Cognitive-AI-Systems/mats-lp

[AAAI-2024] MATS-LP addresses the challenging problem of decentralized lifelong multi-agent pathfinding. The proposed approach utilizes a combination of Monte Carlo Tree Search and reinforcement learning for resolving conflicts.

25
/ 100
Experimental

This project helps operations engineers and logistics planners solve complex pathfinding problems for multiple agents like robots or vehicles in dynamic, confined spaces such as warehouses. It takes details about the map (e.g., 'wfi_warehouse') and the number of agents as input and outputs optimized paths to efficiently move all agents to their destinations, resolving potential conflicts along the way. This tool is for anyone managing fleets of autonomous entities that need to navigate shared environments without collisions.

No commits in the last 6 months.

Use this if you need to plan efficient, conflict-free paths for many independent robots or vehicles operating in a shared, partially observable environment like a factory floor or automated warehouse.

Not ideal if you are looking for a simple pathfinding solution for a single agent or if your environment is static and fully observable.

robotics logistics warehouse-automation fleet-management multi-agent-systems
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 0 / 25

How are scores calculated?

Stars

29

Forks

Language

C++

License

MIT

Last pushed

Jul 28, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/agents/Cognitive-AI-Systems/mats-lp"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.