UWB×Crazyflow：空中ロボティクス向け劣化フィードバックの大規模シミュレーション
UWB Meets Crazyflow: Simulating Degraded Feedback at Scale for Aerial Robotics
JAXベースの微分可能シミュレータCrazyflowを提案し、UWB/IMUとEKFを統合して劣化した状態フィードバック下での制御器評価を大規模並列で可能にした。
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: Martin Schuck, Marcel P. Rath, Yufei Hua, Abhishek Goudar, SiQi Zhou, Angela P. Schoellig
分類: cs.RO
原文アブストラクト
In this work, we introduce Crazyflow, an accurate, differentiable simulator built on JAX. By leveraging jit compilation via XLA, Crazyflow unifies physics and control into a single differentiable computation graph, enabling massive parallelization on accelerated hardware without sacrificing modeling accuracy. This architecture achieves order-of-magnitude speedups over existing baselines, capable of training deployable reinforcement learning agents in seconds. To highlight its highly modular design, we demonstrate how easily Crazyflow can be extended by integrating a complete, high-fidelity Ultra-Wideband (UWB) and Inertial Measurement Unit (IMU) simulation pipeline coupled with a full-state Extended Kalman Filter (EKF). This capability allows for massive parallel controller evaluation under realistic, degraded state feedback with minimal impact on GPU throughput. By combining speed, accuracy, and extensibility, Crazyflow serves as a foundational tool for the next generation of aerial robotics research.
