Enregistré dans:
Détails bibliographiques
Auteurs principaux: Shan, Dandan, Mo, Kaichun, Yang, Wei, Chao, Yu-Wei, Fouhey, David, Fox, Dieter, Mousavian, Arsalan
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:https://arxiv.org/abs/2504.01959
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866915223968940032
author Shan, Dandan
Mo, Kaichun
Yang, Wei
Chao, Yu-Wei
Fouhey, David
Fox, Dieter
Mousavian, Arsalan
author_facet Shan, Dandan
Mo, Kaichun
Yang, Wei
Chao, Yu-Wei
Fouhey, David
Fox, Dieter
Mousavian, Arsalan
contents The majority of modern robot learning methods focus on learning a set of pre-defined tasks with limited or no generalization to new tasks. Extending the robot skillset to novel tasks involves gathering an extensive amount of training data for additional tasks. In this paper, we address the problem of teaching new tasks to robots using human demonstration videos for repetitive tasks (e.g., packing). This task requires understanding the human video to identify which object is being manipulated (the pick object) and where it is being placed (the placement slot). In addition, it needs to re-identify the pick object and the placement slots during inference along with the relative poses to enable robot execution of the task. To tackle this, we propose SLeRP, a modular system that leverages several advanced visual foundation models and a novel slot-level placement detector Slot-Net, eliminating the need for expensive video demonstrations for training. We evaluate our system using a new benchmark of real-world videos. The evaluation results show that SLeRP outperforms several baselines and can be deployed on a real robot.
format Preprint
id arxiv_https___arxiv_org_abs_2504_01959
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Slot-Level Robotic Placement via Visual Imitation from Single Human Video
Shan, Dandan
Mo, Kaichun
Yang, Wei
Chao, Yu-Wei
Fouhey, David
Fox, Dieter
Mousavian, Arsalan
Robotics
Computer Vision and Pattern Recognition
The majority of modern robot learning methods focus on learning a set of pre-defined tasks with limited or no generalization to new tasks. Extending the robot skillset to novel tasks involves gathering an extensive amount of training data for additional tasks. In this paper, we address the problem of teaching new tasks to robots using human demonstration videos for repetitive tasks (e.g., packing). This task requires understanding the human video to identify which object is being manipulated (the pick object) and where it is being placed (the placement slot). In addition, it needs to re-identify the pick object and the placement slots during inference along with the relative poses to enable robot execution of the task. To tackle this, we propose SLeRP, a modular system that leverages several advanced visual foundation models and a novel slot-level placement detector Slot-Net, eliminating the need for expensive video demonstrations for training. We evaluate our system using a new benchmark of real-world videos. The evaluation results show that SLeRP outperforms several baselines and can be deployed on a real robot.
title Slot-Level Robotic Placement via Visual Imitation from Single Human Video
topic Robotics
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2504.01959