Humans leverage the dynamics of the environment and their own bodies to accomplish challenging tasks such as grasping an object while walking past it or pushing off a wall to turn a corner. Such tasks often involve switching dynamics as the robot makes and breaks contact. Learning these dynamics is a challenging problem and prone to model inaccuracies, especially near contact regions. In this work, we present a framework for learning composite dynamical behaviors from expert demonstrations. We learn a switching linear dynamical model with contacts encoded in switching conditions as a close approximation of our system dynamics. We then use discrete-time LQR as the differentiable policy class for data-efficient learning of control to develop a control strategy that operates over multiple dynamical modes and takes into account discontinuities due to contact. In addition to predicting interactions with the environment, our policy effectively reacts to inaccurate predictions such as unanticipated contacts. Through simulation and real world experiments, we demonstrate generalization of learned behaviors to different scenarios and robustness to model inaccuracies during execution.
REASAN: Learning Reactive Safe Navigation for Legged Robots
Bernoulli Institute for Mathematics, Computer Science and Artificial Intelligence, University of Groningen, The Netherlands（格罗宁根大学伯努利数学、计算机科学与人工智能研究所）；Department of Electrical Engineering, Linköping University, Sweden（利厄普大学电气工程系）；Engineering and Technology Institute Groningen, University of Groningen, The Netherlands（格罗宁根大学格罗宁根工程与技术研究所）
Resolving Conflicts Where and When They Arise: Reactive Composition of Multi-Goal Behavior
Robotics and Biology Laboratory, Technische Universität Berlin（技术大学柏林机器人与生物学实验室）；Science of Intelligence (SCIoI), Cluster of Excellence, Berlin, Germany（智能科学（SCIoI），卓越中心，柏林，德国）；Robotics Institute Germany（德国机器人研究所）
Differentiable Physics-Informed Adaptive Koopman Control for Stable Flight under Unknown Disturbances
Research Center for Intelligent Robotics, School of Astronautics, Northwestern Polytechnical University（西北工业大学航天学院智能机器人研究中心）；Department of Automation, Tsinghua University（清华大学自动化系）
Learning a Structured Neural Network Policy for a Hopping Task
Tandon School of Engineering, New York University（纽约大学坦登工程学院）；Max Planck Institute for Intelligent Systems（马克斯·普朗克智能系统研究所）；Ecole Normale Supérieure Paris-Saclay（巴黎-萨克雷高等师范学院）
Leveraging Forward Model Prediction Error for Learning Control
Max Planck Institute for Intelligent Systems（马克斯·普朗克智能系统研究所）；Tandon School of Engineering, New York University（纽约大学坦登工程学院）；Facebook AI Research（Facebook人工智能研究院）
