Uncertainty-Aware Perception-Based Control for Autonomous Racing

TL;DR

This paper presents an uncertainty-aware perception-based control method for autonomous racing that integrates road estimation, quantifies uncertainty, and improves robustness using a Frenet frame formulation, validated in simulation.

Contribution

It introduces a novel perception-control integration with uncertainty quantification and a parametric road model optimized via visual data, enhancing autonomous vehicle robustness.

Findings

Effective in simulated autonomous racing scenarios

Improves robustness by explicitly accounting for perception uncertainty

Demonstrates reliable control with visual-based road estimation

Abstract

Autonomous systems operating in unknown environments often rely heavily on visual sensor data, yet making safe and informed control decisions based on these measurements remains a significant challenge. To facilitate the integration of perception and control in autonomous vehicles, we propose a novel perception-based control approach that incorporates road estimation, quantification of its uncertainty, and uncertainty-aware control based on this estimate. At the core of our method is a parametric road curvature model, optimized using visual measurements of the road through a constrained nonlinear optimization problem. This process ensures adherence to constraints on both model parameters and curvature. By leveraging the Frenet frame formulation, we embed the estimated track curvature into the system dynamics, allowing the controller to explicitly account for perception uncertainty and enhancing robustness to estimation errors based on visual input. We validate our approach in a simulated environment, using a high-fidelity 3D rendering engine, and demonstrate its effectiveness in achieving reliable and uncertainty-aware control for autonomous racing.