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.

An apparatus for constructing kinematic information of a robot manipulator is provided. The apparatus includes: a robot image acquisition part for acquiring a robot image containing shape information and coordinate information of the robot manipulator; a feature detection part for detecting the type of each of a plurality of joints of the robot manipulator and the three-dimensional coordinates of the joint using a feature detection model generated through deep learning based on the robot image containing shape information and coordinate information; and a variable derivation part for deriving Denavit-Hartenberg (DH) parameters based on the type of each of the plurality of joints of the robot manipulator and the three-dimensional coordinates of the joint.

A robot control system includes circuitry configured to: acquire an input command value indicating a manipulation of a robot by a subject user; acquire a current state of the robot and a target state associated with the manipulation of the robot; determine a state difference between the current state and the target state; acquire from a learned model, a degree of distribution associated with a motion of the robot, based on the state difference, wherein the learned model is generated based on a past robot manipulation; set a level of assistance to be given during the manipulation of the robot by the subject user, based on the degree of distribution acquired; and generate an output command value for operating the robot, based on the input command value and the level of assistance.

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.

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.

System and techniques for tool position determination in a robotic appendage are described herein. A robotic appendage is put through a rotational movement to induce acceleration in a tool mounted to the appendage. A model for acceleration is created from positional kinematics of the appendage. A measurement of acceleration is taken at the tool and fit to the model to determine distance from the axis of rotation to the tool. The distance is provided for use in control or modeling of the robotic appendage.

A method for determining placement of support-platform joints (8a, 9a, 10a, 11a, 12a, 13a) on a support-platform (17) of a parallel kinematic manipulator, PKM. The PKM comprises: the support-platform (17), a first support linkage (SL1), a second support linkage (SL2) and a third support linkage (SL3). The first support linkage (SL1), the second support linkage (SL2) and the third support linkage (SL3) together comprises at least five support-links (8, 9, 10, 11, 12, 13). The method comprises estimating (S1) parameters indicative of stiffness for the PKM, based on a kinematic model and an elastic model of the PKM and chosen defined forces and/or torques applied to a tool (22) during a processing sequence, and checking (S2) whether the estimated parameters indicative of stiffness of the PKM fulfill one or more stiffness criteria. Upon the estimated parameters indicative of stiffness fulfilling one or more stiffness criteria, the method comprises choosing (S3) the current placement configuration as an optimal placement configuration of the support-platform joints. The disclosure also relates to a system comprising a computer configured to perform the method and to output an optimal placement configuration, and a PKM with support-platform joints that are placed to the support-platform according to the optimal placement configuration outputted by the computer. The disclosure also relates to PKMs with support-platform joints that are placed to the support-platform to achieve high stiffness.

Disclosed are a method and an apparatus for controlling a multi-legged robot, and a storage medium. The method includes: acquiring current state parameters of the multi-legged robot; when types and/or quantities of the current state parameters meet a first preset condition, acquiring a first motion control policy by inputting the current state parameters into a first model generated by training; and controlling the multi-legged robot based on the first motion control policy.

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.

Methods, apparatus, systems, and computer readable media are provided for determining: 1) sensor parameters for sensors of a robot and 2) model parameters of a dynamic model of the robot. The sensor parameters and model parameters are determined based on applying, as values for known variables of a system equation of the robot, sensor readings and position values for each of a plurality of instances of a traversal of the robot along a trajectory. The system equation of the robot is a dynamic model for the robot that includes sensor models substituted for one or more corresponding variables of the dynamic model. The system equation includes unknown variables representing unknown sensor biases for the sensors of the robot and unknown model parameters of the dynamic model of the robot. Solutions to the unknown variables are generated and utilized to determine the sensor parameters and the model parameters.