Deere & Company

Carnegie Mellon University

John M Hageman

Tarik Loukili

Michael G Kean

Herman Herman

Mark John Cherney

Aaron J Bruns

Sean Patrick West

Keith N Chaston

Suraj Amatya

Bhanu Kiran Reddy Palla

Michael D Peat

Victor S Sierra

Carlos Vallespi-Gonzalez

Scott Svend Hendron

James Joseph Phelan

Reginald M Bindl

Craig Christofferson

Carl Knox Wellington

Cristian Dima

Joshua C Heitsman

Mathew J Zeringue

Chad M Indovina

Zachary Pezzementi

Joan Campoy

Douglas K Wink

Halit Bener Suay

Cody R Gros

Cason Robert Male

Hanke Boesch

Francois Stander

Vladimir Altman

Brian Joseph Gilmore

Zimin W Vilar

Timothy S Hunt

Calin L Raszga

Joshua T Lawson

Douglas John Bollin

Nathaniel M Czarnecki

Mark E Breutzman

Jonathan Spendlove

Jaime W Bourne

Adam G Harwood

Paul Readel

Justin Sticksel

Lacy Scott Bayless

David J Kaney

Zach Abraham Pazzementi

L Scott Bayless

Vladimir A Altman

Carlos Vallespi

Cason Male

Zach Pezzementi

A system and method are provided for work cycle tracking for a self-propelled work vehicle having an integrated or drawn/pushed implement, for example comprising a scraper, and a loading container for receiving material worked thereby. First sensors generate data corresponding to operating parameters of the work vehicle, and second sensors generate data corresponding to operating parameters of the implement. Data storage includes, for each of various work states associated with the work cycle, correlations between operating parameters, of the work vehicle and/or implement, and a start or completion of the respective work state. A controller determines a current work state of the various work states associated with the work cycle based on current input data from the first and second sets of sensors, with respect to the stored correlations, and generates one or more output signals based on the determined work state.

Work cycle identification for scrapers and corresponding feature automation

A system and method are provided for real-time deduction of material carryback in a loading container of a transport vehicle, wherein the material is loaded in the loading container by a work machine at a first site and dumped from the loading container by the transport vehicle at a second site. A first sensor (e.g., a camera associated with the work machine) provides first data corresponding to a volume of material loaded in the loading container in a first work state (e.g., loaded). A second sensor (e.g., a camera or a payload measuring unit associated with the transport vehicle) provides second data corresponding to a volume of material loaded in the loading container in a second work state (e.g., unloaded). A generated output signal corresponds to a calculated total volume of material associated with a work cycle, said total volume based on at least the provided first and second data.

System and method for real-time material carryback deduction in loading and dumping work cycles

An example work machine control system may include cost factor logic to obtain a cost factor for a resource, cost variable logic to obtain a consumption signal from a consumption sensor indicative of consumption of the resource, fill measurement logic configured to receive a fill signal from a fill sensor, the fill signal indicative of a fill state of a container of an earth-moving work machine, fill target logic to determine a target fill level for the container based on the cost factor, the consumption signal and the fill signal and control logic to generate a machine control signal based on the target fill level.

Earth-moving machine sensing and control system

An example work machine control system includes target fill level determination logic configured to determine a target fill level for a container of an earth-moving work machine, fill level measurement logic configured to receive a sensor signal from a sensor that detects contents of the container and generate a measurement metric indicative of a current fill level of the container based on the sensor signal, and control logic configured to generate a machine control signal based on the measurement metric and the target fill level.

Systems and methods are described for determining an actual pose of an articulating boom arm using an artificial intelligence mechanism (e.g., a neural network) trained to determine the actual pose of the articulating boom arm based on captured image data. In some implementations, an electronic processor is configured to control movement of the articulating boom arm based at least in part on pose information determined by applying the image-based neural network. In some implementations, an electronic processor is configured to train the neural network by using, as training data, captured image data and output signals from sensors indicative of measured positions of the components of the articulating boom arm.

Camera-based boom control

A volume of contents in a container of a work vehicle can be estimated in various examples. One example involves a system with a 3D sensor on a work vehicle, where the sensor captures images of a material in a container of the work vehicle. A processor device that is in communication with the 3D sensor determines a volume of the material in the container using the images.

