Abstract
Purpose
The structural adaptive ability of the soft robot is fully demonstrated in the grasping task of the soft hand. A soft hand can easily realize the envelope operation of the object without planning. With the continuous development of robot applications, researchers are no longer satisfied with the ability of the soft hand to grasp. The purpose of this paper is to perceive the object’s shape while grasping to provide a decision-making basis for more intelligent robot applications.
Design/methodology/approach
This paper proposes a dual-signal comparison method to obtain the fingertip position. The dual signal includes the displacement calculated by the static model without considering the external load change and the displacement calculated by the bending sensor. The dual-signal comparison method can use the obvious change trend difference between the above two signals in the hover and contact states to identify the touch position. The authors make the soft hand scan around the object through touch operation to detect the object’s shape, and the tracks of every touch fingertip position can envelop the object’s shape.
Findings
The experimental results show that the dual-signal comparison method can accurately identify the contact moment of soft fingers. This detection method makes the soft hand develop the shape detection ability. The soft hand in the experiment can perceive squares, circles and a few other complex shapes.
Originality/value
The dual-signal comparison method proposed in this paper can detect a touch action by using the signal change trend when the working condition suddenly changes with the rough robotic model and sensing, thus improving the utilization value of the measured signal. The problems of large model errors and inaccurate sensors also negatively impact the use of other soft robots. It is generally difficult to achieve good results by directly using these models and sensors with the thinking of rigid robot analysis. The dual-signal comparison method in this paper can provide some reference for this aspect.
Subject
Industrial and Manufacturing Engineering,Computer Science Applications,Control and Systems Engineering
Reference25 articles.
1. A dexterous soft robotic hand for delicate in-hand manipulation;IEEE Robotics and Automation Letters,2020
2. Monolithic fabrication of sensors and actuators in a soft robotic gripper,2015
3. Design, fabrication, and analysis of a sensorized soft robotic gripper,2018
4. Fabrication and dynamic modeling of bidirectional bending soft actuator integrated with optical waveguide curvature sensor;Soft Robotics, Mary Ann Liebert, Inc., Publishers 140 Huguenot Street, 3rd Floor New …,2019
5. A multimodal hydrogel soft-robotic sensor for multi-functional perception;Frontiers in Robotics and AI,2021