AI Paper Atlas

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

PixelPilot: Scalable Vision-Language-Action Models for End-to-End Autonomous Driving

Pin Tang, Guoqing Wang, Xiangxuan Ren, Zhongdao Wang, Guodongfang Zhao, Bailan Feng, Chao Ma

ECCV 2026 · Vision-language and multimodal › Robot action and navigation · approach: Vision-language-action foundation models · 0 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 SFT to the base model (ablation)Qwen2.5-VL-7B · nuScenes open-loop planningaverage L2 (m): 1.92 -> 0.46Improved
add RL to the base model (ablation)Qwen2.5-VL-7B · nuScenes open-loop planningaverage L2 (m): 1.92 -> 0.49Improved
add RL after SFT (full two-stage) (ablation)PixelPilot · nuScenes open-loop planningaverage L2 (m): 0.46 -> 0.30Improved
add ego-centric consistent multi-view input (ablation)PixelPilot · nuScenes open-loop planningaverage L2 (m): 0.43 -> 0.30Improved
use multi-view ego-centric input instead of front view only (ablation)PixelPilot · nuScenes open-loop planningaverage L2 (m): 0.40 -> 0.30Improved
add perception-to-planning multi-task SFT (ablation)PixelPilot · nuScenes open-loop planningaverage L2 (m): 0.45 -> 0.30Improved
add trajectory reward (ablation)PixelPilot · nuScenes open-loop planningaverage L2 (m): 0.44 -> 0.30Improved
add perception IoU reward (ablation)PixelPilot · nuScenes open-loop planningaverage L2 (m): 0.41 -> 0.30Improved
add action reward (ablation)PixelPilot · nuScenes open-loop planningaverage L2 (m): 0.40 -> 0.30Improved
add fine-grained perception-to-planning CoT instead of none (ablation)PixelPilot · nuScenes open-loop planningaverage L2 (m): 0.41 -> 0.30Improved
use fine CoT instead of coarse CoT (ablation)PixelPilot · nuScenes open-loop planningaverage L2 (m): 0.35 -> 0.30Improved
include Waymo data in training (ablation)PixelPilot · nuScenes open-loop planningaverage L2 (m): 0.06 higher L2 without WaymoImproved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 3 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