OpenDriveLab/DriveLM
DriveLM applies large language models to autonomous driving via graph-based visual question answering with structured reasoning.
Not currently ranked — collecting fresh signals.
star history
DriveLM is an ECCV 2024 Oral paper that uses LLMs for autonomous driving by framing driving as graph visual question answering. It employs structured reasoning approaches including chain-of-thought, graph-of-thoughts, and tree-of-thoughts to enable visual understanding and decision-making for self-driving systems. The project provides datasets and evaluation benchmarks for the Autonomous Driving Challenge 2024.
Frequently asked
- What is OpenDriveLab/DriveLM?
- DriveLM applies large language models to autonomous driving via graph-based visual question answering with structured reasoning.
- Is DriveLM open source?
- Yes — OpenDriveLab/DriveLM is open source, released under the Apache-2.0 license.
- What language is DriveLM written in?
- OpenDriveLab/DriveLM is primarily written in HTML.
- How popular is DriveLM?
- OpenDriveLab/DriveLM has 1.3k stars on GitHub.
- Where can I find DriveLM?
- OpenDriveLab/DriveLM is on GitHub at https://github.com/OpenDriveLab/DriveLM.