AI Paper Atlas

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

ORION: A Holistic End-to-End Autonomous Driving Framework by Vision-Language Instructed Action Generation

Haoyu Fu, Diankun Zhang, Zongchuang Zhao, Jianfeng Cui, Dingkang Liang, Chong Zhang, Dingyuan Zhang, Hongwei Xie, Bing Wang, Xiang Bai

ICCV 2025 · Vision-language and multimodal › Robot action and navigation · approach: Vision-language-action foundation models · 130 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
replace diffusion planner with VAE generative planner (ablation)ORION · Bench2Drive closed-loopDriving Score: 71.97 -> 77.74Improved
add generative planner output instead of plain text trajectory output (ablation)ORION with QT-Former · Bench2Drive closed-loopDriving Score: 42.23 -> 77.74Improved
use generative planner instead of MLP decoder for the special planning token (ablation)ORION · Bench2Drive closed-loopDriving Score: +7.01 DS, +9.5% SR, +6.28% mean abilityImproved
add explicit traffic state supervision to QT-Former (ablation)ORION · Bench2Drive closed-loopDriving Score: 56.33 -> 74.65Improved
add motion prediction to QT-Former perception head (ablation)ORION · Bench2Drive closed-loopDriving Score / Success Rate: DS 74.65 -> 74.07, SR 49.31 -> 49.77Mixed
add long-term memory bank with history queries to QT-Former (ablation)ORION · Bench2Drive closed-loopDriving Score: 74.07 -> 77.74Improved
add QT-Former designs to plain text output model (ablation)plain text VLM planner · Bench2Drive closed-loopDriving Score: 25.45 -> 42.23Improved
increase history queries from 0 to 16 (ablation)ORION (planning-only training) · Bench2Drive closed-loopDriving Score: 65.10 -> 74.10Improved
increase history queries from 16 to 32 (ablation)ORION (planning-only training) · Bench2Drive closed-loopDriving Score: 74.10 -> 62.46Hurt
add joint VQA and planning training instead of planning-only training (ablation)ORION · Bench2Drive closed-loopDriving Score: 74.10 -> 77.74Improved
add VQA fine-tuning stage (V to L) before planning training (ablation)ORION · Bench2Drive closed-loopDriving Score: 57.96 -> 65.10Improved
add third-stage end-to-end joint fine-tuning (V to L to A) (ablation)ORION · Bench2Drive closed-loopDriving Score: 65.10 -> 74.65Improved

Later papers that compared with this method

13 later accepted papers report ORION as a baseline in their results tables; 12 of them report a better number on most of the results they share with it.

5 more not listed.

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