Abstract: A method performed by a controller of a vehicle includes generating and emitting sound signals into an environment around the vehicle using a plurality of ultrasonic sensors arranged on the vehicle by controlling a firing sequence of the plurality of ultrasonic sensors, receiving, at the plurality of ultrasonic sensors, the sound signals as reflected back toward the vehicle by at least one object in the environment, calculating, at the controller, a plurality of relevancy scores for the plurality of ultrasonic sensors, each of the plurality of relevancy scores corresponding to a relevance of one of the plurality of ultrasonic sensors to the at least one object, adjusting, at the controller, the firing sequence of the plurality of ultrasonic sensors based on the plurality of relevancy scores, and controlling, at the controller, the plurality of ultrasonic sensors to generate and emit the sound signals in accordance with the adjusted firing sequence.

Abstract: A method for automatically parking a vehicle on a sloped roadway. The method detects a roadway slope gradient, utilizing at least one vehicle sensor, at a roadway where the vehicle is presently located. The method calculates at least one vehicle slope value responsive to the detected slope gradient and a validation threshold over a period of time. The method instructs, using a vehicle controller, a plurality of vehicle tires to turn in a direction according to the at least one vehicle slope value. The method applies a parking brake to the vehicle, using the vehicle controller. The method sends an acknowledgement notification, using the vehicle controller, to inform a user of the vehicle.

Abstract: A method includes obtaining image frames from each camera disposed along a vehicle, where each image frame corresponds to a same timestamp. The method further includes constructing a first birds-eye view (BEV) image from each image frame with a first BEV module and constructing a second BEV image from each image frame by Inverse Perspective Mapping (IPM) with a second BEV module. The first BEV module extracts features of an external environment of the vehicle from each image frame, transforms the features to a three-dimensional space, and projects the three-dimensional space onto an overhead two-dimensional plane. Subsequently, a merging module merges the first and second BEV images to produce a hybrid BEV image. Features of an external environment of the vehicle within the hybrid BEV image are detected by a deep learning neural network and the hybrid BEV image is displayed to a user in the vehicle.

Abstract: For training a perception algorithm to detect an emergency vehicle, respective audio datasets are received from two microphones and respective spectrograms are generated. At least one interaural difference map is generated based on the spectrograms, audio source localization data is generated, which specifies a number of audio sources in respective grid cells of a spatial grid, by applying a CRNN to first input data containing the spectrograms and the least one interaural difference map. An image is received from a camera and output data comprising a bounding box for the emergency vehicle is predicted by applying at least one further ANN to second input data containing the image and the spectrograms. Network parameters are adapted depending on the output data and the audio source localization data.

Abstract: Methods and systems for assisting drivers in finding available parking spots by estimating parking spot availabilities. Vehicle image sensors, and associated image processing techniques, detect whether or not other vehicles are located in parking spaces. An occupancy status of each parking spot is determined over time based on these image processing results, and the occupancy status is stored, for example as historical data. The occupancy statuses can be stored or retrieved based on a particular geographical region. An estimated occupancy status of a first parking spot can be generated based upon a last-known occupancy status of that parking spot and the average parking spot availabilities of nearby parking spots in that geographic region. The estimated occupancy status can be displayed, for example as overlaid into a map or navigation application.

Abstract: A system for generating a map of a paved surface for a vehicle and localizing the vehicle on the map of the paved surface includes an imaging sensor, a vehicle odometry sensor, a memory, a processor, and a transceiver. The imaging sensor captures a series of image frames. The vehicle odometry sensor measures an orientation, a velocity, and an acceleration of the vehicle. The memory stores a mapping engine as computer readable code. The processor executes the mapping engine to generate a map. The transceiver uploads the map to a server such that the map is accessed by a second vehicle that uses the map to traverse the external environment.

Abstract: A method performed by a computing device configured to detect a lane direction in a parking zone being navigated by a vehicle includes capturing, using an image capture device, at least one image of an environment surrounding the vehicle that includes an arrow marking on a ground surface of the parking zone, generating a top-down image, including the arrow marking, of the environment surrounding the vehicle based on the captured at least one image, performing an image analysis of the top-down image to determine an arrow direction of the arrow marking, detecting, based on results of the image analysis, the lane direction of a lane occupied by the vehicle based on the determined arrow direction, generating and providing an output indicating the lane direction of the lane occupied by the vehicle.

Abstract: A method includes obtaining image frames from each camera disposed along a vehicle, where each image frame corresponds to a same timestamp. The method further includes constructing a first birds-eye view (BEV) image from each image frame with a first BEV module and constructing a second BEV image from each image frame by Inverse Perspective Mapping (IPM) with a second BEV module. The first BEV module extracts features of an external environment of the vehicle from each image frame, transforms the features to a three-dimensional space, and projects the three-dimensional space onto an overhead two-dimensional plane. Subsequently, a merging module merges the first and second BEV images to produce a hybrid BEV image. Features of an external environment of the vehicle within the hybrid BEV image are detected by a deep learning neural network and the hybrid BEV image is displayed to a user in the vehicle.

Abstract: A method for executing an autonomous parking process of a vehicle using a driver assistance system includes sensing an external environment of the vehicle, receiving coordinates identifying a location of the vehicle, receiving a navigational speed limit that is associated with the location identified by the coordinates, and transmitting data associated with the external environment and the navigational speed limit to an Electronic Control Unit of the vehicle. The method further includes carrying out the autonomous parking process of the vehicle, determining a region of interest of the external environment of the vehicle based on the data and the navigational speed limit, and monitoring on-coming traffic within the region of interest.

Abstract: For training a perception algorithm to detect an emergency vehicle, respective audio datasets are received from two microphones and respective spectrograms are generated. At least one interaural difference map is generated based on the spectrograms, audio source localization data is generated, which specifies a number of audio sources in respective grid cells of a spatial grid, by applying a CRNN to first input data containing the spectrograms and the least one interaural difference map. An image is received from a camera and output data comprising a bounding box for the emergency vehicle is predicted by applying at least one further ANN to second input data containing the image and the spectrograms. Network parameters are adapted depending on the output data and the audio source localization data.