A method for implementing autonomous driving and a vehicle-mounted control system includes: obtaining a first signal from at least one first sensor fixedly arranged at a specific location, where the first signal indicates static travelling information related to a lane; obtaining, from a vehicle-mounted sensor, a second signal indicating dynamic travelling information related to a vehicle travelling road; and establishing a travelling route corridor on the basis of at least one of the first signal and the second signal.

A computer-implemented method comprises receiving, by an image processing system, a depth image captured by a stereo camera on an unmanned aerial vehicle (UAV). One or more pixels of the depth image are associated with corresponding depth values indicative of distances of one or more objects to the stereo camera. The image processing system determines that one or more pixels of the depth image are associated with invalid depth values. The image processing system infers, based on a distribution of the one or more pixels of the depth image that are associated with invalid depth values, a presence of a potential obstacle in an environment of the UAV. The UAV is controlled based on the inferred presence of the potential obstacle.

An example embodiment of the present invention provides a method of assessing the condition of a pavement site, comprising: (a) acquiring aerial images of the site from above, for example by an unmanned aerial system (UAS); (b) using photogrammetry tools to generate an orthomosaic that represents the airport pavement surface; (c) using image analysis tools and machine learning methods to determine the location and extent of defects in the pavement; (c) producing an image representation of the site and the defects, where the location and extent of defects are discernible from the image; (d) using software application techniques to store and present defect data and other related information for client-side user access.

A method for providing cues to an aerial vehicle operator is disclosed. The method includes: determining when a vehicle is on final approach; processing a plurality of ground images of a ground path ahead of the vehicle; identifying a lane in the processed ground images; determining whether the identified lane corresponds to an assigned runway based on a relative position or a relative geometry of the identified lane; tracking during landing a left and a right side edge, a front edge, and a runway center line of the assigned runway; determining, relative to the runway center line, whether a relative position of the vehicle during landing is left of, right of, or aligned with the runway center line; and providing visual and/or audible guidance to the vehicle operator to take corrective action when the relative position of the vehicle during landing is not aligned with the runway center line.

A system for detecting and extracting a ground surface condition from an image comprising a memory and a processor in communication with the memory. The processor performs a high resolution scan of at least one input image and generates an orthomosaic model and a digital surface model based on the performed high resolution scan. The processor generates an image tile based on the generated models and determines a label indicative of a probability of a presence of a ground surface condition for each pixel of the generated image tile via a computer vision model. The processor generates a label tensor for the at least one input image based on the determined labels and extracts a two-dimensional geospatial representation of a detected ground surface condition based on the generated label tensor. The processor generates a report indicative of damage associated with the detected ground surface condition based on the extracted two-dimensional geospatial representation.

A method of surveying roads includes generating a dynamic flight plan for a drone using a vehicle traveling on a road as a target. The dynamic flight plan includes instructions for movement of the drone. The method includes controlling the drone as a function of position of the vehicle based on the dynamic flight plan. The method includes maintaining, based on the controlling, line of sight with the drone while the drone with an onboard camera follows the vehicle and captures images of the road being traveled by the vehicle using the onboard camera.

Input coordinates identify a tile on the globe and a biome is identified for each pixel of the tile. We choose a random segmentation mask of the corresponding biome for the tile. Every segment of the mask carries a unique identifier and access to a random value via a corner reference. These parameters ensure that (when executed in parallel) each pixel with the same identifier and random value is handled the same way. For each pixel of the tile, using the selected mask, we identify the segment corresponding to that pixel, we retrieve a color variation for that pixel based upon the segment identifier and the random value. We thus choose a color variation for each segment of a segmentation mask. Pixels in the same segment are treated the same way. Instead of a color variation for flat areas (crop fields) we choose a density variation for regions like forests.

A system and method for pipeline data acquisition may include a software program that can autonomously review new and legacy videos collected by camera-equipped robotic systems from inside the pipelines, and automatically detect and categorize different features. Three-dimensional (3-D) point cloud may also be generated using software algorithms that stitch together like features in different video frames.

A map generation device extracts, by inputting an image in which a road is represented to a classifier that outputs, for each pixel of the image, a type of a feature object on the road represented by the pixel, a pixel representing a boundary feature object that represents a boundary of a lane among feature objects on the road, calculates a Voronoi boundary by Voronoi-dividing the image with each pixel representing the boundary feature object as a generating point, detects each of the calculated Voronoi boundaries as one lane, and generates map information representing each of the detected lanes.

Method and system for providing a mobility service is described. The mobility service can include delivering goods in rough terrain, rural areas, and other similar environments, by selecting and configuring vehicles for terrain considerations based on known and dynamically changing information. The disclosed system can include a vehicle configured with a deployable autonomous drone, and can determine optimized vehicle routes to remote locations using the deployable drone and vehicle navigation sensors, for real time mapping that can be combined with existing map/terrain data. The terrain data may also be sent to a vehicle in a vehicle fleet, and/or to a cloud-based server, and be used to compute the best available vehicles designed for the mobility service. The system may deploy one or more mobility solutions, collect telematics, road information, navigational data, and other information during the delivery. This feedback may then be used for future mobility services.