Tactile Sensing approach description and hand implementation
Topic 1: Implementation of Robotic hand in the Manipulator and Data acquisition
Data acquisition from robotic gripper
Repeatability check for same grasp configuration
Topic 2: Implement Existing Algorithm
Implement any existing algorithm when the robotic hand implementation is done. This needs to be discussed later.
Next Steps
Attach the Robot hand to the Manipulator.
Collect the tactile data for different objects and check repeatability of data.
Literature
Tactile Data Prediction from Tactile Sensing and Computer Vision without touch
B. S. Zapata-Impata, P. Gil, Y. Mezouar and F. Torres, “Generation of Tactile Data From 3D Vision and Target Robotic Grasps,” in IEEE Transactions on Haptics, vol. 14, no. 1, pp. 57-67, 1 Jan.-March 2021, doi: 10.1109/TOH.2020.3011899.
Tactile Data Prediction on Novel objects through Touch
Z. Abderrahmane, G. Ganesh, A. Crosnier and A. Cherubini, “A Deep Learning Framework for Tactile Recognition of Known as Well as Novel Objects,” in IEEE Transactions on Industrial Informatics, vol. 16, no. 1, pp. 423-432, Jan. 2020, doi: 10.1109/TII.2019.2898264.
Zambelli, M., Aytar, Y., Visin, F., Zhou, Y., & Hadsell, R. (2021). Learning rich touch representations through cross-modal self-supervision. ArXiv, abs/2101.08616.
Tactile knowledge
M. Kaboli, R. Walker and G. Cheng, “Re-using prior tactile experience by robotic hands to discriminate in-hand objects via texture properties,” 2016 IEEE International Conference on Robotics and Automation (ICRA), 2016, pp. 2242-2247, doi: 10.1109/ICRA.2016.7487372.
Next Meeting
Next meeting will take place on Thursday, 21st August, 2021. 01:00 pm – 02:00 pm.