Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2510.24949 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917049116131328 |
|---|---|
| author | Yildiz, Anil Thornton, Sarah M. Hildebrandt, Carl Roy-Singh, Sreeja Kochenderfer, Mykel J. |
| author_facet | Yildiz, Anil Thornton, Sarah M. Hildebrandt, Carl Roy-Singh, Sreeja Kochenderfer, Mykel J. |
| contents | Assessing scenario coverage is crucial for evaluating the robustness of autonomous agents, yet existing methods rely on expensive human annotations or computationally intensive Large Vision-Language Models (LVLMs). These approaches are impractical for large-scale deployment due to cost and efficiency constraints. To address these shortcomings, we propose SCOUT (Scenario Coverage Oversight and Understanding Tool), a lightweight surrogate model designed to predict scenario coverage labels directly from an agent's latent sensor representations. SCOUT is trained through a distillation process, learning to approximate LVLM-generated coverage labels while eliminating the need for continuous LVLM inference or human annotation. By leveraging precomputed perception features, SCOUT avoids redundant computations and enables fast, scalable scenario coverage estimation. We evaluate our method across a large dataset of real-life autonomous navigation scenarios, demonstrating that it maintains high accuracy while significantly reducing computational cost. Our results show that SCOUT provides an effective and practical alternative for large-scale coverage analysis. While its performance depends on the quality of LVLM-generated training labels, SCOUT represents a major step toward efficient scenario coverage oversight in autonomous systems. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_24949 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | SCOUT: A Lightweight Framework for Scenario Coverage Assessment in Autonomous Driving Yildiz, Anil Thornton, Sarah M. Hildebrandt, Carl Roy-Singh, Sreeja Kochenderfer, Mykel J. Robotics Artificial Intelligence Computer Vision and Pattern Recognition Machine Learning Assessing scenario coverage is crucial for evaluating the robustness of autonomous agents, yet existing methods rely on expensive human annotations or computationally intensive Large Vision-Language Models (LVLMs). These approaches are impractical for large-scale deployment due to cost and efficiency constraints. To address these shortcomings, we propose SCOUT (Scenario Coverage Oversight and Understanding Tool), a lightweight surrogate model designed to predict scenario coverage labels directly from an agent's latent sensor representations. SCOUT is trained through a distillation process, learning to approximate LVLM-generated coverage labels while eliminating the need for continuous LVLM inference or human annotation. By leveraging precomputed perception features, SCOUT avoids redundant computations and enables fast, scalable scenario coverage estimation. We evaluate our method across a large dataset of real-life autonomous navigation scenarios, demonstrating that it maintains high accuracy while significantly reducing computational cost. Our results show that SCOUT provides an effective and practical alternative for large-scale coverage analysis. While its performance depends on the quality of LVLM-generated training labels, SCOUT represents a major step toward efficient scenario coverage oversight in autonomous systems. |
| title | SCOUT: A Lightweight Framework for Scenario Coverage Assessment in Autonomous Driving |
| topic | Robotics Artificial Intelligence Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2510.24949 |