Methods, systems, and apparatus, including computer-readable media storing executable instructions, for enhancing robot learning. In some implementations, a robot stores first embeddings generated using a first machine learning model, and the first embeddings include one or more first private embeddings that are not shared with other robots. The robot receives a second machine learning model from a server system over a communication network. The robot generates a second private embedding for each of the one or more first private embeddings using the second machine learning model. The robot adds the second private embeddings to the cache of the robot and removes the one or more first private embeddings from the cache of the robot.

There is provided a method for programming an industrial robot, where distributors and integrators can present accessories that run successfully at end users. Also the developer can define customized installation screens and program nodes for the end user. There is provided a software platform, where the developer can define customized installation screens and program nodes for the end user thereby extending an existing robot system with customized functionalities by still using the software platform available in the robot system. Hereby a robot developer can define customized installation screens and program nodes for the end user. These can, for example, encapsulate complex new robot programming concepts, or provide friendly hardware configuration interfaces.

A remote control robot system includes a master arm, and a slave arm having a plurality of control modes of an automatic mode in which the slave arm operates based on a prestored task program and a manual mode in which the slave arm operates based on manipulation of an operator received by the master arm. The master arm includes one or more motors configured to drive joints of the master arm, and a motor actuator configured to generate a torque instruction value that operates the joints according to an external force applied to the master arm and gives drive current corresponding to the torque instruction value to the motor. The motor actuator generates, when the control mode is the manual mode, the torque instruction value so that the joints operate according to the external force while resisting a frictional force of the motor.

A remote-control manipulator system which includes a manipulator, a slave arm installed in a workspace and configured to perform a series of works comprised of a plurality of processes, a situation information acquisition device configured to acquire situation information indicating a situation of the slave arm, an environment reproducing device configured to reproduce, in a space where the manipulator is installed, environment information relating to an environment in the workspace, and a control device. The control device is configured to cause the environment reproducing device to reproduce the environment information corresponding to the situation information outputted from the situation information acquisition device.

A system for performing industrial tasks includes a robot and a computing device. The robot includes one or more sensors that collect data corresponding to the robot and an environment surrounding the robot. The computing device includes a user interface, a processor, and a memory. The memory includes instructions that, when executed by the processor, cause the processor to receive the collected data from the robot, generate a virtual recreation of the robot and the environment surrounding the robot, receive inputs from a human operator controlling the robot to demonstrate an industrial task. The system is configured to learn how to perform the industrial task based on the human operator's demonstration of the task, and perform, via the robot, the industrial task autonomously or semi-autonomously.

A teaching system, includes a computer configured to calculate trajectories of a plurality of robots disposed so as to have a common working area on a virtual space and a display unit. The computer calculates a robot passing area which is a set of trajectories drawn by a point constituting each robot when a driving unit of each robot is operated based on a teaching value on the virtual space for each robot. The computer detects whether the robot passing areas of the robots cross with each other. The computer sets a constraint condition by which none of the plurality of robots is permitted to pass through at least to a partial space within a crossing area in a case where the computer detects that the robot passing areas cross with each other.

A system enables teleoperation of a robot based on a pose of a subject. The system includes an image capturing device and an operator system controller that are remotely located from a robotic system controller and a robot. The image capturing device captures images of the subject. The operator system controller maps a processed version of the captured image to a three-dimensional skeleton model of the subject and generates body pose information of the subject in the captured image. The robotic system controller communicates with the operator system controller over a network. The robotic system controller generates a plurality of kinematic parameters for the robot and causes the robot to take a pose corresponding to the pose of the subject in the captured image.

A remote control robot system is provided, which includes robotic arm configured to perform a given work, remote control device for an operator to remotely manipulate operation of robotic arm, plurality of cameras configured to image the work of robotic arm, monitor configured to display a captured image that is sent, camera selecting device configured to generate, in response to receiving an operator's selection of one camera from the plurality of cameras, camera selection information for switching captured image displayed on monitor to captured image from selected camera, storage device configured to store information where operational information related to operation of robotic arm in work is associated with camera selection information, as automatic switching information, and an image processor configured to send to monitor the captured image from camera selected from plurality of cameras based on automatic switching information stored in storage device.

A system enables teleoperation of a robot based on a pose of a subject. The system includes an image capturing device and an operator system controller that are remotely located from a robotic system controller and a robot. The image capturing device captures images of the subject. The operator system controller maps a processed version of the captured image to a three-dimensional skeleton model of the subject and generates body pose information of the subject in the captured image. The robotic system controller communicates with the operator system controller over a network. The robotic system controller generates a plurality of kinematic parameters for the robot and causes the robot to take a pose corresponding to the pose of the subject in the captured image.

A robot system includes a robot, a control circuit, a first wireless circuit, a second wireless circuit, and a teaching circuit. The first wireless circuit is connected to the control circuit. The teaching circuit is connected to the second wireless circuit to control the robot via the second wireless circuit, the first wireless circuit and the control circuit. The second wireless circuit is configured to transmit a control signal to the first wireless circuit with a first wireless communication scheme using frequency hopping, the robot being configured to be driven or not to be driven according to the control signal, and transmit an information signal to the first wireless circuit with a second wireless communication scheme in which a signal is transmitted in a case where a wireless resource is determined to be available, the information signal relating to driving of the robot.