Dynamic Tube MPC: Learning Tube Dynamics with Massively Parallel Simulation for Robust Safety in Practice
This work addresses the challenge of robust safety in robotics navigation, particularly for dynamic systems in cluttered environments, representing an incremental improvement over existing robust planning methods.
The paper tackles the problem of safe navigation in cluttered environments for robotics by introducing Dynamic Tube MPC, which learns a dynamic tube representation to optimize planning trajectories for better tracking and safety. The method was applied to the 3D hopping robot ARCHER, enabling agile, collision-free navigation in narrow corridors.
Safe navigation of cluttered environments is a critical challenge in robotics. It is typically approached by separating the planning and tracking problems, with planning executed on a reduced order model to generate reference trajectories, and control techniques used to track these trajectories on the full order dynamics. Inevitable tracking error necessitates robustification of the nominal plan to ensure safety; in many cases, this is accomplished via worst-case bounding, which ignores the fact that some trajectories of the planning model may be easier to track than others. In this work, we present a novel method leveraging massively parallel simulation to learn a dynamic tube representation, which characterizes tracking performance as a function of actions taken by the planning model. Planning model trajectories are then optimized such that the dynamic tube lies in the free space, allowing a balance between performance and safety to be traded off in real time. The resulting Dynamic Tube MPC is applied to the 3D hopping robot ARCHER, enabling agile and performant navigation of cluttered environments, and safe collision-free traversal of narrow corridors.