Abstract: A system and method for installing solar panels are provided. The method includes obtaining an image of an in-progress solar installation. The image includes an image of one or more solar panels and one or more torque tubes. The method also includes detecting solar panel segments by inputting the image to a trained neural network that is trained to detect solar panels in poor lighting conditions. The method also includes estimating panel poses for the one or more solar panels, based on the solar panel segments, using a computer vision pipeline. The method also includes generating control signals, based on the estimated panel poses, for operating a robotic controller for installing the one or more solar panels.

Abstract: A system and method for installing solar panels are provided. The method obtains an image of a solar panel during an in-progress solar installation and estimates features of the solar panel based on a first image using distance simulation, geometric correction, and/or angular adjustment. The method also generates control signals, based on the estimated features, for operating a robotic controller for picking the solar panel. The method also obtains a second image of the solar panel when the solar panel is in a perspective view and detects placement of the solar panel based on the image by determining if the solar panel is co-planar with and at a predetermined offset from a fixed solar panel. Based on the detected placement, control signals are generated for operating a second robotic controller for aligning the solar panel with the fixed solar panel.

Abstract: A system and method for installing solar panels are provided. The method includes obtaining images of solar panels an installation structure during installation. The method also includes pre-processing the images by compensating for camera intrinsics or distortions, rectifying the images, and/or determining depth information. The method also includes detecting the solar panels by inputting the images into neural networks. The method also includes a first post-processing to compute a first panel pose based on an output of the neural networks. The method also includes generating control signals, based on the first panel pose, for operating a robotic controller for installing the solar panels. In some embodiments, the method also includes homography transforms to obtain a second panel pose, based on the first panel pose and visual patterns or fiducials on a solar panel, and generating the control signals further based on the second panel pose.

Abstract: A system for installing a solar panel may include a first end-of-arm assembly tool coupled to a first robotic arm and part of a first assembly robot and a second end-of-arm assembly tool coupled to a second robotic arm and part of a second assembly robot. The first and the second end-of-arm assembly tools have different tooling and perform different functions to assembly solar panels to support structure. The first assembly robot and the second assembly robot may be located on autonomous and non-autonomous vehicles and the various components can be operated by a control system based on operation instructions received from a neural network.

Abstract: A system for installing a solar panel may include an end of arm assembly tool and a linear guide assembly coupled to the end of arm assembly tool. The end of arm assembly tool includes a frame and plurality of attachment devices, such as suction cups, coupled to the frame. The linear guide assembly includes a linearly moveable clamping tool including an engagement member configured to engage a clamp assembly slidably coupled to an installation structure, and a force torque transducer configured to move the clamping tool along the installation structure. A controller configured to control the force torque transducer and the plurality of attachment devices. The end of arm assembly tool is coupled to a robotic arm and is part of an assembly robot that includes autonomous and non-autonomous vehicles. The various components can be operated by a control system based on operation instructions received from a neural network.