Learning Reactive and Predictive Differentiable Controllers for Switching Linear Dynamical Models

2021 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA 2021)(2021)

引用 4|浏览12
暂无评分
摘要
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.
更多
查看译文
关键词
reactive controllers,predictive differentiable controllers,linear dynamical models,humans leverage,switching dynamics,model inaccuracies,contact regions,composite dynamical behaviors,expert demonstrations,switching linear dynamical model,switching conditions,system dynamics,discrete-time LQR,differentiable policy class,control strategy,multiple dynamical modes,predicting interactions,inaccurate predictions,unanticipated contacts,learned behaviors
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要