worldbench/awesome-vla-for-ad

🌐 Vision-Language-Action Models for Autonomous Driving: Past, Present, and Future

50
/ 100
Established

This project offers a comprehensive survey of Vision-Language-Action (VLA) models for autonomous driving. It explains how these models integrate real-world visual data and natural language commands to produce driving actions, moving beyond traditional, error-prone modular systems. Robotics engineers and researchers in autonomous vehicle development would use this to understand the current state and future directions of AI-driven self-driving systems.

331 stars.

Use this if you are exploring how to build more robust and intelligent autonomous driving systems that can understand complex scenarios and natural language instructions.

Not ideal if you are looking for an off-the-shelf software library for immediate implementation, as this is a research survey.

autonomous-driving robotics self-driving-cars vision-systems vehicle-intelligence
No Package No Dependents
Maintenance 10 / 25
Adoption 10 / 25
Maturity 15 / 25
Community 15 / 25

How are scores calculated?

Stars

331

Forks

31

Language

HTML

License

MIT

Last pushed

Mar 04, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/worldbench/awesome-vla-for-ad"

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