Grounding Driving VLA via Inverse Kinematics
Overview
This research paper introduces a method to improve driving Vision-Language-Action (VLA) models by addressing blind planning issues through counterfactual obstacle insertion analysis and an inverse kinematics-inspired architecture. The proposed approach uses a next visual state prediction objective and a separate Inverse Kinematics Network to suppress reliance on ego status and textual shortcuts during trajectory decoding. A 0.5B model achieves state-of-the-art performance on NAVSIM-v1, NAVSIM-v2, and nuScenes benchmarks using only cameras, without LiDAR or a BEV encoder, improving NAVSIM PDMS and EPDMS scores by 19.0 and 20.4 points respectively compared to the OpenDriveVLA* baseline.
Generated from attributed reports · Updated 1 days ago
Event evidence and corrections
0 attributed source owners. Ownership does not establish independent confirmation. Quantities are reported separately and are never added together.
Dataset · modalities: cameras alone
“ture visual states as input is designed to suppress reliance on ego status and textual shortcuts during trajectory decoding. Our 0.5B model achieves state-of-the-art trajectory planning performance on NAVSIM-v1, NAVSIM-v2, and nuScenes using cameras alone, without LiDAR or a BEV encoder. Against the matched OpenDriveVLA* baseline, it improves NAVSIM PDMS and EPDMS by 19.0 and 20.4 points, respectively. Controlled abl”
Exact source · revision 1Source owner not reported
Dataset · embodiments: without LiDAR or a BEV encoder
“ture visual states as input is designed to suppress reliance on ego status and textual shortcuts during trajectory decoding. Our 0.5B model achieves state-of-the-art trajectory planning performance on NAVSIM-v1, NAVSIM-v2, and nuScenes using cameras alone, without LiDAR or a BEV encoder. Against the matched OpenDriveVLA* baseline, it improves NAVSIM PDMS and EPDMS by 19.0 and 20.4 points, respectively. Controlled abl”
Exact source · revision 1Source owner not reported
Report timeline
Follow attributed reports and material updates.
- arXiv Robotics — research abstractsSignalGrounding Driving VLA via Inverse Kinematics
This research paper introduces a method to improve driving Vision-Language-Action (VLA) models by addressing blind planning issues through counterfactual obstacle insertion analysis and an inverse kinematics-inspired architecture. The proposed approach uses a next visual state prediction objective and a separate Inverse Kinematics Network to suppress reliance on ego status and textual shortcuts during trajectory decoding. A 0.5B model achieves state-of-the-art performance on NAVSIM-v1, NAVSIM-v2, and nuScenes benchmarks using only cameras, without LiDAR or a BEV encoder, improving NAVSIM PDMS and EPDMS scores by 19.0 and 20.4 points respectively compared to the OpenDriveVLA* baseline.
Timezone · UTC
Article dates follow your selected timezone. Briefing editions use Hong Kong time (UTC+8).