A method for dynamic loop closure in a mobile automation apparatus includes: obtaining mapping trajectory data defining a plurality of trajectory segments traversing a facility to be mapped; controlling a locomotive mechanism of the apparatus to traverse a current segment; generating a sequence of keyframes for the current segment using sensor data captured via a navigational sensor of the apparatus; and, for each keyframe: determining an estimated apparatus pose based on the sensor data and a preceding estimated pose corresponding to a preceding keyframe; and, determining a noise metric defining a level of uncertainty associated with the estimated pose relative to the preceding estimated pose; determining, for a selected keyframe, an accumulated noise metric based on the noise metrics for the selected keyframe and each previous keyframe; and when the accumulated noise metric exceeds a threshold, updating the mapping trajectory data to insert a repetition of one of the segments.

Aspects of the disclosure relate generally to controlling an autonomous vehicle in a variety of unique circumstances. These include adapting control strategies of the vehicle based on discrepancies between map data and sensor data obtained by the vehicle. These further include adapting position and routing strategies for the vehicle based on changes in the environment and traffic conditions. Other aspects of the disclosure relate to using vehicular sensor data to update hazard information on a centralized map database. Other aspects of the disclosure relate to using sensors independent of the vehicle to compensate for blind spots in the field of view of the vehicular sensors. Other aspects of the disclosure involve communication with other vehicles to indicate that the autonomous vehicle is not under human control, or to give signals to other vehicles about the intended behavior of the autonomous vehicle.

The present invention relates to a vacuum cleaner robot comprising a floor nozzle supported on wheels and a dust collection unit, wherein the floor nozzle comprises a driving device for driving at least one of the wheels of the floor nozzle, wherein one of the wheels, a plurality of or all of the wheels of the floor nozzle are omnidirectional wheels, wherein the floor nozzle comprises a base plate with a base surface, which, when the vacuum cleaner robot is in operation, faces the surface to be cleaned, the base plate having provided therein an air flow channel, which extends parallel to the base surface and through which air to be cleaned enters the floor nozzle, and wherein the floor nozzle comprises a rotating means for rotating the air flow channel about an axis perpendicular to the base surface.

Systems and methods for controlling an autonomous vehicle are provided. In one example embodiment, a computer-implemented method includes obtaining sensor data indicative of a surrounding environment of the autonomous vehicle, the surrounding environment including one or more occluded sensor zones. The method includes determining that a first occluded sensor zone of the occluded sensor zone(s) is occupied based at least in part on the sensor data. The method includes, in response to determining that the first occluded sensor zone is occupied, controlling the autonomous vehicle to travel clear of the first occluded sensor zone.

Systems and methods for detecting an error in the mounting of a front hazard sensor are disclosed herein. According to at least one exemplary embodiment, an error in a pose of a front hazard sensor may comprise the front hazard sensor being orientated or positioned incorrectly with respect to a default pose. The present disclosure provides systems and methods for determining if this error in the pose is present.

A positioning system and a method based on neural network models are provided. The positioning method includes collecting WI-FI® fingerprint data; configuring a computing device to receive the WI-FI® fingerprint data, and the computing device includes a processor and a database storing positioning map data and a group of neural network models including a global positioning model, a coarse positioning model and a fine positioning model; configuring the processor to input the WI-FI® fingerprint data and perform the following steps: estimating a global coordinate through the global positioning model; obtaining the corresponding coarse positioning model from a corresponding primary sub-region to estimate an estimated coarse coordinate of a current position; estimating a plurality of estimated fine coordinates of the current position from the corresponding fine positioning model; and performing a merging process on the estimated fine coordinates to generate a final coordinate.

The disclosed subject matter includes a method and system for navigating an unmanned ground vehicle (UGV), that include: generating, based on the scanning output data, a first map comprising a first group of cells and characterized by a first size; generating, based on the scanning output data, a second map representing an area smaller than that of the first map comprising a second group of cells, which are characterized by a second size being smaller than the first size; wherein each cell in the first group of cells and the second group of cells is classified to a class selected from at least two classes, comprising traversable and non-traversable, wherein the second part at least partly overlaps the first part; navigating the UGV based on data deduced from crossing between cells in the first map and second map.

The present specification relates to a mobile robot system and a boundary information generation method for the mobile robot system, the mobile robot system comprising a signal processing device that comprises a receiving tag for receiving a transmission signal and a distance sensor, so as to recognize coordinate information about a spot at which the point of the distance sensor is designated on the basis of the reception result of the receiving tag and the distance measurement result of the distance sensor, thereby generating boundary information according to the path designated as the point of the distance sensor on the basis of the recognized coordinate information.

A work management system for managing work to be performed on a work subject. The work management system includes multiple work robots, a storage unit, a generator, and an instruction unit. The work robots each include movement means capable of moving to any location. The storage unit stores target information on a target state of the work subject and current state information on a current state of the work subject. The generator generates work procedure information indicating a work procedure to be performed by the work robots so that the work subject is brought close to the target state, on the basis of the target information and the current state information. The work procedure information includes work instruction information for instructing the work robots to perform one or more types of work to be performed on the work subject.

A method may include obtaining sensor data about a total measurable world around an autonomous vehicle. The sensor data may be captured by sensor units co-located with the autonomous vehicle. The method may include generating a mapping dataset including the obtained sensor data and identifying data elements that each represents a point in the mapping dataset. The method may include sorting the data elements according to a structural data categorization that is a template for a high-definition map of the total measurable world and determining a mapping trajectory of the autonomous vehicle. The mapping trajectory may describe a localization and a path of motion of the autonomous vehicle. The method may include generating the high-definition map based on the structural data categorization and relative to the mapping trajectory of the autonomous vehicle, and the high-definition map may be updated based on the path of motion of the autonomous vehicle.