An autonomous robot is maneuvered around a feature in an environment along a first trajectory. Data characterizing the first trajectory is stored as a trajectory landmark. The autonomous cleaning robot is maneuvered along a second trajectory. Data characterizing the second trajectory is compared to the trajectory landmark. Based on comparing the data characterizing the second trajectory to the trajectory landmark, it is determined that the first trajectory matches the second trajectory. A transform that aligns the first trajectory with the second trajectory is determined. The transform is applied to an estimate of a position of the autonomous cleaning robot as a correction of the estimate.

An electronic device is provided. The electronic device includes a communication module, a processor, and a memory storing instructions, the electronic device receives information indicating that a first external electronic device entered a designated space, from at least one anchor in the designated space, in response to receiving the information, establishes a communication connection with the first external electronic device using the communication module, after establishing the communication connection with the first external electronic device, receives a request of use authority of a first device among devices positioned in the designated space from the first external electronic device, identifies use authority set for the first external electronic device, based on information on the first device and information on the first external electronic device, and transmits information to the first external electronic device and the first device so the set use authority is applied to the first external electronic device.

A hybrid mapping and localization system using continuous localization algorithms is disclosed. When a localization quality is sufficiently high, based on a validated points localization monitor metric, then the map updates are allowed to be made on the localization map. This helps localizing in dynamic environments because these environment changes are actually integrated into the underlying map, so that the particle filter does not snap to incorrect object locations.

This specification describes systems and methods for generating a mapping of a physical space from point cloud data for the physical space. The methods can include receiving the point cloud data for the physical space, filtering the point cloud data to, at least, remove sparse points from the point cloud data, aligning the point cloud data along x, y, and z dimensions that correspond to an orientation of the physical space, and classifying the points in the point cloud data as corresponding to one or more types of physical surfaces. The methods can also include identifying specific physical structures in the physical space based, at least in part, on classifications for the points in the point cloud data, and generating the mapping of the physical space to identify the specific physical structures and corresponding contours for the specific physical structures within the orientation of the physical space.

A floorplan modelling method and system. The floorplan modelling method includes receiving 2D images of each corner of an interior space from a camera, generating a corresponding camera position and camera orientation in a 3D coordinate system in the interior space for each 2D image, generating a depth map for each 2D image to estimate depth for each pixel, generating a corresponding edge map for each 2D image, and generating a 3D point cloud for each 2D image using the corresponding depth map and parameters of the camera. The floorplan modelling method includes transforming the 3D point clouds with the corresponding edge map into a 2D space in the 3D coordinate system of the camera, regularizing the 3D point clouds into 2D boundary lines, and generating a 2D plan of the interior space from the boundary lines.

This application provides an indoor map generation method and apparatus. In the method, a plurality of first tracks are obtained based on a PDR algorithm. A plurality of first target tracks are further selected from the plurality of first tracks, and at least one second track corresponding to each first target track is extended to the first target track based on the first target track, to obtain a branch. The obtained branches are combined, to obtain a map.

Methods, systems, and apparatus for receiving a reference to an object located in an environment of a robot, accessing mapping data that indicates, for each of a plurality of object instances, respective probabilities of the object instance being located at one or more locations in the environment, wherein the respective probabilities are based at least on an amount of time that has passed since a prior observation of the object instance was made, identifying one or more particular object instances that correspond to the referenced object, determining, based at least on the mapping data, the respective probabilities of the one or more particular object instances being located at the one or more locations in the environment, selecting, based at least on the respective probabilities, a particular location in the environment where the referenced object is most likely located, and directing the robot to navigate to the particular location.

A navigation method based on ground texture images, an electronic device and storage medium. The method includes: performing transform domain based image registration on an acquired image of a current frame and an image of a previous frame, and determining a first pose of the image of the current frame; determining whether the image of the current frame meets a preset condition, and if so, inserting the image of the current frame as the key-frame image into a map, and performing loop closure detection and determining a loop key-frame image; performing transform domain based image registration on the image of the current frame and the loop key-frame image, and determining a second pose of the image of the current frame; and determining an accumulated error according to the first pose and the second pose, and correcting the map according to the accumulated error.

The present disclosure relates to a building management system (BMS) with indoor navigation features. The BMS comprises a processing circuit and a database. The database comprises a building model, an entity model and spatial anchors. The processing circuit receives camera-derived data from an electronic device associated with a user. Further, a current location of the user within a building is determined by comparing the camera-derived data with the building model. Additionally, a target location may be determined using the entity model. Further, one or more spatial anchors between the target location and the current location are identified to determine a shortest navigable path between the current location and the target location. Subsequently, the spatial anchors are interconnected and provided to the electronic device, wherein the user associated with the electronic device navigates towards the target location by following the interconnected spatial anchors.

In some embodiments, a method comprises receiving a plurality of digital images depicting an indoor scene of a room and captured using a capture device, and trajectory data of a trajectory that the capture device followed as the capture device was capturing the images; wherein the images and the trajectory data satisfy quality checks, including a closed loop check that requires that first images, of the plurality of digital images, and last images, of the plurality of digital images, overlap; determining a point cloud by preprocessing the digital images and the trajectory data to satisfy optimization constraints, and by identifying and labelling a plurality of feature points in data obtained by preprocessing the digital images and the trajectory data; based on the point cloud and the trajectory data, generating room geometry for the room and a 3D model of the room; and displaying a graphical representation of the 3D model.