Abstract: Current technologies allow a robot to acquire a tool only if the tool is in a set known location, such as in a rack. In an embodiment, a method and corresponding system, can determine the previously unknown pose of a tool freely placed in an environment. The method can then calculate a trajectory that allows for a robot to move from its current position to the tool and attach with the tool. In such a way, tools can be located and used by a robot when placed at any location in an environment.

Abstract: A robot apparatus includes a storage that stores first instructional information which serves as a guide to first work operation, an acquirer that acquires second instructional information which serves as a guide to second work operation similar to the first work operation or second work operation related to the first work operation from a different apparatus having the second instructional information, and a work controller that performs the first work operation based on the first instructional information stored in the storage and the second work operation based on the second instructional information acquired by the acquirer.

Abstract: A parking facility management server for a parking facility, including a communication interface, which is designed to receive a request via a communication network from a user of the communication network to carry out at least one vehicle-specific service for a vehicle in the parking facility, and a processor, which is designed to process the request, in order to check whether or not the at least one service may be carried out in the parking facility for the vehicle in accordance with the request, the processor being further designed to ascertain a response as a function of the check. The communication interface further being designed to transmit the response via the communication network back to the user, the processor further being designed to plan and to coordinate the carrying out of the service in the event of a positive response that at least one service may be carried out.

Abstract: A machine learning system builds and uses computer models for controlling robotic performance of a task. Such computer models may be first trained using feedback on computer simulations of the robotic system performing the task, and then refined using feedback on real-world trials of the robot performing the task. Some examples of the computer models can be trained to automatically evaluate robotic task performance and provide the feedback. This feedback can be used by a machine learning system, for example an evolution strategies system or reinforcement learning system, to generate and refine the controller.

Abstract: Methods of operating a robotic breaker-racking apparatus are provided. A method of operating a robotic breaker-racking apparatus includes controlling a motor to drive the robotic breaker-racking apparatus to a first circuit breaker. The method includes accessing the first circuit breaker via remote or autonomous control of the robotic breaker-racking apparatus. Moreover, the method includes visually inspecting, via a camera of the robotic breaker-racking apparatus, a first relay of the first circuit breaker and/or a second relay of a second circuit breaker. Related robotic breaker-racking apparatuses are also provided.

Abstract: A substrate transport apparatus including, a torsional motion driver member having an exterior perimeter circumscribing an axis of rotation of the torsional motion driver member, and a torsional motion follower member including a body portion and a bearing collar rotatably coupled to the body portion, the torsional motion follower member being coupled to the torsional motion driver member with a dimensionally substantially invariant interface, wherein the bearing collar is decoupled from the exterior perimeter of the torsional motion driver member so that the exterior perimeter, as a whole, is free of the bearing collar.

Abstract: A controller of the robot apparatus performs approaching control for making a second workpiece approach a first workpiece and position adjustment control for adjusting a position of the second workpiece with respect to a position of the first workpiece. The approaching control includes control for calculating a movement direction and a movement amount of a position of the robot based on an image captured by a first camera, and making the second workpiece approach the first workpiece. The position adjustment control includes control for calculating a movement direction and a movement amount of a position of the robot based on an image captured by the first camera and an image captured by the second camera, and precisely adjusting a position of the first workpiece with respect to the second workpiece.

Abstract: Systems, methods, devices, and other techniques are described for planning motions of one or more robots to perform at least one specified task. In some implementations, a task to execute with a robotic system using a tool is identified. A partially constrained pose is identified for the tool that is to apply during execution of the task. A set of possible constraints for the unconstrained pose parameter are selected for each unconstrained pose parameter. The sets of possible constraints are evaluated for the unconstrained pose parameters with respect to one or more task execution criteria. A nominal pose is determined for the tool based on a result of evaluating the sets of possible constraints for the unconstrained pose parameters with respect to the one or more task execution criteria. The robotic system is then directed to execute the task, including positioning the tool according to the nominal pose.

Abstract: Deep machine learning methods and apparatus, some of which are related to determining a grasp outcome prediction for a candidate grasp pose of an end effector of a robot. Some implementations are directed to training and utilization of both a geometry network and a grasp outcome prediction network. The trained geometry network can be utilized to generate, based on two-dimensional or two-and-a-half-dimensional image(s), geometry output(s) that are: geometry-aware, and that represent (e.g., high-dimensionally) three-dimensional features captured by the image(s). In some implementations, the geometry output(s) include at least an encoding that is generated based on a trained encoding neural network trained to generate encodings that represent three-dimensional features (e.g., shape). The trained grasp outcome prediction network can be utilized to generate, based on applying the geometry output(s) and additional data as input(s) to the network, a grasp outcome prediction for a candidate grasp pose.

Abstract: The present invention relates to an interaction training system of a robot with a Mixed Reality (MR) environment, and to a training system in which a robot including a camera and a sensor is driven in a training space and a virtual environment like an actual environment is provided to a trainee to train the trainee.

