C-Uniform Trajectory Sampling For Fast Motion Planning

Authors: O. Goktug Poyrazoglu, Yukang Cao, Volkan Isler

Published: 2024 (Conference Paper)

Source: IEEE International Conference on Robotics and Automation (ICRA)

Algorithm: C-Uniform MPPI

arXiv: 2409.12266

DOI: 10.1109/ICRA55743.2025.11127482

Summary

Proposes a C-Uniform action sampling distribution based on the dynamically reachable sets of the controlled system, enabling far more efficient exploration of trajectory space compared to naive Gaussian sampling, especially for tight obstacle avoidance. Offline training takes ~4 hours for a 3-state unicycle model, but runtime cost matches naive sampling.

Abstract

We study the problem of sampling robot trajectories and introduce the notion of C-Uniformity. As opposed to the standard method of uniformly sampling control inputs (which lead to biased samples of the configuration space), C-Uniform trajectories are generated by control actions which lead to uniform sampling of the configuration space. After presenting an intuitive closed-form solution to generate C-Uniform trajectories for the 1D random-walker, we present a network-flow based optimization method to precompute C-Uniform trajectories for general robot systems. We apply the notion of C-Uniformity to the design of Model Predictive Path Integral controllers. Through simulation experiments, we show that using C-Uniform trajectories significantly improves the performance of MPPI-style controllers, achieving up to 40% coverage performance gain compared to the best baseline. We demonstrate the practical applicability of our method with an implementation on a 1/10th scale racer.

Links

Primary

Paper arxiv.org

Standard

arXiv Abstract 2409.12266 arXiv PDF 2409.12266 arXiv HTML 2409.12266 DOI 10.1109/ICRA55743.2025.11127482

Alternate

ieeexplore.ieee.org ieeexplore.ieee.org

Tags

• MPPI

• Trajectory optimization

• Sampling-based control

• Action sampling

• Reachable sets

• Configuration space