Planning}",
    year = "2022"
}

TR;DR

Geometric Fabrics: Generalizing Classical Mechanics to Capture the Physics of Behavior
IEEE Robotics and Automation Letters (RA-L) (Presented at ICRA), 2022
K. Van Wyk, M. Xie, A. Li, M. Rana, B. Babich, B. Peele, Q. Wan, I. Akinola, B. Sundaralingam, D. Fox, B. Boots, and N. Ratliff
[BibTeX] 

BibTeX

@article{VanWyk-RAL-22,
    author = "Van Wyk, Karl and Xie, Man and Li, Anqi and Rana, Muhammad and Babich, Buck and Peele, Bryan and Wan, Qian and Akinola, Iretiayo and Sundaralingam, Balakumar and Fox, Dieter and Boots, Byron and Ratliff, Nathan",
    journal = "{IEEE} Robotics and Automation Letters ({RA-L}) (Presented at ICRA)",
    title = "{Geometric Fabrics: Generalizing Classical Mechanics to Capture the Physics of Behavior}",
    year = "2022"
}

TR;DR

Stein Variational Probabilistic Roadmaps
IEEE International Conference on Robotics and Automation (ICRA), 2022
A. Lambert, B. Hou, R. Scalise, S. Srinivasa, and B. Boots
[BibTeX]  [arXiv] 

BibTeX

@inproceedings{Lambert-ICRA-22,
    author = "Lambert, Alexander, and Hou, Brian and Scalise, Rosario and S. Srinivasa, Siddhartha and Boots, Byron",
    booktitle = "{IEEE} International Conference on Robotics and Automation ({ICRA})",
    title = "{Stein Variational Probabilistic Roadmaps}",
    year = "2022"
}

TR;DR

Learning to Optimize in Model Predictive Control
IEEE International Conference on Robotics and Automation (ICRA), 2022
J. Sacks and B. Boots
[BibTeX] 

BibTeX

@inproceedings{Sacks-ICRA-22,
    author = "Sacks, Jacob and Boots, Byron",
    booktitle = "{IEEE} International Conference on Robotics and Automation ({ICRA})",
    title = "{Learning to Optimize in Model Predictive Control}",
    year = "2022"
}

TR;DR

Sampling Over Riemannian Manifolds Using Kernel Herding
IEEE International Conference on Robotics and Automation (ICRA), 2022
S. Adhikary and B. Boots
[BibTeX] 

BibTeX

@inproceedings{Adhikary-ICRA-22,
    author = "Adhikary, Sandesh and Boots, Byron",
    booktitle = "{IEEE} International Conference on Robotics and Automation ({ICRA})",
    title = "{Sampling Over Riemannian Manifolds Using Kernel Herding}",
    year = "2022"
}

TR;DR

Few-shot Weakly-Supervised Object Detection via Directional Statistics
Winter Conference on Applications of Computer Vision (WACV), 2022
A. Shaban, A. Rahimi, T. Ajanthan, B. Boots, and R. Hartley
[BibTeX] 

BibTeX

@inproceedings{Shaban-WACV-22,
    author = "Shaban, Amirreza and Rahimi, Amir and Ajanthan, Thalaiyasingam and Boots, Byron and Hartley, Richard",
    booktitle = "Winter Conference on Applications of Computer Vision ({WACV})",
    title = "{Few-shot Weakly-Supervised Object Detection via Directional Statistics}",
    year = "2022"
}

TR;DR


2021

Towards a Trace-Preserving Tensor Network Representation of Quantum Channels
Workshop on Quantum Tensor Networks in Machine Learning (in conjunction with NeurIPS), 2021
S. Srinivasan, S. Adhikary, J. Miller, B. Pokharel, G. Rabusseau, and B. Boots
[BibTeX] 

BibTeX

@inproceedings{Srinivasan-QTNML-21,
    author = "Srinivasan, Siddarth and Adhikary, Sandesh and Miller, Jacob and Pokharel, Bibek and Rabusseau, Guillaume and Boots, Byron",
    booktitle = "Workshop on Quantum Tensor Networks in Machine Learning (in conjunction with NeurIPS)",
    title = "{Towards a Trace-Preserving Tensor Network Representation of Quantum Channels}",
    year = "2021"
}

TR;DR

Semantic Terrain Classification for Off-Road Autonomous Driving
Conference on Robot Learning (CoRL), 2021
A. Shaban*, X. Meng*, J. Lee*, B. Boots, and D. Fox
[BibTeX]  [Website] 

BibTeX

@inproceedings{Shaban-CORL-21,
    author = "Shaban, Amirreza and Meng, Xiangyun and Lee, JoonHo and Boots, Byron and Fox, Dieter",
    booktitle = "Conference on Robot Learning ({CoRL})",
    title = "{Semantic Terrain Classification for Off-Road Autonomous Driving}",
    year = "2021",
    abstract = "Producing dense and accurate traversability maps is crucial for autonomous off-road navigation. In this paper, we focus on the problem of classifying terrains into 4 cost classes (free, low-cost, medium-cost, obstacle) for traversability assessment. This requires a robot to reason about both semantics (what objects are present?) and geometric properties (where are the objects located?) of the environment. To achieve this goal, we develop a novel Bird's Eye View Network (BEVNet), a deep neural network that directly predicts a local map encoding terrain classes from sparse LiDAR inputs. BEVNet processes both geometric and semantic information in a temporally consistent fashion. More importantly, it uses learned prior and history to predict terrain classes in unseen space and into the future, allowing a robot to better appraise its situation. We quantitatively evaluate BEVNet on both on-road and off-road scenarios and show that it outperforms a variety of strong baselines."
}

TR;DR

Motivating Physical Activity via Competitive Human-Robot Interaction
Selected for Oral Presentation
Conference on Robot Learning (CoRL), 2021
B. Yang, G. Habibi, P. Lancaster, B. Boots, and J. Smith
[BibTeX] 

BibTeX

@inproceedings{Boling-CORL-21,
    author = "Yang, Boling and Habibi, Golnaz and Lancaster, Patrick and Boots, Byron and Smith, Joshua",
    booktitle = "Conference on Robot Learning ({CoRL})",
    title = "{Motivating Physical Activity via Competitive Human-Robot Interaction}",
    year = "2021",
    abstract = "This project aims to motivate research in competitive human-robot interaction by creating a robot competitor that can challenge human users in certain scenarios such as physical exercise and games. With this goal in mind, we introduce the Fencing Game, a human-robot competition used to evaluate both the capabilities of the robot competitor and user experience. We develop the robot competitor through iterative multi-agent reinforcement learning, and show that it can perform well against human competitors. Our user study additionally found that our system was able to continuously create challenging and enjoyable interactions for humans and the majority of human subjects considered the system to be entertaining and useful for improving the quality of their exercise."
}

TR;DR

Fast and Efficient Locomotion via Learned Gait Transitions
Finalist for Best Systems Paper
Conference on Robot Learning (CoRL), 2021
Y. Yang, T. Zhang, E. Coumans, J. Tan, and B. Boots
[BibTeX]  [Video]  [arXiv]  [Website] 

BibTeX

@inproceedings{Yang-CORL-21,
    author = "Yang, Yuxiang and Zhang, Tingnan and Coumans, Erwin and Tan, Jie and Boots, Byron",
    booktitle = "Conference on Robot Learning ({CoRL})",
    title = "{Fast and Efficient Locomotion via Learned Gait Transitions}",
    year = "2021",
    abstract = "We focus on the problem of developing energy efficient controllers for quadrupedal robots. Animals can actively switch gaits at different speeds to lower their energy consumption. In this paper, we devise a hierarchical learning framework, in which distinctive locomotion gaits and natural gait transitions emerge automatically with a simple reward of energy minimization. We use evolutionary strategies (ES) to train a high-level gait policy that specifies gait patterns of each foot, while the low-level convex MPC controller optimizes the motor commands so that the robot can walk at a desired velocity using that gait pattern. We test our learning framework on a quadruped robot and demonstrate automatic gait transitions, from walking to trotting and to fly-trotting, as the robot increases its speed. We show that the learned hierarchical controller consumes much less energy across a wide range of locomotion speed than baseline controllers."
}

TR;DR

STORM: An Integrated Framework for Fast Joint-Space Model-Predictive Control for Reactive Manipulation
Selected for Oral Presentation
Conference on Robot Learning (CoRL), 2021
M. Bhardwaj, B. Sundaralingam, A. Mousavian, N. Ratliff, D. Fox, F. Ramos, and B. Boots
[BibTeX]  [arXiv]  [Website]  [Code] 

BibTeX

@inproceedings{Bhardwaj-CORL-21,
    author = "Bhardwaj, Mohak and Sundaralingam, Balakumar and Mousavian, Arsalan and Ratliff, Nathan and Fox, Dieter and Ramos, Fabio and Boots, Byron",
    booktitle = "Conference on Robot Learning ({CoRL})",
    title = "{STORM: An Integrated Framework for Fast Joint-Space Model-Predictive Control for Reactive Manipulation}",
    year = "2021",
    abstract = "Sampling-based model-predictive control (MPC) is a promising tool for feedback control of robots with complex, non-smooth dynamics, and cost functions. However, the computationally demanding nature of sampling-based MPC algorithms has been a key bottleneck in their application to high-dimensional robotic manipulation problems in the real world. Previous methods have addressed this issue by running MPC in the task space while relying on a low-level operational space controller for joint control. However, by not using the joint space of the robot in the MPC formulation, existing methods cannot directly account for non-task space related constraints such as avoiding joint limits, singular configurations, and link collisions. In this paper, we develop a system for fast, joint space sampling-based MPC for manipulators that is efficiently parallelized using GPUs. Our approach can handle task and joint space constraints while taking less than 8ms\textasciitilde (125Hz) to compute the next control command. Further, our method can tightly integrate perception into the control problem by utilizing learned cost functions from raw sensor data. We validate our approach by deploying it on a Franka Panda robot for a variety of dynamic manipulation tasks. We study the effect of different cost formulations and MPC parameters on the synthesized behavior and provide key insights that pave the way for the application of sampling-based MPC for manipulators in a principled manner. We also provide highly optimized, open-source code to be used by the wider robot learning and control community."
}

TR;DR

Towards Coordinated Robot Motions: End-to-End Learning of Motion Policies on Transform Trees
IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2021
M. Rana*, A. Li*, D. Fox, S. Chernova, B. Boots, and N. Ratliff
[BibTeX]  [arXiv] 

BibTeX

@inproceedings{Rana-IROS-21,
    author = "Rana, M Asif and Li, Anqi and Fox, Dieter and Chernova, Sonia and Boots, Byron and Ratliff, Nathan",
    booktitle = "{IEEE/RSJ} International Conference on Intelligent Robots and Systems ({IROS})",
    title = "{Towards Coordinated Robot Motions: End-to-End Learning of Motion Policies on Transform Trees}",
    year = "2021"
}

TR;DR

Reactive Long Horizon Task Execution via Visual Skill and Precondition Model
IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2021
S. Mukherjee, C. Paxton, A. Mousavian, A. Fishman, M. Likhachev, and D. Fox
[BibTeX] 

