Abstract: A computer-implemented method for controlling an unmanned aerial vehicle (UAV) includes obtaining a first image captured by an imaging device carried by the UAV during a takeoff of the UAV from a target location, obtaining a second image from the imaging device in response to an indication to return to the target location, determining a spatial relationship between the UAV and the target location by comparing the first image and the second image, and controlling the UAV to approach the target location based at least in part on the spatial relationship.

Abstract: The present disclosure relates to an elevation detection system for an Autonomous Vehicle (AV) and a method for detecting elevation of surrounding of the AV. The elevation detection system includes an elevation sensor unit and a computation unit. The elevation sensor unit is configured to detect an elevation of a plurality of objects having a lower most elevation, in the surrounding of the AV to determine a boundary elevation of the road. The elevation sensor unit is vertically movable within a range of vertical positions. A Light Detection and Ranging (LIDAR) sensor unit is associated with the elevation sensor unit, to detect the surrounding of the AV, having a predefined Field of View (FoV). The computation unit determines a lower limit value of the FoV and provides it to the LIDAR sensor unit for accurately detecting obstacles in the road.

Abstract: In one embodiment, a computing system may receive an uncompressed image from a camera. The computing system may generate a compressed image by performing a compression process on the uncompressed image, wherein a decompressed image may be generated as a byproduct during the compression process. The computing system may send the decompressed image to a machine-learning model that was trained using decompressed images. The computing system may generate, by the machine-learning model, an output based on the decompressed image. The computing system may provide operational instructions to a vehicle based on the output.

Abstract: A system for training simultaneous localization and mapping (SLAM) models, including a camera, mounted in a vehicle and in communication with an image server via a cellular connection, that captures images labeled with a geographic position system location and a timestamp, and uploads them to an image server, a storage device that stores geographical maps and images, and indexes the images geographically with reference to the geographical maps, an images server that receives uploaded images, labels the uploaded images with a GPS location and a timestamp, and stores the uploaded images on the storage device, and a training server that trains a SLAM model using images labeled with a GPS location and a timestamp, wherein the SLAM model (i) receives an image as input and predicts the image location as output, and/or (ii) receives an image having error as input and predicts a local correction for the image as output.

Abstract: Methods, systems, and articles of manufacture configured to operate an aerial vehicle are provided. Various embodiments may be implemented with an aerial vehicle. In one exemplary implementation, a method of operating an aerial vehicle may include identifying, from image data, a set of predetermined features based on one or more invariant properties associated with the predetermined features. The predetermined features may be associated with predetermined physical locations. Based on the image locations of the predetermined features within the image data and the predetermined physical locations of the predetermined features, a system may be configured to determine at least one of a location and an orientation of the aerial vehicle. The disclosed embodiments may provide enhanced accuracy, usability, and robustness in tracking the location and orientation of an aerial vehicle under various operation conditions.

Abstract: The present invention is designed to instrumentation and methods for providing runway obstacle clearance for instrument and non-instrument landing of an aircraft. The device provides a simple method of determining if there are any obstacles within the FAA required path of landing of an aircraft. Typically, there are trees and other obstacles which have to be precisely located to determine if such trees and other obstacles are within the required clearance space for permitted landing of an aircraft. This is particularly important when visual verification of the landing of the aircraft is required.

Abstract: System and methods are provided for predicting a roadway feature. A geometric pattern in a roadway network is selected. The geometric pattern comprises one or more first links and one or more first nodes. A similar pattern to the geometric pattern is identified that comprises one or more second links and one or more second nodes in the roadway network. One or more features for the geometric pattern are identified. An absence of a feature in the similar pattern is determined based on the one or more features for the geometric pattern. A notification relating to the absence of the feature is generated.

Abstract: This disclosure relates to improved techniques for performing image segmentation functions using neural network architectures. The neural network architecture integrates an edge guidance module and object segmentation network into a single framework for detecting target objects and performing segmentation functions. The neural network architecture can be trained to generate edge-attention representations that preserve the edge information included in images. The neural network architecture can be trained to generate multi-scale feature information that preserves and enhances object-level feature information included in images. The edge-attention representations and multi-scale feature information can be fused to generate segmentation results that identify target object boundaries with increased accuracy.

