DTCCL: 自動運転バスプランナーのための介入トリガ型対照継続学習
DTCCL: Disengagement-Triggered Contrastive Continual Learning for Autonomous Bus Planners
自動運転バスの介入イベントを契機に、クラウドで周辺エージェントを摂動させた対照学習を行い、人間の監督なしに計画方針を継続的に改善する枠組みを提案した。
詳しい要約
1. どんなもの?
2. 先行研究と比べてどこがすごい?
3. 技術・手法の肝は?
4. どうやって有効だと検証した?
5. 議論はある?
6. 次に読むべき論文は?
※ AIが要旨から生成した要約です。正確性は原文をご確認ください。
著者: Yanding Yang, Weitao Zhou, Jinhai Wang, Xiaomin Guo, Junze Wen, Xiaolong Liu, Lang Ding, Zheng Fu, Jinyu Miao, Kun Jiang, Diange Yang
分類: cs.RO
原文アブストラクト
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.
関連論文
- 漸進的エキスパート混合ネットワークによる自動運転の継続的適応自動運転/継続学習
- 交通ダイバージェンス計測に基づく動的勾配シナリオメモリを用いた継続的対話型行動学習自動運転/継続学習