BibTeX

@inproceedings{Mukherjee-IROS-21,
    author = "Mukherjee, Shohin and Paxton, Chris and Mousavian, Arsalan and Fishman, Adam and Likhachev, Maxime and Fox, Dieter",
    booktitle = "{IEEE/RSJ} International Conference on Intelligent Robots and Systems ({IROS})",
    title = "{Reactive Long Horizon Task Execution via Visual Skill and Precondition Model}",
    year = "2021"
}

TR;DR

Explaining Fast Improvement in Online Imitation Learning
International Conference on Uncertainty in Artificial Intelligence (UAI), 2021
X. Yan, B. Boots, and C.-A. Cheng
[BibTeX] 

BibTeX

@inproceedings{Yan-UAI-21,
    author = "Yan, Xinyan and Boots, Byron and Cheng, Ching-An",
    abstract = "Online imitation learning (IL) is an algorithmic framework that leverages interactions with expert policies for efficient policy optimization. Here policies are optimized by performing online learning on a sequence of loss functions that encourage the learner to mimic expert actions, and if the online learning has no regret, the agent can provably learn an expert-like policy. Online IL has demonstrated empirical successes in many applications and interestingly, its policy improvement speed observed in practice is usually much faster than existing theory suggests. In this work, we provide an explanation of this phenomenon. Let $\xi$ denote the policy class bias and assume the online IL loss functions are convex, smooth, and non-negative. We prove that, after $N$ rounds of online IL with stochastic feedback, the policy improves in $\tilde{O}(1/N + \sqrt{\xi/N})$ in both expectation and high probability. In other words, we show that adopting a sufficiently expressive policy class in online IL has two benefits: both the policy improvement speed increases and the performance bias decreases.",
    booktitle = "International Conference on Uncertainty in Artificial Intelligence ({UAI})",
    title = "{Explaining Fast Improvement in Online Imitation Learning}",
    year = "2021"
}

TR;DR

Safe Reinforcement Learning Using Advantage-Based Intervention
International Conference on Machine Learning (ICML), 2021
N. Wagener, B. Boots, and C.-A. Cheng
[TL;DR]  [BibTeX]  [arXiv]  [Code]  [Talk]  [Poster]  [Slides] 

BibTeX

@inproceedings{Wagener-ICML-21,
    author = "Wagener, Nolan and Boots, Byron and Cheng, Ching-An",
    abstract = "Many sequential decision problems involve finding a policy that maximizes total reward while obeying safety constraints. Although much recent research has focused on the development of safe reinforcement learning (RL) algorithms that produce a safe policy after training, ensuring safety during training as well remains an open problem. A fundamental challenge is performing exploration while still satisfying constraints in an unknown Markov decision process (MDP). In this work, we address this problem for the chance-constrained setting. We propose a new algorithm, SAILR, that uses an intervention mechanism based on advantage functions to keep the agent safe throughout training and optimizes the agent's policy using off-the-shelf RL algorithms designed for unconstrained MDPs. Our method comes with strong guarantees on safety during both training and deployment (i.e., after training and without the intervention mechanism) and policy performance compared to the optimal safety-constrained policy. In our experiments, we show that SAILR violates constraints far less during training than standard safe RL and constrained MDP approaches and converges to a well-performing policy that can be deployed safely without intervention.",
    booktitle = "International Conference on Machine Learning ({ICML})",
    title = "{Safe Reinforcement Learning Using Advantage-Based Intervention}",
    year = "2021"
}

TR;DR

We present an intervention-based technique for safe reinforcement learning. The intervention is based on an advantage function estimate with respect to a given baseline policy. Our work comes with strong theoretical guarantees on performance after training and safety during and after training, which we corroborate with simulated experiments.

Dual Online Stein Variational Inference for Control and Dynamics
Robotics: Science and Systems (R:SS), 2021
L. Barcelos, A. Lambert, R. Oliveira, P. Borges, B. Boots, and F. Ramos
[BibTeX]  [arXiv] 

BibTeX

@inproceedings{Barcelos-RSS-21,
    author = "Barcelos, Lucas and Lambert, Alexander and Oliveira, Rafael and Borges, Paulo and Boots, Byron and Ramos, Fabio",
    booktitle = "Robotics: Science and Systems ({R:SS})",
    title = "{Dual Online Stein Variational Inference for Control and Dynamics}",
    year = "2021"
}

TR;DR

RMP²: A Structured Composable Policy Class for Robot Learning
Robotics: Science and Systems (R:SS), 2021
A. Li*, C.-A. Cheng*, M. Rana, M. Xie, K. Van, N. Ratliff, and B. Boots
[BibTeX]  [Video]  [arXiv]  [Code] 

BibTeX

@inproceedings{Li-RSS-21,
    author = "Li, Anqi and Cheng, Ching-An and Rana, M Asif and Xie, Man and Van Wyk, Karl and Ratliff, Nathan and Boots, Byron",
    booktitle = "Robotics: Science and Systems ({R:SS})",
    title = "{{RMP}$^2$: A Structured Composable Policy Class for Robot Learning}",
    year = "2021"
}

TR;DR

Composable Energy Policies for Reactive Motion Generation and Reinforcement Learning
Robotics: Science and Systems (R:SS), 2021
J. Urain, A. Li, P. Liu, C. D'Eramo, and J. Peters
[BibTeX]  [arXiv] 

BibTeX

@inproceedings{Urain-RSS-21,
    author = "Urain, Julen and Li, Anqi and Liu, Puze and D'Eramo, Carlo and Peters, Jan",
    booktitle = "Robotics: Science and Systems ({R:SS})",
    title = "{Composable Energy Policies for Reactive Motion Generation and Reinforcement Learning}",
    year = "2021"
}

TR;DR

Grasping with Chopsticks: Combating Covariate Shift in Model-free Imitation Learning for Fine Manipulation
IEEE International Conference on Robotics and Automation (ICRA), 2021
L. Ke, J. Wang, T. Bhattacharjee, B. Boots, and S. Srinivasa
[BibTeX] 

BibTeX

@inproceedings{Ke-ICRA-21,
    author = "Ke, Liyiming and Wang, Jingqiang and Bhattacharjee, Tapomayukh and Boots, Byron and Srinivasa, Siddhartha",
    booktitle = "{IEEE} International Conference on Robotics and Automation ({ICRA})",
    title = "{Grasping with Chopsticks: Combating Covariate Shift in Model-free Imitation Learning for Fine Manipulation}",
    year = "2021"
}

TR;DR

The Value of Planning for Infinite-Horizon Model Predictive Control
IEEE International Conference on Robotics and Automation (ICRA), 2021
N. Hatch and B. Boots
[TL;DR]  [BibTeX]  [Video]  [arXiv]  [Code] 

BibTeX

@inproceedings{Hatch-ICRA-21,
    author = "Hatch, Nathan and Boots, Byron",
    abstract = "Model Predictive Control (MPC) is a classic tool for optimal control of complex, real-world systems. Although it has been successfully applied to a wide range of challenging tasks in robotics, it is fundamentally limited by the prediction horizon, which, if too short, will result in myopic decisions. Recently, several papers have suggested using a learned value function as the terminal cost for MPC. If the value function is accurate, it effectively allows MPC to reason over an \emph{infinite} horizon. Unfortunately, Reinforcement Learning (RL) solutions to value function approximation can be difficult to realize for robotics tasks. In this paper, we suggest a more efficient method for value function approximation that applies to goal-directed problems, like reaching and navigation. In these problems, MPC is often formulated to track a path or trajectory returned by a planner. However, this strategy is brittle in that unexpected perturbations to the robot will require replanning, which can be costly at runtime. Instead, we show how the intermediate data structures used by modern planners can be interpreted as an approximate \emph{value function}. We show that that this value function can be used by MPC \emph{directly}, resulting in more efficient and resilient behavior at runtime.",
    booktitle = "{IEEE} International Conference on Robotics and Automation ({ICRA})",
    title = "{The Value of Planning for Infinite-Horizon Model Predictive Control}",
    year = "2021"
}

TR;DR

While solving motion planning problems, planners often explore parts of the state space that are not ultimately used in the optimal plan. On the other hand, due to stochasticity or modeling errors, control algorithms often end up in those non-optimal parts of the state space. By making a connection between planning trees and value functions, this paper shows how we can reuse planning computations to recover from such control errors.

Generalized Nonlinear and Finsler Geometry for Robotics
IEEE International Conference on Robotics and Automation (ICRA), 2021
N. D. Ratliff, K. Van Wyk, M. Xie, A. Li, and M. A. Rana
[BibTeX]  [arXiv] 

BibTeX

@inproceedings{Ratliff-ICRA-21,
    author = "Ratliff, Nathan D and Van Wyk, Karl and Xie, Mandy and Li, Anqi and Rana, Muhammad Asif",
    title = "{Generalized Nonlinear and {F}insler Geometry for Robotics}",
    booktitle = "{IEEE} International Conference on Robotics and Automation ({ICRA})",
    year = "2021"
}

TR;DR

Blending MPC & Value Function Approximation for Efficient Reinforcement Learning
International Conference on Learning Representations (ICLR), 2021
M. Bhardwaj, S. Choudhury, and B. Boots
[BibTeX]  [arXiv] 

BibTeX

@inproceedings{Bhardwaj-ICLR-21,
    author = "Bhardwaj, Mohak and Choudhury, Sanjiban and Boots, Byron",
    abstract = "Model-Predictive Control (MPC) is a powerful tool for controlling complex, real-world systems that uses a model to make predictions about future behavior. For each state encountered, MPC solves an online optimization problem to choose a control action that will minimize future cost. This is a surprisingly effective strategy, but real-time performance requirements warrant the use of simple models. If the model is not sufficiently accurate, then the resulting controller can be biased, limiting performance. We present a framework for improving on MPC with model-free reinforcement learning (RL). The key insight is to view MPC as constructing a series of local Q-function approximations. We show that by using a parameter $\lambda$, similar to the trace decay parameter in TD($\lambda$), we can systematically trade-off learned value estimates against the local Q-function approximations. We present a theoretical analysis that shows how error from inaccurate models in MPC and value function estimation in RL can be balanced. We further propose an algorithm that changes $\lambda$ over time to reduce the dependence on MPC as our estimates of the value function improve, and test the efficacy our approach on challenging high-dimensional manipulation tasks with biased models in simulation. We demonstrate that our approach can obtain performance comparable with MPC with access to true dynamics even under severe model bias and is more sample efficient as compared to model-free RL.",
    booktitle = "International Conference on Learning Representations ({ICLR})",
    title = "{Blending MPC {\\&} Value Function Approximation for Efficient Reinforcement Learning}",
    year = "2021"
}

TR;DR

Quantum Tensor Networks, Stochastic Processes, and Weighted Automata
International Conference on Artificial Intelligence and Statistics (AISTATS), 2021
S. Adhikary*, S. Srinivasan*, J. Miller, G. Rabusseau, and B. Boots
[BibTeX]  [arXiv] 