Abstract: A computer-implemented image processing method includes accessing image data representing a plurality of images of a plurality of vehicles and reading a data model representing a predefined vehicle attribute. The method further includes processing a portion of the image data to detect a vehicle feature of at least one of the vehicles represented in at least one of the images based on the predefined vehicle attribute, and processing the portion of the image data to generate vehicle data representing the detected vehicle feature.

Abstract: In one preferred embodiment, the present invention provide a navigation system for a movable platform comprising a GNSS receiver sensor for providing position signals representative of the estimated current position of the movable platform; a camera sensor for providing photographic images representative of the surroundings of the movable platform; and an IMU (Inertial Measurement Unit) sensor for providing specific force and angular rate signals representative of the current specific forces and rate of the movable platform. A processor is responsive to the camera photographic images to estimate the position and attitude of the movable platform, the covariance of the position and attitude estimates and the covariance of consecutive position and attitude estimates.

Abstract: Methods and devices are described for merging maps. In one potential embodiment a method may comprise receiving an indication of at least one plurality of geographically proximate points, where each of the at least one plurality of geographically proximate points are determined by at least one access point in communication with one or more mobile devices. A first and second map may then be received, where the first map and the second map each cover a first area such that the first area is in both the first map and the second map. The first map and the second map may then be merged by matching a mapping of a first portion of an indication of the at least one plurality of geographically proximate points on the first map and a second portion of an indication of an at least one plurality of geographically proximate points on the second map.

Abstract: An apparatus for use with a weather radar system having a radar antenna, the apparatus for mounting to an aircraft and for verifying terrain features shown on an electronic display, the terrain features based on terrain data from a terrain database. The apparatus includes processing electronics configured to receive radar return data from the weather radar system and configured to correlate the radar return data with the terrain data. The processing electronics using the correlation to provide an indication as to whether the terrain features displayed on the electronic display are correct or incorrect.

Abstract: A method of processing probe trace data to determine a measure of correlation of a probe trace with other probe traces comprises obtaining a map that associates a parameter space with a plurality of pixels, wherein at least one correlation value is assigned to each of the plurality of pixels, and determining a correlation score for a probe trace by mapping the probe trace to at least one pixel of the map and determining the correlation score for the probe trace from at least one correlation value of the at least one pixel to which the probe trace is mapped.

Abstract: Disclosed is a flight control support device which sets a flight restricted area W along a terrain, thereby achieving improvement in safety of a small aircraft A and sufficiently securing the degree of freedom of flight course selection of a pilot. The flight control support device includes a terrain information acquirer, an aircraft information acquirer, a flight restricted area setter which sets the flight restricted area W along the terrain on the basis of the terrain information acquired by the terrain information acquirer and the aircraft information acquired by the aircraft information acquirer, and a flight control supporter which supports flight control of a flying object on the basis of the flight restricted area set by the flight restricted area setter.

Abstract: A technique for calculating a location of a first vehicle is described. A method implementation of this technique comprises the steps of detecting, from the perspective of the first vehicle, a movement of a second vehicle relative to the first vehicle, determining, for the time of the relative movement, a location of the second vehicle based on the detected relative movement by matching the detected movement of the second vehicle against map data, measuring, for the time of the relative movement, a distance between the first and second vehicles, and calculating the location of the first vehicle based on the measured distance and the determined location of the second vehicle. The technique also comprises an apparatus, a computer program product, and a vehicle navigation system.

Abstract: An apparatus and method for generating a path using a limited memory size are provided. An approximate path is generated based on a reduced grid map generated by reducing an original grid map. Then, an approximate path is mapped onto the original grid map, and the mapped path is enlarged and divided into a plurality of sections based on an available memory size used for path calculation. Based on a start point and a destination point set in each of the divided sections, a detailed path in each of the sections is generated.

Abstract: Aspects of the present disclosure relate generally to generating elevation maps. More specifically, data points may be collected by a laser moving along a roadway and used to generate an elevation map of the roadway. The collected data points may be projected onto a two dimensional or “2D” grid. The grid may include a plurality of cells, each cell of the grid representing a geolocated second of the roadway. The data points of each cell may be evaluated to identify an elevation for the particular cell. For example, the data points in a particular cell may be filtered in various ways including occlusion, interpolation from neighboring cells, etc. The minimum value of the remaining data points within each cell may then be used as the elevation for the particular cell, and the elevation of a plurality of cells may be used to generate an elevation map of the roadway.

