14 results about "Self localization" patented technology

The invention relates to a method for self-localisation using satellite navigation. In the method, at least two GNSS receiving devices (A1, A2), which are positioned at a previously known distance (dv) from one another, are self-localised, wherein a first ego position (P1) of a first GNSS receiving device (A1) is determined on the basis of a satellite navigation signal which is received by the first GNSS receiving device (A1), and a second ego position (P2) of a second GNSS receiving device (A2) is determined on the basis of a satellite navigation signal which is received by the second GNSS receiving device (A2). An estimated distance (ds) between the first GNSS receiving device (A1) and the second GNSS receiving device (A2) is determined on the basis of the first ego position (P1) and the second ego position (P2). The estimated distance (ds) is compared with the previously known distance (dv). Finally, on the basis of a result (EG) of the comparison, it is determined whether the self-localisation of the GNSS receiving devices (A1, A2) is sufficiently precise and reliable. The invention further relates to a validation device (20). Finally, the invention relates to a vehicle (40).

This invention discloses an adaptive control system for inspection drones, belonging to the field of drone intelligent control technology. This adaptive control system can automatically inspect the furnace, greatly reducing workload and improving inspection efficiency compared to traditional inspection methods. Furthermore, the automatic inspection avoids high-altitude operations, reducing the danger of inspection work. This invention can achieve continuous self-positioning of the drone based on preset reference objects within the furnace. This method can operate independently of GPS navigation, enabling rapid updates of the drone's spatial position even in furnaces with weak GPS signals. The entire process can be performed without signal interaction with other devices or platforms, significantly reducing the impact of signal interference. Additionally, when performing inspection tasks, the drone can operate outside of visual range without affecting its autonomous positioning, greatly enhancing the drone's inspection range and capabilities.

A method for self-localization using satellite navigation is described. The method involves self-localization of at least two vehicles at a known distance (d v ) positioned GNSS receiving devices (A1, A2), wherein a first ego position (P1) of a first GNSS receiving device (A1) is determined on the basis of a satellite navigation signal received by the first GNSS receiving device (A1), and a second ego position (P2) of a second GNSS receiving device (A2) is determined on the basis of a satellite navigation signal received by the second GNSS receiving device (A2). Based on the first ego position (P1) and the second ego position (P2), an estimated distance (d s ) between the first GNSS receiving device (A1) and the second GNSS receiving device (A2). The estimated distance (d s ) is measured with the previously known distance (d v). Finally, based on a comparison result (EG), it is determined whether the self-localization of the GNSS receiving devices (A1, A2) is sufficiently precise and reliable. Furthermore, a validation device (20) is described. Finally, a vehicle (40) is described.

To solve the problem in which: map information used in self-location estimation is not intuitively understandable to humans, resulting that it takes time for humans to understand the map; furthermore, saving all landscape images along with the map information or saving videos therewith is not practical because it would take up too much storage space.SOLUTION: A device includes: image acquisition means for acquiring images of an environment captured by an imaging device mounted on a mobile object; location information acquisition means for acquiring location information obtained from estimating the location of the mobile object; map acquisition means for acquiring a map generated based on the location information of the mobile object; image evaluation means for evaluating the images; and image storage means for storing, based on the evaluation, the images with the evaluation higher than a predetermined threshold, in association with the map.SELECTED DRAWING: Figure 5

To provide an autonomous mobile robot capable of autonomously moving by avoiding obstacles in a passage even in a narrow passage surrounded by walls such as a narrow tunnel where it is difficult to use GNSS or a particle filter and the passage has no branches, and capable of reducing the cost of the device by eliminating the need for map creation and self-position estimation. The autonomous mobile robot includes a motor, a rotation measurement unit, an acceleration sensor, a gyro sensor, and a distance sensor. When the distance to an obstacle is greater than the distance to a virtual target point set in the direction of travel of the autonomous mobile robot, the control unit calculates a path for the autonomous mobile robot to avoid the obstacle based on the acquired translational and rotational speeds, and moves the autonomous mobile robot.

