Design of a Human-Assistance Robot System with Contextual Action Recognition

Abstract:This paper presents a conceptual design for a proactive human assisting robot system capable of recognizing human activities and responding proactively. The system leverages contextual human activity recognition to interpret human actions across diverse contexts, while behavior trees are utilized to define dynamic and interpretable robot behaviors. We outline the system architecture, incorporating contextual human action recognition (HAR), behavior trees (BTs), and ROS, using the Spot robot platform as a representative example. We explain how HAR enables the robot to provide proactive assistance, discuss its limitations, and introduce methodologies for contextual HAR to address these limitations, thereby enhancing the robot's decision-making in complex human activity scenarios.

Published in Automation 2025: Recent Advances in Automation, Robotics and Measurement Techniques, Lecture Notes in Networks and Systems, vol. 1687, Springer Nature, 2025. DOI: https://doi.org/10.1007/978-3-032-08359-3_16

Robotics (cs.RO)

arXiv:2608.22028 [cs.RO]

(or arXiv:2608.22028v1 [cs.RO] for this version)

https://doi.org/10.48550/arXiv.2608.22028 arXiv-issued DOI via DataCite (pending registration)

A. Ergogo and T. Zielińska, Automation 2025: Recent Advances in Automation, Robotics and Measurement Techniques, Lecture Notes in Networks and Systems, vol. 1687, Springer, 2026, pp. 175-186

https://doi.org/10.1007/978-3-032-08359-3_16 DOI(s) linking to related resources