arXiv (Cornell University) · 2020 · 15 citations · 39 references
EngineeringComputer ScienceRobotics EngineeringMotion PlanningRobot ControlRoboticsControl TheoryModel Predictive ControlOptimal ControlPolicy LearningReinforcement LearningRobot Motion PlanningContraction PropertiesLearning-based ControlPredictive ControlReinforcement Learning For RoboticsReinforcement Learning With Learned DynamicsSafe Motion PlanningSafe Robot Motion PlanningSafe Trajectory Planning
In this paper, we solve the problem of finding a certified control policy that drives a robot from any given initial state and under any bounded disturbance to the desired reference trajectory, with guarantees on the convergence or bounds on the tracking error. Such a controller is crucial in safe motion planning. We leverage the advanced theory in Control Contraction Metric and design a learning framework based on neural networks to co-synthesize the contraction metric and the controller for control-affine systems. We further provide methods to validate the convergence and bounded error guarantees. We demonstrate the performance of our method using a suite of challenging robotic models, including models with learned dynamics as neural networks. We compare our approach with leading methods using sum-of-squares programming, reinforcement learning, and model predictive control. Results show that our methods indeed can handle a broader class of systems with less tracking error and faster execution speed. Code is available at https://github.com/sundw2014/C3M.
39
Rapidly-exploring random trees : a new tool for path planning
Steven M. LaValle · 1998 · 3.6K citations
Contraction Analysis of Nonlinear Systems
1999 · 1.5K citations