Abstract: In certain embodiments, determining maritime paths includes accessing a feasibility matrix comprising feasibility values for locations of an area. A feasibility value indicates navigability at a location. One or more non-navigable locations represent one or more barriers. Waypoints around the barriers are determined. A cost matrix comprising cost values is calculated. A cost value indicates a distance between two points of a set of points, where the set of points comprises one or more start points, one or more end points, and the waypoints. Dijkstra's technique is applied to a selected start point and a selected end point to yield a shortest length path between the selected start point and the selected end point.

Abstract: A method includes generating current coarse edge count representation based on current fine grid representation of current section, correlating current edge quantity values of current coarse pixels with historical edge quantity values of historical coarse pixels of historical coarse edge count representation of environment, and identifying first subsection of historical coarse edge count representation with highest correlation to current coarse edge count representation. Each current coarse pixel in current coarse edge count representation represents current fine pixels from current fine grid representation. Fine grid representation of current section of environment is based on data from range and attitude sensor. Each current coarse pixel within current coarse edge count representation includes current edge quantity value that represents quantity of current fine pixels represented by current coarse pixel that include edge.

Abstract: Disclosed herein is a three-dimensional (3D) digital map system for implementing a navigation and ground collision preventing method using 3D terrain information. The 3D digital map system includes a terrain referenced navigation module configured to receive data from EGI (Embedded GPS/INS), a radio-altimeter (RALT) and a map database, corrects the data to perform accurate navigation computation, and outputs the corrected data, a collision avoidance warning module configured to generate a warning against collision of an aircraft with the ground or an obstacle using the corrected data, a 3D terrain database and an obstacle database, a terrain following module configured to generate a terrain following trajectory of the aircraft using the same information, and a Passive Ranging module configured to receive the 3D terrain database and line-of-sight (LOS) information of a target and calculate distance and position information of the target located on the ground.

Abstract: A navigation apparatus includes a satellite positioning section for calculating a present position, and a route setting section for searching for a route to a destination based on map data, and sets a detected route as a recommended route. A satellite positioning disable time guiding section sets as a focus point, a candidate point through which a vehicle first passes when traveling along the recommended route, and displays point guide information for guiding the focus point among candidate points as a route change point, when the satellite positioning section is incapable of calculating the present position.

Abstract: An object detection system for a first machine is disclosed. The object detection system may have at least one transmitter configured to generate a laser beam directed onto a ground surface in proximity to the first machine, and a receiver configured to detect the laser beam and generate a corresponding signal. The object detection system may also have a controller in communication with the at least one transmitter and the receiver. The controller may be configured to generate an electronic terrain map based on the signal. The controller may also be configured to make a determination that a second machine is operating within a range of the first machine, and to adjust operation of the at least one transmitter and receiver based on the determination to reduce undesired interactions caused by operation of the second machine.

Abstract: An object detection system for a mobile machine is disclosed. The object detection system may have a first array of laser beam transmitters configured to generate a first plurality of grid lines on a ground surface, and a second array of laser beam transmitters configured to generate a second plurality of grid lines on the ground surface and produce a plurality of intersections with the first plurality of grid lines. The object detection system may also have a receiver configured to detect the plurality of intersections and generate a signal used to create an electronic terrain map based on the detection. At least one of the first and second arrays of laser beam transmitters may be selectively movable during operation to change a location of the plurality of intersections.

Abstract: A positioning device includes a map data storing unit configured to store map data; autonomous sensors configured to detect behavior information of a moving object; an inertial positioning unit configured to detect an estimated position of the moving object by applying the behavior information detected by the autonomous sensors to positioning results obtained by an electronic navigation positioning unit such as a GPS; a planimetric feature detecting unit configured to detect a planimetric feature located around a road; a planimetric feature position identifying unit configured to identify a position of the planimetric feature; a planimetric feature reference positioning unit configured to estimate a planimetric feature estimated position of the moving object by using the position of the planimetric feature as a reference; and a position estimating unit configured to estimate a position of the moving object by applying the estimated position and the planimetric feature estimated position to a Kalman filter.

