Path Robotics

Abstract Some embodiments described herein relate to optical systems and methods for determining the shape and/or size of objects that include projecting a pattern of light onto the object. The pattern of light can be configured such that first-order reflections can be distinguished from second- and/or higher-order reflections, which can be rejected. Thus, even in instances in which the pattern of light is reflected onto the object multiple times, the original, or first-order, reflection can be detected, distinguished, and/or used for laser triangulation. In some embodiments, a pattern of light that does not have reflection and/or rotational symmetry is projected onto the object, such that second-order and/or higher-order reflections can be distinguished from the first-order reflection.

This disclosure provides systems, methods, and apparatuses, including computer programs encoded on computer storage media, that provide for welding techniques for manufacturing robots, such multipass welding techniques for welding robots. For example, the welding techniques may enable generation of weld instructions based on a welding fill plan. The instructions may be generated based on a bead model or a table that indicates a wire feed speed, a travel speed, or a voltage. As another example, the techniques may enable generation of weld instructions based on the one or more dimensions of a seam. As another example, the techniques may enable generation of a joint model of a cross-section of a seam to be welded. The joint model may be generated based on a combination of a plurality of feature components to generate the joint model of the seam. Other aspects and features are also claimed and described.

Abstract This disclosure provides systems, methods, and apparatuses, including computer programs encoded on computer storage media, for operation of an assembly robotic system. In one aspect of the disclosure, the assembly robotic system includes a tool coupled to a robot device and configured to be selectively coupled to a first object. The assembly robotic system also includes a welding tool, one or more sensors configured to generate sensor data, and a controller. The controller is configured to control the tool to couple the tool to the first object based on the sensor data, control the robot device to bring the first object into a spatial relationship with a second object, and generate a weld instruction to cause the weld tool to weld a seam formed between the first and second objects. Other aspects and features are also claimed and described.

Abstract This disclosure provides systems, methods, and apparatuses, including computer programs encoded on computer storage media, that provide for training, implementing, or updated machine learning logic, such as an artificial neural network, to model a manufacturing process performed in a manufacturing robot environment. For example, the machine learning logic may be trained and implemented to learn from or make adjustments based on one or more operational characteristics associated with the manufacturing robot environment. As another example, the machine learning logic, such as a trained neural network, may be implemented in a semi-autonomous or autonomous manufacturing robot environment to model a manufacturing process and to generate a manufacturing result. As another example, the machine learning logic, such as the trained neural network, may be updated based on data that is captured and associated with a manufacturing result. Other aspects and features are also claimed and described.

Abstract In some examples, a method for determining weldable and unweldable portions of a seam comprises receiving a representation of a part including the seam. The method also includes discretizing a representation of the seam into a plurality of waypoints. The method also includes evaluating each waypoint from the plurality of waypoints for feasibility of welding. The method further includes generating a weld path through at least a subset of the plurality of waypoints in accordance with the feasibility of welding.

Abstract Systems and methods for real time feedback and for updating welding instructions for a welding robot in real time is described herein. The data of a workspace that includes a part to be welded can be received via at least one sensor. This data can be transformed into a point cloud data representing a three-dimensional surface of the part. A desired state indicative of a desired position of at least a portion of the welding robot with respect to the part can be identified. An estimated state indicative of an estimated position of at least the portion of the welding robot with respect to the part can be compared to the desired state. The welding instructions can be updated based on the comparison.

Abstract In some examples, an autonomous robotic welding system comprises a workspace including a part having a seam, a sensor configured to capture multiple images within the workspace, a robot configured to lay weld along the seam, and a controller. The controller is configured to identify the seam on the part in the workspace based on the multiple images, plan a path for the robot to follow when welding the seam, the path including multiple different configurations of the robot, and instruct the robot to weld the seam according to the planned path.