HUMEMBR: Learning Human Routines for Predictive Embodied Navigation
2026-06-29 • Robotics
Robotics
AI summaryⓘ
The authors created HUMEMBR, a system that helps robots remember and use information about people's habits to answer questions and navigate spaces better. This system collects and organizes long-term data about where people usually are and what they typically do. HUMEMBR can then quickly answer questions or make predictions about people's behavior without needing to process all the past data every time. The authors tested HUMEMBR both in simulations and on real robots, showing it works well in understanding and acting based on human routines.
embodied robotshuman behavior modelinglong-term memorynavigationroutine-conditioned navigationquestion answeringstructured memoryroboticsLLM baselinesinteractive querying
Authors
Samira Huber, Klaas Pelzer, Duc M. Nguyen, Xuesu Xiao, Sören Pirk
Abstract
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.