Abstract: One embodiment can provide a robotic system. The system can include a machine-vision module, a robotic arm comprising an end-effector, and a robotic controller configured to control movements of the robotic arm to move a component held by the end-effector from an initial pose to a target pose. While controlling the movements of the robotic arm, the robotic controller can be configured to move the component in a plurality of steps. Displacement of the component in each step is less than or equal to a predetermined maximum displacement value.

Abstract: One embodiment can provide a robotic system. The robotic system can include a robotic arm comprising an end-effector, a robotic controller configured to control movements of the robotic arm, and a dual-resolution computer-vision system. The dual-resolution computer-vision system can include a low-resolution three-dimensional (3D) camera module and a high-resolution 3D camera module. The low-resolution 3D camera module and the high-resolution 3D camera module can be arranged in such a way that a viewing region of the high-resolution 3D camera module is located inside a viewing region of the low-resolution 3D camera module, thereby allowing the dual-resolution computer-vision system to provide 3D visual information associated with the end-effector in two different resolutions when at least a portion of the end-effector enters the viewing region of the high-resolution camera module.

Abstract: One embodiment can provide a robotic system. The system can include a machine-vision module, a robotic arm comprising an end-effector, a robotic controller configured to control movements of the robotic arm, and an error-compensation module configured to compensate for pose errors of the robotic arm by determining a controller-desired pose corresponding to a camera-instructed pose of the end-effector such that, when the robotic controller controls the movements of the robotic arm based on the controller-desired pose, the end-effector achieves, as observed by the machine-vision module, the camera-instructed pose. The error-compensation module can include a machine learning model configured to output an error matrix that correlates the camera-instructed pose to the controller-desired pose.

Abstract: One embodiment can provide a method and system for configuring a robotic system. During operation, the system can present to a user on a graphical user interface an image of a work scene comprising a plurality of components and receive, from the user, a sequence of operation commands. A respective operation command can correspond to a pixel location in the image. For each operation command, the system can determine, based on the image, a task to be performed at a corresponding location in the work scene and generate a directed graph based on the received sequence of operation commands. Each node in the directed graph can correspond to a task, and each directed edge in the directed graph can correspond to a task-performing order, thereby facilitating the robotic system to perform a sequence of tasks based on the sequence of operation commands.

Abstract: One embodiment can provide a computer-vision system. The computer-vision system can include one or more cameras to capture images of a scene and one or more sets of single-color light sources to illuminate the scene, with a respective set of light sources comprising multiple single-color light sources of different colors. The multiple single-color light sources within a given set can be turned on sequentially, one at a time. The cameras can capture an image of the scene each time the scene is illuminated by a respective single-color light source of a particular color.

Abstract: One embodiment can provide a robotic system. The robotic system can include a robotic arm comprising an end-effector, a robotic controller configured to control movements of the robotic arm, and a dual-resolution computer-vision system. The dual-resolution computer-vision system can include a low-resolution three-dimensional (3D) camera module and a high-resolution 3D camera module. The low-resolution 3D camera module and the high-resolution 3D camera module can be arranged in such a way that a viewing region of the high-resolution 3D camera module is located inside a viewing region of the low-resolution 3D camera module, thereby allowing the dual-resolution computer-vision system to provide 3D visual information associated with the end-effector in two different resolutions when at least a portion of the end-effector enters the viewing region of the high-resolution camera module.

Abstract: One embodiment can provide a robotic system. The system can include a machine-vision module, a robotic arm comprising an end-effector, a robotic controller configured to control movements of the robotic arm, and an error-compensation module configured to compensate for pose errors of the robotic arm by determining a controller-desired pose corresponding to a camera-instructed pose of the end-effector such that, when the robotic controller controls the movements of the robotic arm based on the controller-desired pose, the end-effector achieves, as observed by the machine-vision module, the camera-instructed pose. The error-compensation module can include a machine learning model configured to output an error matrix that correlates the camera-instructed pose to the controller-desired pose.

Abstract: One embodiment can provide a robotic system. The system can include a machine-vision module, a robotic arm comprising an end-effector, and a robotic controller configured to control movements of the robotic arm to move a component held by the end-effector from an initial pose to a target pose. While controlling the movements of the robotic arm, the robotic controller can be configured to move the component in a plurality of steps. Displacement of the component in each step is less than or equal to a predetermined maximum displacement value.