论文/arXiv 2610.21586·13 天前

AVALON：基于人类播种拓扑记忆的零样本室内导航

AVALON面向机器人未见但用户熟悉的室内环境，以人类播种分层空间记忆实现拓扑导航，并在Unitree Go2任务上验证。

AI 整理

• 感知与导航
• 端侧部署

宇树 Go2

原文链接：AVALON: Zero-Shot Indoor Navigation with Human-Seeded Topological Memory（arXiv 2610.21586 · 发布日期：2026-10-15）

AVALON: Zero-Shot Indoor Navigation with Human-Seeded Topological Memory

AVALON面向机器人未见但用户熟悉的室内环境，以人类播种分层空间记忆实现拓扑导航，并在Unitree Go2任务上验证。

核心要点

• 室内服务机器人常进入未建图建筑，但用户已了解布局与任务约束。
• 部署仅需平面图、地点线索和初始拓扑-里程计对齐，无需现场遍历或场地训练。
• 通过节点验证执行、重锚定和证据门控的人机记忆共更新，区分权限与可通行性。
• Go2实验中46.4秒5/5完成，较DimOS-Go2少40.9%机器人时间。

验证范围与局限：验证范围为一台Unitree Go2上的12.81米Intersection-to-Dining任务。

英文摘要 (Abstract)

Indoor service robots often enter unmapped buildings whose layouts and task constraints are already familiar to users. We address this human-familiar, robot-unseen setting with AVALON, a topological navigation framework organized around human-seeded layered spatial memory, node-verified topological execution, and task-triggered, evidence-gated human--robot memory co-updating. The robot has no prior on-site traversal or site-specific training. Deployment requires only a floor plan, place clues, and an initial topology-odometry alignment. Visual depth point-goal navigation leverages verified node arrivals to perform translational re-anchoring, without requiring a robot-constructed global SLAM map. Human--robot memory co-updating fuses complementary sources of information. Human operators specify task constraints that are unobservable via vision and report offline environmental modifications, whereas the robot provides physical-state evidence through active in-situ validation. Task relevance governs whether human-reported environmental changes undergo robot validation during the active mission. Field-collected perceptual evidence gates memory updates, maintaining an explicit separation between human-specified permissions and robot-observed traversability. Our experiments on a Unitree Go2 show that AVALON with X-NavDP completes a 12.81 m Intersection-to-Dining mission in 46.4 s (5/5) with no mapping, 40.9% less robot time than DimOS-Go2 (78.5 s, 4/5), while policy-only X-NavDP times out in all of the 5 runs. These demonstrate the superiority of the proposed topological navigation framework.

作者：Jing Xia, Changyan Li, Yuduo Wang, Guiyin Tian, Bo Wang, Yifan Liao, Mingjun Li, Shiyan Hu

来源

本页事实对应的公开页面，以原文为准。

1. arXiv 2610.21586：AVALON: Zero-Shot Indoor Navigation with Human-Seeded Topological Memory访问 2026-10-21