ExistentialRobotics/LLM-Scene-Graph-LTL-Planning

Repository for ICRA'24 Paper "Optimal Scene Graph Planning with Large Language Model Guidance"

35
/ 100
Emerging

This project helps robotics researchers design complex robot behaviors within simulated environments. It takes a detailed textual description of a space (a "scene graph") and natural language instructions for a robot's task. It then outputs a plan for the robot to execute, breaking down the task into smaller, understandable steps. This is ideal for researchers developing and testing advanced robot planning algorithms.

Use this if you are a robotics researcher or engineer looking to generate optimal robot motion plans in simulated indoor environments based on natural language instructions and a detailed scene understanding.

Not ideal if you need a solution for real-world robot deployment without significant adaptation, or if you are not working with scene graph representations and LTL planning.

robotics research motion planning natural language processing simulated environments autonomous systems
No License No Package No Dependents
Maintenance 10 / 25
Adoption 7 / 25
Maturity 8 / 25
Community 10 / 25

How are scores calculated?

Stars

37

Forks

4

Language

C++

License

Last pushed

Jan 30, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/ExistentialRobotics/LLM-Scene-Graph-LTL-Planning"

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