The present invention discloses a method and system for evaluating robot self-positioning accuracy based on a visual sensor. The method includes the following steps: S1: collecting motion data of a mobile robot and recording it in ROS package format; S2: extracting the recorded data, fusing the RGB image and the depth image to obtain point cloud information at the current timestamp; S3: calculating the two-dimensional information entropy using each RGB image frame or converting the point cloud information obtained in step S2 into a global descriptor, finding and merging revisited sample pairs through a search algorithm to obtain a sample pair dataset; S4: obtaining the local displacement vector and point set error of the sample pair dataset by accessing the sample pair dataset; S5: collecting estimated trajectory data under the current recording environment; S6: offline registering the data, randomly selecting registration pairs, and repeatedly running the algorithm to calculate the sample error, which is the error of the robot trajectory. The present invention achieves robot self-positioning accuracy evaluation using a low-cost visual sensor.

A method of self-localizing with respect to surrounding objects, comprising obtaining an approximated geolocation of the vehicle, retrieving mapping data comprising a geolocation of one or more stationary objects located in an area surrounding the approximated geolocation, receiving imagery data of a surrounding environment of the vehicle captured by a plurality of distinct imaging sensors deployed in the vehicle, applying one or more trained machine learning models to identify one or more of the stationary objects in the imagery data, computing a relative positioning of the vehicle with respect to one or more of the stationary objects based on an orientation of each of the plurality of imaging sensors with respect to the stationary object(s), computing an absolute positioning of the vehicle based on the relative positioning and the geolocation of the stationary object(s), and outputting the vehicle's absolute positioning.

Method for providing a virtual competition environment for a real participant of a virtual competition, wherein the virtual competition environment comprises a virtual replica of a real competition route, wherein the real participant first moves along the real competition route in a training run, wherein - during the training session, position data and / or orientation data of the real participant along the real competition route and movement dynamics data of the real participant along the real competition route are recorded by an environment sensor system (14) and transmitted as a time series to a computing device (16), wherein for each recorded data set of position and / or orientation data and / or movement dynamics data, a time stamp is recorded, which is transmitted with the respective data set to the computing device (16), so that the data sets can be sorted according to their chronological order and displayed as a simulation or simulation sequence consisting of successive frames, - the simulation is created as a virtual image of the real participant and his movement along the competition route by the computing device (16) on the basis of the position data and / or the orientation data and the movement dynamics data and is integrated into the virtual competition environment, and the virtual competition environment with the integrated simulation is transmitted to a display device (18), and wherein - the virtual competition environment with the simulation integrated therein is displayed for the real participant by the display device (18), while the real participant moves again along the real competition course in a competition round, wherein the display device (18) is designed as augmented reality glasses, wherein the virtual competition environment with the simulation integrated therein is displayed by the augmented reality glasses (18) as augmented reality display content for the real participant, wherein the augmented reality display content is displayed as display content superimposed on the real competition route, wherein the participant is the driver of a motor vehicle (10), wherein each frame of the simulation is always rendered with the current position and / or orientation of the motor vehicle (10) including the augmented reality glasses (18) during the competition run, wherein the current position and / or orientation of the motor vehicle (10) relative to the augmented reality glasses (18) is taken into account when displaying the simulation during the competition run, wherein, in order for the simulation to always be synchronous with the current temporal position and / or orientation of the motor vehicle (10) during the competition run, the motor vehicle (10) localizes itself on the competition track and the augmented reality glasses (18) localize themselves or are localized within the motor vehicle.

