REVIEW 13 cited by
Are VLMs Ready for Autonomous Driving? An Empirical Study from the Reliability, Data, and Metric Perspectives
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Recent advancements in Vision-Language Models (VLMs) have sparked interest in their use for autonomous driving, particularly in generating interpretable driving decisions through natural language. However, the assumption that VLMs inherently provide visually grounded, reliable, and interpretable explanations for driving remains largely unexamined. To address this gap, we introduce DriveBench, a benchmark dataset designed to evaluate VLM reliability across 17 settings (clean, corrupted, and text-only inputs), encompassing 19,200 frames, 20,498 question-answer pairs, three question types, four mainstream driving tasks, and a total of 12 popular VLMs. Our findings reveal that VLMs often generate plausible responses derived from general knowledge or textual cues rather than true visual grounding, especially under degraded or missing visual inputs. This behavior, concealed by dataset imbalances and insufficient evaluation metrics, poses significant risks in safety-critical scenarios like autonomous driving. We further observe that VLMs struggle with multi-modal reasoning and display heightened sensitivity to input corruptions, leading to inconsistencies in performance. To address these challenges, we propose refined evaluation metrics that prioritize robust visual grounding and multi-modal understanding. Additionally, we highlight the potential of leveraging VLMs' awareness of corruptions to enhance their reliability, offering a roadmap for developing more trustworthy and interpretable decision-making systems in real-world autonomous driving contexts. The benchmark toolkit is publicly accessible.
Forward citations
Cited by 13 Pith papers
-
Steadily moving semi-infinite fracture in plane poroelasticity
XEmbodied achieves SOTA on 18 embodied VQA benchmarks by fusing 3D geometric tokens and distilled physical cues into a 30B VLM with progressive curriculum training.
-
STSBench: A Spatio-temporal Scenario Benchmark for Multi-modal Large Language Models in Autonomous Driving
A new benchmark, STSnu, uses 971 verified multiple-choice questions from NuScenes to test driving vision-language models' spatio-temporal reasoning, and shows they lag far behind text-only LLMs given perfect trajectories.
-
MapTab: A Diagnostic Benchmark for Long-Horizon Multi-Criteria Multimodal Reasoning on Heterogeneous Topological Graphs
MapTab is a new multimodal benchmark with 328 images and nearly 200k queries that shows current MLLMs have substantial difficulty with multi-criteria route planning when visual and tabular information must be combined.
-
DriveQA: Passing the Driving Knowledge Test
DriveQA is a new multimodal driving-knowledge benchmark showing that LLMs and MLLMs struggle with right-of-way, numerical traffic rules, and sign variations, with modest transfer gains to nuScenes and BDD.
-
Monocular Semantic Scene Completion via Masked Recurrent Networks
Decomposing monocular semantic scene completion into a coarse stage plus a masked recurrent refinement network improves NYUv2 and SemanticKITTI completion and semantic IoU over prior monocular methods.
-
Beyond One Shot, Beyond One Perspective: Cross-View and Long-Horizon Distillation for Better LiDAR Representations
LiMA distills long-term multi-camera image features into LiDAR backbones and reports consistent gains on segmentation and detection benchmarks.
-
AD^2-Bench: A Hierarchical CoT Benchmark for MLLM in Autonomous Driving under Adverse Conditions
AD^2-Bench is a new adverse-weather driving benchmark with hierarchical chain-of-thought annotations and LLM-based quality metrics; 12 MLLMs all scored below 60%.
-
Impromptu VLA: Open Weights and Open Data for Driving Vision-Language-Action Models
A new 80K-clip dataset of unstructured driving scenarios with Q&A annotations improves VLA performance on NeuroNCAP and nuScenes benchmarks.
-
PixelThink: Towards Efficient Chain-of-Pixel Reasoning
A soft token-budget penalty driven by task difficulty and model confidence roughly halves the reasoning tokens used by segmentation MLLMs while slightly improving mask accuracy on ReasonSeg-derived benchmarks.
-
Benchmarking the Robustness of Autonomous Driving to Environmental Illusions: A Lane Perception Perspective
Environmental illusions cause 5-7% accuracy drops in lane detection models and can trigger collisions in closed-loop simulation, with a proposed defense (MIDA) recovering ~4% robustness.
-
RoadBench: Benchmarking MLLMs on Fine-Grained Spatial Understanding and Reasoning under Urban Road Scenarios
A new 9,121-case benchmark of road-marking tasks shows most multimodal LLMs perform near or below simple rule-based baselines in fine-grained urban spatial reasoning.
-
A Survey on Vision-Language-Action Models for Autonomous Driving
A survey organizes vision-language-action models for autonomous driving into four stages, compares over 20 systems, and catalogs datasets, benchmarks, and open challenges.
-
Chain-of-Thought for Autonomous Driving: A Comprehensive Survey and Future Prospects
A survey that classifies chain-of-thought methods for autonomous driving into modular, logical, and reflective pipelines, and proposes three evolutionary stages from direct prompting to reinforcement learning.
Discussion (0). Continue with ORCID to comment.