クロスモーダル融合と知識転移によるロバストナビゲーション
Robust Navigation with Cross-Modal Fusion and Knowledge Transfer
教師-生徒蒸留で理想環境の教師からノイズの多いマルチモーダル入力に頑健な生徒を学習し、ナビゲーションの汎化とsim-to-real転移を実現した。
著者: Wenzhe Cai, Guangran Cheng, Lingyue Kong, Lu Dong, Changyin Sun
分類: cs.RO, cs.AI
原文アブストラクト
Recently, learning-based approaches show promising results in navigation tasks. However, the poor generalization capability and the simulation-reality gap prevent a wide range of applications. We consider the problem of improving the generalization of mobile robots and achieving sim-to-real transfer for navigation skills. To that end, we propose a cross-modal fusion method and a knowledge transfer framework for better generalization. This is realized by a teacher-student distillation architecture. The teacher learns a discriminative representation and the near-perfect policy in an ideal environment. By imitating the behavior and representation of the teacher, the student is able to align the features from noisy multi-modal input and reduce the influence of variations on navigation policy. We evaluate our method in simulated and real-world environments. Experiments show that our method outperforms the baselines by a large margin and achieves robust navigation performance with varying working conditions.
