让机器人学会人类日常习惯，精准预测其位置和动向。
HUMEMBR: Learning Human Routines for Predictive Embodied Navigation
- 构建连续记忆系统，记录人类长期行为模式
- 相比大模型少用大量token，仍能准确预测
- 可在真实环境中支持多种导航任务
理解并长时间在以人为中心的环境中导航，同时考虑人类行为与日常规律，仍是机器人领域的一大挑战。在真实场景中，机器人可能需要定位特定人员、预测其可能出现的位置，或估算其离开建筑的时间。解决这些问题需对大量历史观测数据进行推理，并捕捉长期行为模式。为此，我们提出面向具身机器人的类人记忆系统（HUMEMBR），支持具身问答与基于习惯的导航。HUMEMBR结合连续记忆构建与并行检索查询机制，可积累结构化的人类习惯表示，并支持用户交互式查询。实验表明，相较于全上下文大语言模型基线，HUMEMBR在长时序人类行为推理上表现更优，且使用更少的token。此外，我们在两个不同真实环境中部署了物理机器人，验证了其在复杂条件下处理多样查询与导航任务的能力。
原文摘要 · Abstract (English)
Understanding and navigating human-centered environments over extended periods of time while considering human behavior and routines remains a fundamental challenge in robotics. In real-world settings, robots may be asked to locate a specific individual, predict where that person is likely to be, or estimate when they typically leave a building. Addressing such queries requires reasoning over extensive histories of observations and capturing long-term behavioral patterns. To this end, we introduce Human-Centered Memory for Embodied Robots (HUMEMBR), a system designed for embodied question answering and routine-conditioned navigation. HUMEMBR integrates a continuous memory construction process with a parallel retrieval and querying mechanism, enabling the system to accumulate structured representations of human routines while supporting interactive, user-driven queries. Our experimental results indicate that HUMEMBR improves long-horizon reasoning about human behavior relative to full-context LLM baselines, while using substantially fewer tokens. Furthermore, we deploy HUMEMBR on a physical robot in two distinct environments, showing its ability to handle diverse queries and navigation tasks under real-world conditions.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。