Continual Learning for Adaptable Car-Following in Dynamic Traffic Environments

TL;DR

This paper introduces a continual learning-based car-following model that adapts to diverse traffic environments, significantly reducing collisions and outperforming traditional models by integrating EWC and MAS techniques.

Contribution

It presents a novel continual learning framework for car-following that effectively mitigates catastrophic forgetting in dynamic traffic scenarios.

Findings

Achieves 0% collision rate across various traffic conditions.

Outperforms baseline models in adaptability and safety.

Demonstrates effectiveness of EWC and MAS in autonomous driving models.

Abstract

The continual evolution of autonomous driving technology requires car-following models that can adapt to diverse and dynamic traffic environments. Traditional learning-based models often suffer from performance degradation when encountering unseen traffic patterns due to a lack of continual learning capabilities. This paper proposes a novel car-following model based on continual learning that addresses this limitation. Our framework incorporates Elastic Weight Consolidation (EWC) and Memory Aware Synapses (MAS) techniques to mitigate catastrophic forgetting and enable the model to learn incrementally from new traffic data streams. We evaluate the performance of the proposed model on the Waymo and Lyft datasets which encompass various traffic scenarios. The results demonstrate that the continual learning techniques significantly outperform the baseline model, achieving 0\% collision rates across all traffic conditions. This research contributes to the advancement of autonomous driving technology by fostering the development of more robust and adaptable car-following models.