Methods, systems, and apparatus, including computer programs encoded on computer storage media, for computing interpolated robot control parameters. One of the methods includes receiving, by a real-time bridge from a control agent for a robot, a non-real-time command for the robot, wherein the non-real-time command specifies a trajectory to be attained by a component of the robot and a target value for a control parameter, wherein the control parameter controls how a real-time controller will cause the robot to react to one or more external stimuli encountered during a control cycle of the real-time controller. The real-time bridge provides the one or more real-time commands translated from the non-real-time command and interpolated control parameter information to the real-time controller, thereby causing the robot to effectuate the trajectory of the non-real-time command according to the interpolated control parameter information.

One or more force control parameters used in force control is adjusted. A robot system includes a robot, a force detector configured to measure an external force exerted on the robot, and a control section that causes the robot to perform an action through feedback control. A measured force value that is a measured value of the external force is produced by causing the robot to perform an action using one or more second servo gains corresponding to one or more first servo gains used when the robot system is caused to perform an actual task, the second servo gains each having a value greater than the value of the corresponding first servo gain, and further using a candidate value of the force control parameters. A new candidate value of the force control parameters is produced by carrying out an optimization process on the force control parameters by using the measured force value. A parameter determination step of determining the force control parameters by repeating a measurement step and a parameter update step is provided.

An example implementation involves receiving measurements from an inertial sensor coupled to the robot and detecting an occurrence of a foot of the legged robot making contact with a surface. The implementation also involves reducing a gain value of an amplifier from a nominal value to a reduced value upon detecting the occurrence. The amplifier receives the measurements from the inertial sensor and provides a modulated output based on the gain value. The implementation further involves increasing the gain value from the reduced value to the nominal value over a predetermined duration of time after detecting the occurrence. The gain value is increased according to a profile indicative of a manner in which to increase the gain value of the predetermined duration of time. The implementation also involves controlling at least one actuator of the legged robot based on the modulated output during the predetermined duration of time.

An example implementation involves receiving measurements from an inertial sensor coupled to the robot and detecting an occurrence of a foot of the legged robot making contact with a surface. The implementation also involves reducing a gain value of an amplifier from a nominal value to a reduced value upon detecting the occurrence. The amplifier receives the measurements from the inertial sensor and provides a modulated output based on the gain value. The implementation further involves increasing the gain value from the reduced value to the nominal value over a predetermined duration of time after detecting the occurrence. The gain value is increased according to a profile indicative of a manner in which to increase the gain value of the predetermined duration of time. The implementation also involves controlling at least one actuator of the legged robot based on the modulated output during the predetermined duration of time.

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for computing interpolated robot control parameters. One of the methods includes receiving, by a real-time bridge from a control agent for a robot, a non-real-time command for the robot, wherein the non-real-time command specifies a trajectory to be attained by a component of the robot and a target value for a control parameter, wherein the control parameter controls how a real-time controller will cause the robot to react to one or more external stimuli encountered during a control cycle of the real-time controller. The real-time bridge provides the one or more real-time commands translated from the non-real-time command and interpolated control parameter information to the real-time controller, thereby causing the robot to effectuate the trajectory of the non-real-time command according to the interpolated control parameter information.

A servo motor controller includes: a servo motor; a driven member which is driven by the servo motor and in which a load acting on a drive axis is varied depending on the position of the driven member; a position detection portion and a speed detection portion for the driven member; and a motor control portion, where the motor control portion includes: a position control portion which calculates a speed command based on a positional error between a position command for the driven member and the position FB; a speed control portion which calculates a torque command by multiplying a speed error between the speed command and the speed FB by a speed gain and/or adding a torque offset to the speed error; and a change portion which changes at least one of the speed gain and the torque offset according to the position of the driven member.

An example implementation involves receiving measurements from an inertial sensor coupled to the robot and detecting an occurrence of a foot of the legged robot making contact with a surface. The implementation also involves reducing a gain value of an amplifier from a nominal value to a reduced value upon detecting the occurrence. The amplifier receives the measurements from the inertial sensor and provides a modulated output based on the gain value. The implementation further involves increasing the gain value from the reduced value to the nominal value over a predetermined duration of time after detecting the occurrence. The gain value is increased according to a profile indicative of a manner in which to increase the gain value of the predetermined duration of time. The implementation also involves controlling at least one actuator of the legged robot based on the modulated output during the predetermined duration of time.

An example implementation involves receiving measurements from an inertial sensor coupled to the robot and detecting an occurrence of a foot of the legged robot making contact with a surface. The implementation also involves reducing a gain value of an amplifier from a nominal value to a reduced value upon detecting the occurrence. The amplifier receives the measurements from the inertial sensor and provides a modulated output based on the gain value. The implementation further involves increasing the gain value from the reduced value to the nominal value over a predetermined duration of time after detecting the occurrence. The gain value is increased according to a profile indicative of a manner in which to increase the gain value of the predetermined duration of time. The implementation also involves controlling at least one actuator of the legged robot based on the modulated output during the predetermined duration of time.

An example implementation involves receiving measurements from an inertial sensor coupled to the robot and detecting an occurrence of a foot of the legged robot making contact with a surface. The implementation also involves reducing a gain value of an amplifier from a nominal value to a reduced value upon detecting the occurrence. The amplifier receives the measurements from the inertial sensor and provides a modulated output based on the gain value. The implementation further involves increasing the gain value from the reduced value to the nominal value over a predetermined duration of time after detecting the occurrence. The gain value is increased according to a profile indicative of a manner in which to increase the gain value of the predetermined duration of time. The implementation also involves controlling at least one actuator of the legged robot based on the modulated output during the predetermined duration of time.

A motor control apparatus including a controller that controls a servo motor or a spindle motor and includes a switching determining part that determines a switching condition of the controller based on axis position information on a motor related to control of the motor control apparatus, a machine learning part that adjusts one or more parameters for the controller by machine learning for each switching condition, and a parameter holding part that holds the parameter adjusted by the machine learning part for each switching condition. The switching determining part, when determining the switching condition after adjustment of the parameter, uses the adjusted parameter corresponding to the switching condition in the controller. The apparatus enables changing, and automatic adjustment, of a parameter or controller to be used depending on a switching condition of the parameter related to axis position information or a switching condition of the controller using the parameter.