ConDenseDrive: Knowledge-Dense, Token-Sparse Visual Encoder
Overview
ConDenseDrive is a visual encoder for autonomous driving, achieving 94.5 PDMS on NAVSIM v1 and 90.8 EPDMS on NAVSIM v2. It uses token compression for faster inference and planning performance in zero-shot evaluations on HUGSIM with a 37.4 HD-Score.
Generated from attributed reports · Updated 1 hours ago
Event evidence and corrections
0 attributed source owners. Ownership does not establish independent confirmation. Quantities are reported separately and are never added together.
No current evidence-backed claims. Missing information remains not reported.
Report timeline
Follow attributed reports and material updates.
- arXiv Robotics — research abstractsConDenseDrive: Knowledge-Dense, Token-Sparse Visual Encoder for End-to-End Autonomous Driving
This paper presents ConDenseDrive, a knowledge-dense and token-sparse visual encoder for end-to-end autonomous driving. The three-stage framework distills visual, semantic, and geometric knowledge from foundation models, integrates spatiotemp, and applies token compression to improve inference speed and planning performance. It achieves 94.5 PDMS on NAVSIM v1 and 90.8 EPDMS on NAVSIM v2, with a 37.4 HD-Score in zero-shot evaluation on HUGSIM.
Timezone · UTC
Article dates follow your selected timezone. Briefing editions use Hong Kong time (UTC+8).