VERM: Leveraging Foundation Models to Create a Virtual Eye for Efficient 3D Robotic Manipulation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Chen, Yixiang, Huang, Yan, He, Keji, Li, Peiyan, Wang, Liang
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914207636652032
author Chen, Yixiang
Huang, Yan
He, Keji
Li, Peiyan
Wang, Liang
author_facet Chen, Yixiang
Huang, Yan
He, Keji
Li, Peiyan
Wang, Liang
contents When performing 3D manipulation tasks, robots have to execute action planning based on perceptions from multiple fixed cameras. The multi-camera setup introduces substantial redundancy and irrelevant information, which increases computational costs and forces the model to spend extra training time extracting crucial task-relevant details. To filter out redundant information and accurately extract task-relevant features, we propose the VERM (Virtual Eye for Robotic Manipulation) method, leveraging the knowledge in foundation models to imagine a virtual task-adaptive view from the constructed 3D point cloud, which efficiently captures necessary information and mitigates occlusion. To facilitate 3D action planning and fine-grained manipulation, we further design a depth-aware module and a dynamic coarse-to-fine procedure. Extensive experimental results on both simulation benchmark RLBench and real-world evaluations demonstrate the effectiveness of our method, surpassing previous state-of-the-art methods while achieving 1.89x speedup in training time and 1.54x speedup in inference speed. More results can be found on our project website at https://verm-ral.github.io .
format Preprint
id arxiv_https___arxiv_org_abs_2512_16724
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle VERM: Leveraging Foundation Models to Create a Virtual Eye for Efficient 3D Robotic Manipulation
Chen, Yixiang
Huang, Yan
He, Keji
Li, Peiyan
Wang, Liang
Robotics
Computer Vision and Pattern Recognition
When performing 3D manipulation tasks, robots have to execute action planning based on perceptions from multiple fixed cameras. The multi-camera setup introduces substantial redundancy and irrelevant information, which increases computational costs and forces the model to spend extra training time extracting crucial task-relevant details. To filter out redundant information and accurately extract task-relevant features, we propose the VERM (Virtual Eye for Robotic Manipulation) method, leveraging the knowledge in foundation models to imagine a virtual task-adaptive view from the constructed 3D point cloud, which efficiently captures necessary information and mitigates occlusion. To facilitate 3D action planning and fine-grained manipulation, we further design a depth-aware module and a dynamic coarse-to-fine procedure. Extensive experimental results on both simulation benchmark RLBench and real-world evaluations demonstrate the effectiveness of our method, surpassing previous state-of-the-art methods while achieving 1.89x speedup in training time and 1.54x speedup in inference speed. More results can be found on our project website at https://verm-ral.github.io .
title VERM: Leveraging Foundation Models to Create a Virtual Eye for Efficient 3D Robotic Manipulation
topic Robotics
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2512.16724