English

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

Robotics 2021-03-23 v1 Artificial Intelligence Machine Learning

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.

Keywords

Cite

@article{arxiv.2103.11168,
  title  = {Learning Continuous Cost-to-Go Functions for Non-holonomic Systems},
  author = {Jinwook Huh and Daniel D. Lee and Volkan Isler},
  journal= {arXiv preprint arXiv:2103.11168},
  year   = {2021}
}
R2 v1 2026-06-24T00:22:47.815Z