Energy & materialsResearch findings
VLP · Vision-Language Planning for Enhanced Autonomous Driving
Original published 2024.01.11 08:00 KSTAdded to Blackdeck 2026.11.15 03:35 KST
What has changed?
Integrates visual data with language models to enable planning in complex driving scenarios
Key points
- Integrates vision and language models for autonomous driving planning
- Reduces average L2 error and collision rates by 35.9% and 60.5% on NuScenes
- Shows improved generalization in long-tail and new urban environments
Connect it to your work
Interprets driving situations through linguistic representations to generate safe trajectories
What remains unproven
This research note is based on an abstract; check the original for test conditions and application scope.
Originals used for this note
Links open the original publisher in a new tab.