AI Paper Atlas

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

ReAL-AD: Towards Human-Like Reasoning in End-to-End Autonomous Driving

Yuhang Lu, Jiadong Tu, Yuexin Ma, Xinge Zhu

ICCV 2025 · Vision-language and multimodal › Robot action and navigation · approach: Vision-language-action foundation models · 5 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 Strategic Reasoning Injector (ablation)VAD-Base + MiniCPM-V · Bench2Drive valAvg L2 (m): 1.01 -> 0.89Improved
add Tactical Reasoning Integrator (ablation)VAD-Base + MiniCPM-V · Bench2Drive valAvg L2 (m): 1.01 -> 0.97Improved
add Hierarchical Trajectory Decoder instead of MLP decoder (ablation)VAD-Base + MiniCPM-V · Bench2Drive valAvg L2 (m): 1.01 -> 0.93Improved
add all three modules together (ablation)VAD-Base + MiniCPM-V · Bench2Drive valAvg collision rate (%): 0.21 -> 0.12Improved
add similarity loss with GT trajectory encoder for strategy features (ablation)SRI module · Bench2Drive valAvg L2 (m): 0.92 -> 0.89Improved
use MSE loss instead of cosine similarity loss (ablation)SRI module · Bench2Drive valAvg collision rate (%): 0.17 -> 0.20Hurt
use KL divergence loss instead of cosine similarity loss (ablation)SRI module · Bench2Drive valAvg L2 (m): 0.89 -> 0.89No clear effect
increase decoder layers from two to three (ablation)Hierarchical Trajectory Decoder · Bench2Drive valAvg L2 (m): 0.93 -> 0.97Hurt
increase decoder layers from one to two (ablation)Hierarchical Trajectory Decoder · Bench2Drive valAvg L2 (m): 0.99 -> 0.93Improved
encode tactical commands as probabilities instead of one-hot (ablation)TRI module · Bench2Drive valAvg collision rate (%): 0.16 -> 0.20 (L2 0.97 -> 0.86)Mixed
replace MLP adapter with self-attention adapter (ablation)SRI module · Bench2Drive valAvg L2 (m): 0.89 -> 0.90No clear effect
use multi-view input to the VLM instead of front view (ablation)ReAL-AD (VAD & Qwen-VL) · Bench2Drive valAvg L2 (m): 0.53 -> 0.51No clear effect

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