TACT-HAND: Improving control of prosthetic hands using tactile sensors and machine learning

Computer aided rendering of tactile sensor units fitting onto the I-limb Ultra prosthetic hand Despite decades of research, intuitive and robust control of multi-joint prosthetic hands is still an unsolved problem, largely due to missing sensorization of the hand and a poor human-machine interface, that only barely can recognize the intent of the patient. In this project we will employ and evaluate a new generation of tactile sensors coupled with modern machine learning approaches to overcome both problems.

Within this DFG-funded, collaborative project with DLR and IDIAP we will develop tactile sensors to be employed both, in hand prostheses to allow for rich tactile feedback that is so essential for successful grasping and manipulation skills, and in the human-machine interface to replace classical EMG electrodes with a much richer tactile bracelet that will record muscle bulging in the remaining forearm of a subject. This hardware development will be accompanied with the development of tactile-driven grasping algorithms to autonomously adjust grasp forces, e.g. according to slip detection.