A method for operating an electric drivetrain of a working machine is provided wherein the drivetrain comprises a work drive with an electric work motor and a travel drive with an electric travel motor and vehicle wheels, wherein the working machine experiences a speed deceleration from the outside that may result in a braking force acting on the vehicle wheels lower than a driving force acting on the vehicle wheels due to a moment of inertia of the travel motor. The method includes supplying the travel motor with a power in a direction opposite to an operating direction of the travel motor in order to reduce a rotational speed of the travel motor, if it is detected in advance using a situation detection that the braking force acting on the vehicle wheels as a result of the speed deceleration is lower than the driving force acting on the vehicle wheels.

Movement data of a plurality of positions on an observation object performing a predetermined movement action is acquired, feature data is generated by performing frequency analysis on the movement data, a transition sequence of a primitive action is extracted by segmenting the feature data, and based on the transition sequence and an action model obtained by learning a transition sequence of a primitive action obtained by segmenting a movement state of a training object performing a movement action, an occurrence rate of the primitive action in the predetermined movement action is analyzed to extract a pattern of the primitive action, thereby predicting an end timing of the predetermined movement action.

A training machine to generate training data for supervised machine learning. The training machine is a working machine with a camera, a sensor, a body, and a moveable element moveable relative to the body. Training data is generated by capturing images, using the camera of at least a portion of the moveable element; and determining, using the sensor, sensor data which indicates the position of the moveable element in the image. The training data is used to train a machine learning algorithm to determine a position of a moveable element based on an image of at least a portion of the moveable element, without the need for corresponding sensor data.

A confluence control part of a slewing-type construction machine controls a confluence switch valve such that the confluence switch valve is switched to a suspension state when a slewing and boom raising manipulation action is performed. A pump capacity control part of the slewing-type construction machine executes a capacity control when the slewing and boom raising manipulation action is performed, the capacity control including regulating a first pump capacity and a second pump capacity respectively in such a manner that the first pump capacity increases and the second pump capacity decreases as an operating pressure difference resulting from the subtraction of a slewing operating pressure from a boom operating pressure increases, and the first pump capacity decreases and the second pump capacity increases as the operating pressure difference decreases.

A confluence control part of a slewing-type construction machine controls a confluence switch valve such that the confluence switch valve is switched to a suspension state when a slewing and boom raising manipulation action is performed. A pump capacity control part of the slewing-type construction machine executes a capacity control when the slewing and boom raising manipulation action is performed, the capacity control including regulating a first pump capacity and a second pump capacity respectively in such a manner that the first pump capacity increases and the second pump capacity decreases as an operating pressure difference resulting from the subtraction of a slewing operating pressure from a boom operating pressure increases, and the first pump capacity decreases and the second pump capacity increases as the operating pressure difference decreases.

A monitor controller configured to control a display content on a display unit is configured to keep displaying a bird's-eye-view image when an operation of an operation device is sensed in the state where the display unit displays the bird's-eye-view image, and to cause the display unit to display the bird's-eye-view image when the operation of the operation device is sensed in the state where the display unit does not display the bird's-eye-view image.

A monitor controller configured to control a display content on a display unit is configured to keep displaying a bird's-eye-view image when an operation of an operation device is sensed in the state where the display unit displays the bird's-eye-view image, and to cause the display unit to display the bird's-eye-view image when the operation of the operation device is sensed in the state where the display unit does not display the bird's-eye-view image.

When an EMV performs an action comprising moving a tool of the EMV through soil or other material, the EMV can measure a current speed of the tool through the material and a current kinematic pressure exerted on the tool by the material. Using the measured current speed and kinematic pressure, the EMV system can use a machine learned model to determine one or more soil parameters of the material. The EMV can then make decisions based on the soil parameters, such as by selecting a tool speed for the EMV based on the determined soil parameters.

A first payload computation value which represents a weight of loads loaded on the work implement in a first attitude is obtained. The first attitude and a second attitude are equal to each other in ratio between a horizontal distance from a position of a center of gravity of a first link member to a base end of the first link member and a horizontal distance from a position of the center of gravity of the loads loaded on the work implement to the base end. A second payload computation value which represents a weight of loads loaded on the work implement in the second attitude is obtained. When the first payload computation value and the second payload computation value are determined as being different from each other, a weight of a second link member is changed and processing above is repeated.

A first payload computation value which represents a weight of loads loaded on the work implement in a first attitude is obtained. The first attitude and a second attitude are equal to each other in ratio between a horizontal distance from a position of a center of gravity of a first link member to a base end of the first link member and a horizontal distance from a position of the center of gravity of the loads loaded on the work implement to the base end. A second payload computation value which represents a weight of loads loaded on the work implement in the second attitude is obtained. When the first payload computation value and the second payload computation value are determined as being different from each other, a weight of a second link member is changed and processing above is repeated.