Dexterous hand control method, device, agent, and storage medium

Abstract

Embodiments of the present disclosure provide a dexterous hand control method, device, agent, and storage medium. The method includes: acquiring sensor data; preprocessing the sensor data to obtain input information, where the input information includes environmental information and state information of a dexterous hand; inputting the input information into a cerebellar model to obtain a corresponding control instruction, where the cerebellar model includes a trajectory planning model and a motion controller, the trajectory planning model is used to output a corresponding trajectory planning result according to the input information, the motion controller is used to convert the trajectory planning result into the corresponding control instruction, and the motion controller is obtained by combining a cerebellar model neural network with a whole-body dynamics model based on a model predictive control algorithm; and performing a driving control on an actuator module of the dexterous hand according to the control instruction.