Abstract: A method of creating a customizable exercise route for a user of a personal navigation device is disclosed. The method includes providing routing instructions for a user along a first route, recording a first speed for a user traveling between a first point and a second point on the first route, providing routing instructions for a user along a second route, recording a second speed for a user traveling between a third point and a fourth point on the second route, comparing the first speed and the second speed to calculate a performance difference related to the first route and the second route, and notifying the user about the performance difference.

Abstract: A system stores reference data generated by associating image feature point data with an image-capturing position and a recorded vehicle event. The system generates data for matching by extracting image feature points from an actually-captured image. The system generates information on an actual vehicle event, extracts first reference data whose image-capturing position is located in a vicinity of an estimated position of the vehicle, and extracts second reference data that includes a recorded vehicle event that matches the actual vehicle event. The system performs matching between at least one of the first reference data and the second reference data, and the data for matching, and determines a position of the vehicle based on the matching.

Abstract: A system and method of relative location detection on an electronic device using image perspective analysis. The electronic device will consist of a processor module coupled to a camera module. The camera module of an electronic device as well as a target device will be used to capture image(s) of the current surroundings, including common elements, which will then be used to obtain the relative location of the devices in reference to one another.

Abstract: A mapping method is provided. The environment is scanned to obtain depth information of environmental obstacles. The image of the environment is captured to generate an image plane. The depth information of environmental obstacles is projected onto the image plane, so as to obtain projection positions. At least one feature vector is calculated from a predetermined range around each projection position. The environmental obstacle depth information and the environmental feature vector are merged to generate a sub-map at a certain time point. Sub-maps at all time points are combined to generate a map. In addition, a localization method using the map is also provided.

Abstract: A steering system for a work vehicle towing a towed implement is described. A steering control unit is coupled to a location signal generation arrangement on the vehicle, a steering actuator, a memory for storing desired path data of the implement and a slope sensor for detecting a lateral inclination of the work vehicle or the implement. The steering control unit calculates a lateral offset compensation value to steer the work vehicle such that the implement is moved on the desired path and a slope offset compensation value based upon a signal from the tilt sensor to compensate for slope forces pulling the implement down a lateral slope. A steering signal is sent to the steering actuator based upon the lateral offset compensation value and the slope offset compensation value.

Abstract: Methods and apparatus for navigating with the use of correlation within a select area are provided. One method includes, storing data required to reconstruct ranges and associated angles to objects along with statistical accuracy information while initially traversing throughout the select area. Measuring then current ranges and associated angles to the objects during a subsequent traversal throughout the select area. Correlating the then current ranges and associated angles to the objects to reconstructed ranges and associated angles to the objects from the stored data. Determining at least one of then current location and heading estimates within the select area based at least in part on the correlation and using the least one of the then current location and heading estimates for navigation.

Abstract: A route retrieval apparatus is disclosed. The route retrieval apparatus includes a storage component, a first correction component, a second correction component and a retrieval component. The storage component stores therein probe information to specify fuel consumption in each section, the probe information having been collected from probe vehicles. The first correction component corrects gradient information of each section based on the specified fuel consumption in the each section. The second correction component corrects a fuel cost of each section based on the gradient information corrected by the first correction component. The retrieval component retrieves, by using the fuel cost of the each section corrected by the second correction component, a route with a lowest total of the fuel costs from a departure point to a destination point.

Abstract: A computer implemented method for unattended detection of a current terrain to be traversed by a mobile device is disclosed. Visual input of the current terrain is received for a plurality of positions. Audio input corresponding to the current terrain is received for the plurality of positions. The video input is fused with the audio input using a classifier. The type of the current terrain is classified with the classifier. The classifier may also be employed to predict the type of terrain proximal to the current terrain. The classifier is constructed using an expectation-maximization (EM) method.

Abstract: Satellite-based navigation techniques can help determine a user's position on a map and can also determine directions to a destination. Functionality can be implemented to determine the user's orientation and direction of motion based on a captured image taken in the direction of motion. The captured image may be preprocessed to compensate for a camera angle and to vary image properties before being transmitted to a server. The user's orientation may be determined based, at least in part, on knowledge of a user's position on a map and comparing the captured image to a set of other images. Walking directions can accordingly be tailored based on the user's orientation.

