A method for training a control policy for a robot device includes acquiring a reference state of an environment of the robot device and a reference observation of the environment for the reference state. The method also includes generating, for each of a plurality of errors of an estimation of a pose of the robot device, an observation that is disturbed with respect to the reference observation according to the error of the pose estimation and a training data element comprising the generated observation as a training input. The method further includes training the control policy using the generated training data elements.

A management system of a work site includes: a workplace data acquisition unit that acquires workplace data set in a workplace where an unmanned haul vehicle travels; and a sprinkling area setting unit that sets, on the basis of the workplace data, a sprinkling area on which the unmanned sprinkler vehicle sprinkles water in the workplace.

A system for autonomous or semi-autonomous operation of a vehicle is disclosed. The system includes a machine automation portal (MAP) application configured to enable a computing device to (a) display a map of a work site and (b) provide a graphical user interface that enables a user to (i) define a boundary of an autonomous operating zone on the map and (ii) define a boundary of one or more exclusion zones. The system also includes a robotics processing unit configured to (a) receive the boundary of the autonomous operating zone and the boundary of each exclusion zone from the computing device, (b) generate a planned command path that the vehicle will travel to perform a task within the autonomous operating zone while avoiding each exclusion zone, and (c) control operation of the vehicle so that the vehicle travels the planned command path to perform the task.

A hauling vehicle including a vehicle body, a distance meter that measures the distance to an obstacle, an in-vehicle controller that controls the vehicle body, and a communication device that communicates with a management controller that manages the vehicle body is provided. In the hauling vehicle, the in-vehicle controller executes primary determination of whether or not the distance meter is in a dirt-presumed state in which dirt of an objective surface of the distance meter is presumed, commands the vehicle body to stop at a current position when determining that the distance meter is in the dirt-presumed state in the primary determination, executes secondary determination of whether or not the distance meter is in the dirt-presumed state after the elapse of a set time from the execution of the primary determination, transmits an alarm to the management controller through the communication device when determining that the distance meter is in the dirt-presumed state in the secondary determination, and commands the vehicle body to resume travelling of the vehicle body when determining that the dirt-presumed state has been eliminated in the secondary determination.

A self-propelled construction machine for working ground or erecting a structure thereon in a preceding work process, which is followed by another work process with another construction machine, comprises a mobile radio communications device, a GNSS receiver, a GNSS evaluation device or mobile radio evaluation device, and a GNSS evaluation variable acquisition device or mobile radio evaluation variable acquisition device. The GNSS evaluation device or mobile radio evaluation device is configured wherein, during advance of the machine, evaluation variables evaluating the quality of the GNSS signals or the mobile radio signal are determined at respective locations in the terrain, and the GNSS evaluation variable acquisition device or the mobile radio evaluation parameter acquisition device is configured wherein the position data determined by the GNSS receiver at the respective locations is used to generate a spatial (geo-referenced) telemetry data set describing the quality of the signals at the respective locations.

A portable robotic platform system and method for automatically detecting, locating, and marking underground assets are provided. The portable robotic platform includes a housing with a sensor module including ground penetrating radar (GPR), LiDAR, and electromagnetic (EM) sensors. The robotic platform automatically collects GPR and EM data and uses onboard post-processing techniques to interpret the sensor data and identify the location(s) of underground infrastructure. The portable robotic platform can be deployed to apply paint to a ground surface to identify the located underground assets.

In an example, a method of operating a surface marking robot comprises receiving a first digital representation of a floor plan comprising a plurality of floor plan features, and identifying a specific floor plan feature corresponding to a specific printing resources consumption. In response to identifying the specific floor plan feature, the method comprises modifying the first digital representation to produce a second digital representation in which the specific floor plan feature is replaced by an alternative floor plan feature corresponding to an alternative printing resources consumption which is reduced compared to the specific printing resources consumption.

A management system of a work site includes: a workplace data acquisition unit that acquires workplace data set in a workplace where an unmanned haul vehicle travels; and a sprinkling area setting unit that sets, on the basis of the workplace data, a sprinkling area on which the unmanned sprinkler vehicle sprinkles water in the workplace.

A system for autonomous or semi-autonomous operation of a vehicle is disclosed. The system includes a machine automation portal (MAP) application configured to enable a computing device to (a) display a map of a work site and (b) provide a graphical user interface that enables a user to (i) define a boundary of an autonomous operating zone on the map and (ii) define a boundary of one or more exclusion zones. The system also includes a robotics processing unit configured to (a) receive the boundary of the autonomous operating zone and the boundary of each exclusion zone from the computing device, (b) generate a planned command path that the vehicle will travel to perform a task within the autonomous operating zone while avoiding each exclusion zone, and (c) control operation of the vehicle so that the vehicle travels the planned command path to perform the task.

A system and a method for generating three-dimensional scan data of areas of interest, the method comprising a user defining the areas of interest using a mobile device in the environment, and a scanning device performing a scanning procedure at each defined area of interest to generate the scan data of the respective area of interest, wherein defining the areas of interest comprises, for each area of interest, generating identification data, wherein generating the identification data at least comprises generating image data of the respective area of interest, and the scanning procedure at each defined area of interest is performed by a mobile robot comprising the scanning device and being configured for autonomously performing a scan of a surrounding area using the scanning device, the mobile robot having a SLAM functionality for simultaneous localization and mapping and being configured to autonomously move through the environment using the SLAM functionality.