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

03/20/2021
by   Jinwook Huh, et al.
8

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.

READ FULL TEXT

page 1

page 3

page 4

page 5

page 6

research
12/10/2020

Cost-to-Go Function Generating Networks for High Dimensional Motion Planning

This paper presents c2g-HOF networks which learn to generate cost-to-go ...
research
10/27/2020

Learning to Generate Cost-to-Go Functions for Efficient Motion Planning

Traditional motion planning is computationally burdensome for practical ...
research
04/05/2022

A simple algorithm for uniform sampling on the surface of a hypersphere

We propose a simple method for uniform sampling of points on the surface...
research
01/07/2021

qRRT: Quality-Biased Incremental RRT for Optimal Motion Planning in Non-Holonomic Systems

This paper presents a sampling-based method for optimal motion planning ...
research
08/14/2018

Adaptive Sampling for Convex Regression

In this paper, we introduce the first principled adaptive-sampling proce...
research
04/10/2019

Learning Trajectory Prediction with Continuous Inverse Optimal Control via Langevin Sampling of Energy-Based Models

Autonomous driving is a challenging multiagent domain which requires opt...
research
09/01/2020

Adaptive Path Sampling in Metastable Posterior Distributions

The normalizing constant plays an important role in Bayesian computation...

Please sign up or login with your details

Forgot password? Click here to reset