Disclosed are a moving robot and a control method thereof, and the moving robot performs cleaning by moving based on a map and is able to determine, based on a global localization function, the current position on the map no matter where the moving robot is positioned, so that the moving robot is capable of recognizing the current position on the map, and, even when the position of the moving robot is arbitrarily changed, the moving robot is able to recognize the position thereof again and move to an exact designated area, so that the moving robot is capable of perform designated cleaning and move rapidly and accurately, thereby performing cleaning efficiently.

The present disclosure provides a cleaning method for the water surface of swimming pools and cleaning robot, the cleaning robot comprising a cleaning robot body, a sonar arranged around the cleaning robot body, two rear thrusters located at the tail of cleaning robot body. According to the present disclosure, as long as the cleaning robot body is placed on the water surface of the pool, cleaning robot body floating on the surface of the pool may automatically move and steer, so as to ensure that it can turn in advance before encountering the pool wall and won't knock against the pool wall, reduce the probability of malfunction and damaging of cleaning robot body, and the cleaning robot body can cover the entire water surface of pool and the pool wall, there is no omitting of cleaned water surface, and there is no need for excessive human involvement, it makes it easy for cleaning staffs to clean, when the cleaning robot body cleans the water surface of the pool, the cleaning staffs can carry out other cleaning work, which improved the cleaning efficiency of the cleaning staffs.

In various examples, one or more output channels of a deep neural network (DNN) may be used to determine assignments of obstacles to paths. To increase the accuracy of the DNN, the input to the DNN may include an input image, one or more representations of path locations, and/or one or more representations of obstacle locations. The system may thus repurpose previously computed information—e.g., obstacle locations, path locations, etc.—from other operations of the system, and use them to generate more detailed inputs for the DNN to increase accuracy of the obstacle to path assignments. Once the output channels are computed using the DNN, computed bounding shapes for the objects may be compared to the outputs to determine the path assignments for each object.

A method of operating an autonomous cleaning robot includes presenting, on a display of a mobile device, a representation of each of multiple cleaning levels, each cleaning level corresponding to a respective rank overlap parameter for a wet cleaning mission of the autonomous cleaning robot. The method includes receiving, at the mobile device, an input indicative of a selection of one of the cleaning levels; and controlling the autonomous cleaning robot to execute a wet cleaning mission according to the rank overlap parameter corresponding to the selected one of the cleaning levels.

A method of controlling a path providing device for a vehicle, where the method includes: receiving high-definition map data from a server; generating forward path information for the vehicle based on the high-definition map data; receiving, from sensors in the vehicle, sensing information related to an object outside the vehicle; and determining a validity of the object based on the forward path information, wherein the validity of the object relates to whether the object is likely to affect driving operations of the vehicle. Generating the forward path information includes: based on a destination having been set for the vehicle, generating the forward path information to include a path to the destination; and based on the destination not having been set for the vehicle, generating the forward path information to include a path on which the vehicle is most likely to travel.

The present disclosure relates to an ISG control system and an ISG control method for a construction machine capable of controlling ISG even in a working state of a construction machine, the ISG control system including: a surrounding environment determinator configured to determine surrounding environment of the construction machine; and a vehicle controller configured to determine whether the construction machine is in a working state or a traveling state based on a determination result from the surrounding environment determinator, wherein the vehicle controller controls an engine based on a preset work ISG condition when it is determined that the construction machine is in the working state, and wherein the vehicle controller controls the engine based on a preset travel ISG condition when it is determined that the construction machine is in the traveling state.

Various embodiments of an apparatus, methods, systems and computer program products described herein are directed to an agricultural observation and treatment system and method of operation. The agricultural treatment system may determine a first real-world geo-spatial location of the treatment system. The system can receive captured images depicting real-world agricultural objects of a geographic scene. The system can associate captured images with the determined geo-spatial location of the treatment system. The treatment system can identify, from a group of mapped and indexed images, images having a second real-word geo-spatial location that is proximate with the first real-world geo-spatial location. The treatment system can compare at least a portion of the identified images with at least a portion of the captured images. The treatment system can determine a target object and emit a fluid projectile at the target object using a treatment device.

Methods, apparatus, and articles of manufacture to generate acquisition paths are disclosed. An example apparatus includes input interface circuitry to obtain input data associated with a vehicle, threshold calculation circuitry to calculate, based on the input data, a threshold curvature and a threshold curvature rate of the vehicle, and acquisition path generation circuitry to select a point on a target path of the vehicle, generate an acquisition path from a current position of the vehicle to the point, the acquisition path including at least two curves, and cause storage of the acquisition path in response to the at least two curves satisfying the threshold curvature and the threshold curvature rate.

A ground utility robot and implement attachment apparatus having a ground utility robot, at least one implement, at least one solar panel, at least one battery that is chargeable by the at least one solar panel, a power take-off system that is connected to the ground utility robot and to the at least one implement; where the battery powers said ground utility robot and the implement; a safety system that has a computer, a safety program that utilizes a processing logic on the computer, where the safety program initiates precautionary measures that are carried out by the ground utility robot and the power take-off system if an object comes within a predefined distance from the ground utility robot and implement attachment apparatus.

This work vehicle has: a positioning unit for measuring the current position and the current direction of the vehicle body using a satellite positioning system; and an automatic travel control unit for executing automatic travel control based on positioning information from the positioning unit. The positioning unit comprises: a plurality of positioning antennas provided on the vehicle body; a plurality of positioning units for measuring the positions of the positioning antennas; a calculation unit for calculating the current position and the current direction of the vehicle body on the basis of positioning information from the positioning units; and a positioning state determination unit for determining whether or not the positioning state of the positioning units is a high-accuracy positioning state. When at least two positioning units are in the high accuracy positioning state, the positioning state determination unit permits the start of the automatic travel control.