Abstract: A method for controlling a physical system. The method includes training a neural network to output, for a plurality of tasks, a result of the task carried out, in each case in response to the input of a control configuration of the physical system and the input of a value of a task input parameter; ascertaining a control configuration for a further task with the aid of Bayesian optimization, the neural network, parameterized by the task input parameter, being used as a model for the relationship between control configuration and result; and controlling the physical system according to the control configuration to carry out the further task.

Abstract: A device and method for activating a conveyor device. An actual value for a pose of a device movable by the conveyor device by a magnetic force action is received. Depending on the actual value for the pose, as a function of a setpoint value for a torque, as a function of a setpoint value for a force, and as a function of a model, a setpoint value for the activation of at least one actuator of the conveyor device is determined. The model is trained to determine setpoint values for the activation of the at least one actuator as a function of actual values for poses of the device and as a function of setpoint values for torques and setpoint values for forces, using which the device is to be moved.

Abstract: A device and method for activating a conveyor device. An actual value for a pose of a device movable by the conveyor device by a magnetic force action is received. Depending on the actual value for the pose, as a function of a setpoint value for a torque, as a function of a setpoint value for a force, and as a function of a model, a setpoint value for the activation of at least one actuator of the conveyor device is determined. The model is trained to determine setpoint values for the activation of the at least one actuator as a function of actual values for poses of the device and as a function of setpoint values for torques and setpoint values for forces, using which the device is to be moved.

Abstract: A method for controlling a physical system. The method includes training a neural network to output, for a plurality of tasks, a result of the task carried out, in each case in response to the input of a control configuration of the physical system and the input of a value of a task input parameter; ascertaining a control configuration for a further task with the aid of Bayesian optimization, the neural network, parameterized by the task input parameter, being used as a model for the relationship between control configuration and result; and controlling the physical system according to the control configuration to carry out the further task.

Abstract: A computer-implemented method for planning an operation of a technical system within its environment. The method includes: obtaining state information comprising: a current domain, a time step and a current state; determining by heuristics costs for reachable states from the current state; selecting a heuristics by a policy out of a set of predefined heuristics depending on the state information and costs; choosing the state with the lowest cost returned by the selected heuristic from the reachable states, and determining an operation of the technical system out of the set of possible operation that has to be carried out by the technical system to reach said state with the lowest costreturned by the selected heuristic.

Abstract: A robot, a method and a device for controlling a movement of a robot are provided. The method can include controlling multiple steps of the robot. Thus, the method can include multiple iterations of: (i) calculating or receiving a first slope attribute indicative of a slope of a first area of a terrain on which a first leg of the robot steps; (ii) feeding the first slope attribute to a central pattern generator (CPG); and (iii) generating, by the CPG and in response to the slope attribute, at least one control pulse for controlling a torque characteristic of a torque applied by at least one leg of the robot.

Abstract: A robot, a method and a device for controlling a movement of a robot are provided. The method can include controlling multiple steps of the robot. Thus, the method can include multiple iterations of: (i) calculating or receiving a first slope attribute indicative of a slope of a first area of a terrain on which a first leg of the robot steps; (ii) feeding the first slope attribute to a central pattern generator (CPG); and (iii) generating, by the CPG and in response to the slope attribute, at least one control pulse for controlling a torque characteristic of a torque applied by at least one leg of the robot.

Abstract: A rotor assembly comprises a rotor body defining a pole, a winding encircling the pole, a compression member located radially inwards of the winding, and compression means located between the compression member and the rotor body and operable to urge the compression member in an outward direction to apply a compressive load to the winding. A method of assembly of the rotor is also disclosed.

Abstract: A drive transfer device comprising: a first rotating element having a plurality of apertures therein; a second rotating element adjacent the first rotating element; a plurality of transfer elements; and a control element mounted for rotation with the first element and moveable with respect to the first element between a first position in which the control element holds the transfer elements in an engaged position where the transfer elements extend through the apertures of the first rotating element to engage with the second rotating element to urge them to rotate together, and a second position where the transfer elements are moved and held out of engagement with the second rotating element.