Abstract: Systems and methods are provided for estimating atmospheric properties using a LIDAR sensor. A control system includes a LIDAR sensor configured to detect a distance to an object, and an intensity of light reflected by the object. A controller's a target selection module determines whether the object is a target for use in estimating the atmospheric properties. A data collection module collects values of the distance and the intensity as detected by the LIDAR sensor. The atmospheric properties are determined based on the values of the distance and the intensity. In response to the determined atmospheric properties, the actuator is operated to effect an action.

Abstract: A computer-implemented method for detecting one or more three-dimensional structures in a proximity of a vehicle at runtime includes generating, by a processor, a birds-eye-view (BEV) camera image of the proximity of the vehicle, the BEV camera image comprising two-dimensional coordinates of one or more structures in the proximity. The method further includes generating, by the processor, a BEV height image of the proximity of the vehicle, the BEV height image providing height of the one or more structures in the proximity. The method further includes detecting one or more edges of the three-dimensional structures based on the BEV camera image and the BEV height image. The method further includes generating models of the three-dimensional structures by plane-fitting based on the edges of the one or more three-dimensional structures. The method further includes reconfiguring a navigation system receiver based on the models of the three-dimensional structures.

Abstract: An autonomous vehicle, system and method of navigating the autonomous vehicle. The system includes one or more sensors for obtaining data with respect to a remote stationary vehicle, and a processor. The processor is configured to classify the remote stationary vehicle into an object hypothesis based on the data, determine an actionable behavior of the autonomous vehicle based on a probability for the object hypothesis, and navigate the autonomous vehicle with respect to the remote vehicle via the actionable behavior.

Abstract: Methods and systems are provided for navigating a mobile platform in an environment. A processor obtains information about an object in the environment, obtains information about a first satellite, and estimates a probability indicator for a non-line of sight signal transmission between a current satellite location of the first satellite and a current location of the mobile platform using the information about the first satellite and the information about the object. The processor further determines a discrepancy indicator using a movement information of the mobile platform and a movement information of the first satellite such that a weighting indicator can be determined using the estimated probability indicator and the determined discrepancy indicator. The processor then assigns a weighting indicator to a satellite signal transmitted from the first satellite in order to provide a first weighted signal for navigating the mobile platform.

Abstract: Methods and systems are provided for learning a neural network and to determine a pose of a vehicle in an environment. A first processor performs a first feature extraction on sensor-based image data to provide a first feature map. The first processor also performs a second feature extraction on the aerial image data to provide a second feature map. Both feature maps are correlated to provide a correlation result. The first processor learns a neural network using the correlation result and ground-truth data, wherein each of the first feature extraction and the second feature is learned to extract a portion of features from the respective image data. A geo-tagged second feature map can then be retrieved by an on-board processor of the vehicle which, along with on-board processed sensor-based data by the network trained by the first processor, determines the pose of the vehicle.

Abstract: Systems and methods are provided for estimating atmospheric properties using a LIDAR sensor. A control system includes a LIDAR sensor configured to detect a distance to an object, and an intensity of light reflected by the object. A controller's a target selection module determines whether the object is a target for use in estimating the atmospheric properties. A data collection module collects values of the distance and the intensity as detected by the LIDAR sensor. The atmospheric properties are determined based on the values of the distance and the intensity. In response to the determined atmospheric properties, the actuator is operated to effect an action.

Abstract: Methods and systems are provided for learning a neural network and to determine a pose of a vehicle in an environment. A first processor performs a first feature extraction on sensor-based image data to provide a first feature map. The first processor also performs a second feature extraction on the aerial image data to provide a second feature map. Both feature maps are correlated to provide a correlation result. The first processor learns a neural network using the correlation result and ground-truth data, wherein each of the first feature extraction and the second feature is learned to extract a portion of features from the respective image data. A geo-tagged second feature map can then be retrieved by an on-board processor of the vehicle which, along with on-board processed sensor-based data by the network trained by the first processor, determines the pose of the vehicle.

Abstract: A vehicle control system for automated driver-assistance includes a controller that generates a control signal to alter operation of one or more actuators of a vehicle based on a heading of a target. Generating the control signal includes determining a first heading of the target based on sensor data. Further, a probability (pa) of the first heading being accurate is computed based on a number of heading flips encountered in a duration-window of a predetermined length. Further, a map-probability (pm) that the target is traveling according to data from a navigation map is computed. Further, a posterior probability (pf) of the first heading being accurate is computed based on the probability (pa) and the map-probability (pm). Generating the control signal further includes, in response to the posterior probability being less than a predetermined threshold, correcting the first heading, and generating the control signal based on the first heading.

Abstract: A computer-implemented method for detecting one or more three-dimensional structures in a proximity of a vehicle at runtime includes generating, by a processor, a birds-eye-view (BEV) camera image of the proximity of the vehicle, the BEV camera image comprising two-dimensional coordinates of one or more structures in the proximity. The method further includes generating, by the processor, a BEV height image of the proximity of the vehicle, the BEV height image providing height of the one or more structures in the proximity. The method further includes detecting one or more edges of the three-dimensional structures based on the BEV camera image and the BEV height image. The method further includes generating models of the three-dimensional structures by plane-fitting based on the edges of the one or more three-dimensional structures. The method further includes reconfiguring a navigation system receiver based on the models of the three-dimensional structures.

Abstract: A system and method for monitoring a road segment includes determining a geographic position of a vehicle in context of a digitized roadway map. A perceived point cloud and a mapped point cloud associated with the road segment are determined. An error vector is determined based upon a transformation between the mapped point cloud and the perceived point cloud. A first confidence interval is derived from a Gaussian process that is composed from past observations. A second confidence interval associated with a longitudinal dimension and a third confidence interval associated with a lateral dimension are determined based upon the mapped point cloud and the perceived point cloud. A Kalman filter analysis is executed to dynamically determine a position of the vehicle relative to the roadway map based upon the error vector, the first confidence interval, the second confidence interval, and the third confidence interval.