BibTeX

@inproceedings{Adhikary-AISTATS-21,
    author = "Adhikary, Sandesh and Srinivasan, Siddarth and Miller, Jacob and Rabusseau, Guillaume and Boots, Byron",
    abstract = "Modeling joint probability distributions over sequences has been studied from many perspectives. The physics community developed matrix product states, a tensor-train decomposition for probabilistic modeling, motivated by the need to tractably model many-body systems. But similar models have also been studied in the stochastic processes and weighted automata literature, with little work on how these bodies of work relate to each other. We address this gap by showing how stationary or uniform versions of popular quantum tensor network models have equivalent representations in the stochastic processes and weighted automata literature, in the limit of infinitely long sequences. We demonstrate several equivalence results between models used in these three communities: (i) uniform variants of matrix product states, Born machines and locally purified states from the quantum tensor networks literature, (ii) predictive state representations, hidden Markov models, norm-observable operator models and hidden quantum Markov models from the stochastic process literature,and (iii) stochastic weighted automata, probabilistic automata and quadratic automata from the formal languages literature. Such connections may open the door for results and methods developed in one area to be applied in another.",
    booktitle = "International Conference on Artificial Intelligence and Statistics ({AISTATS})",
    keywords = "quantum",
    mendeley-tags = "quantum",
    title = "{Quantum Tensor Networks, Stochastic Processes, and Weighted Automata}",
    year = "2021"
}

TR;DR

Leveraging Experience in Lazy Search
Autonomous Robots (AURO), 2021
M. Bhardwaj, S. Choudhury, and B. Boots
[BibTeX]  [arXiv] 

BibTeX

@inproceedings{Bhardwaj-AURO-21,
    author = "Bhardwaj, Mohak and Choudhury, Sanjiban and Boots, Byron",
    booktitle = "Autonomous Robots ({AURO})",
    title = "{Leveraging Experience in Lazy Search}",
    year = "2021"
}

TR;DR

Sampling over Riemannian Manifolds with Kernel Herding
Winner of Best Workshop Paper Award
Robotics: Science and Systems (R:SS) Workshop on Geometry and Topology in Robotics: Learning, Optimization, Planning, and Control, 2021
S. Adhikary, J. Thompson, and B. Boots
[BibTeX] 

BibTeX

@inproceedings{Adhikary-RSS-GeoTopoRobo-21,
    author = "Adhikary, Sandesh and Thompson, Josie and Boots, Byron",
    booktitle = "Robotics: Science and Systems ({R:SS}) Workshop on Geometry and Topology in Robotics: Learning, Optimization, Planning, and Control",
    title = "{Sampling over Riemannian Manifolds with Kernel Herding}",
    year = "2021"
}

TR;DR


2020

Intra Order-Preserving Functions for Calibration of Multi-Class Neural Networks
Advances in Neural Information Processing Systems (NeurIPS), 2020
A. Rahimi*, A. Shaban*, C.-A. Cheng*, B. Boots, and R. Hartley
[BibTeX]  [arXiv] 

BibTeX

@inproceedings{Rahimi-NeurIPS-20,
    author = "Rahimi, Amir and Shaban, Amirreza and Cheng, Ching-An and Boots, Byron and Hartley, Richard",
    abstract = "Predicting calibrated confidence scores for multi-class deep networks is important for avoiding rare but costly mistakes. A common approach is to learn a post-hoc calibration function that transforms the output of the original network into calibrated confidence scores while maintaining the network's accuracy. However, previous post-hoc calibration techniques work only with simple calibration functions, potentially lacking sufficient representation to calibrate the complex function landscape of deep networks. In this work, we aim to learn general post-hoc calibration functions that can preserve the top-k predictions of any deep network. We call this family of functions intra order-preserving functions. We propose a new neural network architecture that represents a class of intra order-preserving functions by combining common neural network components. Additionally, we introduce order-invariant and diagonal sub-families, which can act as regularization for better generalization when the training data size is small. We show the effectiveness of the proposed method across a wide range of datasets and classifiers. Our method outperforms state-of-the-art post-hoc calibration methods, namely temperature scaling and Dirichlet calibration, in multiple settings.",
    booktitle = "Advances in Neural Information Processing Systems ({NeurIPS})",
    title = "{Intra Order-Preserving Functions for Calibration of Multi-Class Neural Networks}",
    year = "2020"
}

TR;DR

Stein Variational Model Predictive Control
Conference on Robot Learning (CoRL), 2020
A. Lambert, A. Fishman, D. Fox, B. Boots, and F. Ramos
[BibTeX]  [Video]  [arXiv] 

BibTeX

@inproceedings{Lambert-CORL-20,
    author = "Lambert, Alexander and Fishman, Adam and Fox, Dieter and Boots, Byron and Ramos, Fabio",
    abstract = "Decision making under uncertainty is critical to real-world, autonomous systems. Model Predictive Control (MPC) methods have demonstrated favorable performance in practice, but remain limited when dealing with complex probability distributions. In this paper, we propose a generalization of MPC that represents a multitude of solutions as posterior distributions. By casting MPC as a Bayesian inference problem, we employ variational methods for posterior computation, naturally encoding the complexity and multi-modality of the decision making problem. We propose a Stein variational gradient descent method to estimate the posterior over control parameters, given a cost function and a sequence of state observations. We show that this framework leads to successful planning in challenging, non-convex optimal control problems.",
    booktitle = "Conference on Robot Learning ({CoRL})",
    title = "{{S}tein Variational Model Predictive Control}",
    year = "2020"
}

TR;DR

Learning a Contact-Adaptive Controller for Robust, Efficient Legged Locomotion
Conference on Robot Learning (CoRL), 2020
X. Da, Z. Xie, D. Hoeller, B. Boots, A. Anandkumar, Y. Zhu, B. Babich, and A. Garg
[BibTeX]  [arXiv] 

BibTeX

@inproceedings{Da-CoRL-20,
    author = "Da, Xingye and Xie, Zhaoming and Hoeller, David and Boots, Byron and Anandkumar, Animashree and Zhu, Yuke and Babich, Buck and Garg, Animesh",
    abstract = "We present a hierarchical framework that combines model-based control and reinforcement learning (RL) to synthesize robust controllers for a quadruped (the Unitree Laikago). The system consists of a high-level controller that learns to choose from a set of primitives in response to changes in the environment and a low-level controller that utilizes an established control method to robustly execute the primitives. Our framework learns a controller that can adapt to challenging environmental changes on the fly, including novel scenarios not seen during training. The learned controller is up to 85{\\textasciitilde {}}percent more energy efficient and is more robust compared to baseline methods. We also deploy the controller on a physical robot without any randomization or adaptation scheme.",
    booktitle = "Conference on Robot Learning ({CoRL})",
    title = "{Learning a Contact-Adaptive Controller for Robust, Efficient Legged Locomotion}",
    year = "2020"
}

TR;DR

Nonprehensile Riemannian Motion Predictive Control
International Symposium on Experimental Robotics (ISER), 2020
H. Izadinia, B. Boots, and S. Seitz
[BibTeX] 

BibTeX

@inproceedings{Izadina-ISER-20,
    author = "Izadinia, H and Boots, Byron and Seitz, S",
    booktitle = "International Symposium on Experimental Robotics ({ISER})",
    title = "{Nonprehensile {R}iemannian Motion Predictive Control}",
    year = "2020"
}

TR;DR

Collaborative Interaction Models for Optimized Human Robot Teamwork
IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2020
A. Fishman, C. Paxton, W. Yang, D. Fox, B. Boots, and N. Ratliff
[BibTeX]  [arXiv] 

BibTeX

@inproceedings{Fishman-IROS-20,
    author = "Fishman, Adam and Paxton, Chris and Yang, Wei and Fox, Dieter and Boots, Byron and Ratliff, Nathan",
    abstract = "Effective human-robot collaboration requires informed anticipation. The robot must simultaneously anticipate what the human will do and react quickly and intuitively when its predictions are wrong. Additionally, the robot must plan its actions to account for the human's own plan, but with the knowledge that the human's behavior will change based on what the robot actually does. This cyclical game of predicting a human's future actions and generating a corresponding motion plan is extremely difficult to model using standard techniques. In this work, we describe a novel framework for finding optimal trajectories in a multi-agent collaborative setting. We use Model Predictive Control (MPC) to simultaneously plan for the robot while predicting the actions of its external collaborators. We use human-robot handovers to demonstrate that with a strong model of the collaborator, our framework produces fluid, reactive human-robot interactions in novel, cluttered environments. Our method efficiently generates coordinated trajectories, and achieves a high success rate in handover, even in the presence of a large amounts of sensor noise.",
    booktitle = "{IEEE/RSJ} International Conference on Intelligent Robots and Systems ({IROS})",
    title = "{Collaborative Interaction Models for Optimized Human Robot Teamwork}",
    year = "2020"
}

TR;DR

Pairwise Similarity Knowledge Transfer for Weakly Supervised Object Localization
European Conference on Computer Vision (ECCV), 2020
A. Rahimi, A. Shaban, T. Ajanthan, R. Hartley, and B. Boots
[BibTeX]  [arXiv] 

BibTeX

@inproceedings{Rahimi-ECCV-20,
    author = "Rahimi, Amir and Shaban, Amirreza and Ajanthan, Thalaiyasingam and Hartley, Richard and Boots, Byron",
    abstract = "Weakly Supervised Object Localization (WSOL) methods have become increasingly popular since they only require image level labels as opposed to expensive bounding box annotations required by fully supervised algorithms. Typically, a WSOL model is first trained to predict class generic objectness scores on an off-the-shelf fully supervised source dataset and then it is progressively adapted to learn the objects in the weakly supervised target dataset. In this work, we argue that learning only an objectness function is a weak form of knowledge transfer and propose to learn a classwise pairwise similarity function that directly compares two input proposals as well. The combined localization model and the estimated object annotations are jointly learned in an alternating optimization paradigm as is typically done in standard WSOL methods. In contrast to the existing work that learns pairwise similarities, our proposed approach optimizes a unified objective with convergence guarantee and it is computationally efficient for large-scale applications. Experiments on the COCO and ILSVRC 2013 detection datasets show that the performance of the localization model improves significantly with the inclusion of pairwise similarity function. For instance, in the ILSVRC dataset, the Correct Localization (CorLoc) performance improves from 72.7{\\%} to 78.2{\\%} which is a new state-of-the-art for weakly supervised object localization task.",
    booktitle = "European Conference on Computer Vision ({ECCV})",
    title = "{Pairwise Similarity Knowledge Transfer for Weakly Supervised Object Localization}",
    year = "2020"
}

TR;DR

Information Theoretic Model Predictive Q-Learning
Learning for Dynamics & Control (L4DC), 2020
M. Bhardwaj, A. Handa, D. Fox, and B. Boots
[TL;DR]  [BibTeX]  [arXiv] 

BibTeX

@inproceedings{Bhardwaj-L4DC-20,
    author = "Bhardwaj, Mohak and Handa, Ankur and Fox, Dieter and Boots, Byron",
    abstract = "Model-free Reinforcement Learning (RL) algorithms work well in sequential decision-making problems when experience can be collected cheaply and model-based RL is effective when system dynamics can be modeled accurately. However, both of these assumptions can be violated in real world problems such as robotics, where querying the system can be prohibitively expensive and real-world dynamics can be difficult to model accurately. Although sim-to-real approaches such as domain randomization attempt to mitigate the effects of biased simulation,they can still suffer from optimization challenges such as local minima and hand-designed distributions for randomization, making it difficult to learn an accurate global value function or policy that directly transfers to the real world. In contrast to RL, Model Predictive Control (MPC) algorithms use a simulator to optimize a simple policy class online, constructing a closed-loop controller that can effectively contend with real-world dynamics. MPC performance is usually limited by factors such as model bias and the limited horizon of optimization. In this work, we present a novel theoretical connection between information theoretic MPC and entropy regularized RL and develop a Q-learning algorithm that can leverage biased models. We validate the proposed algorithm on sim-to-sim control tasks to demonstrate the improvements over optimal control and reinforcement learning from scratch. Our approach paves the way for deploying reinforcement learning algorithms on real robots in a systematic manner.",
    booktitle = "Learning for Dynamics \& Control ({L4DC})",
    title = "{Information Theoretic Model Predictive Q-Learning}",
    year = "2020"
}

TR;DR

In this work, we present a novel theoretical connection between information theoretic MPC and entropy regularized RL and develop a Q-learning algorithm that can leverage biased models. We validate the proposed algorithm on sim-to-sim control tasks to demonstrate the improvements over optimal control and reinforcement learning from scratch. Our approach paves the way for deploying reinforcement learning algorithms on real robots in a systematic manner.

Euclideanizing Flows: Diffeomorphic Reductions for Learning Stable Dynamical Systems
Learning for Dynamics & Control (L4DC), 2020
M. A. Rana, A. Li, D. Fox, B. Boots, F. Ramos, and N. Ratliff
[BibTeX]  [arXiv]  [Code] 

BibTeX

@inproceedings{Rana-L4DC-20,
    author = "Rana, M Asif and Li, Anqi and Fox, Dieter and Boots, Byron and Ramos, Fabio and Ratliff, Nathan",
    abstract = "Execution of complex tasks in robotics requires motions that have complex geometric structure. We present an approach which allows robots to learn such motions from a few human demonstrations. The motions are encoded as rollouts of a dynamical system on a Riemannian manifold. Additional structure is imposed which guarantees smooth convergent motions to a goal location. The aforementioned structure involves viewing motions on an observed Riemannian manifold as deformations of straight lines on a latent Euclidean space. The observed and latent spaces are related through a diffeomorphism. Thus, this paper presents an approach for learning flexible diffeomorphisms, resulting in a stable dynamical system. The efficacy of this approach is demonstrated through validation on an established benchmark as well demonstrations collected on a real-world robotic system.",
    booktitle = "Learning for Dynamics \& Control ({L4DC})",
    title = "{Euclideanizing Flows: Diffeomorphic Reductions for Learning Stable Dynamical Systems}",
    year = "2020"
}

TR;DR

IRIS: Implicit Reinforcement without Interaction at Scale for Learning Control from Offline Robot Manipulation Data
IEEE International Conference on Robotics and Automation (ICRA), 2020
A. Mandlekar, F. Ramos, B. Boots, F. F. Li, A. Garg, and D. Fox
[BibTeX]  [arXiv] 

BibTeX

@inproceedings{Mandlekar-ICRA-20,
    author = "Mandlekar, Ajay and Ramos, Fabio and Boots, Byron and Li, Fe Fe and Garg, Animesh and Fox, Dieter",
    booktitle = "{IEEE} International Conference on Robotics and Automation ({ICRA})",
    title = "{{IRIS}: Implicit Reinforcement without Interaction at Scale for Learning Control from Offline Robot Manipulation Data}",
    year = "2020"
}

TR;DR

Differential Gaussian Process Motion Planning
IEEE International Conference on Robotics and Automation (ICRA), 2020
M. Bhardwaj, B. Boots, and M. Mukadam.
[BibTeX]  [arXiv] 

BibTeX

@inproceedings{Bhardwaj-ICRA-20,
    author = "Bhardwaj, Mohak and Boots, Byron and Mukadam., Mustafa",
    booktitle = "{IEEE} International Conference on Robotics and Automation ({ICRA})",
    title = "{Differential {G}aussian Process Motion Planning}",
    year = "2020"
}

TR;DR

Exploiting Singular Configurations for Controllable, Low-Power Friction Enhancement on Unmanned Ground Vehicles
IEEE International Conference on Robotics and Automation (ICRA), 2020
A. Foris, N. Wagener, B. Boots, and A. Mazumdar
[BibTeX] 

BibTeX

@inproceedings{Foris-ICRA-20,
    author = "Foris, Adam and Wagener, Nolan and Boots, Byron and Mazumdar, Anirban",
    booktitle = "{IEEE} International Conference on Robotics and Automation ({ICRA})",
    title = "{Exploiting Singular Configurations for Controllable, Low-Power Friction Enhancement on Unmanned Ground Vehicles}",
    year = "2020"
}

TR;DR

Composing Task-Agnostic Policies with Deep Reinforcement Learning
International Conference on Learning Representations (ICLR), 2020
A. H. Qureshi, J. J. Johnson, Y. Qin, T. Henderson, B. Boots, and M. C. Yip
[BibTeX]  [arXiv] 

BibTeX

@inproceedings{Quereshi-ICLR-20,
    author = "Qureshi, Ahmed H and Johnson, Jacob J and Qin, Yuzhe and Henderson, Taylor and Boots, Byron and Yip, Michael C",
    booktitle = "International Conference on Learning Representations ({ICLR})",
    title = "{Composing Task-Agnostic Policies with Deep Reinforcement Learning}",
    year = "2020"
}

TR;DR

A Reduction from Reinforcement Learning to No-Regret Online Learning
International Conference on Artificial Intelligence and Statistics (AISTATS), 2020
C.-A. Cheng, R. T. des Combes, B. Boots, and G. Gordon
[BibTeX]  [arXiv] 

BibTeX

@article{Cheng-AISTATS-20b,
    author = "Cheng, Ching-An and des Combes, Remi Tachet and Boots, Byron and Gordon, Geoff",
    journal = "International Conference on Artificial Intelligence and Statistics ({AISTATS})",
    title = "{A Reduction from Reinforcement Learning to No-Regret Online Learning}",
    year = "2020"
}

TR;DR

Online learning with continuous variations: Dynamic regret and reductions
International Conference on Artificial Intelligence and Statistics (AISTATS), 2020
C.-A. Cheng*, J. Lee*, K. Goldberg, and B. Boots
[BibTeX]  [arXiv] 

BibTeX

@inproceedings{Cheng-AISTATS-20a,
    author = "Cheng, Ching-An and Lee, Jonathan and Goldberg, Ken and Boots, Byron",
    booktitle = "International Conference on Artificial Intelligence and Statistics ({AISTATS})",
    organization = "PMLR",
    pages = "2218--2228",
    title = "{Online learning with continuous variations: Dynamic regret and reductions}",
    year = "2020"
}

TR;DR

Expressiveness and Learning of Hidden Quantum Markov Models
International Conference on Artificial Intelligence and Statistics (AISTATS), 2020
S. Adhikary*, S. Srinivasan*, G. Gordon, and B. Boots
[BibTeX]  [arXiv]  [Code] 

BibTeX

@article{Adhikary-AISTATS-20,
    author = "Adhikary, Sandesh and Srinivasan, Siddarth and Gordon, Geoff and Boots, Byron",
    journal = "International Conference on Artificial Intelligence and Statistics ({AISTATS})",
    title = "{Expressiveness and Learning of Hidden Quantum {M}arkov Models}",
    year = "2020"
}

TR;DR

A Sequential Composition Framework for Coordinating Multirobot Behaviors
IEEE Transactions on Robotics (T-RO), 2020
P. Pierpaoli, A. Li, M. Srinivasan, X. Cai, S. Coogan, and M. Egerstedt
[BibTeX] 

BibTeX

@article{Pierpaoli-TRO-20,
    author = "Pierpaoli, Pietro and Li, Anqi and Srinivasan, Mohit and Cai, Xiaoyi and Coogan, Samuel and Egerstedt, Magnus",
    title = "{A Sequential Composition Framework for Coordinating Multirobot Behaviors}",
    journal = "{IEEE} Transactions on Robotics ({T-RO})",
    year = "2020",
    publisher = "IEEE"
}

TR;DR

RMPflow: A Geometric Framework for Generation of Multi-Task Motion Policies
IEEE Transactions on Automation Science and Engineering (T-ASE), 2020
C.-A. Cheng, M. Mukadam, J. Issac, S. Birchfield, D. Fox, B. Boots, and N. Ratliff
[BibTeX]  [arXiv] 

BibTeX

@article{Cheng-TASE-20,
    author = "Cheng, Ching-An and Mukadam, Mustafa and Issac, Jan and Birchfield, Stan and Fox, Dieter and Boots, Byron and Ratliff, Nathan",
    abstract = "We develop a novel policy synthesis algorithm, RMPflow, based on geometrically consistent transformations of Riemannian Motion Policies (RMPs). RMPs are a class of reactive motion policies designed to parameterize non-Euclidean behaviors as dynamical systems in intrinsically nonlinear task spaces. Given a set of RMPs designed for individual tasks, RMPflow can consistently combine these local policies to generate an expressive global policy, while simultaneously exploiting sparse structure for computational efficiency. We study the geometric properties of RMPflow and provide sufficient conditions for stability. Finally, we experimentally demonstrate that accounting for the geometry of task policies can simplify classically difficult problems, such as planning through clutter on high-DOF manipulation systems.",
    journal = "{IEEE} Transactions on Automation Science and Engineering ({T-ASE})",
    title = "{{RMP}flow: A Geometric Framework for Generation of Multi-Task Motion Policies}",
    year = "2020"
}

TR;DR

Combining pretrained CNN feature extractors to enhance clustering of complex natural images
Neurocomputing, 2020
J. Guerin, S. Thiery, E. Nyiri, O. Gibaru, and B. Boots
[BibTeX]  [arXiv] 

BibTeX

@article{Guerin-Neurocomputing-20,
    author = "Guerin, Joris and Thiery, Stephane and Nyiri, Eric and Gibaru, Olivier and Boots, Byron",
    abstract = "Recently, a common starting point for solving complex unsupervised image classification tasks is to use generic features, extracted with deep Convolutional Neural Networks (CNN) pretrained on a large and versatile dataset (ImageNet). However, in most research, the CNN architecture for feature extraction is chosen arbitrarily, without justification. This paper aims at providing insight on the use of pretrained CNN features for image clustering (IC). First, extensive experiments are conducted and show that, for a given dataset, the choice of the CNN architecture for feature extraction has a huge impact on the final clustering. These experiments also demonstrate that proper extractor selection for a given IC task is difficult. To solve this issue, we propose to rephrase the IC problem as a multi-view clustering (MVC) problem that considers features extracted from different architectures as different “views” of the same data. This approach is based on the assumption that information contained in the different CNN may be complementary, even when pretrained on the same data. We then propose a multi-input neural network architecture that is trained end-to-end to solve the MVC problem effectively. This approach is tested on nine natural image datasets, and produces state-of-the-art results for IC.",
    journal = "Neurocomputing",
    pages = "551--571",
    title = "{Combining pretrained CNN feature extractors to enhance clustering of complex natural images}",
    url = "https://www.sciencedirect.com/science/article/pii/S0925231220316465",
    volume = "423",
    year = "2020"
}

