WILDER SYSTEMS INC.

Aspects of the disclosure are directed towards artificial intelligence-based modeling of target objects, such as aircraft parts. In an example, a system initially trains a machine learning (ML) model based on synthetic images generated based on multi-dimensional representation of target objects. The same system or a different system subsequently further trains the ML model based on actual images generated by cameras positioned by robots relative to target objects. The ML model can be used to process an image generated by a camera positioned by a robot relative to a target object based on a multi-dimensional representation of the target object. The output of the ML model can indicate, for a detected target, position data, a target type, and/or a visual inspection property. This output can then be used to update the multi-dimensional representation, which is then used to perform robotics operations on the target object.

Aspects of the disclosure are directed towards path generation. A method includes a computing system registering a first coordinate system of a target object with a second coordinate system of a robot. The computing system can generate a trajectory over the surface of the target object based on the registration. The computing system can generate a robot job file based at least in part on the generated trajectory. The computing system can transmit the robot job file to a robot controller.

Aspects of the disclosure are directed towards updated an object representation. An example method can include causing, based on a representation of a part of an object, a robot to position an image capturing device relative to the part, the representation indicating a first characteristic of the object. The method can further include receiving a first image generated by the image capturing device while the image capturing device is positioned relative to the part. The method can further include generating a first input to a machine learning model based on the first image. The method can further include determining a first output of the machine learning model based on the first input, the first output indicating a second characteristic different than the first characteristic. The method can further include generating an updated representation that indicates the second characteristic in place of the first characteristic.

Techniques for auto-locating and autonomous operation data storage are disclosed. An example method can include storing a multi-dimensional representation of an aircraft in a data storage. The method can further include causing transmission of the multi-dimensional representation of the aircraft and first control instructions to a robot for performing a first autonomous operation on the aircraft, the robot configured to identify the aircraft based on the multi-dimensional representation, the aircraft located at a premises. The method can further include processing sensor data generated at the premises. The method can further include generating second control instructions for performing a second autonomous operation on the aircraft based on the sensor data. The method can further include causing transmission of the second control instructions to the robot for performing the second autonomous operation on the aircraft.

The present disclosure relates to a multi-tiered computing environment for balancing compute resources in support of robot operations. In an example, a first server can receive from a robot located on a premises, a request and a first data, The first server can access a local configuration table to determine a program code associated with the first operation. The first server can generate second data based on the first data and the local configuration table. The first server can transmit the second data to the robot. The first server can receive, from the robot, third data indicating performance of the operation. The first server can transmit to a second server associated with the airplane model, fourth data, the fourth data generated based on the third data.

Aspects of the disclosure are directed towards artificial intelligence-based modeling of target objects, such as aircraft parts. In an example, a system initially trains a machine learning (ML) model based on synthetic images generated based on multi-dimensional representation of target objects. The same system or a different system subsequently further trains the ML model based on actual images generated by cameras positioned by robots relative to target objects. The ML model can be used to process an image generated by a camera positioned by a robot relative to a target object based on a multi-dimensional representation of the target object. The output of the ML model can indicate, for a detected target, position data, a target type, and/or a visual inspection property. This output can then be used to update the multi-dimensional representation, which is then used to perform robotics operations on the target object.

Techniques for auto-locating and autonomous operation data storage are disclosed. An example method can include storing a representation of an aircraft in a data storage of the computing system. The representation and instructions for performing a first operation on the aircraft can be transmitted to a first robot. The first robot can be configured to identify the aircraft based on a first feature of the representation. The method can further include receiving sensor data. The method can further include transmitting the sensor data to an analysis service to identify a state of a part of the aircraft. The method can further include storing the analysis in the data storage. The method can further include generating second instructions for performing a second operation on the aircraft based on the analysis and the representation stored in the data storage.

The present disclosure relates to a multi-tiered computing environment for balancing compute resources in support of robot operations. In an example, a robot is tasked with performing an operation associated with an airplane having an airplane model. To do so, the robot may need another operation that is computationally complex to be performed. An on-premises server can execute a process that corresponds to this computationally-complex operation based on sensor data of the robot and can output the resulting data to the robot. Next, the robot can use the resulting data to execute another process corresponding to its operation and can indicate performance of this operation to the on-premises network. The on-premises network can send the indication about the operation performance to a top-tier server that is also associated with the airplane model.

Aspects of the disclosure are directed towards artificial intelligence-based modeling of target objects, such as aircraft parts. In an example, a system initially trains a machine learning (ML) model based on synthetic images generated based on multi-dimensional representation of target objects. The same system or a different system subsequently further trains the ML model based on actual images generated by cameras positioned by robots relative to target objects. The ML model can be used to process an image generated by a camera positioned by a robot relative to a target object based on a multi-dimensional representation of the target object. The output of the ML model can indicate, for a detected target, position data, a target type, and/or a visual inspection property. This output can then be used to update the multi-dimensional representation, which is then used to perform robotics operations on the target object.

Aspects of the disclosure are directed towards path generation. A method includes a user interface (UI) displaying a first page on a first pane, wherein the first page provides a first control input for registering a working frame of a target object with a reference frame of a robot. The method further includes receiving, via the UI, a first user selection of the first control input for registering the working frame with the reference frame, based on detection of the first user selection. The UI can display a second page on the first pane, wherein the second page provides a second control input for generating a path for the robot to traverse over a surface of the target object. The method further includes receiving, via the UI, a second user selection of the second control input for generating the path, based on detection of the second user selection.