Uncertainty-Aware Autonomous Vehicles: Predicting the Road Ahead

TL;DR

This paper demonstrates how Random-Set Neural Networks can be integrated into autonomous vehicle perception systems to explicitly quantify uncertainty, improving safety and robustness in real-world driving scenarios.

Contribution

It introduces the use of RS-NNs for uncertainty estimation in AV perception, outperforming traditional CNNs and Bayesian methods in accuracy and calibration.

Findings

RS-NNs achieve higher accuracy than CNNs and Bayesian neural networks.

The system effectively signals uncertainty in ambiguous scenarios.

Uncertainty estimates enable dynamic speed modulation for safety.

Abstract

Autonomous Vehicle (AV) perception systems have advanced rapidly in recent years, providing vehicles with the ability to accurately interpret their environment. Perception systems remain susceptible to errors caused by overly-confident predictions in the case of rare events or out-of-sample data. This study equips an autonomous vehicle with the ability to 'know when it is uncertain', using an uncertainty-aware image classifier as part of the AV software stack. Specifically, the study exploits the ability of Random-Set Neural Networks (RS-NNs) to explicitly quantify prediction uncertainty. Unlike traditional CNNs or Bayesian methods, RS-NNs predict belief functions over sets of classes, allowing the system to identify and signal uncertainty clearly in novel or ambiguous scenarios. The system is tested in a real-world autonomous racing vehicle software stack, with the RS-NN classifying the layout of the road ahead and providing the associated uncertainty of the prediction. Performance of the RS-NN under a range of road conditions is compared against traditional CNN and Bayesian neural networks, with the RS-NN achieving significantly higher accuracy and superior uncertainty calibration. This integration of RS-NNs into Robot Operating System (ROS)-based vehicle control pipeline demonstrates that predictive uncertainty can dynamically modulate vehicle speed, maintaining high-speed performance under confident predictions while proactively improving safety through speed reductions in uncertain scenarios. These results demonstrate the potential of uncertainty-aware neural networks - in particular RS-NNs - as a practical solution for safer and more robust autonomous driving.