Abstract: A device and method aids the evaluation of a flight trajectory that is intended to be followed by an aircraft within a constrained environment. The method includes receiving information from a processing unit regarding stationary and moving obstacles, implementing a collision trial based on this information, and displaying any collision risks to the pilot on a display device in the cockpit. Consequently, a pilot can know within the constrained environment whether a flight trajectory needs to be modified to avoid potential collisions.

Abstract: An exemplary embodiment of portable electronic device with guide function includes a housing, a processing unit, a command unit, and a guiding unit. The processing unit and the guiding unit are positioned inside the housing, and the command unit is positioned at least partially outside of the housing. The processing unit is electrically connected to the command unit and the guiding unit. Operating the command unit, the portable electronic device with guide function is actuated into guiding mode controlled by the processing unit. The guiding unit sends detection signals to detect obstacles, receives feedback signals from the obstacles, the processing unit receives the feedback signal from the guiding unit to generate corresponding obstacle types and distance according to the feedback signal.

Abstract: An apparatus of estimating a position of a moving object creates a global map for a space over which the moving object is moving, on the basis of environment information on moving distance, measured distance, captured image and GIS data, and attribute and position of obstacles within the space. The method also creates a local map on the basis of the environment information obtained from around the moving object, and estimates a position of the moving object on the global map through matching of the local map and the global map.

Abstract: An apparatus for placing marks on a resurfaced roadway. The apparatus includes a GPS-based locator for sampling discrete geographical location data of a pre-existing roadway mark evident on the roadway before resurfacing. A computer determines a continuous smooth geographical location function fitted to the sampled geographical location data. And a marker is responsive to the GPS-based locator and geographical location function for replicating automatically the pre-existing roadway mark onto the resurfaced roadway. The apparatus is typically part of a moving vehicle. A related method is disclosed for placing marks on a resurfaced roadway. A similar apparatus can be used to guide a vehicle having a snow plow along a snow covered roadway, or a paving machine along an unpaved roadway surface.

Abstract: A representative point corresponding to geometry of the road on which the vehicle is traveling is calculated based on positional information on a stationary target detected by a radar, and based on positional information of the calculated representative points, left and right side corresponding straight lines that correspond to left and right side edges of the road are calculated. With one of the corresponding straight lines that has a most distal end more proximal to the vehicle than that of the other being set as a reference corresponding straight line, information on curving geometry of the road is detected based on positional information on a representative point within a process targeted area that is sandwiched between the left and the right side corresponding straight lines and extends in the traveling direction of the vehicle and is also distal to the most distal end of the reference corresponding straight line.

Abstract: A vessel hull robot navigation subsystem and method for a robot including a drive subsystem onboard the robot for driving the robot about the hull. A sensor subsystem onboard the robot outputs data combining robot and vessel motion. A memory onboard the robot includes data concerning the configuration of the hull and a desired path of travel for the robot. A fix subsystem communicates position fix data to the robot. A navigation processor onboard the robot is responsive to the memory data, the sensor subsystem, the position fix data, and the data concerning vessel motion. The navigation processor is configured to determine the position of the robot on the hull by canceling, form the sensor subsystem output data combining both robot and vessel motion, the determined vessel motion.

Abstract: An in-vehicle apparatus includes: a memory for storing a map data; a center communication element for obtaining a latest map data from a center; an inter-vehicle communication element for communicating with another in-vehicle apparatus; an input element for receiving an input signal of a specific area from an user; and a controller for setting the specific area as an initial main area. The inter-vehicle communication element receives another map data from another in-vehicle apparatus. The controller compares the map data with another map data. When another main area includes an area not included in the initial main area, the controller adds the area as a new main area, and updates the map data with another map data. The controller updates the map data corresponding to the initial main area with the latest map data.

Abstract: Vehicle attitude is estimated relative to a ground surface over which the vehicle is traveling. An actual image of the ground surface over which the vehicle is traveling is compared with stored or predicted model images of the ground surface. The model images have corresponding known vehicle attitudes associated therewith. For one of the model images that most closely matches the actual image, the known vehicle attitude associated therewith is an estimate of an actual vehicle attitude relative to the ground surface over which the vehicle is traveling.

