paper-with-me

홈 › Papers

How Well Do Vision-Language Models Understand Sequential Driving Scenes? A Sensitivity Study

2026-04-08 · Roberto Brusnicki, Mattia Piccinini, Johannes Betz arxiv

Vision-Language Models (VLMs) are increasingly proposed for autonomous driving tasks, yet their performance on sequential driving scenes remains poorly characterized, particularly regarding how input configurations affect their capabilities. We introduce VENUSS (VLM Evaluation oN Understanding Sequential Scenes), a framework for systematic sensitivity analysis of VLM performance on sequential driving scenes, establishing baselines for future research. Building upon existing datasets, VENUSS extracts temporal sequences from driving videos, and generates structured evaluations across custom categories. By comparing 25+ existing VLMs across 2,600+ scenarios, we reveal how even top models achieve only 57% accuracy, not matching human performance under similar constraints (65%) and exposing significant capability gaps. Our analysis shows that VLMs excel with static object detection but struggle with understanding vehicle dynamics and temporal relations. VENUSS offers the first systematic sensitivity analysis of VLMs focused on how input image configurations - resolution, frame count, temporal intervals, spatial layouts, and presentation modes - affect performance on sequential driving scenes. Supplementary material available at https://TUM-AVS.github.io/VENUSS/.

📄 PDF Abstract BibTeX arXiv:2604.06750

Code (0)

등록된 구현이 없습니다.

Tasks

Temporal SequencesAutonomous DrivingObject Detection

Similar Papers 제목 키워드 기반

SimLingo: Vision-Only Closed-Loop Autonomous Driving with Language-Action Alignment

2025-03-12 · CVPR 2025 1 · Katrin Renz, Long Chen, Elahe Arani, Oleg Sinavski

Integrating large language models (LLMs) into autonomous driving has attracted significant attention with the hope of improving generalization and explainability. However, existing methods often focus on either driving o…

Autonomous DrivingBench2DriveLanguage ModelingLanguage Modelling+2

ViSTa Dataset: Do vision-language models understand sequential tasks?

2024-11-20 · Evžen Wybitul, Evan Ryan Gunter, Mikhail Seleznyov, David Lindner

Using vision-language models (VLMs) as reward models in reinforcement learning holds promise for reducing costs and improving safety. So far, VLM reward models have only been used for goal-oriented tasks, where the agent…

MinecraftObject Recognition

Less is More: Lean yet Powerful Vision-Language Model for Autonomous Driving

2025-09-29 · Sheng Yang, Tong Zhan, Guancheng Chen, Yanfeng Lu 외 arxiv

In this work, we reconceptualize autonomous driving as a generalized language problem and formulate the trajectory planning task as next waypoint prediction. We introduce Max-V1, a novel framework for one-stage end-to-en…

Trajectory PredictionTrajectory PlanningAutonomous Driving

VLP: Vision Language Planning for Autonomous Driving

2024-01-10 · CVPR 2024 1 · Chenbin Pan, Burhaneddin Yaman, Tommaso Nesti, Abhirup Mallik 외

Autonomous driving is a complex and challenging task that aims at safe motion planning through scene understanding and reasoning. While vision-only autonomous driving methods have recently achieved notable performance, t…

Autonomous DrivingMotion PlanningScene Understanding

Vision Language Models in Autonomous Driving: A Survey and Outlook

2023-10-22 · Xingcheng Zhou, MingYu Liu, Ekim Yurtsever, Bare Luka Zagar 외

The applications of Vision-Language Models (VLMs) in the field of Autonomous Driving (AD) have attracted widespread attention due to their outstanding performance and the ability to leverage Large Language Models (LLMs).…

Autonomous DrivingDecision Making