A method of evaluating safety of a robot includes a step of obtaining a three-dimensional image or three-dimensional model of a test robot comprising shape information of a real robot, a step of setting a movement time and movement path of the test robot by inputting profile information comprising movement time information and movement path information of the test robot, a step of calculating a collision pressure and collision force applied to a collision object in consideration of a shape, effective mass, movement speed, and direction of an injury-causing dangerous portion of the test robot, and a step of evaluating safety of the robot by determining whether magnitudes of the calculated collision pressure and collision force fall within magnitudes of a predetermined maximum collision pressure and predetermined maximum collision force.

A robot control method includes defining a robot monitor model that covers at least a part of the robot and defining a monitor region parallel to a coordinate system for the robot. The monitor region is configured to monitor a range of motion of the robot. The method further includes transforming a position of a definition point that is an arbitrary point contained in the robot monitor model into a position of the definition point in a coordinate system different from the coordinate system for the robot (ST9), determining whether or not the robot monitor model is put into contact with a boundary surface of the monitor region by using the transformed position of the definition point (ST6), and stopping motion of the robot if the robot monitor model is put into contact with the boundary surface (ST8).

A control system includes: a controller configured to operate one or more robots in a real space based on an operation program; and circuitry configured to: operate one or more virtual robots based on the operation program in a virtual space, the one or more virtual robots corresponding to the one or more robots respectively; cause the controller to suspend an operation based on the operation program by the one or more robots; simulate a suspended state of the real space after suspension of the operation by the one or more robots, in the virtual space; and resume at least a part of the operation by the one or more virtual robots based on the operation program, in the virtual space in which the suspended state of the real space has been simulated.

A robot system includes: a robot; a robot controller configured to control the robot based on sequential taught positions; and a teaching device communicative with the robot controller and configured to receive operations by an operator, wherein the robot controller includes circuitry configured to: generate, in response to determining that a target position is designated by the operator on the teaching device, a path from a current position of the robot to the target position by simulation of moving the robot based on surrounding environmental information of the robot; and move the robot toward the target position along the generated path.

A system has a virtual-world (VW) controller and a physical-world (PW) controller. The pairing of a PW element with a VW element establishes them as corresponding physical and virtual twins. The VW controller and/or the PW controller receives measurements from one or more sensors characterizing aspects of the physical world, the VW controller generates the virtual twin, and the VW controller and/or the PW controller generates commands for one or more actuators affecting aspects of the physical world. To coordinate the corresponding virtual and physical twins, (i) the VW controller controls the virtual twin based on the physical twin or (ii) the PW controller controls the physical twin based on the virtual twin. Depending on the operating mode, one of the VW and PW controllers is a master controller, and the other is a slave controller, where the virtual and physical twins are both controlled based on one of VW or PW forces.

A robot control device according to the present invention is configured to: detect a collision of a robot with an object at a predetermined collision detection sensitivity; perform control of operating the robot, and stopping the robot when a detection part detects the collision; and decrease, when a predetermined circumstance causing the robot to have a low temperature is satisfied, the collision detection sensitivity compared to when the predetermined circumstance is unsatisfied.

A robot control device according to an aspect of the invention is a robot control device that controls a robot on the basis of a simulation result of a simulation device that performs a simulation of operation of a virtual robot on a virtual space. In the simulation, a first region and a second region located on an inside of the first region can be set on the virtual space. In the case where the virtual robot operates, when a specific portion of the virtual robot intrudes into the first region, operating speed of the virtual robot is limited. When the specific portion of the virtual robot intrudes into the second region, the operation of the virtual robot stops or the virtual robot retracts from the second region.

A simulation system includes circuitry configured to: determine placement of a robot with respect to another object in a virtual space, based on a placement constraint applied to the robot for executing a plurality of tasks; generate a path representing a trajectory of at least a portion of the robot or a tool operated by the robot during the tasks, based on a spatial relationship between the determined placement of the robot and the other object that satisfies the placement constraint; execute an operation program including the generated path in the virtual space in which the robot and the other object are placed; and check whether the robot interferes with the other object, based on the spatial relationship between the determined placement of the robot and the other object along the generated path in the virtual space, as a result of executing the tasks in the operation program.

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.

In order to detect when a kinematic linkage leaves workspaces and/or enters safe spaces, using little computing power, and therefore doing so more quickly, at least a part of the kinematic linkage is modeled with a number of kinematic objects, and a monitoring space is specified. The number of kinematic objects is modeled in less than two dimensions D<2. For each modeled kinematic object, a geometric variable of a monitoring space is modified by a distance. Each distance is derived from at least one geometric parameter of the modeled kinematic object. The position of each of the number of kinematic objects is checked in relation to the modified monitoring spaces.