Abstract: A carrying device includes a swivel that swivels around a central axis line of a revolution orbit that passes through a workpiece transfer area and a workpiece work area for a workpiece to be worked on by a robot, multiple workpiece holders positioned on the swivel such that when a first one of the workpiece holders is positioned in the workpiece transfer area, a second one of the workpiece holders is positioned in the workpiece work area, a revolution driver that causes the swivel to swivel around the central axis line of the revolution orbit, and a tilting driver that tilts each of the workpiece holders with respect to the central axis line of the revolution orbit.

Abstract: According to the present invention, a terminal device has: a transmission unit which transmits, to a robot, operator state information indicating the state of a user operating the robot; a receiving unit which receives, from the robot, robot state information indicating the state of the robot; a sensation imparting unit which imparts a predetermined sensation to the user; and a control unit which, when a delay time required for the receiving unit to receive the robot state information after the transmission unit transmits the operator state information is no longer than a predetermined time, controls the sensation imparting unit so as to impart a sensation based on the robot state information to the user, and when the delay time is longer than the predetermined time, controls the sensation imparting unit to impart, to the user, a sensation based on virtual state information that indicates an estimated robot state.

Abstract: A vibration display device including a vibration acquisition unit that acquires a vibration state of a distal end section of a robot that is a robot in a simulation or in a real world, the distal end section being moved based on an operation program, and a vibration trajectory drawing unit that draws, on a display device, the vibration state along a trajectory of the distal end section of the robot or that draws, on the display device, the vibration state as the trajectory.

Abstract: A robot may perform emergency stopping. The robot includes: a driving device configured to perform movement of the robot; a stop switch configured to output a stop switch signal; a controller configured to output a stop signal; and a stop circuit configured to output a first control signal and a second control signal for stopping the driving device. The stop circuit may output the first control signal and the second control signal in response to the stop signal and the stop switch signal.

Abstract: An analog input device, which converts an inputted analog signal to a digital signal and outputs the digital signal, includes a high resolution AD converter, a first low resolution AD converter, and a second low resolution AD converter. When a difference between a first digital signal converted by the high resolution AD converter and a second digital signal converted by the first low resolution AD converter is equal to or less than a predetermined first threshold, the analog input device outputs first digital signal. When the difference between the first digital signal and the second digital signal is larger than the predetermined first threshold, the analog input device stops an output of the first digital signal.

Abstract: Implementations of the disclosed subject matter provide a method of moving, using a drive system, a mobile robot within an area. Detecting, using at least one sensor of the mobile robot, at least one of air within the area, a surface within the area, and/or an object within the area. The area may be mapped in three dimensions based on the detecting of at least one of the air, the surface, and the object as the mobile robot moves within the area. Ultraviolet (UV) light may be emitted from a light source of the mobile robot to disinfect at least a portion of the area. A representation of the emission of the UV light may be plotted onto the mapped area to generate an exposure plot, where the representation is of the UV light emitted on at least one of the air, the surface, and the object in the area.

Abstract: A robotic programming apparatus, while using a robot equipped with a spraying device to move the spraying device, for creating an operation program of an application operation for applying a sprayed material sprayed from a nozzle of a spraying device to a member, that includes an operation pattern storage section configured to store a plurality of types of operation patterns each indicating operation of the spraying device that are operation patterns each formed of a continuous trajectory including periodic iteration of a constant pattern, and a pitch interval determination section configured to determine, for one operation pattern of the plurality of types of operation patterns stored in the operation pattern storage section, a pitch interval of the periodic iteration of the constant pattern in the one operation pattern based on a spray parameter representing a spray characteristic of the sprayed material by the nozzle of the spraying device.

Abstract: The invention disclosure a remotely operated pneumatic manipulator based on Kinect, comprising Kinect sensor, computer, D/A embedded board, PWM piezoelectric pneumatic ratio valve, pneumatic triad, air compressor, artificial muscle, spring and finger joint, wherein the Kinect sensor is provided on one side of the finger joint, a camera module of the Kinect sensor is faced to the finger joint. The pneumatic humanoid manipulator of the invention has basically the same dimensions as human hands, can achieve human-computer interaction and remotely operation, the transmission structure thereof is novel, simple and compact, the fingers thereon are convenient to control and flexible to move, the finger movement range is large for wide application, moreover, the PWM piezoelectric pneumatic ratio valve is with advantages of fast dynamic response, low cost, strong resistance to noise, and high detection accuracy of Kinect sensor.

Abstract: A predicted energy consumption calculation unit calculates, when an on-vehicle apparatus of a rental vehicle is operated during the period of depositing an article in a deposit space of the rental vehicle, a predicted energy consumption that is a predicted value of the amount of energy consumed by the on-vehicle apparatus. A rentable period determination unit determines a rentable period of the deposit space on the basis of the predicted energy consumption calculated by the predicted energy consumption calculation unit.

Abstract: Disclosed herein is a terminal including a communication transceiver configured to establish connection with a first action robot, an input interface configured to receive an execution request of a cluster control mode of an application, and a processor configured to search for at least one other action robot other than the first action robot through the communication transceiver in response to the received execution request, control the communication transceiver to attempt connection with the searched at least one other action robot, and control output of action robot content through the first action robot and the at least one other action robot according to execution of the cluster control mode, when connection with the at least one other action robot is established.