TR;DR


2019

Stable, Concurrent Controller Composition for Multi-Objective Robotic Tasks
IEEE Conference on Decision and Control (CDC), 2019
A. Li, C.-A. Cheng, B. Boots, and M. Egerstedt
[BibTeX]  [arXiv] 

BibTeX

@article{Li-CDC-19,
    author = "Li, Anqi and Cheng, Ching-An and Boots, Byron and Egerstedt, Magnus",
    journal = "{IEEE} Conference on Decision and Control ({CDC})",
    title = "{Stable, Concurrent Controller Composition for Multi-Objective Robotic Tasks}",
    year = "2019"
}

TR;DR

Learning Reactive Motion Policies in Multiple Task Spaces from Human Demonstrations
Conference on Robot Learning (CoRL), 2019
M. Rana*, A. Li*, D. Fox, B. Boots, F. Ramos, and N. Ratliff
[BibTeX]  [Video] 

BibTeX

@inproceedings{Rana-CORL-19,
    author = "Rana, Muhammad Asif and Li, Anqi and Ravichandar, Harish and Mukadam, Mustafa and Chernova, Sonia and Fox, Dieter and Boots, Byron and Ratliff, Nathan",
    booktitle = "Conference on Robot Learning ({CoRL})",
    title = "{Learning Reactive Motion Policies in Multiple Task Spaces from Human Demonstrations}",
    year = "2019"
}

TR;DR

Riemannian Motion Policy Fusion through Learnable Lyapunov Function Reshaping
Conference on Robot Learning (CoRL), 2019
M. Mukadam, C.-A. Cheng, D. Fox, B. Boots, and N. Ratliff.
[BibTeX]  [arXiv] 

BibTeX

@inproceedings{Mukadam-CORL-19,
    author = "Mukadam, Mustafa and Cheng, Ching-An and Fox, Dieter and Boots, Byron and Ratliff., Nathan",
    booktitle = "Conference on Robot Learning ({CoRL})",
    title = "{Riemannian Motion Policy Fusion through Learnable {L}yapunov Function Reshaping}",
    year = "2019"
}

TR;DR

Trajectory-wise Control Variates for Variance Reduction in Policy Gradient Methods
Conference on Robot Learning (CoRL), 2019
C.-A. Cheng*, X. Yan*, and B. Boots
[BibTeX]  [arXiv] 

BibTeX

@inproceedings{Cheng-CORL-19,
    author = "Cheng, Ching-An and Yan, Xinyan and Boots, Byron",
    booktitle = "Conference on Robot Learning ({CoRL})",
    title = "{Trajectory-wise Control Variates for Variance Reduction in Policy Gradient Methods}",
    year = "2019"
}

TR;DR

Multi-Objective Policy Generation for Multi-Robot Systems Using Riemannian Motion Policies
International Symposium on Robotics Research (ISRR), 2019
A. Li, M. Mukadam, M. Egerstedt, and B. Boots
[BibTeX]  [arXiv] 

BibTeX

@article{Li-ISRR-19,
    author = "Li, Anqi and Mukadam, Mustafa and Egerstedt, Magnus and Boots, Byron",
    journal = "International Symposium on Robotics Research ({ISRR})",
    title = "{Multi-Objective Policy Generation for Multi-Robot Systems Using Riemannian Motion Policies}",
    year = "2019"
}

TR;DR

Learning to Find Common Objects Across Image Collections
International Conference on Computer Vision (ICCV), 2019
A. Shaban, A. Rahimi, S. Gould, B. Boots, and R. Hartley
[BibTeX]  [arXiv] 

BibTeX

@article{Shaban-ICCV-19,
    author = "Shaban, Amirreza and Rahimi, Amir and Gould, Stephen and Boots, Byron and Hartley, Richard",
    journal = "International Conference on Computer Vision ({ICCV})",
    title = "{Learning to Find Common Objects Across Image Collections}",
    year = "2019"
}

TR;DR

Online Motion Planning Over Multiple Homotopy Classes with Gaussian Process Inference
IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2019
K. Kolur, S. Chintalapudi, B. Boots, and M. Mukadam
[BibTeX]  [arXiv] 

BibTeX

@article{Kolur-IROS-19,
    author = "Kolur, Keshav and Chintalapudi, Sahit and Boots, Byron and Mukadam, Mustafa",
    journal = "{IEEE/RSJ} International Conference on Intelligent Robots and Systems ({IROS})",
    title = "{Online Motion Planning Over Multiple Homotopy Classes with Gaussian Process Inference}",
    year = "2019"
}

TR;DR

Predictor-Corrector Policy Optimization
Selected for Long Talk: 5% Acceptance Rate
International Conference on Machine Learning (ICML), 2019
C.-A. Cheng, X. Yan, N. Ratliff, and B. Boots
[BibTeX]  [arXiv] 

BibTeX

@article{Cheng-ICML-19,
    author = "Cheng, Ching-An and Yan, Xinyan and Ratliff, Nathan and Boots, Byron",
    journal = "International Conference on Machine Learning ({ICML})",
    title = "{Predictor-Corrector Policy Optimization}",
    year = "2019"
}

TR;DR

Provably Efficient Imitation Learning from Observation Alone
International Conference on Machine Learning (ICML), 2019
W. Sun, A. Vemula, B. Boots, and J. A. Bagnell
[BibTeX]  [arXiv] 

BibTeX

@article{Sun-ICML-19,
    author = "Sun, Wen and Vemula, Anirudh and Boots, Byron and Bagnell, J Andrew",
    journal = "International Conference on Machine Learning ({ICML})",
    title = "{Provably Efficient Imitation Learning from Observation Alone}",
    year = "2019"
}

TR;DR

An Online Learning Approach to Model Predictive Control
Winner of Best Student Paper & Finalist for Best Systems Paper
Robotics: Science and Systems (R:SS), 2019
N. Wagener*, C.-A. Cheng*, J. Sacks, and B. Boots
[TL;DR]  [BibTeX]  [Video]  [arXiv]  [Talk]  [Poster]  [Slides] 

BibTeX

@article{Wagener-RSS-19,
    author = "Wagener, Nolan and Cheng, Ching-An and Sacks, Jacob and Boots, Byron",
    journal = "Robotics: Science and Systems ({R:SS})",
    title = "{An Online Learning Approach to Model Predictive Control}",
    year = "2019"
}

TR;DR

We present a connection between model predictive control (MPC) and online learning, demonstrating that many well-known MPC algorithms are special cases of dynamic mirror descent.

Leveraging Experience in Lazy Search
Robotics: Science and Systems (R:SS), 2019
M. Bhardwaj, S. Chowdhury, B. Boots, and S. Srinivasa
[BibTeX]  [arXiv] 

BibTeX

@article{Bhardwaj-RSS-19,
    author = "Bhardwaj, Mohak and Chowdhury, Sanjiban and Boots, Byron and Srinivasa, Siddartha",
    journal = "Robotics: Science and Systems ({R:SS})",
    title = "{Leveraging Experience in Lazy Search}",
    year = "2019"
}

TR;DR

Joint Inference of Kinematic and Force Trajectories with Visuo-Tactile Sensing
IEEE International Conference on Robotics and Automation (ICRA), 2019
A. Lambert, M. Mukadam, B. Sundaralingam, N. Ratliff, B. Boots, and D. Fox
[BibTeX]  [Video]  [arXiv] 

BibTeX

@inproceedings{Lambert-ICRA-19,
    author = "Lambert, Alexander and Mukadam, Mustafa and Sundaralingam, Balakumar and Ratliff, Nathan and Boots, Byron and Fox, Dieter",
    booktitle = "{IEEE} International Conference on Robotics and Automation ({ICRA})",
    title = "{Joint Inference of Kinematic and Force Trajectories with Visuo-Tactile Sensing}",
    year = "2019"
}

TR;DR

Robust Learning of Tactile Force Estimation through Robot Interaction
Finalist for Best Manipulation Paper
IEEE International Conference on Robotics and Automation (ICRA), 2019
B. Sundaralingam, A. Lambert, A. Handa, B. Boots, T. Hermans, S. Birchfield, N. Ratliff, and D. Fox
[BibTeX]  [Video]  [arXiv] 

BibTeX

@inproceedings{Sundaralingam-ICRA-19,
    author = "Sundaralingam, Balakumar and Lambert, Alexander and Handa, Ankur and Boots, Byron and Hermans, Tucker and Birchfield, Stan and Ratliff, Nathan and Fox, Dieter",
    booktitle = "{IEEE} International Conference on Robotics and Automation ({ICRA})",
    title = "{Robust Learning of Tactile Force Estimation through Robot Interaction}",
    year = "2019"
}

TR;DR

Adversarial Imitation via Variational Inverse Reinforcement Learning
IEEE International Conference on Robotics and Automation (ICRA), 2019
A. Quereshi, B. Boots, and M. C. Yip
[BibTeX]  [Video]  [arXiv] 

BibTeX

@inproceedings{Quereshi-ICLR-19,
    author = "Quereshi, Ahmed and Boots, Byron and Yip, Michael C",
    booktitle = "{IEEE} International Conference on Robotics and Automation ({ICRA})",
    title = "{Adversarial Imitation via Variational Inverse Reinforcement Learning}",
    year = "2019"
}

TR;DR

On the Trade-Off Between Communication and Execution Overhead for Control of Multi-Agent Systems
American Control Conference (ACC), 2019
A. Li and M. Egerstedt
[BibTeX] 

BibTeX

@inproceedings{Li-ACC-19,
    author = "Li, Anqi and Egerstedt, Magnus",
    title = "{On the Trade-Off Between Communication and Execution Overhead for Control of Multi-Agent Systems}",
    booktitle = "American Control Conference ({ACC})",
    pages = "79--85",
    year = "2019",
    organization = "IEEE"
}

TR;DR

Accelerating Imitation Learning with Predictive Models
International Conference on Artificial Intelligence and Statistics (AISTATS), 2019
C.-A. Cheng, X. Yan, E. Theodorou, and B. Boots
[BibTeX]  [arXiv] 

BibTeX

@inproceedings{Cheng-AISTATS-19,
    author = "Cheng, Ching-An and Yan, Xinyan and Theodorou, Evangelos and Boots, Byron",
    booktitle = "International Conference on Artificial Intelligence and Statistics ({AISTATS})",
    title = "{Accelerating Imitation Learning with Predictive Models}",
    year = "2019"
}

TR;DR

Truncated Backpropogation for Bi-Level Optimization
International Conference on Artificial Intelligence and Statistics (AISTATS), 2019
A. Shaban*, C.-A. Cheng*, N. Hatch, and B. Boots
[BibTeX]  [arXiv] 

BibTeX

@inproceedings{Shaban-AISTATS-19,
    author = "Shaban, Amirreza and Cheng, Ching-An and Hatch, Nathan and Boots, Byron",
    booktitle = "International Conference on Artificial Intelligence and Statistics ({AISTATS})",
    title = "{Truncated Backpropogation for Bi-Level Optimization}",
    year = "2019"
}

TR;DR

Imitation Learning for Agile Autonomous Driving
The International Journal of Robotics Research (IJRR), 2019
Y. Pan, C.-A. Cheng, K. Saigol, K. Lee, X. Yan, E. Theodorou, and B. Boots
[BibTeX] 

