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

2025/12/22 by Yanding Yang, Weitao Zhou, Yang, Yanding +19
Computer Science · Engineering · #Autonomous Vehicle Technology and Safety #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Reinforcement Learning in Robotics #Robotics (cs.RO)

paper · doi:10.48550/arxiv.2512.18988

openalex publication_date 2025/12/22 · openalex created_date 2025/12/24 · openalex updated_date 2026/07/28

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.

Citations

• DRARL: Disengagement-Reason-Augmented Reinforcement Learning for Efficient Improvement of Autonomous Driving Policy
• RALAD: Bridging the Real-to-Sim Domain Gap in Autonomous Driving with Retrieval-Augmented Learning
• Continuously Learning, Adapting, and Improving: A Dual-Process Approach to Autonomous Driving
• PLUTO: Pushing the Limit of Imitation Learning-based Planning for Autonomous Driving
• Adaptive Memory Replay for Continual Learning
• Towards learning-based planning:The nuPlan benchmark for real-world autonomous driving
• A Robust Integrated Multi-Strategy Bus Control System via Deep Reinforcement Learning
• How Simulation Helps Autonomous Driving:A Survey of Sim2real, Digital Twins, and Parallel Intelligence
• Dynamically Conservative Self-Driving Planner for Long-Tail Cases
• COMPASS: Contrastive Multimodal Pretraining for Autonomous Systems
• DR2L: Surfacing Corner Cases to Robustify Autonomous Driving via Domain Randomization Reinforcement Learning
• Decision-Making Technology for Autonomous Vehicles Learning-Based Methods, Applications and Future Outlook
• NuPlan: A closed-loop ML-based planning benchmark for autonomous vehicles
• Trajectory Planning for Autonomous Vehicles Using Hierarchical Reinforcement Learning
• Action-Based Representation Learning for Autonomous Driving
• Active Domain Randomization
• End-to-end Driving via Conditional Imitation Learning
• Progressive Neural Networks
• End to End Learning for Self-Driving Cars
• DeepDriving: Learning Affordance for Direct Perception in Autonomous Driving

Related

• Semi-on-Demand Transit Feeders with Shared Autonomous Vehicles and Reinforcement-Learning-Based Zonal Dispatching Control
• A Robust Integrated Multi-Strategy Bus Control System via Deep Reinforcement Learning
• Single Agent Robust Deep Reinforcement Learning for Bus Fleet Control
• DeFIX: Detecting and Fixing Failure Scenarios with Reinforcement Learning in Imitation Learning Based Autonomous Driving
• Realistic Urban Traffic Generator using Decentralized Federated Learning for the SUMO simulator