GNN-based decentralized perception in multi-robot systems for predicting worker actions

Imran, Ali, Beltrame, Giovanni and St-Onge, David. 2025. « GNN-based decentralized perception in multi-robot systems for predicting worker actions ». IEEE Robotics and Automation Letters, vol. 10, nº 6. pp. 6336-6343.
Compte des citations dans Scopus : 2.

PDF St-Onge-D-2025-30850.pdf - Accepted Version Restricted access to Repository staff only until 2 May 2027. Use licence: All rights reserved to copyright holder. Download (42MB) | Request a copy

Abstract

In industrial environments, predicting human actions is essential for ensuring safe and effective collaboration between humans and robots. This paper introduces a perception framework that enables mobile robots to understand and share information about human actions in a decentralized way. The framework first allows each robot to build a spatial graph representing its surroundings, which it then shares with other robots. This shared spatial data is combined with temporal information to track human behavior over time. A swarminspired decision-making process is used to ensure all robots agree on a unified interpretation of the human’s actions. Results show that adding more robots and incorporating longer time sequences improve prediction accuracy. Additionally, the consensus mechanism increases system resilience, making the multi-robot setup more reliable in dynamic industrial settings.

Item Type:	Peer reviewed article published in a journal
Researcher:	Researcher St-Onge, David
Affiliation:	Génie mécanique
Date Deposited:	23 Apr 2025 18:06
Last Modified:	22 May 2025 16:32
URI:	https://espace2.etsmtl.ca/id/eprint/30850

Actions (login required)

View Item