Distracted Robot: How Visual Clutter Undermine Robotic Manipulation
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908679852261376 |
|---|---|
| author | Rasouli, Amir Alban, Montgomery Pakdamansavoji, Sajjad Li, Zhiyuan Zhang, Zhanguang Wu, Aaron Zhao, Xuan |
| author_facet | Rasouli, Amir Alban, Montgomery Pakdamansavoji, Sajjad Li, Zhiyuan Zhang, Zhanguang Wu, Aaron Zhao, Xuan |
| contents | In this work, we propose an evaluation protocol for examining the performance of robotic manipulation policies in cluttered scenes. Contrary to prior works, we approach evaluation from a psychophysical perspective, therefore we use a unified measure of clutter that accounts for environmental factors as well as the distractors quantity, characteristics, and arrangement. Using this measure, we systematically construct evaluation scenarios in both hyper-realistic simulation and real-world and conduct extensive experimentation on manipulation policies, in particular vision-language-action (VLA) models. Our experiments highlight the significant impact of scene clutter, lowering the performance of the policies, by as much as 34% and show that despite achieving similar average performance across the tasks, different VLA policies have unique vulnerabilities and a relatively low agreement on success scenarios. We further show that our clutter measure is an effective indicator of performance degradation and analyze the impact of distractors in terms of their quantity and occluding influence. At the end, we show that finetuning on enhanced data, although effective, does not equally remedy all negative impacts of clutter on performance. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_22780 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Distracted Robot: How Visual Clutter Undermine Robotic Manipulation Rasouli, Amir Alban, Montgomery Pakdamansavoji, Sajjad Li, Zhiyuan Zhang, Zhanguang Wu, Aaron Zhao, Xuan Robotics Artificial Intelligence Computer Vision and Pattern Recognition In this work, we propose an evaluation protocol for examining the performance of robotic manipulation policies in cluttered scenes. Contrary to prior works, we approach evaluation from a psychophysical perspective, therefore we use a unified measure of clutter that accounts for environmental factors as well as the distractors quantity, characteristics, and arrangement. Using this measure, we systematically construct evaluation scenarios in both hyper-realistic simulation and real-world and conduct extensive experimentation on manipulation policies, in particular vision-language-action (VLA) models. Our experiments highlight the significant impact of scene clutter, lowering the performance of the policies, by as much as 34% and show that despite achieving similar average performance across the tasks, different VLA policies have unique vulnerabilities and a relatively low agreement on success scenarios. We further show that our clutter measure is an effective indicator of performance degradation and analyze the impact of distractors in terms of their quantity and occluding influence. At the end, we show that finetuning on enhanced data, although effective, does not equally remedy all negative impacts of clutter on performance. |
| title | Distracted Robot: How Visual Clutter Undermine Robotic Manipulation |
| topic | Robotics Artificial Intelligence Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2511.22780 |