Data-driven Shape Sensing of Continuum Dexterous Manipulators Using Embedded Capacitive Sensor

We propose a novel inexpensive embedded capacitive sensor (ECS) for sensing the shape of Continuum Dexterous Manipulators (CDMs). Our approach addresses some limitations associated with the prevalent Fiber Bragg Grating (FBG) sensors, such as temperature sensitivity and high production costs. ECSs are calibrated using a vision-based system. The calibration of the ECS is performed by a recurrent neural network that uses the kinematic data collected from the vision-based system along with the uncalibrated data from ECSs. We evaluated the performance on a 3D printed prototype of a cable-driven CDM with multiple markers along its length. Using data from three ECSs along the length of the CDM, we computed the angle and position of its tip with respect to its base and compared the results to the measurements of the visual-based system. We found a 6.6% tip position error normalized to the length of the CDM. The work shows the early feasibility of using ECSs for shape sensing and feedback control of CDMs and discusses potential future improvements.