Research map / Vision-language and multimodal / Multimodal LLMs
Benchmarking the Robustness of Autonomous Driving to Environmental Illusions: A Lane Perception Perspective
Tianyuan Zhang, Xianglong Liu, Aishan Liu, L Wang, Yitong Zhang, Yue Peng, Mingchuan Zhang, Siyuan Liang, Dacheng Tao
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 changed | Where | Measured | Effect |
|---|---|---|---|
| introduce environmental illusions into test scenes | conventional LD models · LanEvil++ | accuracy: 5.27% average drop | Hurt |
| introduce environmental illusions into test scenes | conventional LD models · LanEvil++ | F1-score: 10.49% average drop | Hurt |
| add shadow illusions | conventional LD models · LanEvil++ | accuracy: 7.20% average decrease | Hurt |
| add road damage illusions | conventional LD models · LanEvil++ | accuracy: 2.59% average decrease | Hurt |
| introduce environmental illusions into test scenes | ADVLMs · LanEvil++ | GPT score: 2.03% decrease in GPT score | Hurt |
| add traffic obstruction illusions | ADVLMs · LanEvil++ | GPT score: 3.51% GPT Score drop | Hurt |
| raise illusion severity from level 1 to level 5 | conventional LD models · LanEvil++ | accuracy: 2.51% -> 19.07% accuracy drop | Hurt |
| raise illusion severity from level 1 to level 5 | ADVLMs · LanEvil++ | GPT score: 1.34% -> 9.11% GPT score drop | Hurt |
| add AAM++ hard-example attention mixing | LaneATT and UFLD (ResNet-18) · LanEvil++ | accuracy: 4.23% average accuracy gain | Improved |
| add MIDA (AAM++ and PAT++) | DriveLM and Dolphins · LanEvil++ | GPT score: 3.82% GPT score gain | Improved |
| add generic robustness techniques (PGD AT, cutout, copy paste, HSV, MixUp) | LaneATT and UFLD · LanEvil++ | accuracy: 1.24% average gain | Improved |
| fine-tune on LanEvil++ training set | LaneATT ResNet-34 pretrained on TuSimple · LanEvil++ test set | F1-score: 48.34 -> 62.92 | Improved |
Closest papers by meaning
- LaneSegNet: Map Learning with Lane Segment Perception for Autonomous Driving (ICLR 2024 · similarity 0.87)
- Perception Characteristics Distance: Measuring Stability and Robustness of Perception System in Dynamic Conditions under a Certain Decision Rule (CVPR 2026 · similarity 0.87)
- Dual-View Interaction-Aware Lane Change Prediction for Autonomous Driving (AAAI 2025 · similarity 0.86)
- DriveHierarchy: A Benchmark for Diagnosing VLM Driving Capabilities from Open-Loop Understanding to Closed-Loop Execution (NeurIPS 2026 · similarity 0.86)
- V2X-Radar: A Multi-modal Dataset with 4D Radar for Cooperative Perception (NeurIPS 2025 · similarity 0.86)
- Selective Focus: Investigating Semantics Sensitivity in Post-training Quantization for Lane Detection (AAAI 2024 · similarity 0.86)
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.
