Control Barrier Function Augmentation in Sampling-based Control Algorithm for Sample Efficiency

TL;DR

This paper introduces a novel control algorithm that combines control barrier functions with sampling-based control to enhance sample efficiency and safety in cluttered, obstacle-rich environments for nonlinear stochastic path planning.

Contribution

It proposes a new algorithm integrating control barrier functions with model predictive path integral control, reducing sample requirements and improving performance in complex environments.

Findings

Requires fewer samples and time-steps than previous methods.

Achieves better safety and efficiency in obstacle-rich environments.

Outperforms original model predictive path integral control algorithm.

Abstract

For a nonlinear stochastic path planning problem, sampling-based algorithms generate thousands of random sample trajectories to find the optimal path while guaranteeing safety by Lagrangian penalty methods. However, the sampling-based algorithm can perform poorly in obstacle-rich environments because most samples might violate safety constraints, invalidating the corresponding samples. To improve the sample efficiency of sampling-based algorithms in cluttered environments, we propose an algorithm based on model predictive path integral control and control barrier functions. The proposed algorithm needs fewer samples and time-steps and has a better performance in cluttered environments compared to the original model predictive path integral control algorithm.