A Vision-Based Collision Sensing Method for Stable Circular Object Grasping with A Soft Gripper System

TL;DR

This paper introduces a vision-based collision detection system integrated with a soft robotic gripper to enhance the stability and safety of grasping circular objects, demonstrating real-time response and collision localization.

Contribution

It presents a novel vision-based sensing module and collision-rich grasping strategy for soft robotic systems, enabling stable grasping with collision detection and response capabilities.

Findings

The system reacts instantaneously to collisions.

It accurately detects the direction and scale of external impacts.

The soft gripper maintains stable grasping during collisions.

Abstract

External collisions to robot actuators typically pose risks to grasping circular objects. This work presents a vision-based sensing module capable of detecting collisions to maintain stable grasping with a soft gripper system. The system employs an eye-in-palm camera with a broad field of view to simultaneously monitor the motion of fingers and the grasped object. Furthermore, we have developed a collision-rich grasping strategy to ensure the stability and security of the entire dynamic grasping process. A physical soft gripper was manufactured and affixed to a collaborative robotic arm to evaluate the performance of the collision detection mechanism. An experiment regarding testing the response time of the mechanism confirmed the system has the capability to react to the collision instantaneously. A dodging test was conducted to demonstrate the gripper can detect the direction and scale of external collisions precisely.