Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for causing a transducer to transmit an acoustic input signal into a member of a device. Receiving a detection signal representing reverberations of the input signal traveling within the member from a receiver. Detecting a contact of the member with an object external to the member based on a change in the detection signal, where the change in the detection signal represents an alteration in the reverberations of the input signal caused by the contact of the member with the object. Determining a position along the member of a point of the contact of the member with the object based on the change in the detection signal.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for causing a transducer to transmit an acoustic input signal into a member of a device. Receiving a detection signal representing reverberations of the input signal traveling within the member from a receiver. Detecting a contact of the member with an object external to the member based on a change in the detection signal, where the change in the detection signal represents an alteration in the reverberations of the input signal caused by the contact of the member with the object. Determining a position along the member of a point of the contact of the member with the object based on the change in the detection signal.

Abstract: Examples are provided that describe a model free power detector. In one example, a method includes receiving, by one or more computing devices, a measurement of electrical power to a robotic device. The method also includes receiving, by the one or more computing devices, a measurement of mechanical power by the robotic device. Based on combinations of the electrical power to the robotic device being one of positive, negative, or about zero, and the mechanical power by the robotic device being one of positive, negative, or about zero, the method includes determining possible states of operation of the robotic device. The method also includes providing, by the one or more computing devices, the possible states of operation of the robotic device to a detector.

Abstract: Example implementations may relate to a cloud service that stores a detection metric corresponding to a maintenance request for a particular component. In particular, the cloud may receive sensor data from various robotic systems each having the particular component. The cloud may then determine, based on the sensor data, performance data for the particular component over time at the various robotic systems. The cloud may also determine various maintenance events for the particular component. Based on the performance data, the cloud may determine that at least one maintenance event occurs at other metrics that are different from the detection metric. Responsively, the cloud may adjust the detection metric based on a difference between the detection metric and the other metrics. The cloud may then detect operation of a particular robotic system at the adjusted detection metric and may responsively request maintenance for the particular component at the particular robotic system.

Abstract: Example implementations may relate to a robotic system that provides feedback. The robotic system is configured to receive information related to a path in an environment of the robotic system. The robotic system is also configured to initiate a recording process for storing data related to motion of a component in the environment. The robotic system is additionally configured to detect, during the recording process, movement of the component along the path in the environment, where the movement results from application of an external force to the robotic system. The robotic system is further configured to determine, during the recording process, deviation of the movement away from the path by at least a threshold amount and responsively provide feedback including one or more of (i) resisting the deviation of the movement away from the path and (ii) guiding the at least one component back towards the path.

Abstract: An encoder is provided that comprises a disk to rotate about an axis. The encoder also comprises a first index mark and a second index mark on the disk. A first orientation of the disk associated with the first index mark is at an offset angle to a second orientation of the disk associated with the second index mark. The encoder also comprises a detector to provide an index signal responsive to an index mark being aligned with the detector. The device also comprises a controller to receive a first index signal and a second index signal from the detector, determine an angle of rotation of the disk between provision of the first index signal and provision of the second index signal, and identify a defect in the encoder based on the angle of rotation being different from the offset angle.

Abstract: A device is provided that comprises a hardware segment and an actuator to adjust a position of the segment within a range of positions. The device also comprises an encoder to rotate about an encoder axis responsive to the actuator adjusting the position. The device also comprises data storage that includes a dataset indicating offset angles between a reference configuration and a plurality of configurations of the encoder. The device also comprises a controller to cause the actuator to adjust the position to an end of the range of positions, responsively identify a range of encoder positions of the encoder that corresponds to the range of positions of the segment, modify the dataset such that the reference configuration corresponds to an end of the range of encoder positions, and determine a mapping between the offset angles indicated by the modified dataset and the range of positions of the hardware segment.

Abstract: Example implementations may relate to a robotic system that provides feedback. The robotic system is configured to receive information related to a path in an environment of the robotic system. The robotic system is also configured to initiate a recording process for storing data related to motion of a component in the environment. The robotic system is additionally configured to detect, during the recording process, movement of the component along the path in the environment, where the movement results from application of an external force to the robotic system. The robotic system is further configured to determine, during the recording process, deviation of the movement away from the path by at least a threshold amount and responsively provide feedback including one or more of (i) resisting the deviation of the movement away from the path and (ii) guiding the at least one component back towards the path.

Abstract: Examples are provided that describe calibration of a sensor of a robotic device. In one example, a system includes least one processor and data storage comprising instructions executable by the at least one processor to cause the system to perform operations. The operations include simulating a movement of a robotic component of a robotic device to a plurality of positions. The operations may also include determining a relationship between a simulated torque values and simulated force values at the plurality of positions. The operations may also include determining expected torque values based on detected force values and the determined relationship. Based on the expected torque values satisfying a threshold associated with the simulated torque values, determining a plurality of calibration parameters of the one or more sensors according to the optimization.

Abstract: A device is provided that comprises a hardware segment and an actuator to adjust a position of the segment within a range of positions. The device also comprises an encoder to rotate about an encoder axis responsive to the actuator adjusting the position. The device also comprises data storage that includes a dataset indicating offset angles between a reference configuration and a plurality of configurations of the encoder. The device also comprises a controller to cause the actuator to adjust the position to an end of the range of positions, responsively identify a range of encoder positions of the encoder that corresponds to the range of positions of the segment, modify the dataset such that the reference configuration corresponds to an end of the range of encoder positions, and determine a mapping between the offset angles indicated by the modified dataset and the range of positions of the hardware segment.

Abstract: Example implementations may relate to a cloud service that stores a detection metric corresponding to a maintenance request for a particular component. In particular, the cloud may receive sensor data from various robotic systems each having the particular component. The cloud may then determine, based on the sensor data, performance data for the particular component over time at the various robotic systems. The cloud may also determine various maintenance events for the particular component. Based on the performance data, the cloud may determine that at least one maintenance event occurs at other metrics that are different from the detection metric. Responsively, the cloud may adjust the detection metric based on a difference between the detection metric and the other metrics. The cloud may then detect operation of a particular robotic system at the adjusted detection metric and may responsively request maintenance for the particular component at the particular robotic system.

Abstract: A device is provided that comprises a hardware segment and an actuator to adjust a position of the segment within a range of positions. The device also comprises an encoder to rotate about an encoder axis responsive to the actuator adjusting the position. The device also comprises data storage that includes a dataset indicating offset angles between a reference configuration and a plurality of configurations of the encoder. The device also comprises a controller to cause the actuator to adjust the position to an end of the range of positions, responsively identify a range of encoder positions of the encoder that corresponds to the range of positions of the segment, modify the dataset such that the reference configuration corresponds to an end of the range of encoder positions, and determine a mapping between the offset angles indicated by the modified dataset and the range of positions of the hardware segment.