Methods and systems for testing robotic systems in an environment blending both physical and virtual test environments are presented herein. A realistic, three dimensional physical environment for testing and evaluating a robotic system is augmented with simulated, virtual elements. In this manner, robotic systems, humans, and other machines dynamically interact with both real and virtual elements. In one aspect, a model of a physical test environment and a model of a virtual test environment are combined, and signals indicative of a state of the combined model are employed to control a robotic system. In a further aspect, a mobile robot present in a physical test environment is commanded to emulate movements of a virtual robot under control. In another further aspect, images of the virtual robot under control are projected onto the physical test environment to provide a visual representation of the presence and action taken by the virtual robot.

A method for determining values influencing movement of a robot is disclosed. The method includes the following steps: a) provision of a task to be performed by the robot and a worker; b) provision of a layout of a workstation; c) provision of tool data; d) determination of respective axial movement patterns of the robot on the basis of steps a) to c); e) provision of a worker workspace; f) determination of critical path points of the robot, where a specified movement speed is exceeded by the robot and/or a specified mass of an element to be moved by the robot is exceeded, on the basis of the axial movement patterns and the workspace; g) simulation of respective collisions at the critical path points by a second robot; and h) determination of permissible operating speeds of the robot for each critical path point on the basis of the simulated collisions.

A robot system includes a robot, a teach pendant having an operator interface, and a robot controller with a computer and associated hardware and software containing a virtual representation of the robot and the environment. The system employs a method for avoiding collisions including moving a manipulator arm along an actual path in an environment containing objects constituting collision geometry. Operator input is entered into the teach pendant, whereby the operator is able to directly control motion of the robot along the actual path. A recent history of the motion of the robot is recorded, and a predicted path of the robot is developed based on the input entered into the teach pendant and the recent history of the motion of the robot. Real-time collision checking between the predicted path and the collision geometry is performed while the operator manually controls the robot using the teach pendant.

An interference avoidance device is provided with: a three-dimensional sensor that is attached to a tip portion of a robot arm and acquires a distance image of an area around a robot; a position data creating portion that converts coordinates of a nearby object in the distance image to coordinates on a robot coordinate system and creates the position data of the nearby object based on the coordinates of the nearby object on the robot coordinate system; a storage portion that stores the position data; and a control portion that controls the robot based on the robot coordinate system; and the control portion controls the robot to avoid interference of the robot with the nearby object, based on the position data stored in the storage portion.

When a machining system that includes a machine tool and a robot detects that an operator is present in a dangerous area in the system, a robot controller that controls the robot determines an operation restriction on the machine tool and notifies a numerical controller that controls the machine tool of the determined operation restriction. The numerical controller restricts the operation of the machine tool in accordance with the notified operation restriction.

Collision of a robot is detected by the following method. The robot includes a motor, a gear reducer connected to the motor, an encoder detecting a rotation of the motor, a temperature sensor installed to the encoder, and an object which is driven by the motor via the gear reducer. An external force torque due to a collision as a collision torque estimation value is estimated by subtracting a dynamic torque obtained by an inverse dynamic calculation of the robot from a torque output to the gear reducer by the motor. It is determined that the robot receives an external force if the collision torque estimation value is greater than a predetermined collision detection threshold. The predetermined collision detection threshold is set to a first value in a case where a temperature detected by the temperature sensor is less than a predetermined temperature threshold. The predetermined collision detection threshold is set to a second value less than the first value at a first time point at which the detected temperature is equal to or greater than the predetermined temperature threshold in a case where a maximum value of the collision torque estimation value is less than a first maximum value determination threshold in a period to the first time point from a second time point prior to the first time point by a predetermined length of time. The predetermined collision detection threshold is set to the first value at the first time point in a case where the maximum value of the collision torque estimation value is equal to or greater than the first maximum value determination threshold in the period.

Apparatuses, systems, and techniques to grasp objects with a robot. In at least one embodiment, a neural network is trained to determine a grasp pose of an object within a cluttered scene using a point cloud generated by a depth camera.

A method for queuing robots destined for one or more target locations in an environment, includes determining if a plurality of robots destined for the one or more target locations have entered a predefined target zone proximate the one or more target locations. The method also includes assigning each of the robots to either its target location or one of a plurality of queue locations based on an assigned priority. The plurality of queue locations are grouped into one or more queue groups.

It becomes possible to optimize setting of a layout of a robot and a peripheral device efficiently and at high speed in a robot workspace. A teaching point acquiring unit acquires a teaching point which corresponds to a specific operation that a robot arm accesses the peripheral device, and through which it allows a reference region of the robot arm to pass. An initial layout generating unit generates an initial layout of the robot arm and the peripheral device. A trajectory generating unit generates a trajectory of the robot arm based on the teaching point. Layout evaluating and layout moving units generate a new layout by changing an arrangement of each device based on the initial layout using a meta-heuristic calculation, set an evaluation value concerning fitness for the specific operation in the initial layout or the new layout, and set the layout based on the set evaluation value.

A teaching device constructs, in a virtual space, a virtual robot system in which a virtual 3D model of a robot and a virtual 3D model of a peripheral structure of the robot are arranged, and teaches a moving path of the robot. The teaching device includes an acquisition unit configured to acquire information about a geometric error between the virtual 3D models, and a correction unit configured to correct the moving path of the robot in accordance with the information acquired by the acquisition unit.