Attention based visual analysis for fast grasp planning with multi-fingered robotic hand

TL;DR

This paper introduces an attention-based visual analysis framework that enhances grasp planning for multi-fingered robotic hands by efficiently identifying relevant scene regions and predicting grasp points, improving speed and stability.

Contribution

It presents a novel framework combining visual attention and deep learning for fast, stable grasp planning, and introduces a new dataset for grasp type classification.

Findings

Speeds up grasp planning process.

Handles unknown objects effectively.

Operates well in cluttered environments.

Abstract

We present an attention based visual analysis framework to compute grasp-relevant information in order to guide grasp planning using a multi-fingered robotic hand. Our approach uses a computational visual attention model to locate regions of interest in a scene, and uses a deep convolutional neural network to detect grasp type and point for a sub-region of the object presented in a region of interest. We demonstrate the proposed framework in object grasping tasks, in which the information generated from the proposed framework is used as prior information to guide the grasp planning. Results show that the proposed framework can not only speed up grasp planning with more stable configurations, but also is able to handle unknown objects. Furthermore, our framework can handle cluttered scenarios. A new Grasp Type Dataset (GTD) that considers 6 commonly used grasp types and covers 12 household objects is also presented.