AGCO Intellectual Property Department

A cart management system includes a stereo camera system and is configured to: capture, via the stereo camera system, first and second image data and second image data of the agricultural vehicle, the cart, and a transport vehicle, estimate depth data from the first image data and the second image data; receive GNSS data and IMU data related to at least one of the agricultural vehicle, the cart, and a transport vehicle; fuse the depth data with the GNSS data and IMU data to generate enhanced fused data; based at least partially on the enhanced fused data, determine an aligned position of the cart relative to the transport vehicle; and responsive to determining the aligned position, cause the cart to automatically align with the transport vehicle.

A cart management system for monitoring and controlling operation of a cart of an autonomous agricultural system includes an array of sensors mounted on at least one the agricultural vehicle or the cart. The cart management system configured to: detect a commencement of an unloading operation by an auger of an unloading system of the cart into a trailer of a transport vehicle; responsive to detecting the commencement of the unloading operation, capture, via the array of sensors and in real-time, image data of a commodity being unloaded into the trailer of the transport vehicle and the trailer of the transport vehicle; utilize a mono-depth convolutional neural network (CNN) to estimate depth data from the image data; and based at least partially on the estimated depth data, determine a fill level of the trailer of the transport vehicle.

A cart management system for monitoring and controlling operation of a cart of an autonomous agricultural system. The cart management system includes an array of sensors mounted on the cart and is configured to: capture, via the array of sensors and in real-time, sensor data of the cart, an auger of an unloading system of the cart, and a commodity within a hopper of the cart; analyze the captured sensor data utilizing machine learning models to identify the cart, the auger of the unloading system of the cart, and the commodity within the hopper of the cart depicted within the sensor data; and based on the analysis of the captured sensor data, automatically cause the auger of the unloading system to extend or to retract prior to or subsequent to an unloading process of unloading the commodity.

A cart management system includes an array of sensors mounted on at least one an agricultural vehicle or a cart and is configured to capture first 3D data of an interior of a trailer of a transport vehicle in an empty state, based on the first 3D data, generate a three-dimensional (3D) map of the trailer, detect a commencement of an unloading operation by an auger of the cart into the trailer; responsive to detecting the commencement of the unloading operation, capture second 3D data of the interior of the trailer and a commodity being unloaded into the trailer, capture image data of the interior of the trailer and the commodity being unloaded into the trailer, and based at least partially on the 3D map of the trailer, the second 3D data, and the image data, determine a fill level of the trailer.

A cart management system includes an array of sensors mounted on at least one an agricultural vehicle or a cart and is configured to: capture, via the array of sensors, image data of the agricultural vehicle, the cart, and a transport vehicle; utilize a mono-depth deep neural network to estimate depth data from the image data; analyze the image data and the depth data to identify and classify the agricultural vehicle, the cart, and the transport vehicle to generate labeled sensor data; receive GNSS data and IMU data; fuse the labeled sensor data with the GNSS data and IMU data to generate enhanced fused data; based at least partially on the enhanced fused data, determine an aligned position of the cart relative to the transport vehicle; and responsive to determining the aligned position, cause the cart to automatically align with the transport vehicle.

A cart management system for monitoring and controlling operation of a cart of an autonomous agricultural system. The cart management system includes an array of sensors mounted proximate or on an end of the agricultural vehicle facing the cart and is configured to: capture, via the array of sensors and in real-time, sensor data of the cart and an auger system of an unloading system of the cart; analyze the captured sensor data to determine a state of the auger system and whether auger system is in a folded state or a unfolded state; responsive to determining that the determined state does not match the folded state or the unfolded state, adjust operation of the auger system, and responsive to determining that the determined state matches the folded state or the unfolded state, provide an indication that the auger system is in either the folded state or the unfolded state.

A cart management system for monitoring and controlling operation of a cart of an autonomous agricultural system. The cart management system includes an array of sensors mounted proximate or on an end of the agricultural vehicle facing the cart and is configured to: capture, via the array of sensors and in real-time, sensor data of the cart, an auger of an unloading system of the cart, and a commodity within a hopper of the cart; analyze the captured sensor data utilizing machine learning models to identify the cart, the auger of the unloading system of the cart, and the commodity within the hopper of the cart depicted within the sensor data; and based on the analysis of the captured sensor data, automatically cause the auger of the unloading system to extend or to retract prior to or subsequent to an unloading process of unloading the commodity.

An autonomous agricultural system includes: an agricultural vehicle; a cart operably coupled to the agricultural vehicle; and a guidance system configured to: capture, via an array of sensors and in real-time, sensor data of a combine harvester; analyze the sensor data to detect a header of the combine harvester; determine an initial aligned position relative to the detected header of the combine harvester; responsive to determining the initial aligned position, cause the autonomous agricultural system to automatically align with the header of the combine harvester at the initial aligned position; subsequent to aligning with the header of the combine harvester, determine an operating aligned position relative to an unloading auger or a body of the combine harvester; and responsive to determining the operating aligned position, cause the autonomous agricultural system to automatically align with the unloading auger or the body of the combine harvester at the operating aligned position.

A cart management system for monitoring and controlling operation of a cart of an autonomous agricultural system. The cart is operably coupled to an agricultural vehicle of the autonomous agricultural system. The cart management system includes an array of sensors mounted on at least one the agricultural vehicle or the cart; at least one processor; and at least one non-transitory computer-readable storage medium storing instructions thereon that, when executed by the at least one processor, cause the cart management system to: responsive to a commencement of an unloading operation by an auger of an unloading system of the cart into a trailer of a transport vehicle, track at least one of time or actuator actions; and responsive a predetermined amount of time elapsing or a predetermined number of actuator actions occurring, cause the autonomous agricultural system to move relative to the transport vehicle or terminating the unloading operation.

A cart management system for monitoring and controlling operation of a cart of an autonomous agricultural system. The cart management system includes an array of sensors mounted on the cart and configured to: capture, via the array of sensors and in real-time, sensor data of the cart and an auger system of an unloading system of the cart; analyze the captured sensor data to determine at least one of a length of an auger of the auger system and an orientation of the auger system; based on the determined length of the auger of the auger system and the determined orientation of the auger of the auger system, determine an aligned position of the cart relative to a transport vehicle; and responsive to determining the aligned position, cause the cart to automatically align with the transport vehicle.