Cost-Efficient Barometric Tactile Sensor
We developed an $80 barometric tactile sensor with a separately molded rubber element, making it easier to fabricate and repair compared to traditional designs. Despite the 6 mm spacing between each sensing unit, machine learning enhances the sensor's resolution to 0.28 mm. Additionally, the sensor has been integrated into a robotic gripper for object pose estimation tasks.
Instagrasp
Instagrasp is an entierly 3D printed gripper that can be made on a hobby grade printer. It is based on the Yale OpenHand T42, but is significantly easier and cheaper to assemble. TPU parts replace molded finger parts and threads (tendons). The whole hand can be assembled in 10minutes, using only a screwdriver and hammer.
Read the Original Paper: X. Zhou and A. J. Spiers, "InstaGrasp: An Entirely 3D Printed Adaptive Gripper with TPU Soft Elements and Minimal Assembly Time," 2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Detroit, MI, USA, 2023, pp. 4555-4561, doi: 10.1109/IROS55552.2023.10341385.
Download the CAD File: InstaGrasp
D-PALI
D-PALI stands for Dexterous-PArrallel Linkage. It is a £150 gripper designed as an in-hand manipulation platform. By making use of parrallel mechanisms commonly found in industrial manipulators, we faciliatate the ability to translate and rotate objects within the grasp on the hand.
Read the Original Paper: A. Patra and A. J. Spiers, "D-PALI: A Low-Cost Open Source Robotic Gripper Platform for Planar In-Hand-Manipulation," 2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Detroit, MI, USA, 2023, pp. 4540-4546, doi: 10.1109/IROS55552.2023.10341860.
Tactile Identification of Object Shapes
The E- TRoll robotic hand, equipped with a barometric tactile array on one finger, was used to roll test objects within its grasp, taking just under 3.4 seconds for data collection under the fastest tested speed setting, compared to 33 seconds in our previous work.
Read the Original Paper: X. Zhou and A. J. Spiers, "Tactile Identification of Object Shapes via In-Hand Manipulation with A Minimalistic Barometric Tactile Sensor Array," 2023 IEEE International Conference on Robotics and Automation (ICRA), London, United Kingdom, 2023, pp. 12590-12596, doi: 10.1109/ICRA48891.2023.10160975.
E-TRoll Robotic Gripper
The E-TRoll (Enhanced Tactile Rolling) Hand is a 3-DoF Robotic Hand/Gripper with a prismatic palm and two revolute fingers. This hand is originally designed for rolling prismatic objects (and collecting tactile data), but it can be used for grasping, caging, and other in-hand manipulation techniques.
Read the Original Paper: X. Zhou and A. J. Spiers, "E-TRoll: Tactile Sensing and Classification via A Simple Robotic Gripper for Extended Rolling Manipulations," 2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Kyoto, Japan, 2022, pp. 11826-11833, doi: 10.1109/IROS47612.2022.9982191.
Download the CAD File: E-TRoll