Learning of a Basketball Free Throw With a Flexible Link Robot

Abstract

Object throwing is an efficient approach for overcoming the kinematic workspace limitations of robots in placement scenarios. Throwing of objects with rigid link robots has been widely studied in literature. Although using robots with spring-like flexible links can significantly increase the throwing distance, existing contributions are very rare. Therefore, we propose an efficient iterative learning control throwing algorithm and apply it to a flexible link robot. A simple rigid link throwing model is used to generate the motor motion. Errors caused by this simplification are corrected by a flexible link throwing model based on the finite element method. As representative scenario a basketball free throw is selected which requires high throwing accuracy. Here, we demonstrate that the controller can be efficiently pre-learned in simulations to reduce real-world training time. Experiments then validate that our learning control method achieves the required free throw accuracy within very few real-world learning iterations.