The invention relates to a method for self-localisation using satellite navigation. In the method, at least two GNSS receiving devices (A1, A2), which are positioned at a previously known distance (dv) from one another, are self-localised, wherein a first ego position (P1) of a first GNSS receiving device (A1) is determined on the basis of a satellite navigation signal which is received by the first GNSS receiving device (A1), and a second ego position (P2) of a second GNSS receiving device (A2) is determined on the basis of a satellite navigation signal which is received by the second GNSS receiving device (A2). An estimated distance (ds) between the first GNSS receiving device (A1) and the second GNSS receiving device (A2) is determined on the basis of the first ego position (P1) and the second ego position (P2). The estimated distance (ds) is compared with the previously known distance (dv). Finally, on the basis of a result (EG) of the comparison, it is determined whether the self-localisation of the GNSS receiving devices (A1, A2) is sufficiently precise and reliable. The invention further relates to a validation device (20). Finally, the invention relates to a vehicle (40).

A method of self-localizing with respect to surrounding objects, comprising obtaining an approximated geolocation of the vehicle, retrieving mapping data comprising a geolocation of one or more stationary objects located in an area surrounding the approximated geolocation, receiving imagery data of a surrounding environment of the vehicle captured by a plurality of distinct imaging sensors deployed in the vehicle, applying one or more trained machine learning models to identify one or more of the stationary objects in the imagery data, computing a relative positioning of the vehicle with respect to one or more of the stationary objects based on an orientation of each of the plurality of imaging sensors with respect to the stationary object(s), computing an absolute positioning of the vehicle based on the relative positioning and the geolocation of the stationary object(s), and outputting the vehicle's absolute positioning.

To provide a method for creating a reliability-degree map for a self-position as determined where a plurality of sensors are usable.SOLUTION: An apparatus for creating a reliability-degree map is adapted to: identify a temporary self-position which is a position on a reliability-degree map corresponding to a position at a noticing point of time of a mobile robot presumed based on a travel history of the mobile robot; determine an established self-position based on a self-position calculated using a result detected by a selected sensor in the noticing point of time corresponding to a reliability-degree satisfying a predetermined reference indicative of high reliability degree out of registered reliability degrees if reliability degree is registered in association with the temporary self-position; calculate a reliability degree based on a temporary self-position, an established self-position determined based on the temporary self-position and an environment map; and register a calculated reliability degree and information identifying a selected sensor in association with a position on the reliability-degree map corresponding to the established self-position.SELECTED DRAWING: Figure 3

The invention belongs to the technical field of mobile robot navigation, and particularly relates to a robot joint SLAM and multi-target tracking method based on a random finite set. A mobile robot, a plurality of static landmarks and dynamic targets exist in the scene, and the positions of the static landmarks and the dynamic targets are unknown, so that the positioning method comprises joint positioning of the robot, the static landmarks and the dynamic targets. Distance, angle and category measurement values acquired by a sensor can be combined, and a Gaussian mixture probability hypothesis density filtering and multi-model interaction method is used for solving, so that robot self-positioning, environment mapping and target tracking are realized. The positions of the maneuvering target and the static environment can be accurately estimated, the method is simple, and the effect is good.

For self-localization of a motor vehicle (1), a point cloud is generated by emitting light pulses and detecting reflected portions of the emitted light pulses by a detector array (3b) of the active optical sensor system (3). An image of the environment is generated by detecting ambient light impinging on the detector array (3b). A first vehicle position of the motor vehicle (1) is determined depending on the point cloud and a second vehicle position of the motor vehicle (1) is determined depending on the image. A position deviation of the first vehicle position from the second vehicle position is determined. A consolidated vehicle position (7b) is determined as the first vehicle position, if the position deviation is less than a predefined threshold value, and the consolidated vehicle position (7b) is determined as the second vehicle position, if the position deviation is greater than the threshold value.

A self-localization method according to the present disclosure includes the following first to fourth steps. The first step is acquiring terrain data in which a position and an elevation of a ground surface on a traveling area of the vehicle are managed. The second step is acquiring time series data of acceleration in a vertical direction of the vehicle. The third step is estimating an altitude of the vehicle based on an initial altitude of the vehicle and the time series data of acceleration. The fourth step is estimating a vehicle position based on the position of the ground surface at which the elevation of the ground surface approximates the estimated altitude of the vehicle.