Abstract: A system and method for providing information for autonomous vehicle navigation are disclosed. The system comprises at least one laser scanner configured to perform one or more range and intensity scans of an area around the autonomous vehicle, and a geo-location unit comprising one or more global positioning system sensors and inertial navigation system sensors. The system also includes at least one processor in operative communication with the laser scanner and the geo-location unit.

Abstract: In at least one embodiment of the present invention a driving aid system for mounting in a road vehicle is provided. The driving aid system comprises a detection system for detecting and storing profiles of characteristics of objects around the vehicle along a road on which the vehicle is being driven. A positioning system is for providing a current position of the vehicle. Profiles of characteristics of objects are stored in relation to the detected position of the vehicle. A processing arrangement compares currently detected profiles with earlier stored profiles and, if a match between a currently detected profile and an earlier stored profile is found, then the current position of the vehicle is determined relative to an object corresponding to the earlier stored profile, and the same or other earlier stored profiles is used to predict the future surroundings of the vehicle.

Abstract: A landmark-based method of estimating the position of an AGV (autonomous ground vehicle) or conventional vehicle, which has an onboard database of landmarks and their locations coordinates. During travel, the AGV looks for and identifies landmarks. It navigates according to position estimations that are based on measured yaw rate and speed. When a landmark s encountered and recognized, its true location coordinates are looked up from the database. These true coordinates are then used to enhance position estimation accuracy between landmarks.

Abstract: A system for operating a remotely controlled powered system, the system including a feedfoward gains element configured to provide information to the remotely controlled powered system to establish a velocity, and a feedback gains element configured to provide information from the remotely controlled powered system to the feedforward gains element. A method and a computer software code are further disclosed for operating the remotely controlled powered system.

Abstract: A method and apparatus for identifying access points using a positioning device and a map having a plurality of segments; determining that the positioning device is near a first location; detecting that the positioning device is off-route at a second location; and storing the second location as a first access point associated with the first location on the map.

Abstract: Techniques are described that may be implemented in a mobile electronic device providing navigation functionality to facilitate selection of a route to a destination from multiple route options. In one or more implementations, route selection information is displayed on a display of the mobile electronic device to facilitate selection of a route to a destination. The route selection information describes one or more routes to the destination and includes one or more metrics, associated with each route, that identify a characteristic of the route (e.g., a difficulty rating, topography, total climb distance, number of turns, and so on). A map may then be displayed on the display to furnish navigation information for the selected route to facilitate navigation to the destination.

Abstract: A method for collaborative navigation between two or more platforms is provided. The method comprises establishing a communication link between a first platform and a second platform, making a sensor measurement from the first platform, updating state and covariance elements of the first platform, and transmitting the updated state and covariance elements from the first platform to the second platform. A conditional update is performed on the second platform to compute a new estimate of state and covariance elements on the second platform, which takes into account the measurement from the first platform. The method further comprises making a sensor measurement from the second platform, updating state and covariance elements of the second platform, and transmitting the updated state and covariance elements from the second platform to the first platform.

Abstract: A present novel and non-trivial system, module, and method for constructing a flight path used by an avionics system are disclosed. A processor receives flight plan data and object data associated with terrain and obstacles. Free cells are extracted above the objects using a recursive space decomposition technique, and a reference path is formed through traversable free space determined from the availability of free cells. In an additional embodiment, threat data associated with hostile military weaponry and significant meteorological conditions could affect the availability of free cells. A genetic algorithm applying genetic operators which include mutators is employed with aircraft kinematic constraints to refine the reference path used to form a population of best path candidates. When a best path is reached after cycling through a re-generation process of path candidates, flight path data representative of the best path is generated and provided to at least one avionics system.

Abstract: A method of displaying a background sky in a navigation system, the method including: storing and maintaining map data and background sky image data with respect to one or more directions of the map data in a database; detecting a driving direction angle of a vehicle; computing a position of a background sky image corresponding to the detected driving direction angle; extracting background sky image data corresponding to the computed position of the background sky image from the database; and displaying the extracted background sky image data as a background sky with respect to the map data.