OpenDriveLab/DriveLM
[ECCV 2024 Oral] DriveLM: Driving with Graph Visual Question Answering
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.
Stars
1,263
Forks
83
Language
HTML
License
Apache-2.0
Category
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.
Related tools
ShiZhengyan/PowerfulPromptFT
[NeurIPS 2023 Main Track] This is the repository for the paper titled "Don’t Stop Pretraining?...
MILVLG/prophet
Implementation of CVPR 2023 paper "Prompting Large Language Models with Answer Heuristics for...
deepankar27/Prompt_Organizer
Managed Prompt Engineering
mala-lab/NegPrompt
The official implementation of CVPR 24' Paper "Learning Transferable Negative Prompts for...
iamrk04/LLM-Solutions-Playbook
Unlock the potential of AI-driven solutions and delve into the world of Large Language Models....