A MARL framework lets robot teams optimize monitoring accuracy for dynamic indoor human activities via decentralized policies that handle variable human counts and time dependencies, outperforming coverage baselines in simulations.
Using gps to learn significant locations and predict movement across multiple users,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.RO 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Cooperative Informative Sensing for Monitoring Dynamic Indoor Environments via Multi-Agent Reinforcement Learning
A MARL framework lets robot teams optimize monitoring accuracy for dynamic indoor human activities via decentralized policies that handle variable human counts and time dependencies, outperforming coverage baselines in simulations.