Cooperative Informative Sensing for Monitoring Dynamic Indoor Environments via Multi-Agent Reinforcement Learning

2026-04-25

AI Summary

This work addresses the limitations of existing indoor multi-robot surveillance approaches, which typically rely on coverage or visit frequency metrics and struggle to meet the accuracy demands of human-centric monitoring tasks. The problem is formulated as a decentralized multi-agent active perception task under partial observability, and a collaborative perception framework is proposed that directly optimizes monitoring accuracy. Integrating multi-agent reinforcement learning with a neural architecture capable of modeling dynamic human counts and temporal dependencies, the framework operates efficiently in decentralized settings. Extensive simulations demonstrate that the method significantly outperforms conventional baselines—including coverage-based, persistent monitoring, and non-learning strategies—across diverse indoor environments, while exhibiting strong robustness to variations in the number of humans present.

Technology Category

• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Multiagent Systems: Multiagent Learning
• Humans and AI: Planning and Decision Support for Human-Machine Teams

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Monitoring human activity in indoor environments is important for applications such as facility management, safety assessment, and space utilization analysis. While mobile robot teams offer the potential to actively improve observation quality, existing multi-robot monitoring and active perception approaches typically rely on coverage or visitation based objectives that are weakly aligned with the accuracy requirements of human-centric monitoring tasks. In this work, we formulate cooperative active observation as a decentralized control problem in which multiple robots adjust their motion to directly optimize monitoring accuracy under partial observability. We propose a learning-based framework for cooperative policies from decentralized observations using multi-agent reinforcement learning (MARL), supported by an architecture that handles variable numbers of humans and temporal dependencies. Simulation results across diverse indoor environments and monitoring tasks show that the proposed approach consistently outperforms classical coverage, persistent monitoring, and learning-free multi-robot baselines, while remaining robust to changes in the number of observed humans.

Problem

• multi-agent reinforcement learning
• active perception
• human activity monitoring
• indoor environment monitoring
• cooperative sensing

Innovation

• multi-agent reinforcement learning
• cooperative active sensing
• decentralized control
• human activity monitoring
• partial observability