Abstract: A work machine loads materials onto a conveyance vehicle. The work machine includes a work implement having a bucket, a topography sensor configured to measure a topography and a controller. The controller determines a target digging path of the bucket based on topographical data indicative of the topography measured by the topography sensor. The controller acquires an actual digging path based on positions of the bucket during digging. The controller is calculates at least one of a viscosity and a hardness of materials based on a difference between the target digging path and the actual digging path.

Abstract: A system includes a conveyance vehicle, and a work machine that loads materials onto the conveyance vehicle. A first processor of a work machine determines a target stop position of a conveyance vehicle based on a position of the work machine, a target offset distance, and the direction of the loading position. A second processor of the conveyance vehicle acquires data indicative of the target stop position of the conveyance vehicle from the work machine. The second processor controls the conveyance vehicle to move the conveyance vehicle to the target stop position.

Abstract: A system controls a work machine including a work implement, a rotating body, and a support body to load materials onto a conveyance vehicle. The system includes a first processor. The first processor acquires data indicative of a position of a predetermined reference point included in the conveyance vehicle. The first processor acquires data indicative of a position of a rotation center of the rotating body. The first processor acquires data indicative of a position of a blade tip of the work implement. The first processor determines a target rotation angle of the rotating body from a straight line connecting the position of the rotation center of the rotating body and the position of the reference point of the conveyance vehicle, and a current position of the blade tip of the work implement. The first processor controls the rotating body to rotate according to the target rotation angle.

Abstract: A system controls a work machine that loads materials onto a conveyance vehicle. The system includes a controller. The controller performs a loading work by the work machine when the conveyance vehicle is stopped at a predetermined loading position. The controller acquires a loading amount onto the conveyance vehicle. The controller determines whether the loading work is finished based on the loading amount. The controller outputs a withdraw command to the conveyance vehicle to withdraw from the loading position upon determining that the loading work is finished. The controller determines whether the conveyance vehicle has withdrawn after outputting the withdraw command.

Abstract: A work machine loads materials onto a conveyance vehicle. A system for controlling the work machine includes a detection device that detects an operation of the conveyance vehicle, and a controller that controls the work machine. The work machine includes a work implement attached to a rotating body. The controller acquires operation data indicative of an operation of the conveyance vehicle from the detection device. The controller causes the rotating body to rotate toward a predetermined unloading position. The controller determines whether the conveyance vehicle is stopped at a predetermined loading position based on the operation data. The controller causes the work implement to wait on standby at the unloading position upon determining that the conveyance vehicle is operating. The controller controls the work machine to unload materials at the unloading position upon determining that the conveyance vehicle is stopped at the loading position.

Abstract: A system controls a work machine that loads materials onto a conveyance vehicle. The system includes a controller and a detection device. The controller controls the work machine in an automatic control mode in which work is performed automatically. The detection device detects a presence of a person in a peripheral region of the work machine. The automatic control mode includes a loading mode in which the work machine is caused to move to perform loading work for loading onto the conveyance vehicle, and an other mode other than the loading mode. The controller causes the automatic control mode to transition from the other mode to the loading mode when a predetermined transition condition is satisfied. The predetermined transition condition includes non-detection of a person by the detection device.

Abstract: An excavation plan creation device includes a storage unit configured to store a plurality of planning models each of which is a machine learning model that receives, as an input, terrain information and that outputs a planned value of an excavation trajectory and a swing direction. The planning models have performed machine learning with parameters related to soil quality which are different from each other. A soil quality estimation unit is configured to estimate soil quality. A terrain information acquisition unit is configured to acquire terrain information. A planned value calculation unit is configured to select the planning model on the basis of the soil quality estimated by the soil quality estimation unit, input the terrain information acquired by the terrain information acquisition unit to the selected planning model, and calculate the planned value as an output of the planning model.

Abstract: A method is performed by a computer. The method includes obtaining motion data indicating a motion change of a work vehicle, and determining an operation classification of the work vehicle from the motion data by performing image classification using a trained classification model. The motion data is generated from a plurality of images indicating the work vehicle in operation in time series.

Abstract: A method is performed by a computer. The method includes obtaining motion data indicating a motion change of a work vehicle, and determining an operation classification of the work vehicle from the motion data by performing image classification using a trained classification model. The motion data is generated from a plurality of images indicating the work vehicle in operation in time series.

Abstract: A system controls a work machine that loads materials onto a conveyance vehicle. The system includes a controller and a detection device. The controller controls the work machine in an automatic control mode in which work is performed automatically. The detection device detects an approach of the conveyance vehicle toward the work machine. The automatic control mode includes a loading mode in which the work machine is caused to move to perform loading work for loading onto the conveyance vehicle, and an other mode other than the loading mode. The other mode includes at least one of a mode for gathering fallen materials and a digging mode for further increasing the materials by digging. The controller causes the automatic control mode to transition from the other mode to the loading mode when the approach of the conveyance vehicle is detected.

