DTCCL: Disengagement-Triggered Contrastive Continual Learning for Autonomous Bus Planners

TL;DR

This paper introduces DTCCL, a novel framework that uses disengagement events to enhance autonomous bus planning policies through contrastive continual learning, significantly improving safety and performance in urban environments.

Contribution

The paper proposes a disengagement-triggered contrastive continual learning method that leverages real-world disengagement data for scalable policy improvement in autonomous buses.

Findings

DTCCL improves planning performance by 48.6% over direct retraining.

The framework effectively distinguishes safe and unsafe behaviors.

Experiments validate DTCCL's scalability and effectiveness in urban bus routes.

Abstract

Autonomous buses run on fixed routes but must operate in open, dynamic urban environments. Disengagement events on these routes are often geographically concentrated and typically arise from planner failures in highly interactive regions. Such policy-level failures are difficult to correct using conventional imitation learning, which easily overfits to sparse disengagement data. To address this issue, this paper presents a Disengagement-Triggered Contrastive Continual Learning (DTCCL) framework that enables autonomous buses to improve planning policies through real-world operation. Each disengagement triggers cloud-based data augmentation that generates positive and negative samples by perturbing surrounding agents while preserving route context. Contrastive learning refines policy representations to better distinguish safe and unsafe behaviors, and continual updates are applied in a cloud-edge loop without human supervision. Experiments on urban bus routes demonstrate that DTCCL improves overall planning performance by 48.6 percent compared with direct retraining, validating its effectiveness for scalable, closed-loop policy improvement in autonomous public transport.