mengyuest/pSTL-diffusion-policy

[RA-L/ICRA2025] Official implementation for paper "Diverse Controllable Diffusion Policy with Signal Temporal Logic."

21
/ 100
Experimental

This project offers a generative AI framework to help autonomous vehicle engineers design driving policies. It takes existing driving data from the NuScenes dataset and generates diverse driving behaviors that explicitly satisfy safety and operational rules (like 'avoid collisions' or 'stay in lane'), providing a range of compliant driving options for specific scenarios. This tool is for autonomous system developers and researchers working on self-driving car behaviors.

No commits in the last 6 months.

Use this if you need to generate a variety of safe and rule-compliant driving behaviors for autonomous vehicles, going beyond single, predefined paths.

Not ideal if you are a general user looking for an out-of-the-box self-driving car solution or if you lack experience with deep learning frameworks and large-scale robotics datasets.

autonomous-driving robotics-control motion-planning AI-safety scenario-generation
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 8 / 25
Community 6 / 25

How are scores calculated?

Stars

34

Forks

2

Language

Python

License

Last pushed

Oct 17, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/mengyuest/pSTL-diffusion-policy"

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