Search papers, labs, and topics across Lattice.
This paper introduces a cooperative active search framework for localizing people in industrial environments using heterogeneous robot teams by leveraging prior information and behavioral models. They estimate human motion trajectories by combining global path planning with the Social Force Model and formulate multi-robot coordination as a Mixed Integer Linear Programming (MILP) optimization problem. Experiments in real-world industrial scenarios demonstrate that this approach outperforms baseline search strategies.
Coordinating heterogeneous robot teams with predictive models of human behavior can significantly improve search efficiency in complex industrial environments.
We propose a cooperative active search framework for localizing people in industrial environments with a team of heterogeneous robots. In contrast to exhaustive search methods, our approach leverages prior information about the initial target distribution and potential behavior to enable primed probabilistic search strategies. To estimate a person's motion trajectory, we combine global path planning with the Social Force Model. We formulate the multi-robot coordination problem as a Mixed Integer Linear Programming (MILP) optimization that accounts for visibility constraints and heterogeneous robot capabilities. Monte Carlo simulation experiments in two real-world industrial scenarios based on simulated and real human trajectory data show that our approach outperforms several baselines. The results demonstrate the effectiveness of combining predictive target modeling for coordinating robot search teams.