Chance-Constrained Information-Theoretic Stochastic Model Predictive Control with Safety Shielding

TL;DR

This paper presents a belief-space stochastic MPPI method with chance constraints and safety shielding, enabling real-time, nonlinear, safe control in autonomous racing with reduced constraint violations.

Contribution

It introduces a novel belief-space stochastic MPPI approach that handles nonlinear dynamics and chance constraints without linearization, using GPU acceleration for real-time safety-critical applications.

Findings

Significant reduction in constraint violations in simulation

Comparable computation times to prior MPPI methods

Effective real-time planning for autonomous racing

Abstract

This paper introduces a novel nonlinear stochastic model predictive control path integral (MPPI) method, which considers chance constraints on system states. The proposed belief-space stochastic MPPI (BSS-MPPI) applies Monte-Carlo sampling to evaluate state distributions resulting from underlying systematic disturbances, and utilizes a Control Barrier Function (CBF) inspired heuristic in belief space to fulfill the specified chance constraints. Compared to several previous stochastic predictive control methods, our approach applies to general nonlinear dynamics without requiring the computationally expensive system linearization step. Moreover, the BSS-MPPI controller can solve optimization problems without limiting the form of the objective function and chance constraints. By multi-threading the sampling process using a GPU, we can achieve fast real-time planning for time- and safety-critical tasks such as autonomous racing. Our results on a realistic race-car simulation study show significant reductions in constraint violation compared to some of the prior MPPI approaches, while being comparable in computation times.