Check out our paper on "Memory-based Controllers for Efficient Data-driven Control of Soft Robots". Controller design for soft robots is challenging due to non-linear deformation and high degrees of freedom of flexible material. The data-driven approach is a promising solution to the controller design problem for soft robots. However, the existing data-driven methods for controller design for soft robots suffer from two drawbacks: (i) they require excessively long training time, and (ii) they may result in potentially inefficient controllers. In this paper, we address these challenges by developing two memory-based controllers for soft robots that can be designed in a data-driven fashion: the finite memory controller and the long short-term memory controller. #robotics #softrobotics #pneumatic #LSTM #finitememorycontroller #datadrivencontrol
Update on our research work: 'Memory-based Controllers for Efficient Data-driven Control of Soft Robots'. For detailed findings and methodologies, please refer to the video and the full paper: https://lnkd.in/eswqcqjT and https://lnkd.in/eS7zFySd.