Systems and methods for collision detection and avoidance are provided. In one aspect, a robotic medical system including a first set of links, a second set of links, a console configured to receive input commanding motion of the first set of links and the second set of links, a processor, and at least one computer-readable memory in communication with the processor. The processor is configured to access the model of the first set of links and the second set of links, control movement of the first set of links and the second set of links based on the input received by the console, determine a distance between the first set of links and the second set of links based on the model, and prevent a collision between the first set of links and the second set of links based on the determined distance.

A machine learning method includes: a first learning step which is performed in a phase before a neural network is installed in a mobile robot and in which a stationary first obstacle is placed in a set space and the first obstacle is placed at different positions using simulation so that the neural network repeatedly learns a path from a starting point to the destination which avoids the first obstacle; and a second learning step which is performed in a phase after the neural network is installed in the mobile robot and in which, when the mobile robot recognizes a second obstacle that operates around the mobile robot in a space where the mobile robot moves, the neural network repeatedly learns a path to the destination which avoids the second obstacle every time the mobile robot recognizes the second obstacle.

Systems and methods for detection of people are disclosed. In some exemplary implementations, a robot can have a plurality of sensor units. Each sensor unit can be configured to generate sensor data indicative of a portion of a moving body at a plurality of times. Based on at least the sensor data, the robot can determine that the moving body is a person by at least detecting the motion of the moving body and determining that the moving body has characteristics of a person. The robot can then perform an action based at least in part on the determination that the moving body is a person.

Systems and methods assisting a robotic apparatus are disclosed. In some exemplary implementations, a robot can encounter situations where the robot cannot proceed and/or does not know with a high degree of certainty it can proceed. Accordingly, the robot can determine that it has encountered an error and/or assist event. In some exemplary implementations, the robot can receive assistance from an operator and/or attempt to resolve the issue itself. In some cases, the robot can be configured to delay actions in order to allow resolution of the error and/or assist event.

As a preferred embodiment of the present invention, a device for controlling a collaborative robot includes a collision detection unit configured to sense a collision of the collaborative robot; a control unit configured to control an operation mode of the collaborative robot when the collision detection unit senses the collision; and a collision countermeasure unit configured to apply, when the collision detection unit senses the collision, a collision compensation value to each of a plurality of joints in the collaborative robot so as to change a proceeding direction of a force applied to the each of the plurality of joints.

A robot teaching system includes a teaching unit and a robot including a robotic arm and a robot controller. In the robot teaching system, a workpiece includes an internal space having an opening, and a target object of a work by the end effector exists in the internal space. The robot controller determines a possibility that the arm part interferes with an edge of the opening while the robotic arm is jogging or inching.

A robot management system (RMS) includes a plurality of service robots deployed within an operations venue that includes a plurality of gaming devices, an operator terminal presenting a graphical user interface (GUI) to an operator, and a robot management system server (RMS server) configured in networked communication with the plurality of service robots. The RMS server is configured to: identify location data for the service robots; create an interactive overlay map of the operations venue that includes a static map of the operations venue, overlay data showing the location data of the plurality of service robots over the static map, and an interactive icon for each service robot of the plurality of service robots; display, via the GUI, the overlay map; receive a first input indicating a selection of a first interactive icon associated with a first service robot; and display current status information associated with the first service robot.

The present invention relates to a system for detecting the collision of a robot manipulator using an artificial neural network. The system may comprise: joint driving units provided in a plurality of joints of the robot manipulator to drive the plurality of joints, respectively; encoder units provided on sides of the joint driving units to measure the angles of the plurality of joints; and a neural network calculation unit for training the neural network with a large amount of data and inferring, via a preprocessing calculation, to detect that the plurality of joints collide with the outside.

A technique allows verification of a robot operation without any cost for an additional robot or for a person entering a monitoring area. A robot control system includes a monitored robot for which a monitoring area is defined and a robot controller that controls the monitored robot in a plurality of modes including a first mode to change an operation of the monitored robot in response to an object detected in the monitoring area being a robot.

The present teaching relates to a method and system for path planning. A target is tracked via one or more sensors. Information of a desired pose of an end-effector with respect to the target and a current pose of the end-effector is obtained. Also, a minimum distance permitted between an arm including the end-effector and each of at least one obstacle identified between the current pose of the end-effector and the target is obtained. A weighting factor previously learned is retrieved and a cost based on a cost function is computed in accordance with a weighted smallest distance between the arm including the end-effector and the at least one obstacle, wherein the smallest distance is weighted by the weighting factor. A trajectory is computed from the current pose to the desired pose by minimizing the cost function.