AI Paper Atlas

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

Driving with Advice: Large Model as Motion Advisor for Joint Planning

Junyin Wang, Jinlei Yu, Hao Lin, Huikai Liu, Wenqian Zhu, Shengwu Xiong

AAAI 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 Driving Advice Generation and trajectory reinforcement (ablation)Qwen2.5-3B planner · NAVSIM navtestPDMS: 88.1 -> 91.5Improved
add DAG and reinforcement to the 0.5B VLM (ablation)Qwen2.5-0.5B planner · NAVSIM navtestPDMS: 87.5 -> 88.7Improved
use 3B VLM instead of 0.5B (ablation)Driving with Advice · NAVSIM navtestPDMS: 88.7 -> 91.5Improved
add DAG with binary alignment reward after SIP (ablation)Qwen2.5-3B · NAVSIM navtestAll Match Accuracy (%): 76.4 -> 97.5Improved
use binary alignment reward instead of regex reward (ablation)DAG · NAVSIM navtestPDMS: 88.1 -> 91.5Improved
add collision avoidance reward to motion reward (ablation)trajectory reinforcement · NAVSIM navtestPDMS: 87.7 -> 87.8No clear effect
add smoothness reward to motion and collision rewards (ablation)trajectory reinforcement · NAVSIM navtestPDMS: 87.8 -> 88.7Improved
increase denoising steps from 5 to 10 (ablation)diffusion planner · NAVSIM navtestPDMS: 89.4 -> 91.5Improved
increase denoising steps from 10 to 20 (ablation)diffusion planner · NAVSIM navtestPDMS: 91.5 -> 91.1Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 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