Policy Optimization to Learn Adaptive Motion Primitives in Path Planning with Dynamic Obstacles

TL;DR

This paper introduces POLAMP, a policy optimization approach for adaptive motion primitives in kinodynamic path planning, demonstrating high success rates in complex dynamic obstacle environments.

Contribution

It presents a novel learnable steering function trained via policy optimization that generalizes well and improves kinodynamic planning in dynamic environments.

Findings

Achieves over 92% success rate in complex obstacle scenarios.

Outperforms state-of-the-art methods in dynamic obstacle-rich environments.

Demonstrates effective generalization to unseen problems.

Abstract

This paper addresses the kinodynamic motion planning for non-holonomic robots in dynamic environments with both static and dynamic obstacles -- a challenging problem that lacks a universal solution yet. One of the promising approaches to solve it is decomposing the problem into the smaller sub problems and combining the local solutions into the global one. The crux of any planning method for non-holonomic robots is the generation of motion primitives that generates solutions to local planning sub-problems. In this work we introduce a novel learnable steering function (policy), which takes into account kinodynamic constraints of the robot and both static and dynamic obstacles. This policy is efficiently trained via the policy optimization. Empirically, we show that our steering function generalizes well to unseen problems. We then plug in the trained policy into the sampling-based and lattice-based planners, and evaluate the resultant POLAMP algorithm (Policy Optimization that Learns Adaptive Motion Primitives) in a range of challenging setups that involve a car-like robot operating in the obstacle-rich parking-lot environments. We show that POLAMP is able to plan collision-free kinodynamic trajectories with success rates higher than 92%, when 50 simultaneously moving obstacles populate the environment showing better performance than the state-of-the-art competitors.