Image 1 - A soft hand that is capable of robustly grasping and identifying objects based on internal state measurements along with a system that autonomously performs grasps.

All images/graphics may be copyrighted and property of the author, creator and/or ETH Zurich.

Proprioceptive Soft Robotic Hand

Creator: ETH Zurich

Country: Switzerland

Summary

A soft hand that is capable of robustly grasping and identifying objects based on internal state measurements along with a system that autonomously performs grasps.

Status: Prototype, Research

Operation: Autonomous, Other

Robot Type / Domain: Multi/General-Purpose, Research, Gripper

Tasks: Grasping, gripping, object identification and manipulation

Learn More

Below is from the online article: ETH Zurich. Proprioceptive Soft Robotic Hand. Retrieved from https://srl.ethz.ch/platforms/srh/proprioceptive-soft-robotic-hand.html

"We developed a soft hand that is capable of robustly grasping and identifying objects based on internal state measurements along with a system that autonomously performs grasps. The highly compliant soft hand allows for intrinsic robustness to grasping uncertainties. The addition of internal sensing allows the configuration of the hand and object to be detected. The finger module includes resistive force sensors on the fingertips for contact detection and resistive bend sensors for measuring the curvature profile of the finger. The curvature sensors can be used to estimate the contact geometry. This capability allows to distinguish between a set of grasped objects. With one data point from each finger, the object can be identified by grasping it. A clustering algorithm finds the correspondence for each grasped object.

We tested this for both enveloping grasps and pinch grasps. A closed loop system uses a camera to detect approximate object locations. Compliance in the soft hand handles that uncertainty in addition to geometric uncertainty in the shape of the object."

Technical Specifications

Min. Size: N/A

Max. Size: 100L 18W 27H (mm)

Max. Size: 3.937L 0.709W 1.063H (in)

Max. Payload: N/A

Weight: N/A

Average Runtime: N/A

Max. Runtime: N/A

Battery Recharge Time: N/A

Actuation: Pneumatic, pneumatic piston - tube along the arm

Number of Actuators: N/A

Body Material: wax core mold using 3d printed model

Number of Axes: N/A

IP Rating: N/A

Operating Temperature: N/A

Open-source? N/A

Price: N/A

Show more specs

Sensors: hand cameras, Flexi-force force sensor at the tip of the finger and the Bendshort-2.0 flex sensor from iCubeX

Software: ROS, OpenCV, MoveIt planner

Controller & Computing: A middle-level controller to command the hand (“close the hand” or “open the hand”). Middle-level controller communicates with the low-level motor controllers via serial communication.Receives sensor values from Arduino board

No more specs to show.

Please visit the official website for more accurate, up-to-date, and complete information on this post. Visit Website

References

Homberg, B.S., Katzschmann, R.K., Dogar, M.R. et al. Robust proprioceptive grasping with a soft robot hand. Auton Robot 43, 681–696 (2019). https://doi.org/10.1007/s10514-018-9754-1

Disclaimer: For informational purposes only. The provided data and/or content are intended as references and may contain errors. We appreciate your help in maintaining accuracy; if you spot any errors, please notify us. For the most reliable and up-to-date information, kindly refer to the official website. By using addoobot and its contents and services, you agree to our Terms and Conditions, Privacy Policy, and Cookie Policy.