pqh22/ColaVLA

[CVPR2026] ColaVLA: Leveraging Cognitive Latent Reasoning for Hierarchical Parallel Trajectory Planning in Autonomous Driving

34
/ 100
Emerging

This project offers an advanced trajectory planning system for self-driving vehicles, allowing them to make faster, more reliable decisions. It takes in real-time environmental data (like what a car's sensors 'see') and outputs a precise, multi-scale driving path in a single step. The primary users are autonomous driving engineers and researchers focused on developing safer and more efficient self-driving technology.

Use this if you need to improve the real-time decision-making and planning capabilities of an autonomous vehicle system, especially for complex or high-stakes driving scenarios.

Not ideal if you are looking for a system that relies solely on human-readable text-based reasoning for planning decisions.

autonomous-driving vehicle-planning robotics driverless-cars motion-planning
No Package No Dependents
Maintenance 10 / 25
Adoption 7 / 25
Maturity 13 / 25
Community 4 / 25

How are scores calculated?

Stars

27

Forks

1

Language

License

MIT

Last pushed

Feb 21, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/pqh22/ColaVLA"

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