DTCCL：基于脱钩触发的对比连续学习用于自动驾驶巴士规划
DTCCL: Disengagement-Triggered Contrastive Continual Learning for Autonomous Bus Planners
AI总结：
DTCCL通过脱钩触发对比连续学习，提升自动驾驶巴士在动态城市环境中的规划性能，有效解决传统方法在稀疏脱钩数据下的过拟合问题。
摘要：
自动驾驶巴士运行在固定路线但必须在开放的动态城市环境中运行。这些路线上的脱钩事件往往在地理上集中，通常源于规划者在高度互动区域的失败。此类政策层面的失败难以通过传统模仿学习纠正，因为模仿学习容易过度拟合稀疏的脱钩数据。为了解决这个问题，本文提出了一种脱钩触发的对比连续学习（DTCCL）框架，使自动驾驶巴士能够通过真实世界运行改进规划策略。每次脱钩都会触发基于云的数据增强，通过扰动周围代理生成正负样本，同时保持路线上下文。对比学习优化策略表示以更好地区分安全和危险行为，连续更新在云-边循环中进行，无需人工监督。在城市巴士路线上的实验表明，DTCCL相比直接重新训练整体规划性能提高了48.6个百分点，验证了其在自动驾驶公共交通中的有效性，适用于可扩展的闭环策略改进。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
