From Kinematics to Dynamics: Learning to Refine Hybrid Plans for Physically Feasible Execution
For robotic task planning, this method bridges the gap between high-level planners and low-level control by ensuring physical feasibility, though it is incremental over existing hybrid planning approaches.
This work addresses the problem of generating physically feasible trajectories for robots given a high-level action sequence, where hybrid planners using first-order dynamics fail to respect true physical constraints. The authors use reinforcement learning to refine first-order plans into dynamically feasible trajectories, reliably recovering physical feasibility.
In many robotic tasks, agents must traverse a sequence of spatial regions to complete a mission. Such problems are inherently mixed discrete-continuous: a high-level action sequence and a physically feasible continuous trajectory. The resulting trajectory and action sequence must also satisfy problem constraints such as deadlines, time windows, and velocity or acceleration limits. While hybrid temporal planners attempt to address this challenge, they typically model motion using linear (first-order) dynamics, which cannot guarantee that the resulting plan respects the robot's true physical constraints. Consequently, even when the high-level action sequence is fixed, producing a dynamically feasible trajectory becomes a bi-level optimization problem. We address this problem via reinforcement learning in continuous space. We define a Markov Decision Process that explicitly incorporates analytical second-order constraints and use it to refine first-order plans generated by a hybrid planner. Our results show that this approach can reliably recover physical feasibility and effectively bridge the gap between a planner's initial first-order trajectory and the dynamics required for real execution.