TAME-Nav:時間的非対称Mixture-of-Experts蒸留による俊敏で汎用なロボットナビゲーション
TAME-Nav: Temporal Asymmetric Mixture-of-Experts Distillation for Agile and Versatile Robot Navigation
教師が特権的な動的障害物追跡を使い、生徒が劣化観測から時間エンコーディングとSoft-MoE蒸留でナビゲーション方策を学習する枠組みを提案し、四足ロボットでの実機実験で有効性を示した。
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: Lingjie Zhang, Jun Xue, Shanze Wang, Haoyu Xi, Xinming Zhang, Xiaoyu Shen, Wei Zhang
分類: cs.RO
原文アブストラクト
Agile and reliable navigation is a core capability for embodied robots navigating complex spatial constraints and dynamic interactions. However, a single policy often struggles to accommodate the distinct decision-making demands of diverse scenarios. We present TAME-Nav, an asymmetric Teacher-Student navigation framework built around a temporal soft mixture of experts (Soft-MoE). The Teacher combines clean observations with causally maintained dynamic-obstacle tracks to construct privileged representations, while the Student learns complementary navigation features from corrupted observation histories through temporal encoding, soft expert routing, and latent distillation. Procedural scenario generation and parallel task-level simulation broaden training coverage, while deployment-informed asymmetric domain randomization supports sim-to-real transfer. Across in-distribution and unseen compositional scenarios, TAME-Nav achieves higher success rates, lower collision rates, and higher navigation scores than representative baselines. On a real quadruped robot, it completes all twenty trials across local-trap escape and narrow-passage navigation with sudden dynamic obstacles, with only one minor contact.