CPC B25J 9/163 (2013.01) [B25J 9/161 (2013.01); B25J 9/1633 (2013.01); B25J 9/1664 (2013.01); B25J 15/08 (2013.01)] | 16 Claims |
1. A method for operating a robot, comprising the following steps:
determining, as a function of a first state of the robot and/or surroundings of the robot, and as a function of an output of a first model, a first part of a manipulated variable for activating the robot for a transition from the first state into a second state of the robot;
determining a second part of the manipulated variable as a function of the first state and regardless of the first model;
determining a quality measure as a function of the first state and as a function of the output of the first model using a second model;
determining at least one parameter of the first model as a function of the quality measure;
determining at least one parameter of the second model as a function of the quality measure and a setpoint value, the setpoint value being determined as a function of a reward, which is associated with the transition from the first state into the second state.
|