BibTeX

@inproceedings{Pan-IJRR-19,
    author = "Pan, Yunpeng and Cheng, Ching-An and Saigol, Kamil and Lee, Keuntaek and Yan, Xinyan and Theodorou, Evangelos and Boots, Byron",
    booktitle = "The International Journal of Robotics Research ({IJRR})",
    title = "{Imitation Learning for Agile Autonomous Driving}",
    year = "2019"
}

TR;DR


2018

RMPflow: A Computational Graph for Automatic Motion Policy Generation
Workshop on the Algorithmic Foundations of Robotics (WAFR), 2018
C.-A. Cheng, M. Mukadam, J. Issac, S. Birchfield, D. Fox, B. Boots, and N. Ratliff
[BibTeX]  [Video]  [arXiv] 

BibTeX

@inproceedings{Cheng-WAFR-18,
    author = "Cheng, Ching-An and Mukadam, Mustafa and Issac, Jan and Birchfield, Stan and Fox, Dieter and Boots, Byron and Ratliff, Nathan",
    booktitle = "Workshop on the Algorithmic Foundations of Robotics ({WAFR})",
    title = "{{RMP}flow: A Computational Graph for Automatic Motion Policy Generation}",
    year = "2018"
}

TR;DR

Differentiable MPC for End-to-end Planning and Control
Advances in Neural Information Processing Systems (NeurIPS), 2018
B. Amos, I. D. J. Rodriguez, J. Sacks, B. Boots, and Z. Kolter
[BibTeX]  [arXiv]  [Code] 

BibTeX

@inproceedings{Amos-NeurIPS-18,
    author = "Amos, Brandon and Rodriguez, Ivan Dario Jimenez and Sacks, Jacob and Boots, Byron and Kolter, Zico",
    booktitle = "Advances in Neural Information Processing Systems ({NeurIPS})",
    title = "{Differentiable {MPC} for End-to-end Planning and Control}",
    year = "2018"
}

TR;DR

Dual Policy Iteration
Advances in Neural Information Processing Systems (NeurIPS), 2018
W. Sun, G. J. Gordon, B. Boots, and J. A. Bagnell
[BibTeX]  [arXiv] 

BibTeX

@inproceedings{Sun-NeurIPS-18,
    author = "Sun, Wen and Gordon, Geoffrey J and Boots, Byron and Bagnell, J Andrew",
    booktitle = "Advances in Neural Information Processing Systems ({NeurIPS})",
    title = "{Dual Policy Iteration}",
    year = "2018"
}

TR;DR

Learning and Inference in Hilbert Space with Quantum Graphical Models
Advances in Neural Information Processing Systems (NeurIPS), 2018
S. Srinivasan, C. Downey, and B. Boots
[BibTeX]  [arXiv] 

BibTeX

@inproceedings{Srinivasan-NeurIPS-18,
    author = "Srinivasan, Siddarth and Downey, Carlton and Boots, Byron",
    booktitle = "Advances in Neural Information Processing Systems ({NeurIPS})",
    title = "{Learning and Inference in Hilbert Space with Quantum Graphical Models}",
    year = "2018"
}

TR;DR

Orthogonally Decoupled Variational Gaussian Processes
Advances in Neural Information Processing Systems (NeurIPS), 2018
H. Samilbeni*, C.-A. Cheng*, B. Boots, and M. Deisenroth
[BibTeX]  [arXiv] 

BibTeX

@inproceedings{Cheng-NeurIPS-18,
    author = "Samilbeni, Hugh and Cheng, Ching-An and Boots, Byron and Deisenroth, Marc",
    booktitle = "Advances in Neural Information Processing Systems ({NeurIPS})",
    title = "{Orthogonally Decoupled Variational {G}aussian Processes}",
    year = "2018"
}

TR;DR

Learning to Align Images using Weak Geometric Supervision
International Conference on 3D Vision (3DV), 2018
J. Dong, B. Boots, F. Dellaert, R. Chandra, and S. Sinha
[BibTeX]  [Video]  [arXiv] 

BibTeX

@inproceedings{Dong-3DV-18,
    author = "Dong, Jing and Boots, Byron and Dellaert, Frank and Chandra, Ranveer and Sinha, Sudipta",
    booktitle = "International Conference on 3D Vision ({3DV})",
    title = "{Learning to Align Images using Weak Geometric Supervision}",
    year = "2018"
}

TR;DR

Improving Image Clustering With Multiple Pretrained CNN Feature Extractors
British Machine Vision Conference (BMVC), 2018
J. Guerin and B. Boots
[BibTeX]  [arXiv] 

BibTeX

@inproceedings{Guerin-BMVC-18,
    author = "Guerin, Joris and Boots, Byron",
    booktitle = "British Machine Vision Conference ({BMVC})",
    title = "{Improving Image Clustering With Multiple Pretrained CNN Feature Extractors}",
    year = "2018"
}

TR;DR

Semi-parametric Approaches to Learning in Model-Based Hierarchical Control of Complex Systems
International Symposium on Experimental Robotics (ISER), 2018
M. Zafar, A. Mehmood, M. Khan, S. Zhang, M. Murtaza, V. Aladele, E. A. Theodorou, S. Hutchinson, and B. Boots
[BibTeX] 

BibTeX

@inproceedings{Zafar-ISER-18,
    author = "Zafar, Munzir and Mehmood, Areeb and Khan, Mouhyemen and Zhang, Shimin and Murtaza, Muhammad and Aladele, Victor and Theodorou, Evangelos A and Hutchinson, Seth and Boots, Byron",
    booktitle = "International Symposium on Experimental Robotics ({ISER})",
    title = "{Semi-parametric Approaches to Learning in Model-Based Hierarchical Control of Complex Systems}",
    year = "2018"
}

TR;DR

Learning-based Air Data System for Safe and Efficient Control of Fixed-wing Aerial Vehicles
IEEE International Symposium on Safety, Security, and Rescue Robotics (SSRR), 2018
K. Choromanski, V. Sindhwani, B. Jones, D. Jourdan, M. Chociej, and B. Boots
[BibTeX] 

BibTeX

@inproceedings{Choromanski-SSRR-18,
    author = "Choromanski, Krzysztof and Sindhwani, Vikas and Jones, Brandon and Jourdan, Damien and Chociej, Maciej and Boots, Byron",
    booktitle = "{IEEE} International Symposium on Safety, Security, and Rescue Robotics ({SSRR})",
    title = "{Learning-based Air Data System for Safe and Efficient Control of Fixed-wing Aerial Vehicles}",
    year = "2018"
}

TR;DR

Learning Generalizable Robot Skills from Demonstrations in Cluttered Environments
IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2018
M. A. Rana, M. Mukadam, S. R. Ahmadzadeh, S. Chernova, and B. Boots
[BibTeX]  [arXiv] 

BibTeX

@inproceedings{Rana-IROS-18,
    author = "Rana, M Asif and Mukadam, Mustafa and Ahmadzadeh, S Reza and Chernova, Sonia and Boots, Byron",
    booktitle = "{IEEE/RSJ} International Conference on Intelligent Robots and Systems ({IROS})",
    title = "{Learning Generalizable Robot Skills from Demonstrations in Cluttered Environments}",
    year = "2018"
}

TR;DR

Semantically Meaningful View Selection
IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2018
J. Guerin, O. Gibaru, E. Nyiri, S. Thiery, and B. Boots
[BibTeX]  [arXiv] 

BibTeX

@inproceedings{Guerin-IROS-18,
    author = "Guerin, Joris and Gibaru, Olivier and Nyiri, Eric and Thiery, Stephane and Boots, Byron",
    booktitle = "{IEEE/RSJ} International Conference on Intelligent Robots and Systems ({IROS})",
    title = "{Semantically Meaningful View Selection}",
    year = "2018"
}

TR;DR

Formally Correct Composition of Coordinated Behaviors Using Control Barrier Certificates
IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2018
A. Li, L. Wang, P. Pierpaoli, and M. Egerstedt
[BibTeX] 

BibTeX

@inproceedings{Li-IROS-18,
    author = "Li, Anqi and Wang, Li and Pierpaoli, Pietro and Egerstedt, Magnus",
    title = "{Formally Correct Composition of Coordinated Behaviors Using Control Barrier Certificates}",
    booktitle = "{IEEE/RSJ} International Conference on Intelligent Robots and Systems ({IROS})",
    pages = "3723--3729",
    year = "2018",
    organization = "IEEE"
}

TR;DR

Fast Policy Learning through Imitation and Reinforcement
Selected for Plenary Presentation: 8% Acceptance Rate
International Conference on Uncertainty in Artificial Intelligence (UAI), 2018
C.-A. Cheng, X. Yan, N. Wagener, and B. Boots
[BibTeX]  [arXiv] 

BibTeX

@inproceedings{Cheng-UAI-18,
    author = "Cheng, Ching-An and Yan, Xinyan and Wagener, Nolan and Boots, Byron",
    booktitle = "International Conference on Uncertainty in Artificial Intelligence ({UAI})",
    title = "{Fast Policy Learning through Imitation and Reinforcement}",
    year = "2018"
}

TR;DR

Agile Autonomous Driving via End-to-End Deep Imitation Learning
Finalist for Best Systems Paper
Robotics: Science and Systems (R:SS), 2018
Y. Pan, C.-A. Cheng, K. Saigol, K. Lee, X. Yan, E. Theodorou, and B. Boots
[BibTeX]  [arXiv] 

BibTeX

@inproceedings{Pan-RSS-18,
    author = "Pan, Yunpeng and Cheng, Ching-An and Saigol, Kamil and Lee, Keuntak and Yan, Xinyan and Theodorou, Evangelos and Boots, Byron",
    booktitle = "Robotics: Science and Systems ({R:SS})",
    title = "{Agile Autonomous Driving via End-to-End Deep Imitation Learning}",
    year = "2018"
}

TR;DR

Deep Forward and Inverse Perceptual Models for Tracking and Prediction
IEEE International Conference on Robotics and Automation (ICRA), 2018
A. Lambert, A. Shaban, A. Raj, Z. Liu, and B. Boots
[BibTeX]  [arXiv] 

BibTeX

@inproceedings{Lambert-ICRA-18,
    author = "Lambert, Alexander and Shaban, Amirreza and Raj, Amit and Liu, Zhen and Boots, Byron",
    booktitle = "{IEEE} International Conference on Robotics and Automation ({ICRA})",
    title = "{Deep Forward and Inverse Perceptual Models for Tracking and Prediction}",
    year = "2018"
}

TR;DR

Sparse Gaussian Processes on Matrix Lie Groups: A Unified Framework for Optimizing Continuous-Time Trajectories
IEEE International Conference on Robotics and Automation (ICRA), 2018
J. Dong, M. Mukadam, B. Boots, and F. Dellaert
[BibTeX] 

BibTeX

@inproceedings{Dong-ICRA-18,
    author = "Dong, Jing and Mukadam, Mustafa and Boots, Byron and Dellaert, Frank",
    booktitle = "{IEEE} International Conference on Robotics and Automation ({ICRA})",
    title = "{Sparse Gaussian Processes on Matrix {L}ie Groups: A Unified Framework for Optimizing Continuous-Time Trajectories}",
    year = "2018"
}

