A method for stock keeping in a store includes: accessing an image captured by a fixed camera within the store; retrieving a field of view of the fixed camera; estimating a segment of an inventory structure in the store depicted in the image based on a projection of the field of view onto a planogram of the store; identifying a set of slots within the inventory structure segment; retrieving a product model representing a set of visual characteristics of a product type assigned to a slot, in the set of slots, by the planogram; extracting a constellation of features from the image; if the constellation of features approximates the set of visual characteristics in the product model, detecting presence of a product unit of the product type occupying the inventory structure segment; and representing presence of the product unit, occupying the inventory structure segment, in a realogram.

A robot control system acquires request information requesting a robot to keep within a prescribed distance from a user and to collect surrounding information, acquires, from the robot, location information indicating a location of the robot and confirmation information indicating that the robot is near the user, and transmits, to the robot, a command for changing a setting of the robot from a first specification to a second specification in response to the request in a case where it is determined, on a basis of the map information, the location information, and the confirmation information, that the user of the robot is accompanying the robot outside a home area of the user, the first specification enabling the robot to collect the surrounding information inside the home area, and the second specification enabling the robot to collect the surrounding information outside the home area.

An intelligent robot control method is provided for an intelligent robot. The method includes obtaining a first position at which the intelligent robot is currently located and a target position to be reached, and determining a movement path from the first position to the target position. The movement path has a particular roadblock. The method also includes transmitting a removal request when the intelligent robot moves from the first position to a second position, and a distance between the second position and a third position at which the particular roadblock is located and that is to be reached reaches a target distance. The removal request is used for requesting a removal instruction to be transmitted to the particular roadblock, and the removal instruction is used for, based on a roadblock type of the particular roadblock, instructing to remove the particular roadblock before the intelligent robot arrives.

A vehicle control device includes: a situation detection device that detects a situation around a periphery of a vehicle and outputs a situation detection signal based on detection results; and a processor (i) that is input with the situation detection signal when the vehicle travels in an autonomous automatic driving mode, that controls travel of the vehicle based on the situation detection signal, and (ii) that enters a prohibited state that prohibits control of the travel of the vehicle in the autonomous automatic driving mode in a prohibited area in which the travel of the vehicle in the autonomous automatic driving mode is prohibited.

A system, method and apparatus for executing tasks with unmanned vehicles is provided. The system includes an unmanned vehicle comprising: a chassis; a propulsion system configured to move the chassis; sensor(s) configured to sense features around the chassis; a memory storing feature reference data; a communication interface; and a processor configured to: receive, using the interface, a command having task data and a location associated with a given feature; control the propulsion system to move the chassis to the location; while the chassis is moving to the location, determine, using the sensor(s), that the given feature is detected based on the feature reference data; and, responsive to the given feature being detected, control the propulsion system to execute a task based on the task data.

An unmanned aerial system and a method are disclosed. An unmanned aerial system may include: a telematics service server; an unmanned aerial apparatus; and a vehicle. In particular, the telematics service server obtains a destination of the unmanned aerial apparatus, a movement path of the vehicle, a current location of the unmanned aerial apparatus, and a current location of the vehicle, and also searches for the vehicle with which the unmanned aerial apparatus is able to move in collaboration. The telematics service server controls a collaborative movement between the unmanned aerial apparatus and the vehicle, and the unmanned aerial apparatus transmits and receives information for the collaborative movement from the telematics service server. In addition, the vehicle carries the unmanned aerial apparatus according to a request from the telematics service server, and moves together with the unmanned aerial apparatus.

A mobile robot, capable of communicating with neighboring devices in a 5G communication environment and capable of efficient cleaning via machine learning based on such communication, comprises a main body configured to move in the movement space, a driving unit mounted on the main body to move the main body, a receiving unit configured to receive moving history information of a user robot that has been moved by a user in the movement space, a memory in which a computer-readable program and map information of the movement space are stored, and a control unit configured to communicate with the receiving unit, the memory, and the driving unit to control the main body, wherein the control unit establishes a moving area of the mobile robot based on the moving history information of the user robot received by the receiving unit.

Method, apparatuses, and computer program products provide for configuration of failsafe behavior for autonomous navigation. In particular, an active failsafe home is repeatedly established from a plurality of failsafe homes, and an autonomous vehicle is configured to travel to the active failsafe home when a communication fault occurs. An example method includes determining a location of the autonomous vehicle and determining whether a particular failsafe home of a plurality of failsafe homes associated with the autonomous vehicle satisfies a pre-determined visibility condition with respect to the location of the autonomous vehicle and one or more constraint areas. The method further includes, in accordance with a determination that the particular failsafe home satisfies the pre-determined visibility condition, establishing the particular failsafe home as an active failsafe home for the autonomous vehicle. The method further includes causing transmission of an indication of the active failsafe home to the autonomous vehicle.

Systems and methods for use of autonomous mobile machine for blind spot coverage may include a security controller that determines a security coverage area based on data from a facility map indicating physical and functional representations of a facility and objects within the facility. The security controller may also determine a surveillance area based on the security coverage area. The security controller may also transmit, to an autonomous mobile machine, instructions for the autonomous mobile machine to deploy to the surveillance area and perform a surveillance task at the surveillance area.

A plurality of virtual three-dimensional (3D) points distributed on a 3D reference plane for a camera array including a plurality of cameras are randomly selected. The plurality of cameras includes a host camera and one or more additional cameras. Respective two-dimensional (2D) projections of the plurality of virtual 3D points for the plurality of cameras are determined based on respective poses of the cameras. For the respective one or more additional cameras, respective homography matrices are determined based on the 2D projections for the respective camera and the 2D projections for the host camera. The respective homography matrices map the 2D projections for the respective camera to the 2D projections for the host camera. A stitched image is generated based on respective images captured by the plurality of cameras and the respective homography matrices.