Enhance Planning with Physics-informed Safety Controller for End-to-end Autonomous Driving

TL;DR

This paper introduces FusionAssurance, a novel framework that combines physics-informed control with neural network planning to improve safety and generalization in autonomous driving, especially in unseen scenarios.

Contribution

FusionAssurance uniquely integrates Potential Field with Model Predictive Control to enhance safety and robustness in end-to-end autonomous driving systems.

Findings

Effective in navigating unseen scenarios

Improves safety in out-of-distribution situations

Demonstrated on CARLA benchmark with extensive experiments

Abstract

Recent years have seen a growing research interest in applications of Deep Neural Networks (DNN) on autonomous vehicle technology. The trend started with perception and prediction a few years ago and it is gradually being applied to motion planning tasks. Despite the performance of networks improve over time, DNN planners inherit the natural drawbacks of Deep Learning. Learning-based planners have limitations in achieving perfect accuracy on the training dataset and network performance can be affected by out-of-distribution problem. In this paper, we propose FusionAssurance, a novel trajectory-based end-to-end driving fusion framework which combines physics-informed control for safety assurance. By incorporating Potential Field into Model Predictive Control, FusionAssurance is capable of navigating through scenarios that are not included in the training dataset and scenarios where neural network fail to generalize. The effectiveness of the approach is demonstrated by extensive experiments under various scenarios on the CARLA benchmark.