Lifelong LaCAM with Local Guidance for Lifelong MAPF
This work addresses the need for scalable, real-time lifelong MAPF solvers, which is important for applications like warehouse robotics and autonomous vehicles.
The paper proposes LLLG, a lifelong version of LaCAM enhanced with local guidance for lifelong multi-agent pathfinding (LMAPF). It achieves state-of-the-art performance, scaling effectively and maintaining high throughput in dense environments.
Local guidance has recently proven to be a powerful driver of empirical performance in real-time, suboptimal multi-agent pathfinding (MAPF), improving the scalable configuration-based solver LaCAM. By injecting informative spatiotemporal cues around each agent, local guidance mitigates congestion, reduces waiting, and remains scalable enough even with tight time budgets, yielding state-of-the-art performance for one-shot MAPF. This study asks whether the same benefits can be lifted to the lifelong setting (LMAPF), where tasks arrive continuously and improvements in per-step plans can increase task completion throughput over long horizons. We propose LLLG, a Lifelong version of LaCAM enhanced with Local Guidance, which employs a receding-horizon windowed planning framework and warm-starts guidance from the previous solution at each timestep. Our method scales effectively, maintains high throughput even in compact, dense environments, and surpasses existing planners, thereby pushing the frontier of real-time, lifelong MAPF.