In the present disclosure, methods, systems, and apparatuses for in-process assembly error correction are described. In various embodiments, a target arrangement of parts of an assembly may be obtained, with the target arrangement including a first target position of a first part, a second target position of a second part, and a third target position of a third part. The first part and the second part may be robotically joined based on the first target position and the second target position to obtain a first subassembly of the assembly, with the first subassembly having a first physical arrangement that includes the physical arrangement of the first and second parts after joining. The first physical arrangement may be fitted to the target arrangement to obtain a fitted first physical arrangement. The first subassembly and the third part may be robotically joined based on the fitted first physical arrangement.

The present disclosure discloses an autonomous mobile grabbing method for a mechanical arm based on visual-haptic fusion under a complex illumination condition, which mainly includes approaching control over a target position and feedback control over environment information.

According to the method, under the complex illumination condition, weighted fusion is conducted on visible light and depth images of a preselected region, identification and positioning of a target object are completed based on a deep neural network, and a mobile mechanical arm is driven to continuously approach the target object; in addition, the pose of the mechanical arm is adjusted according to contact force information of a sensor module, the external environment and the target object; and meanwhile, visual information and haptic information of the target object are fused, and the optimal grabbing pose and the appropriate grabbing force of the target object are selected.

By adopting the method, the object positioning precision and the grabbing accuracy are improved, the collision damage and instability of the mechanical arm are effectively prevented, and the harmful deformation of the grabbed object is reduced.

In an embodiment, a method includes determining a given material to manipulate to achieve a goal state. The goal state can be one or more deformable or granular materials in a particular arrangement. The method further includes, for the given material, determining, a respective outcome for each of a plurality of candidate actions to manipulate the given material. The determining can be performed with a physics-based model, in one embodiment. The method further can include determining a given action of the candidate actions, where the outcome of the given action reaching the goal state is within at least one tolerance. The method further includes, based on a selected action of the given actions, generating a first motion plan for the selected action.

Mitigating the reality gap through optimization of one or more simulated hardware parameters for simulated hardware components of a simulated robot. Implementations generate and store real navigation data instances that are each based on a corresponding episode of locomotion of a real robot. A real navigation data instance can include a sequence of velocity control instances generated to control a real robot during a real episode of locomotion of the real robot, and one or more ground truth values, where each of the ground truth values is a measured value of a corresponding property of the real robot (e.g., pose). The velocity control instances can be applied to a simulated robot, and one or more losses can be generated based on comparing the ground truth value(s) to corresponding simulated value(s) generated from applying the velocity control instances to the simulated robot. The simulated hardware parameters and environmental parameters can be optimized based on the loss(es).

According to the present invention, provided is a robot control device that can improve relatively easily the positioning accuracy of a robot. A robot control device according to one aspect of the present disclosure comprises: a position information acquisition unit which acquires position information indicating the actual position of a reference point at the end of a robot having a plurality of drive shafts; a parameter storage unit which stores a plurality of error parameters used to calculate the accurate position of the reference point from a command value for the robot; a sensitivity calculation unit which calculates a sensitivity value representing the magnitude of the change amount of the calculated position of the reference point with respect to the change amount for each error parameter; a target selection unit which selects, on the basis of the sensitivity value, an error parameter to be corrected by the parameter correction unit; and a parameter correction unit which corrects the error parameter to be corrected on the basis of the command value for the robot and the position information, assuming that error parameters other than the error parameter to be corrected do not affect the position of the reference point.

A robot system according to an embodiment includes an arm mechanism that is articulated, a parallel link mechanism, an end effector, a detector, and a control device. The parallel link mechanism includes a fixed part mounted to a distal part of the arm mechanism, and a movable part that is mounted to the fixed part via multiple parallel links and is movable with respect to the fixed part. The end effector is mounted to the movable part. The detector is provided for detecting a position or orientation of a control point. The control device controls the arm mechanism and the parallel link mechanism. The control device performs a first operation of setting a posture of the control point to a first posture, and a second operation of setting the posture of the control point to a task posture in which the end effector performs a task.

A control device according to an embodiment receives first posture data of a posture of a first robot. The first robot includes a first manipulator and a first end effector. Furthermore, the control device sets the posture of the first robot based on the first posture data and causes the first robot to perform a first task on a first member. The first posture data is generated based on second posture data. The second posture data is of a posture when a second robot that includes a second manipulator and a second end effector performs a second task on the first member.

Systems, methods, and computer-readable media for robotic joining of components, parts, and structures are disclosed. A method in accordance with an aspect of the present disclosure comprises determining a target first position and a target second position in a reference frame, controlling robotic arms to move a first part to the target first position and a second part to the target second position, measuring the parts at the target first and second positions to obtain a measured first and second positions, performing a first operation to determine differences between the measured positions and the target positions, and when the differences exceeds desired tolerances, controlling the robotic arms to move the parts to compensate for the differences, and controlling at least the first or second robotic arm to join the first and second parts after the first and second operations are concluded.

A method includes: (a) causing a robotic arm to position a contacting structure of the arm laterally in a horizontal direction in relation to a first subject on a target object; (b) causing the arrn to bring the contacting structure into contact with at least three locations on the first subject; (c) detecting positions of the contacting structure in relation to the robot when contacting the locations; (d) detecting a position of the first subject in relation to the robot by using the detected positions of the contacting structure; (e) performing same steps as the steps (a) to (d) for a second subject on the target object; and (f) detecting a position of the robot in relation to the target object by using the positions of the subjects in relation to the robot and using positions of the subjects in relation to the target object.

The disclosure provides a dynamic interaction-oriented subject's limb time-varying stiffness identification method and device. The method includes: the combination of subject's limb displacement and measured force data or the combination of angle and measured torque data is collected; based on the time-varying dynamic system constructed based on a second-order impedance model, the linear parameter varying method is utilized to substitute the time-varying impedance parameters and reconstruct the restoring force/torque expression; iterative identification is performed on variable weights, dynamic interaction force/torque, and restoring force/torque by using time-varying dynamic parameters based on the dynamic interaction force/torque expression expanded from basis function; the time-varying stiffness is solved by using variable weights and dynamic interaction force/torque according to expression with substituted the time-varying impedance parameters. The disclosure not only improves the accuracy of the time-varying stiffness identification technology but also expands the application scenarios of the time-varying stiffness identification technology.