TR;DR

Optical Sensing and Control Methods for Soft Pneumatically Actuated Robotic Manipulators
IEEE International Conference on Robotics and Automation (ICRA), 2018
J. L. Molnar, C.-A. Cheng, L. O. Tiziani, B. Boots, and F. L. Hammond
[BibTeX] 

BibTeX

@inproceedings{Molnar-ICRA-18,
    author = "Molnar, Jennifer L and Cheng, Ching-An and Tiziani, Lucas O and Boots, Byron and Hammond, Frank L",
    booktitle = "{IEEE} International Conference on Robotics and Automation ({ICRA})",
    title = "{Optical Sensing and Control Methods for Soft Pneumatically Actuated Robotic Manipulators}",
    year = "2018"
}

TR;DR

Truncated Horizon Policy Search: Combining Reinforcement Learning and Imitation Learning
International Conference on Learning Representations (ICLR), 2018
W. Sun, J. A. Bagnell, and B. Boots
[BibTeX]  [arXiv] 

BibTeX

@inproceedings{Sun-ICLR-18,
    author = "Sun, Wen and Bagnell, James Andrew and Boots, Byron",
    booktitle = "International Conference on Learning Representations ({ICLR})",
    title = "{Truncated Horizon Policy Search: Combining Reinforcement Learning and Imitation Learning}",
    year = "2018"
}

TR;DR

Initialization matters: Orthogonal Predictive State Recurrent Neural Networks
International Conference on Learning Representations (ICLR), 2018
K. Choromanski, C. Downey, and B. Boots
[BibTeX] 

BibTeX

@inproceedings{Choromanski-ICLR-18,
    author = "Choromanski, Krzysztof and Downey, Carlton and Boots, Byron",
    booktitle = "International Conference on Learning Representations ({ICLR})",
    title = "{Initialization matters: Orthogonal Predictive State Recurrent Neural Networks}",
    year = "2018"
}

TR;DR

Learning Hidden Quantum Markov Models
International Conference on Artificial Intelligence and Statistics (AISTATS), 2018
S. Srinivasan, G. J. Gordon, and B. Boots
[BibTeX]  [arXiv] 

BibTeX

@inproceedings{Srinivasan-AISTATS-18,
    author = "Srinivasan, Siddarth and Gordon, Geoffrey J and Boots, Byron",
    booktitle = "International Conference on Artificial Intelligence and Statistics ({AISTATS})",
    title = "{Learning Hidden Quantum Markov Models}",
    year = "2018"
}

TR;DR

Convergence of Value Aggregagtion for Imitation Learning
Winner of Best Overall Paper
International Conference on Artificial Intelligence and Statistics (AISTATS), 2018
C.-A. Cheng and B. Boots
[BibTeX]  [arXiv] 

BibTeX

@inproceedings{Cheng-AISTATS-18,
    author = "Cheng, Ching-An and Boots, Byron",
    booktitle = "International Conference on Artificial Intelligence and Statistics ({AISTATS})",
    title = "{Convergence of Value Aggregagtion for Imitation Learning}",
    year = "2018"
}

TR;DR

Continuous-time Gaussian Process Motion Planning via Probabilistic Inference
IJRR Paper of the Year
The International Journal of Robotics Research (IJRR), 2018
M. Mukadam, J. Dong, X. Yan, F. Dellaert, and B. Boots
[BibTeX]  [arXiv] 

BibTeX

@inproceedings{Mukadam-IJRR-18,
    author = "Mukadam, Mustafa and Dong, Jing and Yan, Xinyan and Dellaert, Frank and Boots, Byron",
    booktitle = "The International Journal of Robotics Research ({IJRR})",
    title = "{Continuous-time {G}aussian Process Motion Planning via Probabilistic Inference}",
    year = "2018"
}

TR;DR

STEAP: Simultaneous Trajectory Estimation and Planning
Autonomous Robots (AURO), 2018
M. Mukadam, J. Dong, F. Dellaert, and B. Boots
[BibTeX]  [arXiv] 

BibTeX

@inproceedings{Mukadam-AURO-18,
    author = "Mukadam, Mustafa and Dong, Jing and Dellaert, Frank and Boots, Byron",
    booktitle = "Autonomous Robots ({AURO})",
    title = "{{STEAP}: Simultaneous Trajectory Estimation and Planning}",
    year = "2018"
}

TR;DR


2017

Predictive State Recurrent Neural Networks
Advances in Neural Information Processing Systems (NIPS), 2017
C. Downey, A. Hefny, B. Li, B. Boots, and G. J. Gordon
[BibTeX]  [arXiv] 

BibTeX

@inproceedings{Downey-NIPS-17,
    author = "Downey, Carlton and Hefny, Ahmed and Li, Boyue and Boots, Byron and Gordon, Geoffrey J",
    booktitle = "Advances in Neural Information Processing Systems ({NIPS})",
    title = "{Predictive State Recurrent Neural Networks}",
    year = "2017"
}

TR;DR

Predictive State Decoders: Encoding the Future into Recurrent Networks
Advances in Neural Information Processing Systems (NIPS), 2017
A. Venkatraman, N. Rhinehart, W. Sun, L. Pinto, B. Boots, K. Kitani, and J. A. Bagnell
[BibTeX]  [arXiv] 

BibTeX

@inproceedings{Venkatraman-NIPS-17,
    author = "Venkatraman, Arun and Rhinehart, Nicholas and Sun, Wen and Pinto, Lerrel and Boots, Byron and Kitani, Kris and Bagnell, James Andrew",
    booktitle = "Advances in Neural Information Processing Systems ({NIPS})",
    title = "{Predictive State Decoders: Encoding the Future into Recurrent Networks}",
    year = "2017"
}

TR;DR

Variational Inference for Gaussian Process Models with Linear Complexity
Advances in Neural Information Processing Systems (NIPS), 2017
C.-A. Cheng and B. Boots
[BibTeX]  [arXiv]  [Code] 

BibTeX

@inproceedings{Cheng-NIPS-17,
    author = "Cheng, Ching-An and Boots, Byron",
    booktitle = "Advances in Neural Information Processing Systems ({NIPS})",
    title = "{Variational Inference for Gaussian Process Models with Linear Complexity}",
    year = "2017"
}

TR;DR

One-Shot Learning for Semantic Segmentation
British Machine Vision Conference (BMVC), 2017
A. Shaban, S. Bansal, Z. Liu, I. Essa, and B. Boots
[BibTeX]  [arXiv] 

BibTeX

@inproceedings{Shaban-BMVC-17,
    author = "Shaban, Amirreza and Bansal, Shray and Liu, Zhen and Essa, Irfan and Boots, Byron",
    booktitle = "British Machine Vision Conference ({BMVC})",
    title = "{One-Shot Learning for Semantic Segmentation}",
    year = "2017"
}

TR;DR

Towards Robust Skill Generalization: Unifying Learning from Demonstration and Motion Planning
Selected for Plenary Presentation: 8% Acceptance Rate
Conference on Robot Learning (CoRL), 2017
M. A. Rana, M. Mukadam, S. R. Ahmadzadeh, S. Chernova, and B. Boots
[BibTeX] 

BibTeX

@inproceedings{Rana-CoRL-17,
    author = "Rana, M Asif and Mukadam, Mustafa and Ahmadzadeh, S Reza and Chernova, Sonia and Boots, Byron",
    booktitle = "Conference on Robot Learning ({CoRL})",
    title = "{Towards Robust Skill Generalization: Unifying Learning from Demonstration and Motion Planning}",
    year = "2017"
}

TR;DR

Prediction under Uncertainty in Sparse Spectrum Gaussian Processes with Applications to Filtering and Control
International Conference on Machine Learning (ICML), 2017
Y. Pan, X. Yan, E. Theodorou, and B. Boots
[BibTeX] 

BibTeX

@inproceedings{Pan-ICML-17,
    author = "Pan, Yunpeng and Yan, Xinyan and Theodorou, Evangelos and Boots, Byron",
    booktitle = "International Conference on Machine Learning ({ICML})",
    title = "{Prediction under Uncertainty in Sparse Spectrum {G}aussian Processes with Applications to Filtering and Control}",
    year = "2017"
}

TR;DR

Deeply AggreVaTeD: Differentiable Imitation Learning for Sequential Prediction
International Conference on Machine Learning (ICML), 2017
W. Sun, A. Venkatraman, G. J. Gordon, B. Boots, and J. A. Bagnell
[BibTeX]  [arXiv] 

BibTeX

@inproceedings{Sun-ICML-17,
    author = "Sun, Wen and Venkatraman, Arun and Gordon, Geoffrey J and Boots, Byron and Bagnell, J Andrew",
    booktitle = "International Conference on Machine Learning ({ICML})",
    title = "{Deeply AggreVaTeD: Differentiable Imitation Learning for Sequential Prediction}",
    year = "2017"
}

TR;DR

Simultaneous Trajectory Estimation and Planning via Probabilistic Inference
Robotics: Science and Systems (R:SS), 2017
M. Mukadam, J. Dong, F. Dellaert, and B. Boots
[BibTeX]  [Video] 

BibTeX

@inproceedings{Mukadam-RSS-17,
    author = "Mukadam, Mustafa and Dong, Jing and Dellaert, Frank and Boots, Byron",
    booktitle = "Robotics: Science and Systems ({R:SS})",
    title = "{Simultaneous Trajectory Estimation and Planning via Probabilistic Inference}",
    year = "2017"
}

TR;DR

Exact Bounds on the Contact-Driven Motion of a Sliding Object, With Applications to Robotic Pulling
Robotics: Science and Systems (R:SS), 2017
E. Huang, A. Bhatia, B. Boots, and M. T. Mason
[BibTeX] 

BibTeX

@inproceedings{Huang-RSS-17,
    author = "Huang, Eric and Bhatia, Ankit and Boots, Byron and Mason, Matthew T",
    booktitle = "Robotics: Science and Systems ({R:SS})",
    title = "{Exact Bounds on the Contact-Driven Motion of a Sliding Object, With Applications to Robotic Pulling}",
    year = "2017"
}

TR;DR

Information Theoretic MPC for Model-Based Reinforcement Learning
Finalist for Best Overall Paper
IEEE International Conference on Robotics and Automation (ICRA), 2017
G. Williams, N. Wagener, B. Goldfain, P. Drews, J. Rehg, B. Boots, and E. Theodorou
[BibTeX]  [Video] 

BibTeX

@inproceedings{Williams-ICRA-17,
    author = "Williams, Grady and Wagener, Nolan and Goldfain, Brian and Drews, Paul and Rehg, James and Boots, Byron and Theodorou, Evangelos",
    booktitle = "{IEEE} International Conference on Robotics and Automation ({ICRA})",
    title = "{Information Theoretic {MPC} for Model-Based Reinforcement Learning}",
    year = "2017"
}

TR;DR

Approximately Optimal Continuous-Time Motion Planning and Control via Probabilistic Inference
IEEE International Conference on Robotics and Automation (ICRA), 2017
M. Mukadam, C.-A. Cheng, X. Yan, and B. Boots
[BibTeX]  [Video]  [arXiv] 