Estimating a volume of contents in a container of a work vehicle

One or more undesired objects can be detected in a restricted zone at worksite. In one example, a base station is configured to be placed in or around the restricted zone. The base station includes a housing, a sensor suite, and a base station controller. The sensor suite is configured to detect one or more undesired object in a subzone at least partially overlapping with the restricted zone and generate an output signal based on the undesired object. The subzone is limited by a range of detection from the sensor suite. The base station controller can receive the output signal from the sensor suite and transmit an alert signal. A warning indicator can receive the alert signal and activate in response to receiving the alert signal. The warning indicator can be positioned on the base station or on a mobile device located remote from the base station.

Detecting objects in a restricted zone

A vehicle grade control system and method of controlling an implement position of a motor grader moving along a path of a surface. The motor grader includes a frame supported by wheels and an implement adjustably coupled to the frame. The control system includes a processor and a memory configured to receive a grade target to grade the surface to a desired grade with the implement based on the grade target. Surface irregularities of the surface in a path of the motor grader are located. An angle of the frame is determined based on the located surface irregularities and a difference between the identified angle of the frame and the grade target is determined. A position of the implement with respect to the frame based on the determined difference is identified and the surface is graded with the identified position of the implement.

Forward looking sensor for predictive grade control

A pattern recognition system receives an image captured by an image capture device, of an operator and the operator is identified. Operator information is accessed, based upon the identified operator, and a control signal is generated to control a mobile machine, based upon the operator information.

Machine control using biometric recognition

A vehicle grade control system and method of controlling an implement position of a motor grader moving along a path of a surface. The motor grader includes a frame supported by a ground engaging traction device and an implement adjustably coupled to the frame. The control system includes a processor and a memory configured to receive a grade target to grade the surface to a desired grade with the implement, based on the grade target. A front image sensor provides images of a front surface profile, an implement image sensor provides images of collected surface material on the implement, and a rear image sensor provides images on a rear surface profile. The surface is graded by adjusting a position of the implement based on the images provided by each of the front image sensor, the implement image sensor, and the rear image sensor.

System and method of soil management for an implement

An overall machine operational state (such as a problem state, field state, machine state, other non-problem state, etc.) is identified, and exit and entry conditions are monitored to determine whether the machine transitions into another operational state. When the machine transitions into a problem state, a multiple input, multiple output control system uses a state machine to identify the problem state and a solution is identified. The solution is indicative of machine settings that will return the machine to an acceptable, operational state. Control signals are generated to modify the machine settings based on the identified solution.

State machine for multiple input-multiple output harvester control

A mobile work machine includes a frame and a ground engaging element movably supported by the frame and driven by an engine to drive movement of the mobile work machine. The mobile work machine includes a container movably supported by the frame, the container configured to receive contents and an actuator configured to controllably drive movement of the container relative to the frame. The mobile work machine includes a control system configured to generate an actuator control signal, indicative of a commanded movement of the actuator, and provide the actuator control signal to the actuator to control the actuator to perform the commanded movement and a content density determination system, communicatively coupled to the control system, configured to determine a density of the contents of the container.

Controlling a work machine based on sensed variables

A composite panoramic vision system utilized onboard a work vehicle includes a display device, a vehicle-mounted camera array, and a controller. The vehicle-mounted camera array includes, in turn, first and second vehicle cameras having partially overlapping fields of view and positioned to capture first and second camera feeds, respectively, of the work vehicle's exterior environment from different first vantage points. During operation of the composite panoramic vision system, the controller receives the first and second camera feeds from the first and second cameras, respectively; generates a composite panoramic image of the work vehicle's exterior environment from at least the first and second camera feeds; and then presents the composite panoramic image on the display device for viewing by an operator of the work vehicle.

Work vehicle composite panoramic vision systems

A mobile construction machine detects a speech processing trigger. It then performs speech processing (such as speech recognition and natural language understanding, speech synthesis, etc.) based on the detected speech processing trigger, to generate a speech processing result. A control signal generator generates control signals based on the speech processing result. The control signals can be used to control the mobile construction machine, to control another mobile construction machine, to provide information to a remote server location, or to aggregate information from multiple remote server locations.

Construction machine mode switching with voice services

A volume of contents in a container of a work vehicle can be estimated in various examples. One example involves a system with a 3D sensor on a work vehicle, where the 3D sensor captures images of the contents in a container of the work vehicle. The system also includes a sensor for detecting an angle of the container. A processor device that is in communication with the 3D sensor and the sensor determines a volume of the contents in the container using the images and the angle.

Growing community of inventors

Silvis, IL, United States of America

John M Hageman