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

TL;DR

VERM introduces a virtual eye mechanism using foundation models to improve 3D robotic manipulation by filtering redundant information, leading to faster training and inference, and better task performance.

Contribution

The paper proposes VERM, a novel virtual view generation method leveraging foundation models for efficient 3D manipulation with reduced computational costs.

Findings

Achieves 1.89x faster training

Achieves 1.54x faster inference

Outperforms previous state-of-the-art methods

Abstract

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 .