OpenDriveLab/DriveLM

[ECCV 2024 Oral] DriveLM: Driving with Graph Visual Question Answering

44
/ 100
Emerging

DriveLM helps autonomous vehicle developers evaluate their driving systems' ability to understand complex road scenarios using natural language. It takes driving scene data, including visual information and sensor readings, and processes human-written questions about perception, prediction, and planning to produce answers and an end-to-end driving action. This is for engineers and researchers building and testing self-driving car AI.

1,263 stars. No commits in the last 6 months.

Use this if you are developing or benchmarking autonomous driving systems and need to assess their reasoning capabilities and ability to respond to language-based queries about driving scenarios.

Not ideal if you are looking for a pre-built, production-ready autonomous driving system or a tool for general-purpose natural language processing.

autonomous-driving vehicle-intelligence robotics-evaluation perception-systems motion-planning
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 16 / 25

How are scores calculated?

Stars

1,263

Forks

83

Language

HTML

License

Apache-2.0

Last pushed

Jul 02, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/prompt-engineering/OpenDriveLab/DriveLM"

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