Learning Continuous Cost-to-Go Functions for Non-holonomic Systems
Huh, Jinwook, Lee, Daniel D., Isler, Volkan
–arXiv.org Artificial Intelligence
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.
arXiv.org Artificial Intelligence
Mar-20-2021
- Country:
- Africa > Togo (0.04)
- North America > United States
- New York > New York County > New York City (0.04)
- Europe > United Kingdom
- England > Cambridgeshire > Cambridge (0.04)
- Asia > Middle East
- Republic of Türkiye > Karaman Province > Karaman (0.04)
- Genre:
- Research Report (0.40)
- Technology: