DTCCL: Disengagement-Triggered Contrastive Continual Learning for Autonomous Bus Planners
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911331726131200 |
|---|---|
| author | Yang, Yanding Zhou, Weitao Wang, Jinhai Guo, Xiaomin Wen, Junze Liu, Xiaolong Ding, Lang Fu, Zheng Miao, Jinyu Jiang, Kun Yang, Diange |
| author_facet | Yang, Yanding Zhou, Weitao Wang, Jinhai Guo, Xiaomin Wen, Junze Liu, Xiaolong Ding, Lang Fu, Zheng Miao, Jinyu Jiang, Kun Yang, Diange |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_18988 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | DTCCL: Disengagement-Triggered Contrastive Continual Learning for Autonomous Bus Planners Yang, Yanding Zhou, Weitao Wang, Jinhai Guo, Xiaomin Wen, Junze Liu, Xiaolong Ding, Lang Fu, Zheng Miao, Jinyu Jiang, Kun Yang, Diange Robotics 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. |
| title | DTCCL: Disengagement-Triggered Contrastive Continual Learning for Autonomous Bus Planners |
| topic | Robotics |
| url | https://arxiv.org/abs/2512.18988 |