Abstract

This paper presents the design and calibration of a new force/tactile sensor for robotic applications. The sensor is suitably designed to provide the robotic grasping device with a sensory system mimicking the human sense of touch, namely, a device sensitive to contact forces, object slip and object geometry. This type of perception information is of paramount importance not only in dexterous manipulation but even in simple grasping tasks, especially when objects are fragile, such that only a minimum amount of grasping force can be applied to hold the object without damaging it. Moreover, sensing only forces and not moments can be very limiting to securely grasp an object when it is grasped far from its center of gravity. Therefore, the perception of torsional moments is a key requirement of the designed sensor. Furthermore, the sensor is also the mechanical interface between the gripper and the manipulated object, therefore its design should consider also the requirements for a correct holding of the object. The most relevant of such requirements is the necessity to hold a torsional moment, therefore a soft distributed contact is necessary. The presence of a soft contact poses a number of challenges in the calibration of the sensor, and that is another contribution of this work. Experimental validation is provided in real grasping tasks with two sensors mounted on an industrial gripper.

Highlights

  • The ability of modern service robots to grasp and manipulate objects in a dexterous way is still very far from human manipulation skills

  • This paper has presented the detailed design and experimental characterization of a force/tactile sensor able to measure distributed contacts and estimate contact force and torsional moments to be used for robotic dexterous manipulation tasks

  • The mechanical interface of the device is a soft pad of silicone so as to adapt to different object shapes and hold high torsional moments

Read more

Summary

Introduction

The ability of modern service robots to grasp and manipulate objects in a dexterous way is still very far from human manipulation skills. The same task has been executed by resorting only to force/tactile feedback in [16], where the measurement of both normal and tangential force components together with the torsional moment demonstrated to be effective without the need of any additional external sensors These experiments, were carried out only with rigid objects of parallelepiped shape. The new sensor design starts from the main requirement to manipulate objects of generic shape avoiding both linear and rotational slippage This goal leads to the need of a soft contact surface so that significant torsional moments can be held by the sensor. To allow application of slipping avoidance algorithms when a soft sensor pad interacts with an object with generic shape, estimation of the contact geometry is essential for the determination of friction model parameters [17], and a tactile map with suitable spatial resolution should be designed based on the accuracy requirement on the contact geometry estimation. A discussion about the generalization of the design procedure is presented, which allows the acquisition of an optimal and detailed design of the force/tactile sensor for the integration into commercial grippers

Requirements for Dexterous Manipulation
The Working Principle and the Technology
Detailed Design of the Rigid-Flex PCB
Detailed Design of the Deformable Pad
Integration of the Sensor into a Commercial Gripper
Sensor Calibration
Construction of the Training Set
Training Set Pre-Processing
FF-NN Training
Experimental Validation
Reconstruction of the Normal Force Component
Reconstruction of the Tangential Force Components
Assessment of Sensor Sensitivity and Dynamic Range
Reconstruction of the Contact Plane Orientation
Reconstruction of the Torsional Moment
Findings
Conclusions
Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call