A robot programming device is provided with: a robot model movement unit that moves a prescribed movable part of a robot model from a first position to a second position in accordance with instruction content; an arm inversion detection unit that detects whether or not a prescribed state has occurred in which, when the prescribed movable part of the robot model is moved to the second position, any axis constituting the robot model is rotated 180°±a first prescribed value from a rotation angle serving as a reference; and an arm inversion correction unit that, when occurrence of the prescribed state has been detected for any axis constituting the robot model, corrects the posture of the robot model when the prescribed movable part is in the second position so that said axis is not in the prescribed state.

A robot programming device 1 is provided with a model layout unit 112 that lays out a workpiece model of a workpiece, a robot model of a robot, and a tool model of a tool in the virtual space, a machining site designation unit 113 that designates a machining site on the workpiece model, a stereoscopic shape layout unit 115 that lays out a predetermined stereoscopic shape such that a surface of the stereoscopic shape is filled in with a predetermined operation pattern and that the operation pattern is projected to at least one surface of the workpiece model, a machining path creation unit 116 that projects the operation pattern to at least one surface of the workpiece model to create a machining path for the tool, and a change unit 117 that changes the machining path and/or an operation program on the basis of the machining site.

An automatic program-correction device includes: a clearance detecting unit that detects an amount of clearance between a robot and a peripheral device in an operation program; a near-miss detecting unit that detects a near-miss section; a closest-point detecting unit that detects a pair of closest points, in the near-miss section; and a program updating unit that generates a new operation program having an intermediate teaching point to which the closest points have been moved, along a straight line passing through the detected pair of closest points, until the amount of clearance becomes greater than a minimum amount of clearance and equal to or less than the threshold. While gradually reducing, from the threshold, the amount of clearance at the intermediate teaching point, the program updating unit obtains an intermediate teaching point that provides a maximum amount of clearance at which a new near-miss section is not detected.

A method for controlling a robotic device is presented. The method includes positioning the robotic device within a task environment. The method also includes mapping descriptors of a task image of a scene in the task environment to a teaching image of a teaching environment. The method further includes defining a relative transform between the task image and the teaching image based on the mapping. Furthermore, the method includes updating parameters of a set of parameterized behaviors based on the relative transform to perform a task corresponding to the teaching image.

For a kinematic modelled in a kinematics coordinate system by hingedly interconnected single axles, a method calculates a braking region possibly covered by at least one of the single axles connected to an origin of the kinematics coordinate system and at least one of the single axles moving relative to the origin. In the event of a braking process, for a point that is coupled to a single axle, at least one virtual end position of the point is determined from an initial position of the point, a vectorial speed of at least one single axle, and a minimum deceleration of at least one single axle. The braking region of the point is determined using an envelope of the initial position and the at least one virtual end position, the extent of the envelope being calculated from the initial position and the at least one virtual end position.

A master unit includes a welding DB in which prescribed motion data associated with an object to be welded is stored, a state sensor which measures, as welding state data, a situation of welding by a robot which executes welding in a real environment according to the prescribed motion data, a simulated environment which imitates the real environment and notifies a worker of the welding state data, and a motion control unit which receives, as an input, worker motion data indicating a motion of welding by the worker from the simulated environment, operates the robot in the real environment by using the worker motion data instead of the prescribed motion data, and records, as new prescribed motion data, the input worker motion data in the welding DB.

Disclosed is a deep reinforcement learning apparatus and method for a pick-and-place system. According to the present disclosure, a simulation learning framework is configured to apply reinforcement learning to make pick-and-place decisions using a robot operating system (ROS) in a real-time environment, thereby generating stable path motion that meets various hardware and real-time constraints.

Methods, systems, and apparatus, including computer-readable storage devices, for robot navigation using 2D and 3D path planning. In the disclosed method, a robot accesses map data indicating two-dimensional layout of objects in a space and evaluates candidate paths for the robot to traverse. In response to determining that the candidate paths do not include a collision-free path across the space for a two-dimensional profile of the robot, the robot evaluates a three-dimensional shape of the robot with respect to a three-dimensional shape of an object in the space. Based on the evaluation of the three-dimensional shapes, the robot determines a collision-free path to traverse through the space.

A system and method for collecting data regarding operation of a robot using, at least in part, responses from a first operation model to an input of sensed data from a plurality of sensors. The collected data can be used to optimize the first operation model to generate a second operation model. While the first operation model is being optimized, a train data-driven model that utilizes an end-to-end learning approach can be generated that is based, at least in part, on the collected data. Both the second operation model and the train data-driven model can be evaluated, and, based on such evaluation, a determination can be made as to whether the train data-driven model is reliable. Moreover, based on a comparison of the models, one of the second operation model and the train data-driven model can be selected for validation, and if validated, used in the operation of the robot.

Computer-implemented digital image analysis methods, apparatuses, and systems for robotic installation of surgical implants are disclosed. A disclosed apparatus plans a route within an anatomy of a patient from an incision site to a surgical implant site for robotic installation of a surgical implant. The apparatus uses digital imaging data to identify less-invasive installation paths and determine the dimensions of the surgical implant components being used. The apparatus segments the surgical implant into surgical implant subcomponents and modifies the surgical implant subcomponents, such that they can be inserted using the identified less-invasive installation paths.