Risk-Aware Model Predictive Path Integral Control Using Conditional Value-at-Risk

TL;DR

This paper introduces a risk-aware Model Predictive Path Integral control method that uses CVaR to enhance safety in autonomous robot navigation without linearizing dynamics, demonstrated through aggressive driving in cluttered environments.

Contribution

The paper presents a novel RA-MPPI control approach that directly incorporates original dynamics and CVaR, improving safety and efficiency in robotic control tasks.

Findings

Achieves similar lap times with fewer collisions.

Operates at up to 80Hz using GPU acceleration.

Effective in cluttered, safety-critical environments.

Abstract

In this paper, we present a novel Model Predictive Control method for autonomous robots subject to arbitrary forms of uncertainty. The proposed Risk-Aware Model Predictive Path Integral (RA-MPPI) control utilizes the Conditional Value-at-Risk (CVaR) measure to generate optimal control actions for safety-critical robotic applications. Different from most existing Stochastic MPCs and CVaR optimization methods that linearize the original dynamics and formulate control tasks as convex programs, the proposed method directly uses the original dynamics without restricting the form of the cost functions or the noise. We apply the novel RA-MPPI controller to an autonomous vehicle to perform aggressive driving maneuvers in cluttered environments. Our simulations and experiments show that the proposed RA-MPPI controller can achieve about the same lap time with significantly fewer collisions compared to the baseline MPPI controller. The proposed controller performs on-line computation at an update frequency of up to 80Hz, utilizing modern Graphics Processing Units (GPUs) to multi-thread the generation of trajectories as well as the CVaR values.