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.
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.
Stars
61
Forks
7
Language
Python
License
MIT
Category
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.
Compare
Higher-rated alternatives
galilai-group/stable-pretraining
Reliable, minimal and scalable library for pretraining foundation and world models
CognitiveAISystems/MAPF-GPT
[AAAI-2025] This repository contains MAPF-GPT, a deep learning-based model for solving MAPF...
UKPLab/gpl
Powerful unsupervised domain adaptation method for dense retrieval. Requires only unlabeled...
larslorch/avici
Amortized Inference for Causal Structure Learning, NeurIPS 2022
svdrecbd/mhc-mlx
MLX + Metal implementation of mHC: Manifold-Constrained Hyper-Connections by DeepSeek-AI.