Learning Continuous Cost-to-Go Functions for Non-holonomic Systems

TL;DR

This paper introduces an adaptive sampling-based supervised learning approach to efficiently generate continuous cost-to-go functions for non-holonomic systems, enabling faster and near-optimal trajectory planning in complex environments.

Contribution

It presents a novel adaptive sampling method combined with neural networks to accurately learn cost-to-go functions for non-holonomic systems, overcoming limitations of uniform sampling.

Findings

Method achieves two orders of magnitude speedup over traditional approaches.

Network successfully generates near-optimal trajectories in cluttered environments.

Adaptive sampling improves learning accuracy for high-curvature trajectory manifolds.

Abstract

This paper presents a supervised learning method to generate continuous cost-to-go functions of non-holonomic systems directly from the workspace description. Supervision from informative examples reduces training time and improves network performance. The manifold representing the optimal trajectories of a non-holonomic system has high-curvature regions which can not be efficiently captured with uniform sampling. To address this challenge, we present an adaptive sampling method which makes use of sampling-based planners along with local, closed-form solutions to generate training samples. The cost-to-go function over a specific workspace is represented as a neural network whose weights are generated by a second, higher order network. The networks are trained in an end-to-end fashion. In our previous work, this architecture was shown to successfully learn to generate the cost-to-go functions of holonomic systems using uniform sampling. In this work, we show that uniform sampling fails for non-holonomic systems. However, with the proposed adaptive sampling methodology, our network can generate near-optimal trajectories for non-holonomic systems while avoiding obstacles. Experiments show that our method is two orders of magnitude faster compared to traditional approaches in cluttered environments.