用突发事故触发对比学习，让自动驾驶公交持续优化决策。
DTCCL: Disengagement-Triggered Contrastive Continual Learning for Autonomous Bus Planners
- 事故触发云端数据增强，生成正负样本。
- 对比学习提升安全行为辨识能力，性能提升48.6%。
- 无需人工干预，适合城市公交长期运行场景。
自动驾驶公交在固定路线运行，但需应对开放动态的城市环境。路线上的脱手事件常集中于特定地理区域，多源于规划器在高交互区域的策略失败。传统模仿学习难以有效纠正此类问题，因其易对稀疏的脱手数据过拟合。为此，本文提出一种脱手触发的对比持续学习框架（DTCCL），使自动驾驶公交通过真实运行持续优化规划策略。每次脱手事件触发云端数据增强，通过扰动周边交通参与者并保留路线上下文，生成正负样本。对比学习优化策略表征，更好区分安全与危险行为，且通过云-边闭环实现无监督持续更新。在城市公交路线上的实验表明，相较于直接重训练，DTCCL整体规划性能提升48.6%，验证了其在自动驾驶公共交通中可扩展、闭环策略优化的有效性。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。