Caterpillar Inc.

Caterpillar of Australia Pty, Ltd.

Caterpillar Global Mining LLC

Catepillar Inc.

Darryl Victor Collins

Craig L Koehrsen

Bryan James Everett

Thomas Frank Doherty

Michael Siemer

Cameron T Lane

Stefan Jacob Wulf

Andrew Seungyul Yun

Ben Lincoln Clare

Greg Davis

Systems and methods are disclosed for managing task assignments for a fleet of haul trucks at a mine site. An assignment engine may: receive state data for a haul truck including haul weight data and second state data for the mine site that is indicative of a plurality of available tasks and associated task material weight data; assign a task to the haul truck by inputting the state data into a trained reinforcement-learning model, wherein: the model has been trained to learn an assignment policy that optimizes a reward function, such that the learned policy accounts for vehicle performance variance due to changing vehicle haul weight and/or road conditions; and cause the at least one haul truck to be operated according to the at least one task assignment.

Systems and methods for managing assignments of tasks for mining equipment using machine learning

A drilling detection system may include a drilling detection circuitry including one or more detection processors configured to receive a vibration signal indicative of vibration associated with a drilling machine configured to drill holes into a substrate and receive a movement signal indicative of movement of the drilling machine relative to one or more positions on the substrate. The one or more detection processors may also be configured to determine vibration associated with the drilling machine, and determine movement associated with the drilling machine. The one or more detection processors may also be configured to determine, based at least in part on the vibration associated with the drilling machine and the movement associated with the drilling machine, the drilling machine has drilled holes into the substrate and a position on the substrate at which the drilling machine has drilled the holes into the substrate.

System and method for automated drilling activity monitoring

An operating status identification system for a machine includes a position sensing module configured to generate a first signal value corresponding to a speed of the machine. The operating status identification system also includes a motion sensing module configured to generate a second signal value corresponding to at least one motion parameter of the machine. The operating status identification system further includes a control module communicably coupled to each of the position sensing module and the motion sensing module. The control module is configured to receive the first signal value and the second signal value. The control module is further configured to identify whether the machine is in at least one of an operating state and a non-operating state based on a combination of the first and second signal values. The control module is configured to identify that the machine is in the operating state when the machine is stationary.

Operating status identification system for machine

Described herein is a method of determining a mine worksite's terrain. The method may include determining positions of a surface of the worksite based on measurements relating to the worksite's terrain. At least some of the measurements may be received from a plurality of mobile machines on the worksite. The method may include transmitting a first subset of the determined positions to a first mobile machine on the worksite. A corresponding computing system and computer-readable medium for executing the method are also described.

Processing of terrain data

Described herein is a method of determining a terrain of a mine worksite. The method may include determining positions of a surface of the worksite from measurements relating to the worksite's terrain. The method may also include determining errors corresponding to the determined positions. The method may also include generating a terrain model that maps the positions and the errors corresponding the positions.

Determining terrain model error

A system is disclosed for monitoring work cycles on a worksite including a truck and a loading machine. The system includes a communications interface, memory storing instructions, and a processing unit configured to execute the instructions. The processing unit receives, via the communications interface, location information and acceleration information for the truck and location information for the loading machine. The processing unit determines a distance between the truck and the loading machine based on the location information. The processing unit determines a phase of a work cycle of the truck based on the determined distance between the truck and the loading machine and on the acceleration information for the truck.

System and method for identifying machine work cycle phases

A control system for determining a location of loading of a machine operating at a worksite is provided. The control system includes a controller coupled to a dump switch. The controller receives a dump signal and velocity data associated with the machine. The velocity data includes a speed of the machine at various positions along a route followed by the machine from a first dump location to a second dump location. The controller identifies the first dump location, the second dump location, and a plurality of stops made along the route. The controller estimates, a first distance and a second distance between the stop and each of the dump locations. The controller estimates a baseline distance between the dump locations and assigns a weighting factor to the stops. Further, the controller determines a load location from the plurality of stops based on the assigned weighting factors.

System and method for detection of loading location

A computer-implemented method for processing loading operation data to estimate one or more delivery events is described. The loading operation data comprises payload records, each representing a delivery event. The method comprises, for a selected payload record, operating a processing unit to determine whether a delivery weight in respect of the selected payload record is likely to reflect a single delivery event. If the delivery weight is unlikely to reflect a single delivery event the method further comprises generating a synthetic payload record representing an estimated delivery event and comprising synthetic weight and timing values.

System and method for estimating delivery events

A method of tracking a fleet of machines operating at a common worksite is disclosed. The method may include receiving at a central controller an unacknowledged message from communicating devices onboard the fleet of machines, the unacknowledged message including a current location of each of the fleet of machines determined by locating devices onboard the fleet of machines. The method may also include updating a location listing of the fleet of machines with the current location, and repetitively multicasting the location listing to the communicating devices.

Fleet tracking method using unicast and multicast communication

A tracking system is disclosed for use with a fleet of machines operating at a common worksite. The tracking system may have a locating device located onboard each machine of the fleet of machine that is configured to determine a current location of an associated machine of the fleet of machines, and a communicating device located onboard each machine in communication with the locating device. The tracking system may also have a central controller located offboard the fleet of machines in communication with each communicating device. The central controller may be configured to receive an unacknowledged message from each communicating device relaying the current location of the associated machine. The central controller may also be configured to update a location listing of the fleet of machines with the current location, and to repetitively multicast the location listing to the communicating devices of the fleet of machines.

Growing community of inventors

Jindalee, Australia

Darryl Victor Collins