ベクトル場拡張によるビジョンベースドローンレースの微分可能ポリシー学習
Vector Field Augmented Differentiable Policy Learning for Vision-Based Drone Racing
ドローンレース向けに、微分可能な損失とベクトル場を組み合わせた新しい学習フレームワークDiffRacingを提案し、シミュレーションと実機で高いサンプル効率と堅牢な飛行性能を実証した。
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: Yang Su, Feng Yu, Yu Hu, Xinze Niu, Linzuo Zhang, Fangyu Sun, Danping Zou
分類: cs.RO
原文アブストラクト
Autonomous drone racing in complex environments requires agile, high-speed flight while maintaining reliable obstacle avoidance. Differentiable-physics-based policy learning has recently demonstrated high sample efficiency and remarkable performance across various tasks, including agile drone flight and quadruped locomotion. However, applying such methods to drone racing remains difficult, as key objective like gate traversal are inherently hard to express as smooth, differentiable losses. To address these challenges, we propose DiffRacing, a novel vector field-augmented differentiable policy learning framework. DiffRacing integrates differentiable losses and vector fields into the training process to provide continuous and stable gradient signals, balancing obstacle avoidance and high-speed gate traversal. In addition, a differentiable Delta Action Model compensates for dynamics mismatch, enabling efficient sim-to-real transfer without explicit system identification. Extensive simulation and real-world experiments demonstrate that DiffRacing achieves superior sample efficiency, faster convergence, and robust flight performance, thereby demonstrating that vector fields can augment traditional gradient-based policy learning with a task-specific geometric prior.
関連論文
- 障害物を考慮した自律ドローンレースのための汎化可能な方策の学習ドローンレース/強化学習
- 環境をポリシーとして：未知のコースを走るドローンレースの学習ドローンレース/強化学習
- 深層強化学習による自律ドローンレースドローンレース/強化学習
