Cognitive-AI-Systems/MAPF-GPT-DDG

[IROS-2025] MAPF-GPT-DDG is a scalable decentralized multi-agent pathfinding (MAPF) solver based on imitation learning. It builds upon MAPF-GPT by introducing a novel fine-tuning method called Delta Data Generation (DDG) — a reward-free active learning approach that identifies and corrects failure cases in the policy.

46
/ 100
Emerging

This project helps robotics engineers and logistics planners efficiently coordinate multiple autonomous agents, like warehouse robots or delivery drones, to move through shared spaces without collisions. You input map layouts and the number of agents, and it outputs an optimized path plan, often visualized as an SVG animation. It's designed for anyone managing large fleets of robots in complex environments.

Use this if you need to generate collision-free paths for many robots or automated vehicles in dynamic, shared operational areas like warehouses or urban delivery networks.

Not ideal if you are controlling a single robot or if your agents operate in very simple, static environments where basic pathfinding is sufficient.

robotics logistics-automation multi-agent-systems warehouse-operations autonomous-navigation
No Package No Dependents
Maintenance 10 / 25
Adoption 8 / 25
Maturity 16 / 25
Community 12 / 25

How are scores calculated?

Stars

61

Forks

7

Language

Python

License

MIT

Last pushed

Feb 21, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/Cognitive-AI-Systems/MAPF-GPT-DDG"

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