Abstract: A system controls a work machine that loads materials onto a conveyance vehicle. The system includes a controller. The controller performs a loading work by the work machine when the conveyance vehicle is stopped at a predetermined loading position. The controller acquires a loading amount onto the conveyance vehicle. The controller determines whether the loading work is finished based on the loading amount. The controller outputs a withdraw command to the conveyance vehicle to withdraw from the loading position upon determining that the loading work is finished. The controller determines whether the conveyance vehicle has withdrawn after outputting the withdraw command.

Abstract: A system includes a work machine, a camera, and a processor. The camera captures an image including a periphery of the work machine. A processor acquires image data indicative of a captured image captured by a camera. The processor acquires, from image data, a specific object present within the captured image and a distance from the work machine to the specific object by performing image analysis using an object detection model. The object detection model is trained an image of the specific object and the distance to the specific object. The processor controls the work machine based on the distance from the work machine to the specific object when the specific object is detected in the captured image.

Abstract: A first processor acquires data indicative of a position of a predetermined reference point included in a conveyance vehicle. The first processor acquires data indicative of a position of a rotation center of a rotating body of a work machine. The first processor acquires data indicative of a position of a blade tip of a work implement of the work machine. The first processor determines a target rotation angle of the rotating body from a straight line connecting the position of the rotation center of the rotating body and the position of the reference point of the conveyance vehicle, and a current position of the blade tip of the work implement. The first processor controls the rotating body to rotate according to the target rotation angle.

Abstract: A loading machine includes a swing body and work equipment with a bucket. A control device of the loading machine includes a loading target specifying unit that specifies a position and shape of a loading target, an avoidance position specifying unit, and a movement processing unit. The avoidance position specifying unit specifies an interference avoidance position based on the position and shape of the loading target. The movement processing unit outputs an operation signal to drive only the swing body until the bucket reaches the interference avoidance position from a loading position above the loading target, to cause the bucket to move to the interference avoidance position. The movement processing unit outputs an operation signal to drive the swing body and the work equipment after the bucket has reached the interference avoidance position, to cause the bucket to move to an excavation position above an excavation target.

Abstract: A system includes a conveyance vehicle, and a work machine that loads materials onto the conveyance vehicle. A first processor of a work machine determines a target stop position of a conveyance vehicle based on a position of the work machine, a target offset distance, and the direction of the loading position. A second processor of the conveyance vehicle acquires data indicative of the target stop position of the conveyance vehicle from the work machine. The second processor controls the conveyance vehicle to move the conveyance vehicle to the target stop position.

Abstract: A work machine loads materials onto a conveyance vehicle. A system for controlling the work machine includes a detection device that detects an operation of the conveyance vehicle, and a controller that controls the work machine. The work machine includes a work implement attached to a rotating body. The controller acquires operation data indicative of an operation of the conveyance vehicle from the detection device. The controller causes the rotating body to rotate toward a predetermined unloading position. The controller determines whether the conveyance vehicle is stopped at a predetermined loading position based on the operation data. The controller causes the work implement to wait on standby at the unloading position upon determining that the conveyance vehicle is operating. The controller controls the work machine to unload materials at the unloading position upon determining that the conveyance vehicle is stopped at the loading position.

Abstract: A work machine loads materials onto a conveyance vehicle. The work machine includes a work implement having a bucket, a topography sensor configured to measure a topography and a controller. The controller determines a target digging path of the bucket based on topographical data indicative of the topography measured by the topography sensor. The controller acquires an actual digging path based on positions of the bucket during digging. The controller is calculates at least one of a viscosity and a hardness of materials based on a difference between the target digging path and the actual digging path.

Abstract: A work machine includes a work implement, a rotating body to which the work implement is attached; a topography sensor configured to measure a topography, and a controller. The controller determines a digging start point of the work implement based on topographical data indicative of the topography measured by the topography sensor. The controller moves the work implement from a current position of the work implement to the digging start point.

Abstract: A system controls a work machine that loads materials onto a conveyance vehicle. The system includes a controller and a detection device. The controller controls the work machine in an automatic control mode in which work is performed automatically. The detection device detects a presence of a person in a peripheral region of the work machine. The automatic control mode includes a loading mode in which the work machine is caused to move to perform loading work for loading onto the conveyance vehicle, and an other mode other than the loading mode. The controller causes the automatic control mode to transition from the other mode to the loading mode when a predetermined transition condition is satisfied. The predetermined transition condition includes non-detection of a person by the detection device.

Abstract: A method is performed by a computer. The method includes obtaining motion data indicating a motion change of a work vehicle, and determining an operation classification of the work vehicle from the motion data by performing image classification using a trained classification model. The motion data is generated from a plurality of images indicating the work vehicle in operation in time series.