Researchers have introduced CMU-Drive, a new benchmark for evaluating cooperative autonomous driving among multiple connected vehicles. Alongside this benchmark, they propose V2V-VLA, a vision-language-action model designed for cooperative driving scenarios. This model integrates cooperative perception, reasoning, and planning into a single forward pass, generating driving actions, future waypoints, and language-based reasoning. The goal is to advance research in multi-agent, closed-loop, end-to-end cooperative autonomous driving, with code and model checkpoints to be released publicly. AI
IMPACT Establishes a new benchmark for multi-agent driving systems, potentially accelerating research in cooperative AI.
RANK_REASON Academic paper introducing a new benchmark and model. [lever_c_demoted from research: ic=1 ai=1.0]
- alphaXiv
- arXiv
- CatalyzeX
- CMU-Drive
- DagsHub
- Gotit.pub
- Hugging Face
- ScienceCast
- V2V-VLA
- Vision-Language-Action model
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →
