Abstract: A system for performing autonomous agriculture within an agriculture production environment includes one or more agriculture pods, a stationary robot system, and one or more mobile robots. The agriculture pods include one or more plants and one or more sensor modules for monitoring the plants. The stationary robot system collects sensor data from the sensor modules, performs farming operations on the plants according to an operation schedule based on the collected sensor data, and generates a set of instruction for transporting the agriculture pods within the agriculture production environment. The stationary robot system communicates the set of instructions to the agriculture pods. The mobile robots transport the agriculture pods between the stationary robot system and one or more other locations within the agriculture production environment according to the set of instructions.

Abstract: A system for safe interaction between a human and an industrial machine includes a cyber-mechanical system. The cyber-mechanical system includes at least one industrial machine and a cyber-mechanical control system for processing inputs and producing control outputs for the at least one industrial machine; The system further includes a task planner configured to translate high level goals into scheduled tasks of the industrial machine. The system includes an interaction reasoner that identifies at least one interaction between the industrial machine and a human working in cooperation with the industrial machine. Output of the interaction reasoner is provided to an image generator that produces an interaction image. The interaction image represents information relating to one or more of the scheduled tasks of the industrial machine. An image projector associated with the industrial machine conveys information about the scheduled tasks of the associated industrial machine to the human.

Abstract: A computer-based system and method is disclosed for spatial programming of a robotic device. A mixed reality tool may select an object related to one or more interactive tasks for the robotic device. A spatial location of the object may be located including Cartesian coordinates and orientation coordinates of the object. An application program may be executed to operate the robotic device using the spatial location. Based on initial parameters, execution of the one or more tasks by the robotic device on the object related to a skill set may be simulated in a mixed reality environment.

Abstract: Systems, methods, and computer-readable media are disclosed for planning and scheduling of manufacturing using a receding horizon planning approach that enables the manufacture of multiple products in a flexible and efficient manner. A receding horizon planning engine is provided that receives input data indicative of various manufacturing parameters associated with the manufacture of various products and utilizes the input data to solve an optimization problem with respect to a cost function to generate a receding horizon execution plan indicative of a set of planned manufacturing steps to be executed. Some subset of the planned manufacturing steps (which may include all planned steps) may then be executed. Upon completion of execution of the subset of planned manufacturing steps or upon the occurrence of a trigger event, the optimization problem may be re-solved to obtain a new receding horizon execution plan for a subsequent set of planned manufacturing steps.

Abstract: A method for executing a machine learning model with a controller includes a processor within the controller writing input values to a process image within the controller. The term process image refers to a predefined address space within volatile memory of the controller. A co-processor connected to the controller reads the input values from the process image and applies a machine learning model to the input values to generate output values. The co-processor writes output values to the process image and the processor reads those output values from the process image. The process can then execute an application program that utilizes the one or more output values.

Abstract: A system and method is disclosed for development of a control application for a controller of an automation system. The controller receives sensor signals associated with perception of a first real component during an execution of the control application program. Activity of a virtual component, including interaction with the real first component, is simulated, the virtual component being a digital twin of a second real component designed for the work environment and absent in the work environment. Virtual data is produced in response to the simulated activity of the virtual component. A control application module determines parameters for development of the control application program using the sensor signals for the first real component and the virtual data. An AR display signal for the work environment is rendered and displayed based on a digital representation of the virtual data during an execution of the control application program.

Abstract: Systems, techniques, and computer-program products are provided for tracking and traceability of parts of a finished product. In some embodiments, the tracking and traceability generates streams of semantic data obtained from an imaging sensor system that records the execution of a manufacturing process in industrial equipment. The execution of the manufacturing process yields a finished product from initial materials and/or parts. The tracking and traceability also implements artificial reasoning about the execution of the manufacturing process to generate assertions that characterize the execution of the manufacturing process. Semantic data and assertions can be aggregated into a digital trace record that tracks a defined component of the finished product throughout the execution of the manufacturing process and permit tracing the component to a defined event within the manufacturing process.

Abstract: Systems, methods, and computer-readable media are disclosed for planning and scheduling of manufacturing using a receding horizon planning approach that enables the manufacture of multiple products in a flexible and efficient manner. A receding horizon planning engine is provided that receives input data indicative of various manufacturing parameters associated with the manufacture of various products and utilizes the input data to solve an optimization problem with respect to a cost function to generate a receding horizon execution plan indicative of a set of planned manufacturing steps to be executed. Some subset of the planned manufacturing steps (which may include all planned steps) may then be executed. Upon completion of execution of the subset of planned manufacturing steps or upon the occurrence of a trigger event, the optimization problem may be re-solved to obtain a new receding horizon execution plan for a subsequent set of planned manufacturing steps.

Abstract: Systems, techniques, and computer-program products are provided for tracking and traceability of parts of a finished product. In some embodiments, the tracking and traceability generates streams of semantic data obtained from an imaging sensor system that records the execution of a manufacturing process in industrial equipment. The execution of the manufacturing process yields a finished product from initial materials and/or parts. The tracking and traceability also implements artificial reasoning about the execution of the manufacturing process to generate assertions that characterize the execution of the manufacturing process. Semantic data and assertions can be aggregated into a digital trace record that tracks a defined component of the finished product throughout the execution of the manufacturing process and permit tracing the component to a defined event within the manufacturing process.

Abstract: A system for performing autonomous agriculture within an agriculture production environment includes one or more agriculture pods, a stationary robot system, and one or more mobile robots. The agriculture pods include one or more plants and one or more sensor modules for monitoring the plants. The stationary robot system collects sensor data from the sensor modules, performs farming operations on the plants according to an operation schedule based on the collected sensor data, and generates a set of instruction for transporting the agriculture pods within the agriculture production environment. The stationary robot system communicates the set of instructions to the agriculture pods. The mobile robots transport the agriculture pods between the stationary robot system and one or more other locations within the agriculture production environment according to the set of instructions.

Abstract: A computer-based system and method is disclosed for spatial programming of a robotic device. A mixed reality tool may select an object related to one or more interactive tasks for the robotic device. A spatial location of the object may be located including Cartesian coordinates and orientation coordinates of the object. An application program may be executed to operate the robotic device using the spatial location. Based on initial parameters, execution of the one or more tasks by the robotic device on the object related to a skill set may be simulated in a mixed reality environment.

Abstract: An agile manufacturing platform for manufacture of an object includes a substantially planar body (301) supporting a computer processor (303) and a plurality of articulated legs (305). An articulated robotic arm (307) is rotatably mounted to the planar body and includes at least one articulated joint to providing at least 3 degrees of freedom relative to the planar body. A machine tool (315) is coupled to the articulated robotic arm.

Abstract: A system and method is disclosed for development of a control application for a controller of an automation system. The controller receives sensor signals associated with perception of a first real component during an execution of the control application program. Activity of a virtual component, including interaction with the real first component, is simulated, the virtual component being a digital twin of a second real component designed for the work environment and absent in the work environment. Virtual data is produced in response to the simulated activity of the virtual component. A control application module determines parameters for development of the control application program using the sensor signals for the first real component and the virtual data. An AR display signal for the work environment is rendered and displayed based on a digital representation of the virtual data during an execution of the control application program.