AI Paper Atlas

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

ReCogDrive: A Reinforced Cognitive Framework for End-to-End Autonomous Driving

Yongkang Li, Kaixin Xiong, Xiangyu Guo, Fang Li, Sixu Yan, Gangwei Xu, Lijun Zhou, Long Chen, Haiyang Sun, BING WANG, Kun Ma, Guang Chen and 3 more

ICLR 2026 · Vision-language and multimodal › Robot action and navigation · approach: Vision-language-action foundation models · 191 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 driving VQA pre-training of the VLM (ablation)InternVL3 trajectory model · NAVSIM navtestPDMS: 82.4 -> 84.1Improved
add cognition-guided diffusion planner (ablation)ReCogDrive · NAVSIM navtestPDMS: 84.1 -> 86.5Improved
add DiffGRPO reinforcement learning (ablation)ReCogDrive · NAVSIM navtestPDMS: 86.5 -> 90.8Improved
replace text trajectory output with diffusion planner (ablation)ReCogDrive · NAVSIM navtestPDMS and latency: 84.1 -> 86.5 PDMS; 0.5839 -> 0.0750 sImproved
use MLP head instead of diffusion planner (ablation)VLM trajectory decoder · NAVSIM navtestPDMS: 75.5 vs 85.4 (vanilla diffusion)Hurt
add SwiGLU FFN, RMS Norm, RoPE and QK Norm to the diffusion planner (ablation)VLM + Vanilla Diffusion · NAVSIM navtestPDMS: 85.4 -> 86.5Improved
add chain-of-thought reasoning guidance (ablation)ReCogDrive · NAVSIM navtestPDMS: 90.8 -> 90.7No clear effect
add high-level command guidance (ablation)ReCogDrive · NAVSIM navtestPDMS: 90.8 -> 90.8No clear effect
increase behavior cloning loss weight from 0.001 to 0.1 (ablation)DiffGRPO · NAVSIM navtestPDMS: 90.8 -> 89.3Hurt
use discount factor 0.6 instead of 1.0 over diffusion steps (ablation)DiffGRPO · NAVSIM navtestPDMS: 90.3 -> 90.8Improved
set minimum diffusion noise sigma_min to 0.02 instead of 0.01 (ablation)DiffGRPO · NAVSIM navtestPDMS: 89.5 -> 90.8Improved
set minimum diffusion noise sigma_min to 0.04 instead of 0.02 (ablation)DiffGRPO · NAVSIM navtestPDMS: 90.8 -> 90.5Hurt

Later papers that compared with this method

17 later accepted papers report ReCogDrive-8B as a baseline in their results tables; 17 of them report a better number on most of the results they share with it.

9 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