IEEE International Conference on Robotics and Automation - ICRA 2025, Atlanta (Estados Unidos de América). 19-23 mayo 2025
Resumen:
In decentralized multiagent trajectory planners, agents need to communicate and exchange their positions to generate collision-free trajectories. However, due to localization errors/uncertainties, trajectory deconfliction can fail even if trajectories are perfectly shared between agents. To address this issue, we first present PARM and PARM*, perception-aware, decentralized, asynchronous multiagent trajectory planners that enable a team of agents to navigate uncertain environments while deconflicting trajectories and avoiding obstacles using perception information. PARM* differs from PARM as it is less conservative, using more computation to find closer-to-optimal solutions. While these methods achieve state-of-the-art performance, they suffer from high computational costs as they need to solve large optimization problems onboard, making it difficult for agents to replan at high rates. To overcome this challenge, we present our second key contribution, PRIMER, a learning-based planner trained with imitation learning (IL) using PARM* as the expert demonstrator. PRIMER leverages the low computational requirements at deployment of neural networks and achieves a computation speed up to 5614 times faster than optimization-based approaches.
Resumen divulgativo:
Este artículo presenta PARM y PARM*, planificadores que ayudan a múltiples agentes a evitar colisiones utilizando datos de percepción, incluso con errores de localización. Para aumentar la velocidad, presentamos PRIMER, un planificador basado en el aprendizaje que imita a PARM* y es hasta 5500 veces más rápido.
Fecha de publicación: 2025-05-19.
Cita:
K. Kondo, C.T. Tewari, A. Tagliabue, J. Tordesillas Torres, P.C. Lusk, J.P. How, PRIMER: Perception-Aware Robust Learning-based Multiagent Trajectory Planner, IEEE International Conference on Robotics and Automation - ICRA 2025, Atlanta (Estados Unidos de América). 19-23 mayo 2025.