A method for determining parallel lift feedforward control of a bucket of a work vehicle is provided. The method includes calculating a current stroke length of a bucket cylinder at a current moment based on a current bell crank plate angle and a current boom angle. The method includes predicting a future boom angle after a certain number of steps. The method further includes calculating a required bell crank plate angle from a learned cutting edge angle and the future boom angle. The method even further includes calculating a future stroke length of the bucket cylinder after the certain number of steps. The method yet further includes calculating an average speed command for bucket control based on the current stroke length and the future stroke length of the bucket cylinder. The method still further includes calculating a bucket cylinder control command based on the average speed command for bucket control.

Method and systems for operating a work vehicle with a selectively interchangeable implement. Image data is captured by a camera (and/or other type of optical sensor) mounted on the work vehicle. The captured image data includes at least a portion of a first implement and the implement type of the first implement is identified by processing the captured image data. Operation information correspond to the identified implement type is accessed from a non-transitory computer-readable memory and an operation of the work vehicle is automatically adjusted based on the accessed operation information for the identified implement type. In some implementations, the implement type is determined by providing the captured image data as input to an artificial neural network and, in some implementations, the artificial neural network is configured to also output an indication of a current operating position of the implement based on the captured image data.

A shovel includes a lower traveling body, an upper turning body turnably mounted on the lower traveling body, a link unit attached to the upper turning body, and a processing circuitry configured to align an end of the link unit with an end attachment to be attached.

Disclosed embodiments include power machines or loaders, and systems used on loaders, configured to augment the control of the loader to accomplish repetitive tasks. Also disclosed are methods of learning a task for augmented control of a loader, and methods of controlling a loader to perform a learned task to provide augmented control of the loader.

There is provided a system including a work machine, comprising a body of the work machine, a work implement attached to the body of the work machine, and a computer. The computer has a trained target posture estimation model to determine a target posture for the work implement to assume at work. The computer obtains a period of time elapsing since the work implement started to work, and mechanical data for operation of the body of the work machine and the work implement, uses the trained target posture estimation model to estimate a target posture from the elapsed period of time and the mechanical data, and thus outputs the estimated target posture.

A system for controlling implement operation of a work vehicle includes the computing system is configured to receive an input associated with a target position of an implement of the vehicle. Furthermore, the computing system is configured to monitor the current position of the implement of the vehicle. Additionally, the computing system is configured to control the operation of an actuator of the vehicle such that the implement is moved toward the target position based on the monitored current position. Moreover, the computing system is configured to determine a speed-based parameter associated with a speed at which the implement is being moved across a time period. In addition, after the time period has elapsed, the computing system is configured to control the operation of the actuator such that the implement is moved to the target position based on the monitored current position and the determined speed-based parameter.

An autonomous earth moving system can select an action for an earth moving vehicle (EMV) to autonomously perform using a tool (such as an excavator bucket). The system then generates a set of candidate tool paths, each illustrating a potential path for the tool to trace as the earth moving vehicle performs the action. In some cases, the system uses an online learning model iteratively trained to determine which candidate tool path best satisfies one or more metrics measuring the success of the action. The earth moving vehicle the executes the earth moving action using the selected tool path and measures the results of the action. In some implementations, the autonomous earth moving system updates the machine learning model based on the result of the executed action.

This description provides an autonomous or semi-autonomous excavation vehicle that is capable of navigating through a dig site and carrying out an excavation routine using a system of sensors physically mounted to the excavation vehicle. The sensors collects any one or more of spatial, imaging, measurement, and location data representing the status of the excavation vehicle and its surrounding environment. Based on the collected data, the excavation vehicle executes instructions to carry out an excavation routine. The excavation vehicle is also able to carry out numerous other tasks, such as checking the volume of excavated earth in an excavation tool, and helping prepare a digital terrain model of the site as part of a process for creating the excavation routine.

A wheel loader includes: a front frame; a bucket; a boom having a distal end connected to bucket, and a proximal end rotatably supported by front frame; a sensor configured to measure a distance between boom and a loading target; and a controller configured to control an action of wheel loader. The controller causes wheel loader to perform a predetermined action for collision avoidance on condition that a distance to be measured by sensor when wheel loader travels takes a value less than or equal to a threshold value.

A mobile work machine includes a frame, a material loading system having a material receiving area configured to receive material and an actuator configured to control the material loading system to move the material receiving area relative to the frame, and a control system configured to receive an indication of a detected object, determine a location of the object relative to the material loading system, and generate a control signal that controls the mobile work machine based on the determined location.