Automatic AI controller that can drive with confidence: steering vehicle with uncertainty knowledge

TL;DR

This paper presents a Bayesian Neural Network-based vehicle control system that quantifies uncertainty to improve safety and reliability in autonomous driving by signaling low-confidence predictions for manual intervention.

Contribution

It introduces a novel vehicle lateral control approach using BNNs to quantify uncertainty, enabling safer autonomous driving with confidence-based intervention.

Findings

The BNN controller adapts across multiple tracks.

Uncertainty quantification effectively signals potential control failures.

Confidence thresholds enable timely manual intervention.

Abstract

In safety-critical systems that interface with the real world, the role of uncertainty in decision-making is pivotal, particularly in the context of machine learning models. For the secure functioning of Cyber-Physical Systems (CPS), it is imperative to manage such uncertainty adeptly. In this research, we focus on the development of a vehicle's lateral control system using a machine learning framework. Specifically, we employ a Bayesian Neural Network (BNN), a probabilistic learning model, to address uncertainty quantification. This capability allows us to gauge the level of confidence or uncertainty in the model's predictions. The BNN based controller is trained using simulated data gathered from the vehicle traversing a single track and subsequently tested on various other tracks. We want to share two significant results: firstly, the trained model demonstrates the ability to adapt and effectively control the vehicle on multiple similar tracks. Secondly, the quantification of prediction confidence integrated into the controller serves as an early-warning system, signaling when the algorithm lacks confidence in its predictions and is therefore susceptible to failure. By establishing a confidence threshold, we can trigger manual intervention, ensuring that control is relinquished from the algorithm when it operates outside of safe parameters.