Various gripped objects having different sizes, weights, centers of gravity, and the like are continuously and stably moved at a high speed. A control device includes: a state information generation unit that generates and updates state information on a robot and a gripped object; and a control information generation unit that generates, based on the state information and a base trajectory generated in advance on which the robot is configured to move the gripped object from a start point to an end point, control information for controlling the robot.

A system for trajectories imitation for robotic manipulators is provided. The system includes an interface configured to receive a plurality of task descriptions, wherein the interface is configured to communicate with a real-world robot, a memory to store computer-executable programs including a robot simulator, a training module and a transfer module, and a processor, in connection with the memory. The processor is configured to perform training using the training module, for the task descriptions on the robot simulator, to produce a plurality of source policy with subgoals for the task descriptions. The processor performs training using the training module, for the task descriptions on the real-world robot, to produce a plurality of target policy with subgoals for the task descriptions, and update the parameters of the transfer module from corresponding trajectories with the subgoals for the robot simulator and real-world robot.

A method for correcting the processing path of a robot-guided tool for processing at least one component, wherein: a target position for a plurality of points of a target processing path is specified; from the specified points, points to be corrected are selected; the actual position for the selected points to be corrected is measured or detected on at least one component to be processed; and the processing path corresponding to the measured or detected actual position of the points of the component to be processed is correspondingly corrected. The method is suitable, for example, for welding a component into a borehole using a laser beam, wherein the processing path of the laser beam is corrected so as to correspond to the contour of the component.

Methods, apparatus, systems, and computer-readable media are provided for training a path of a robot within a graphical user interface (GUI) and/or by physically moving the robot. In particular, the technology generates a trained path for the robot based on waypoints defined by a user and generates one or more parameters for one or more movement characteristics of the robot along the trained path. The parameters for the movement characteristics are generated based on spatial proximity of a plurality of the waypoints that are defined by the user.

A motion control method, a robot, and a computer-readable storage medium are provided. The method includes: calculating a task matrix and expected information of each task of the robot based on reference trajectory information of each task of the robot in a control period and state estimation information of each task of the robot in the control period; calculating a constraint matrix and a boundary of an inequality constraint that the robot needs to satisfy based on the state estimation information; constructing a hierarchical quadratic programming problem with recursive hierarchical projection based on all the information obtained above, a real-time determined weight coefficient of each task, and a real-time determined priority level of each task: and solving the hierarchical quadratic programming problem to obtain a result, and generating a joint control instruction for controlling each joint of the robot to move.

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for rule execution in an online robotics system. One of the systems includes an execution engine subsystem and an execution memory subsystem. The execution engine receives rules having types and subtypes that represent a particular entity in an operating environment of a robot, provides subscription requests to the execution memory subsystem, and receives events emitted by the execution memory subsystem. The an execution memory receives subscription requests from the execution engine subsystem, receives new observations, converts the new observations into fact updates, performs pattern matching with the fact updates against the patterns of the subscription requests, and emits events to the execution engine subsystem for patterns that have been matched by the fact updates.

The present disclosure provides a method, devices, a numerical control machine, and a computer storage medium for detecting machine processing trajectory space. The method includes: obtaining data of a trajectory AB of a machine processing and spatial data of a specified space area; converting a function of the data of the trajectory AB into a univariate function P=f (u) with respect to a trajectory parameter u; determining a point set U.sub.i of the trajectory AB on an inner side of each curved surface S.sub.i based on spatial data of the individual curved surfaces S.sub.i forming the specified space area and the function P=f (u); and determining a positional relationship between the trajectory AB and the specified space area based on the point sets U.sub.i.

Faster, less computational intense, and more robust techniques to optimize velocity of robots or portions thereof without violating constraints on acceleration and jerk (derivative of acceleration with respect to time) are described. A nonlinear problem of optimizing velocity without violating acceleration constraints is linearized, and produces acceleration constrained velocity estimates. A nonlinear problem of optimizing velocity without violating jerk constraints in linearized, and produces jerk constrained velocity estimates, and may be feed by the acceleration constrained velocity estimates. Configuration and timing may be generated and provided, e.g., as vectors, to control operation of a robot, robotic appendage or other structure.

The present disclosure provides a virtual rail based cruise method as well as an apparatus and a robot using the same. The method includes: obtaining a digital map including a virtual rail; performing a path planning based on the virtual rail, a current position of the robot, and a cruise end point to obtain a cruise path; and obtaining parameter(s) of the robot by calculating through a preset path tracking algorithm based on the cruise path and the current position of the robot, and controlling the robot based on the control parameter(s). In this manner, the problems of the prior art that needs to lay a rail or set an auxiliary device which causes high cost and inconvenience in usage as well as the rail needs to be re-laid or the auxiliary device needs to be reinstalled when the route is to be changed can be solved.

The present disclosure relates to a Web server (104, 60, 70) and a method therein of determining a trajectory for controlling of a robot device over a cloud interface. From a URI-encoded HTTP request (402) for the trajectory between a first pose and a second pose of the robot device, it is determined (S112, 408) the length of matching between cached trajectories and the trajectory requested. The longest length of matching is compared (S114, 410) to a minimal matching length (406), and if the longest length is longer than the minimal matching length, a HTTP response is sent (S122, 412) comprising the trajectory being determined. If the longest length is shorter than the minimal matching length, a HTTP request to calculate is sent (S116, 414). Currently available web service architecture can be reused, and easily up-scaled.