不確実性重み付きDecision Transformerによる密集複雑運転シーンでのナビゲーション
An Uncertainty-Weighted Decision Transformer for Navigation in Dense, Complex Driving Scenarios
鳥瞰図占有グリッドとTransformerを組み合わせ、予測エントロピーで損失を重み付けするUWDTを提案し、ラウンドアバウトでの自動運転判断を安全かつ効率的にした。
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: Zhihao Zhang, Chengyang Peng, Minghao Zhu, Ekim Yurtsever, Keith A. Redmill
分類: cs.RO, cs.AI
原文アブストラクト
Autonomous driving in dense, dynamic environments requires decision-making systems that can exploit both spatial structure and long-horizon temporal dependencies while remaining robust to uncertainty. This work presents a novel framework that integrates multi-channel bird's-eye-view occupancy grids with transformer-based sequence modeling for tactical driving in complex roundabout scenarios. To address the imbalance between frequent low-risk states and rare safety-critical decisions, we propose the Uncertainty-Weighted Decision Transformer (UWDT). UWDT employs a frozen teacher transformer to estimate per-token predictive entropy, which is then used as a weight in the student model's loss function. This mechanism amplifies learning from uncertain, high-impact states while maintaining stability across common low-risk transitions. Experiments in a roundabout simulator, across varying traffic densities, show that UWDT consistently outperforms other baselines in terms of reward, collision rate, and behavioral stability. The results demonstrate that uncertainty-aware, spatial-temporal transformers can deliver safer and more efficient decision-making for autonomous driving in complex traffic environments.