Abstract: Methods and systems are provided for navigating a mobile platform in an environment. A processor obtains information about an object in the environment, obtains information about a first satellite, and estimates a probability indicator for a non-line of sight signal transmission between a current satellite location of the first satellite and a current location of the mobile platform using the information about the first satellite and the information about the object. The processor further determines a discrepancy indicator using a movement information of the mobile platform and a movement information of the first satellite such that a weighting indicator can be determined using the estimated probability indicator and the determined discrepancy indicator. The processor then assigns a weighting indicator to a satellite signal transmitted from the first satellite in order to provide a first weighted signal for navigating the mobile platform.

Abstract: A system and method for monitoring a road segment includes determining a geographic position of a vehicle in context of a digitized roadway map. A perceived point cloud and a mapped point cloud associated with the road segment are determined. An error vector is determined based upon a transformation between the mapped point cloud and the perceived point cloud. A first confidence interval is derived from a Gaussian process that is composed from past observations. A second confidence interval associated with a longitudinal dimension and a third confidence interval associated with a lateral dimension are determined based upon the mapped point cloud and the perceived point cloud. A Kalman filter analysis is executed to dynamically determine a position of the vehicle relative to the roadway map based upon the error vector, the first confidence interval, the second confidence interval, and the third confidence interval.

Abstract: An autonomous vehicle, system and method of navigating the autonomous vehicle. The system includes one or more sensors for obtaining data with respect to a remote stationary vehicle, and a processor. The processor is configured to classify the remote stationary vehicle into an object hypothesis based on the data, determine an actionable behavior of the autonomous vehicle based on a probability for the object hypothesis, and navigate the autonomous vehicle with respect to the remote vehicle via the actionable behavior.

Abstract: A disambiguating system for disambiguating between ambiguous detections is provided. The system includes a plurality of modules, wherein each module is configured to disambiguate between ambiguous detections by selecting, as a true detection, one candidate detection in a set of ambiguous detections and wherein each module is configured to apply a different selection technique. The system includes: one or more modules configured to select as the true detection, the candidate detection whose associated position is closer to a position indicated by other data and one or more modules configured to select as the true detection, the candidate detection with the highest probability of being true based on other sensor data.

Abstract: Methods and systems for enhanced object tracking by receiving sensor fusion data related to target objects and object tracks; determining splines representing trajectories of each target object; filtering the sensor fusion data about each target object based on a first, second and third filtering model wherein each filtering model corresponds to one or more of a set of hypotheses used for processing vectors related to trajectories of a track object wherein the set of hypotheses comprise: a path constraint, a path unconstrained, and a stationary hypothesis; and generating a hypothesis probability for determining whether to use a particular hypothesis based wherein the hypothesis probability is determined based on results from the first, second and third filtering models and from results from classifying, by at least one classification model, one or more features related to the object track for the target object.

Abstract: Systems and methods are provided for controlling a vehicle. In one embodiment, a method includes: receiving, by a processor, landmark data obtained from an image sensor of the vehicle; fusing, by the processor, the landmark data with vehicle pose data to produce fused lane data, wherein the fusing is based on a Kalman filter; retrieving, by the processor, map data from a lane map based on the vehicle pose data; selectively updating, by the processor, the lane map based on a change in the fused lane data from the map data; and controlling, by the processor, the vehicle based on the updated lane map.

Abstract: Methods and apparatus are provided for controlling a vehicle. In one embodiment, a method includes: receiving, by a processor, object detection data that indicates a plurality of objects detected in an environment of the vehicle; computing, by the processor, a correction value associated with at least one of range, roll, and pitch of the plurality of objects based on a likelihood function; applying, by the processor, the correction value to the object detection data to obtain corrected object detection data; and controlling, by the processor, the vehicle based on the corrected object detection data.

Abstract: Methods and systems for enhanced object tracking by receiving sensor fusion data related to target objects and object tracks; determining splines representing trajectories of each target object; filtering the sensor fusion data about each target object based on a first, second and third filtering model wherein each filtering model corresponds to one or more of a set of hypotheses used for processing vectors related to trajectories of a track object wherein the set of hypotheses comprise: a path constraint, a path unconstrained, and a stationary hypothesis; and generating a hypothesis probability for determining whether to use a particular hypothesis based wherein the hypothesis probability is determined based on results from the first, second and third filtering models and from results from classifying, by at least one classification model, one or more features related to the object track for the target object.

Abstract: A method for autonomous vehicle map construction includes automatically capturing location data, movement data, and perception data from a vehicle that has traveled down a road, wherein the perception data includes data that identifies the location of lane edges and lane markers for the road, the location of traffic signs associated with the road, and the location of traffic signaling devices for the road. The method further includes pre-processing to associate the captured perception data with the captured location data, captured movement data, and navigation map data; determining, from the pre-processed data, lane boundary data, traffic device and sign location data, and lane level intersection data that connects the intersecting and adjoining lanes identified through the lane boundary data; and storing the lane boundary data, traffic device and sign location data, and lane level intersection data in a map file configured for use by an autonomous vehicle.

Abstract: A disambiguating system for disambiguating between ambiguous detections is provided. The system includes a plurality of modules, wherein each module is configured to disambiguate between ambiguous detections by selecting, as a true detection, one candidate detection in a set of ambiguous detections and wherein each module is configured to apply a different selection technique. The system includes: one or more modules configured to select as the true detection, the candidate detection whose associated position is closer to a position indicated by other data and one or more modules configured to select as the true detection, the candidate detection with the highest probability of being true based on other sensor data.