Multi-Agent Motion Planning

Motivation How to improve the solution quality of the MAMP in realistic cases?

Mar 1, 2025

Overview We present Scalable Multi-Agent Realistic Testbed (SMART), a realistic and efficient software tool for evaluating Multi-Agent Path Finding (MAPF) algorithms coupling with robot models of different kinodynamics. MAPF focuses on planning collision-free paths for a group of robots. While state-of-the-art MAPF algorithms can plan paths for hundreds of robots in seconds, they often rely on simplified robot models, making their real-world performance unclear. Researchers typically lack access to hundreds of physical robots in laboratory settings to evaluate the algorithms. Meanwhile, industrial professionals who lack expertise in MAPF require a simulator to efficiently test and understand the performance of state-of-the-art MAPF algorithms. SMART fills this gap with several advantages: (1) SMART uses a physics-engine-based simulator to create realistic simulation environments, accounting for complex real-world factors such as robot kinodynamics and movement delays, (2) SMART uses an execution monitor framework based on the Action Dependency Graph, facilitating seamless integration with various MAPF algorithms and robot models, and (3) SMART scales to thousands of robots. In addition, we use SMART to explore and demonstrate research questions about the execution of MAPF algorithms in real-world scenarios.

Mar 1, 2025

Multi-Agent Motion Planning (MAMP) seeks collision-free, dynamically feasible trajectories for multiple agents while minimizing travel time.

Jan 1, 2024