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 work machine includes: a machine body; an actuator attached to the machine body; an operation device used to operate the actuator; an operation sensor that senses an operation of the operation device; a photographing device that photographs surroundings of the machine body; a video data recording device that records video data including video photographed by the photographing device; a controller that controls the video data recording device; and an object sensor that senses an object in the surroundings of the machine body. The controller determines whether or not a recording and retaining condition including a condition that an object is present in the surroundings of the machine body and a condition that the operation device is operated is satisfied on the basis of a result of sensing in the object sensor and a result of sensing in the operation sensor, and makes the video data recording device record and retain the video data when the recording and retaining condition is satisfied.

A system of this disclosure includes an artificial intelligence module, which may include a neural network or a decision tree architecture, configured to analyze data indicative of the manner in which an operator performs tasks using a heavy machine. The artificial intelligence module is further configured to provide instructions pertaining to the control of at least some components of the heavy machine. As such, the heavy machine is operated in whole or in part based on the direction of the artificial intelligence module, which reduces reliance on a human operator. The artificial intelligence module is highly efficient, and in particular the artificial intelligence module is trained relatively quickly. Further, the artificial intelligence module may be embodied on the heavy machinery itself, as opposed to on a cloud-based system or on a more high-powered computer. Accordingly, the cost of implementing and operating the disclosed system is relatively low.

An operator is allowed to easily recognize a difference between a manipulation actually performed when performing a work and a manipulation serving a model for the work. A manipulation guide device for a work machine includes a manipulation device, a storage unit, and a display unit. The manipulation device is manipulated by an operator of the work machine to operate the work machine. The storage unit stores model data serving as a model when the manipulation device is manipulated. The display unit displays a change over time in a result of comparison between actual manipulation data about an actual manipulation of the manipulation device by the operator and model data in a time period during an operation of the work machine.

A method for assisting an operator in operating a machine. The method includes receiving, by a controller, a selection of a task of a plurality of tasks, each task associated with a corresponding movement pattern of the machine; sensing, by a sensor unit, at least one condition of at least one component of the machine associated with the selected task; and determining, by the controller, whether the condition is within a predetermined set of parameters associated with the selected task. In response to determining that the condition is not within the predetermined set of parameters, the method further includes generating, by the controller, an audible or a haptic signal associated with at least one of the condition or the at least one component.

Provided is a sample collecting method for collecting a sample of soil at a predetermined depth by excavation on an extraterrestrial body or the earth. The method comprises forming a first borehole 70 that reaches a first depth from a land surface 69 by preliminary excavation of soil, the first depth being less than a predetermine sampling depth from the land surface 69; and forming a second borehole 73 that has a smaller opening than the first borehole and reaches a second depth from the land surface by further excavation of soil in the first borehole, the second depth being equal to or greater than the sampling depth, wherein, while forming the second borehole 73, part of soil present at the sampling depth in the second borehole 73 is transferred to the land surface 69 as a sample for analysis.

A visual reference system can be used with a loading machine such as a bucket loader having a bucket that can be vertically articulated with respect to a work surface. The visual reference system can include one or more illumination devices configured to project a visual fiducial beam toward the work surface. The visual fiducial beam can create a fiducial indication of where the bucket will contact the work surface when lowered adjacent the work surface. The visual reference system can assist in operation of the loading machine by enabling an operator to visually perceive the expected contact point between the bucket and work surface.

A wear monitoring system includes a pair of track links for a track assembly of a machine, with a sensing device disposed within a cavity formed in a link body of each of the pair of track links. One or more communication devices are associated with the sensing devices, and a computing device is wirelessly connected over a communication network with each of the communication devices. One or more of the sensing devices and the computing device are configured to detect one or more of a distance between the sensing device disposed in one of the pair of track links and the sensing device disposed in another of the pair of track links, and a distance between the sensing device disposed in one of the pair of track links and a remote device. The computing device is configured to determine internal wear between components of at least one of the pair of track links based on changes in the detected distance.

A technique is directed to methods and systems of an implement lock-out on lever-controlled machines. A lock-out system can monitor the position of an implement and lock-out the implement control(s) when the implement is within a threshold distance to parts of the machine. The lock-out system can generate an implement lock-out to slow, stop, or reduce the force of a hydraulic valve(s) controlling the implement. The lock-out system can use inputs such as electronic fence blade position system data, articulation angles, wheel lean angles, steering angles, ripper positions, mode selection or similar data to determine to generate the implement lock-out. The lock-out system can generate the implement lock-out by a flow supply shutoff to the implement while maintaining pressure to the steering valve. The lock-out system can send visual or audible notifications to alert the operator of the implement's proximity to the machine or of an implement lock-out.

A machine includes a rotational sensor configured to sense rotation of an upper frame of the machine relative to a lower frame of the machine. The machine also includes a three-dimensional position sensor spaced from an axis of rotation of the upper frame relative to the lower frame. The machine can also include a number of additional sensors including sensors to detect track movement, imaging sensors, ranging sensors, IMUs, linear displacement sensors and/or the like. A computing system receives the various inputs from the sensors and fuses the data to determine state information for the machine.