外观
论文arXiv 2610.1792715 天前
GLST：用于在线链式目标导航的全局-局部时空记忆分解框架
针对部分可观测且目标在线变化的长程导航，GLST分解全局-局部时空记忆，并在仿真和Spot真机上验证。
Boston Dynamics Spot原文链接：GLST: Global-Local Spatio-Temporal Memory Decomposition Framework for Online Chained-Goal Navigation（arXiv 2610.17927 · 发布日期：2026-10-13）
GLST: Global-Local Spatio-Temporal Memory Decomposition Framework for Online Chained-Goal Navigation
针对部分可观测且目标在线变化的长程导航，GLST分解全局-局部时空记忆，并在仿真和Spot真机上验证。
核心要点
- 研究在线链式目标导航，目标可能重定向或新出现且无显式转换信号。
- 提出GLST，将潜在信念分解为全局-局部空间与长短期时间表示。
- 引入目标条件奖励，在不断变化的目标下平衡探索与利用。
- 多样地形仿真实验优于基线，Spot四足机器人实验进一步验证框架。
验证范围与局限：验证范围为多样地形仿真中的链式目标导航及Spot四足机器人真机实验。
英文摘要 (Abstract)
Autonomous navigation in real-world environments often requires long-horizon operation under partial observability and evolving goals. Existing mapless navigation approaches predominantly assume fixed goals throughout an episode, limiting applicability to practical scenarios where goals change online during execution. We study online chained-goal navigation, where goals evolve through existing-goal redirection or new-goal emergence without explicit transition signals. Under this setting, we find navigation may require either continued exploration or strategic revisitation, creating conflicting memory requirements. We propose Global-Local Spatio-Temporal Belief Learning (GLST), a memory-decomposition framework that separates latent beliefs into global-local spatial and long-short temporal representations for long-horizon reasoning. We further introduce goal-conditioned rewards to balance exploration and exploitation under evolving goals. Extensive experiments in simulation across diverse terrains demonstrate improved chained-goal navigation performance over baselines. Real-robot experiments using the Spot quadruped further validate our memory decomposition framework.
作者：Yousef Liang, Ryan Ardalan, Yarden Goraly, Chenhao Zhu, Yue Yin, Jonas Frey, Claire Tomlin, Marco Pavone, Shankar Sastry
来源
本页事实对应的公开页面，以原文为准。