CognitiveAISystems/MAPF-GPT

[AAAI-2025] This repository contains MAPF-GPT, a deep learning-based model for solving MAPF problems. Trained with imitation learning on trajectories produced by LaCAM, it generates actions under partial observability without heuristics or agent communication. MAPF-GPT excels on unseen instances and outperforms learnable state-of-the-art solvers

53
/ 100
Established

This project helps operations managers, logistics planners, and robotics engineers efficiently coordinate many autonomous agents or robots within a shared space. It takes in a map of an environment and the desired starting and ending points for each agent, then outputs a set of synchronized actions, ensuring all agents reach their destinations without collisions or deadlocks. It's designed for anyone managing complex multi-agent systems where optimal movement is critical.

119 stars.

Use this if you need to find collision-free paths for a large number of agents (e.g., robots in a warehouse, drones in a delivery system) in complex, potentially unknown environments without needing extensive communication between them.

Not ideal if you're dealing with only a few agents or if your environment is simple enough for basic pathfinding algorithms.

robotics logistics-optimization warehouse-automation multi-agent-coordination traffic-management
No Package No Dependents
Maintenance 10 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 17 / 25

How are scores calculated?

Stars

119

Forks

18

Language

C++

License

MIT

Last pushed

Mar 05, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/CognitiveAISystems/MAPF-GPT"

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