In-hand manipulation is an important skill for robots. While recent work in our lab has shown that even open-loop, sensorless behaviors can achieve robust results, we believe that feedback control that takes the pose of objects into account is an important stepping stone to enhance those capabilities. But what type of sensor feedback can we use to estimate the pose of objects in the hand? Another branch of research in our lab has shown that activ acoustic sensing is a promising sensing technique that can be applied to soft hands, and in this thesis we would like to explore if it can be used to estimate the pose of objects in the hand.
Working on this thesis, you are going to learn about active acoustic sensing and are going to apply what you know to design a Bayesian filter to integrate the pose estimates over time.