外观
论文arXiv 2610.1287719 天前
TAME-Nav：用于敏捷且通用机器人导航的时间非对称混合专家蒸馏
原文链接：TAME-Nav: Temporal Asymmetric Mixture-of-Experts Distillation for Agile and Versatile Robot Navigation（arXiv 2610.12877 · 发布日期：2026-10-09）
TAME-Nav: Temporal Asymmetric Mixture-of-Experts Distillation for Agile and Versatile Robot Navigation
TAME-Nav用时间Soft-MoE师生蒸馏提升复杂动态场景导航，并在仿真与真实四足机器人上验证。
核心要点
- 单一策略难以适应多样场景中不同的导航决策需求。
- 教师用干净观测和动态障碍轨迹构造特权表示，学生从受扰历史中蒸馏学习。
- 程序化场景生成、并行任务仿真和非对称域随机化拓展训练并支持迁移。
- 在分布内和未见组合场景优于代表性基线，真机二十次试验仅一次轻微接触。
验证范围与局限：验证范围为分布内和未见组合仿真场景，以及一台真实四足机器人上的局部陷阱逃逸和窄通道突发动态障碍任务。
英文摘要 (Abstract)
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.
作者：Lingjie Zhang, Jun Xue, Shanze Wang, Haoyu Xi, Xinming Zhang, Xiaoyu Shen, Wei Zhang
来源
本页事实对应的公开页面，以原文为准。