Approximately Optimal Continuous-Time Motion Planning and Control via Probabilistic Inference
This work addresses a fundamental challenge in robotics for motion planning and control, though it appears incremental as it builds on probabilistic inference and Gaussian process methods.
The authors tackled the intractable problem of optimal motion planning and control for continuous-time stochastic systems with non-instantaneous nonlinear performance indices, developing the PIPC algorithm that yields approximately optimal policies with linear complexity scaling in the number of nonlinear factors.
The problem of optimal motion planing and control is fundamental in robotics. However, this problem is intractable for continuous-time stochastic systems in general and the solution is difficult to approximate if non-instantaneous nonlinear performance indices are present. In this work, we provide an efficient algorithm, PIPC (Probabilistic Inference for Planning and Control), that yields approximately optimal policies with arbitrary higher-order nonlinear performance indices. Using probabilistic inference and a Gaussian process representation of trajectories, PIPC exploits the underlying sparsity of the problem such that its complexity scales linearly in the number of nonlinear factors. We demonstrate the capabilities of our algorithm in a receding horizon setting with multiple systems in simulation.