AI Paper Atlas

Research map / Vision-language and multimodal / Robot action and navigation

DrivePI: Spatial-aware 4D MLLM for Unified Autonomous Driving Understanding, Perception, Prediction and Planning

Zhe Liu, Runhui Huang, Rui Yang, Siming Yan, Zining Wang, Lu Hou, Di Lin, Xiang Bai, Hengshuang Zhao

CVPR 2026 · Vision-language and multimodal › Robot action and navigation · approach: Vision-language-action foundation models · 10 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add the vision heads (occupancy, flow, planning) to the text head (ablation)DrivePI-0.5B · nuScenes-QA valaccuracy: 61.2 -> 60.7Hurt
add the text head to the vision-only model (ablation)DrivePI-0.5B · OpenOcc valRayIoU: 47.5 -> 49.3Improved
add the text head to the vision-only model (ablation)DrivePI-0.5B · OpenOcc valmAVE: 0.69 -> 0.51Improved
add the text head to the vision-only model (ablation)DrivePI-0.5B · nuScenes planningL2 (m): 1.02 -> 0.50Improved
add the text head to the vision-only model (ablation)DrivePI-0.5B · nuScenes planningcollision rate: 0.39 -> 0.38No clear effect
raise occupancy and flow loss weights from 0.2 to 1.0 (ablation)DrivePI-0.5B · OpenOcc valRayIoU: 48.1 -> 49.3Improved
raise occupancy and flow loss weights from 0.2 to 1.0 (ablation)DrivePI-0.5B · OpenOcc valmAVE: 0.57 -> 0.51Improved
raise occupancy and flow loss weights from 0.2 to 1.0 (ablation)DrivePI-0.5B · nuScenes planningcollision rate: 0.19 -> 0.38Hurt
scale occupancy QA data from 28k to 560k (ablation)DrivePI 3B text head · Occupancy class QAaccuracy: 14.3 -> 59.2Improved
add occupancy-flow, action and nuScenes-QA data to 420k occupancy QA (ablation)DrivePI 3B text head · Occupancy class QAaccuracy: 59.2 -> 59.8Improved
scale model from 0.5B to 3B (ablation)DrivePI · Occupancy status QAaccuracy: 86.0 -> 88.6Improved
scale model from 0.5B to 3B (ablation)DrivePI · PlanningL2 (m): 0.79 -> 0.86Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 2 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy