To generate link information containing association between machining information and/or machine information in a machining program, and an optical feature in a workpiece image. A link information generation device 1 comprises: a machining information acquisition unit 111 that acquires machining information in a machining program for a machine tool that executes machining on a workpiece W; a machine information acquisition unit 112 that acquires machine information about the machining state of the machine tool; a workpiece image acquisition unit 13 that acquires image information about the workpiece W; an optical feature setting unit 14 that sets an image area having an optical feature in the image information about the workpiece W; and a link information generation unit 15 that generates link information containing association between the image area having the optical feature, and the machining information and/or the machine information about a workpiece area associated with the image area.

A method and system for determining geometric properties of a manipulator (2). The manipulator (2) is controlled to perform constrained motions exhibiting force interaction with the environment, or between different links of the manipulator (2), such that a kinematic chain is formed mechanically. The chain may include peripherals and external axes of motion. A constraining device, enables motions that facilitate the determination of geometric properties. A unified model of joint and link compliances facilitates determination of stiffness parameters. The force interaction is controlled with awareness of friction such that non-geometric properties are possible to identify, thereby enabling separation of non-geometric effects from the geometric ones, which improves accuracy.

In one embodiment, a method includes by a robotic system: sending, by an automatic tuning controller, driving commands to actuators of the robotic system, performing, for each of the actuators, one or more measurements of an actual pose of the respective actuator in response to the driving commands, generating, for each of the actuators, one or more configuration parameters for the respective actuator based on the one or more measurements, and storing the configuration parameters for the actuators in a data store of the robotic system.

A design method of serial manipulator that comprises an end effector, a number of random-access links, and a number of motors, includes: obtaining a desired motion profile of the end effector; discretizing the desired motion profile into a plurality of points, wherein each of the points carries information of speed, acceleration, and force/torque of the end effector at the point; determining the number of degrees of freedom of the serial manipulator, and initializing the length of each of the links and the motor type of each of the motors; and at each of the points, optimizing the initialized lengths of the links and the motor types of the motors by calculating a dynamic manipulability ellipsoid at the end effector, to obtain desired lengths of the links and desired motor types of the motors, which allows the end effector to execute the desired motion profile under predetermined constraints.

An autoencoder may be trained to predict 3D pose labels using simulation data extracted from a simulated environment, which may be configured to represent an environment in which the 3D pose estimator is to be deployed. Assets may be used to mimic the deployment environment such as 3D models or textures and parameters used to define deployment scenarios and/or conditions that the 3D pose estimator will operate under in the environment. The autoencoder may be trained to predict a segmentation image from an input image that is invariant to occlusions. Further, the autoencoder may be trained to exclude areas of the input image from the object that correspond to one or more appendages of the object. The 3D pose may be adapted to unlabeled real-world data using a GAN, which predicts whether output of the 3D pose estimator was generated from real-world data or simulated data.

A method of obtaining the gear stiffness of a robot joint gear of a robot joint of a robot arm, where the robot joint is connectable to at least another robot joint. The robot joint comprises a joint motor having a motor axle configured to rotate an output axle via the robot joint gear. The method comprises the steps of: —applying a motor torque to the motor axle using the joint motor; —obtaining the angular position of the motor axle; —obtaining the angular position of the output axle; —determining the gear stiffness based on at least the angular position of the motor axle, the angular position of the output axle and a dynamic model of the robot arm.

What is disclosed is a motion model calculation device which easily creates a motion model for a drive device. The motion model calculation device is connected to a robot arm including a plurality of arms and a joint mechanism which pivotally joins the plurality of arms to a connection part, outputs a predetermined motion command to the joint mechanism, acquires a driving state of the joint mechanism caused by a motion corresponding to the motion command, and calculates, on the basis of the motion command and the driving state, a motion model representing the relationship between an input value representing an input to the joint mechanism and an output value of the joint mechanism with respect to the input.

A method and system for determining geometric properties of a manipulator (2). The manipulator (2) is controlled to perform constrained motions exhibiting force interaction with the environment, or between different links of the manipulator (2), such that a kinematic chain is formed mechanically. The chain may include peripherals and external axes of motion. A constraining device, enables motions that facilitate the determination of geometric properties. A unified model of joint and link compliances facilitates determination of stiffness parameters. The force interaction is controlled with awareness of friction such that non-geometric properties are possible to identify, thereby enabling separation of non-geometric effects from the geometric ones, which improves accuracy.

A computer-implemented method of engineering autonomous system with reusable skills includes displaying a graphical user interface simulating a physical environment. The graphical user interface depicts one or more simulated objects corresponding to one or more physical objects. Graphical markers are created on the simulated objects based on instructions provided by a user via the graphical user interface. The position and orientation of each graphical marker is determined with respect to the simulated objects. A skill function is created which comprises a functional description for using a controllable physical device to interact with the physical objects based on the position and orientation of each graphical marker. Executable code operable to perform the skill function is created and used to actuate the controllable physical device.

The invention proposes an axis-invariant multi-axis system dynamics modeling and solving principle, and realizes iterative explicit dynamic modeling of multi-axis systems with tree chains, closed chains, friction and viscous joints and moving pedestals. The established model has elegant chain symbol system with pseudo-code function, which realizes complete parameterization including topology, coordinate system, polarity, structural parameters, mass inertia, etc.. The principle can be set to circuit, code, directly or indirectly, partially or fully executed inside a multi-axis robot system. In addition, the present invention also includes analytical verification system constructed on these principles for designing and verifying a multi-axis robot system.