BibTeX

@inproceedings{Mukadam-ICRA-17,
    author = "Mukadam, Mustafa and Cheng, Ching-An and Yan, Xinyan and Boots, Byron",
    booktitle = "{IEEE} International Conference on Robotics and Automation ({ICRA})",
    title = "{Approximately Optimal Continuous-Time Motion Planning and Control via Probabilistic Inference}",
    year = "2017"
}

TR;DR

Motion Planning with Graph-Based Trajectories and Gaussian Process Inference
IEEE International Conference on Robotics and Automation (ICRA), 2017
E. Huang, M. Mukadam, Z. Liu, and B. Boots
[BibTeX]  [Video] 

BibTeX

@inproceedings{Huang-ICRA-17,
    author = "Huang, Eric and Mukadam, Mustafa and Liu, Zhen and Boots, Byron",
    booktitle = "{IEEE} International Conference on Robotics and Automation ({ICRA})",
    title = "{Motion Planning with Graph-Based Trajectories and {G}aussian Process Inference}",
    year = "2017"
}

TR;DR

4D Crop Monitoring: Spatio-Temporal Reconstruction for Agriculture
IEEE International Conference on Robotics and Automation (ICRA), 2017
J. Dong, J. Burnhan, B. Boots, G. Rains, and F. Dellaert
[BibTeX]  [Video]  [arXiv] 

BibTeX

@inproceedings{Dong-ICRA-17,
    author = "Dong, Jing and Burnhan, John and Boots, Byron and Rains, Glen and Dellaert, Frank",
    booktitle = "{IEEE} International Conference on Robotics and Automation ({ICRA})",
    title = "{4{D} Crop Monitoring: Spatio-Temporal Reconstruction for Agriculture}",
    year = "2017"
}

TR;DR

Learning from Conditional Distributions via Dual Kernel Embeddings
International Conference on Artificial Intelligence and Statistics (AISTATS), 2017
B. Dai, N. He, Y. Pan, B. Boots, and L. Song
[BibTeX]  [arXiv] 

BibTeX

@inproceedings{Dai-AISTATS-17,
    author = "Dai, Bo and He, Niao and Pan, Yunpeng and Boots, Byron and Song, Le",
    booktitle = "International Conference on Artificial Intelligence and Statistics ({AISTATS})",
    title = "{Learning from Conditional Distributions via Dual Kernel Embeddings}",
    year = "2017"
}

TR;DR

Sampling Beats Fixed Estimate Predictors for Cloning Stochastic Behavior in Multiagent Systems
AAAI Conference on Artificial Intelligence (AAAI), 2017
B. Hrolenok, B. Boots, and T. Balch
[BibTeX] 

BibTeX

@inproceedings{Hrolenok-AAAI-17,
    author = "Hrolenok, Brian and Boots, Byron and Balch, Tucker",
    booktitle = "{AAAI} Conference on Artificial Intelligence ({AAAI})",
    title = "{Sampling Beats Fixed Estimate Predictors for Cloning Stochastic Behavior in Multiagent Systems}",
    year = "2017"
}

TR;DR


2016

Incremental Variational Sparse Gaussian Process Regression
Advances in Neural Information Processing Systems (NIPS), 2016
C.-A. Cheng and B. Boots
[BibTeX] 

BibTeX

@inproceedings{Cheng-NIPS-16,
    author = "Cheng, Ching-An and Boots, Byron",
    booktitle = "Advances in Neural Information Processing Systems ({NIPS})",
    title = "{Incremental Variational Sparse {G}aussian Process Regression}",
    year = "2016"
}

TR;DR

Simulation-Based Design of Dynamic Controllers for Humanoid Balancing
Selected for Oral Presentation
IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2016
J. Tan, Z. Xie, B. Boots, and C. K. Liu
[BibTeX] 

BibTeX

@inproceedings{Tan-IROS-16,
    author = "Tan, Jie and Xie, Zhaoming and Boots, Byron and Liu, C Karen",
    booktitle = "{IEEE/RSJ} International Conference on Intelligent Robots and Systems ({IROS})",
    title = "{Simulation-Based Design of Dynamic Controllers for Humanoid Balancing}",
    year = "2016"
}

TR;DR

Inference Machines for Nonparametric Filter Learning
International Joint Conference on Artificial Intelligence (IJCAI), 2016
A. Venkatraman, W. Sun, M. Hebert, B. Boots, and J. A. Bagnell
[BibTeX] 

BibTeX

@inproceedings{Venkatraman-IJCAI-16,
    author = "Venkatraman, Arun and Sun, Wen and Hebert, Martial and Boots, Byron and Bagnell, J Andrew",
    booktitle = "International Joint Conference on Artificial Intelligence ({IJCAI})",
    title = "{Inference Machines for Nonparametric Filter Learning}",
    year = "2016"
}

TR;DR

Learning to Smooth with Bidirectional Predictive State Inference Machines
International Conference on Uncertainty in Artificial Intelligence (UAI), 2016
W. Sun, R. Capobianco, G. J. Gordon, J. A. Bagnell, and B. Boots
[BibTeX] 

BibTeX

@inproceedings{Sun-UAI-16,
    author = "Sun, Wen and Capobianco, Roberto and Gordon, Geoffrey J and Bagnell, J Andrew and Boots, Byron",
    booktitle = "International Conference on Uncertainty in Artificial Intelligence ({UAI})",
    title = "{Learning to Smooth with Bidirectional Predictive State Inference Machines}",
    year = "2016"
}

TR;DR

Learning to Filter with Predictive State Inference Machines
International Conference on Machine Learning (ICML), 2016
W. Sun, A. Venkatraman, B. Boots, and J. A. Bagnell
[BibTeX]  [arXiv] 

BibTeX

@inproceedings{Sun-ICML-16,
    author = "Sun, Wen and Venkatraman, Arun and Boots, Byron and Bagnell, J Andrew",
    booktitle = "International Conference on Machine Learning ({ICML})",
    title = "{Learning to Filter with Predictive State Inference Machines}",
    year = "2016"
}

TR;DR

Functional Gradient Motion Planning in Reproducing Kernel Hilbert Spaces
Robotics: Science and Systems (R:SS), 2016
Z. Marinho, A. Dragan, A. Byravan, B. Boots, G. J. Gordon, and S. Srinivasa
[BibTeX]  [arXiv] 

BibTeX

@inproceedings{Marinho-RSS-16,
    author = "Marinho, Zita and Dragan, Anca and Byravan, Arunkumar and Boots, Byron and Gordon, Geoffrey J and Srinivasa, Siddhartha",
    booktitle = "Robotics: Science and Systems ({R:SS})",
    title = "{Functional Gradient Motion Planning in Reproducing Kernel {H}ilbert Spaces}",
    year = "2016"
}

TR;DR

Motion Planning as Probabilistic Inference using Gaussian Processes and Factor Graphs
Robotics: Science and Systems (R:SS), 2016
J. Dong, M. Mukadam, F. Dellaert, and B. Boots
[BibTeX]  [Video]  [Code] 

BibTeX

@inproceedings{Dong-RSS-16,
    author = "Dong, Jing and Mukadam, Mustafa and Dellaert, Frank and Boots, Byron",
    booktitle = "Robotics: Science and Systems ({R:SS})",
    title = "{Motion Planning as Probabilistic Inference using {G}aussian Processes and Factor Graphs}",
    year = "2016"
}

TR;DR

Gaussian Process Motion Planning
IEEE International Conference on Robotics and Automation (ICRA), 2016
M. Mukadam, X. Yan, and B. Boots
[BibTeX]  [Video] 

BibTeX

@inproceedings{Mukadam-ICRA-16,
    author = "Mukadam, Mustafa and Yan, Xinyan and Boots, Byron",
    booktitle = "{IEEE} International Conference on Robotics and Automation ({ICRA})",
    title = "{{G}aussian Process Motion Planning}",
    year = "2016"
}

TR;DR

The Nonparametric Kernel Bayes Smoother
International Conference on Artificial Intelligence and Statistics (AISTATS), 2016
Y. Nishiyama, A. H. Afsharinejad, S. Naruse, B. Boots, and L. Song
[BibTeX] 

BibTeX

@inproceedings{Nishiyama-AISTATS-16,
    author = "Nishiyama, Yu and Afsharinejad, Amir Hossein and Naruse, Shunsuke and Boots, Byron and Song, Le",
    booktitle = "International Conference on Artificial Intelligence and Statistics ({AISTATS})",
    title = "{The Nonparametric Kernel {B}ayes Smoother}",
    year = "2016"
}

TR;DR

Online Instrumental Variable Regression with Applications to Online Linear System Identification
AAAI Conference on Artificial Intelligence (AAAI), 2016
A. Venkatraman, W. Sun, M. Hebert, J. A. Bagnell, and B. Boots
[BibTeX] 

BibTeX

@inproceedings{Venkatraman-AAAI-16,
    author = "Venkatraman, Arun and Sun, Wen and Hebert, Martial and Bagnell, J Andrew and Boots, Byron",
    booktitle = "{AAAI} Conference on Artificial Intelligence ({AAAI})",
    title = "{Online Instrumental Variable Regression with Applications to Online Linear System Identification}",
    year = "2016"
}

TR;DR


2015

Incremental Sparse GP Regression for Continuous-time Trajectory Estimation & Mapping
International Symposium on Robotics Research (ISRR), 2015
X. Yan, V. Indelman, and B. Boots
[BibTeX]  [arXiv] 

BibTeX

@inproceedings{Yan-ISRR-15,
    author = "Yan, Xinyan and Indelman, Vadim and Boots, Byron",
    booktitle = "International Symposium on Robotics Research ({ISRR})",
    pages = "120--132",
    title = "{Incremental Sparse {GP} Regression for Continuous-time Trajectory Estimation {\\&} Mapping}",
    volume = "87",
    year = "2015"
}

TR;DR

Layered Hybrid Inverse Optimal Control for Learning Robot Manipulation from Demonstration
International Joint Conference on Artificial Intelligence (IJCAI), 2015
A. Byravan, M. Montfort, B. Ziebart, B. Boots, and D. Fox
[BibTeX] 

BibTeX

@inproceedings{Byravan-IJCAI-15,
    author = "Byravan, Arunkumar and Montfort, Matthew and Ziebart, Brian and Boots, Byron and Fox, Dieter",
    booktitle = "International Joint Conference on Artificial Intelligence ({IJCAI})",
    title = "{Layered Hybrid Inverse Optimal Control for Learning Robot Manipulation from Demonstration}",
    year = "2015"
}

TR;DR

Learning Latent Variable Models by Improving Spectral Solutions with Exterior Point Methods
International Conference on Uncertainty in Artificial Intelligence (UAI), 2015
A. Shaban, M. Farajtabar, B. Xie, L. Song, and B. Boots
[BibTeX] 

BibTeX

@inproceedings{Shaban-UAI-15,
    author = "Shaban, Amirreza and Farajtabar, Mehrdad and Xie, Bo and Song, Le and Boots, Byron",
    booktitle = "International Conference on Uncertainty in Artificial Intelligence ({UAI})",
    title = "{Learning Latent Variable Models by Improving Spectral Solutions with Exterior Point Methods}",
    year = "2015"
}

TR;DR