Abstract: A point cloud based semantic segmentation system includes a first vehicle, a second vehicle, and a server. The first vehicle includes a first imaging sensor, a first position sensor, and a first electronic control unit (ECU). The first ECU receives a point cloud representation of the external environment from the first imaging sensor. The first ECU associates a location of the point cloud representation based on odometry information received from the first position sensor. The server performs semantic segmentation on features in the point cloud representation and generates a map including semantically segmented features. The second vehicle is localized on the generated map using a second imaging sensor, a second position sensor, and a second ECU. The second ECU receives a second point cloud representation and second odometry information and localizes the second vehicle on the generated map based on the received information.

Abstract: Methods and systems for autonomously controlling a first vehicle with a forward vehicle intends to park. An image sensor is mounted to the first vehicle and is configured to generate image data associated with a scene surrounding the first vehicle, wherein the scene includes the forward vehicle located ahead of the first vehicle. A processor is mounted to the first vehicle and communicatively coupled to the image sensor. The processor is programmed to process the image data to identify a plurality of parking spaces, a first roadway lane adjacent to the plurality of parking spaces, and a second roadway lane adjacent to the first roadway lane. The processor determines a speed of the forward vehicle, and classifies the forward vehicle as intending to park based on sensed conditions. In response to the forward vehicle being classified as intending to park, the processor issues commands to maneuver the vehicle accordingly.

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: Methods and systems for assisting a vehicle in predicting the safety of an environment about a vehicle. Image data is sensed by a vehicle image sensor regarding the environment about the vehicle. The system detects one or more first objects surrounding the vehicle based on the images received from the image sensors. An object classification model is performed on the images to determine a class of the one or more first objects. Utilizing deep machine learning on the class of one or more first objects, a safety score of the environment is predicted. While the vehicle is parked, the image sensor is triggered to record images in response to (1) one or more second objects being detected in the images and (2) the safety score being below a threshold.

Abstract: Systems and methods for enhancing safety during motorcycle lane-splitting or lane filtering by using a camera to capture images of adjacent vehicles and a processor to analyze these images to predict vehicle trajectories. The systems and methods disclosed predict future vehicle trajectories, calculates potential distances, and issues a warning if the anticipated separation between vehicles falls below a predefined safety threshold, thereby signaling unsafe conditions for lane splitting.

Abstract: A method performed by a computing device configured to control an autonomous or semi-autonomous driving task of a vehicle includes identifying, based on image data obtained from one or more sensors, an area of interest corresponding to the driving task, determining whether the area of interest includes an obstructed region for which line-of-sight of at least one of the one or more sensors is blocked by an object, determining, in response to a determination that the area of interest includes the obstructed region, whether the area of interest includes a moving vehicle based on audio signals received by one or more audio sensors of the vehicle, and controlling the vehicle to perform the driving task based on the determination of whether the area of interest includes a moving vehicle.

Abstract: A system for creating online vectorized maps for autonomous vehicles includes an image sensor and an electronic control unit (ECU). The image sensor captures a series of image frames. The ECU includes a memory, a central processing unit (CPU), and a transceiver. The memory stores a semantic segmentation deep learning model and a vectorization post-processing module as computer readable code. The CPU executes the semantic segmentation deep learning model and the vectorization post-processing module to output a vectorized map of an external environment of a vehicle. The transceiver uploads the vectorized map to a server such that the vectorized map can be accessed by a second vehicle that uses the vectorized map to traverse the external environment.

Abstract: A method for operating a vehicle includes capturing an image frame and odometry data associated with a vehicle as the vehicle traverses an external environment. The image frame and odometry data are transmitted to an Electronic Control Unit (ECU) of the vehicle. The method further includes determining a local speed limit for the vehicle from the image frame of the external environment and selecting a context of the external environment based upon the odometry data. A global speed limit for the vehicle is determined based upon the selected context. An arbitrated speed limit, which is the local speed limit or the global speed limit, is notified to a driver of the vehicle.

Abstract: A driver-assistance method for a motor vehicle of interest, in which the vehicle of interest detects the third-party vehicles which are present at an initial instant in its environment is disclosed. During a first prediction cycle, an order of priority is assigned to the third-party vehicles which are detected at the initial instant and to the vehicle of interest, corresponding to an order in which the vehicles in the set follow one another in the travel zone starting from a vehicle detected in a position which is furthest ahead of the vehicle of interest. For each selected vehicle in the set, taken in the order of priority, another vehicle in the set is identified which is able to be a primary target vehicle for this selected vehicle. A manoeuvre which is in progress for the selected vehicle is estimated on the basis at least of the identified primary target vehicle.

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 system for creating online vectorized maps for autonomous vehicles includes an image sensor and an electronic control unit (ECU). The image sensor captures a series of image frames. The ECU includes a memory, a central processing unit (CPU), and a transceiver. The memory stores a semantic segmentation deep learning model and a vectorization post-processing module as computer readable code. The CPU executes the semantic segmentation deep learning model and the vectorization post-processing module to output a vectorized map of an external environment of a vehicle. The transceiver uploads the vectorized map to a server such that the vectorized map can be accessed by a second vehicle that uses the vectorized map to traverse the external environment.

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 calculating an optimum route for a first vehicle to travel from a current location to a selected parking space includes receiving map data of a parking zone, the map data including local map data and global map data of the parking zone, sensor data, parking space data indicating availability of parking spaces within the parking zone, and vehicle dynamics and location data, selecting, as the selected parking space, at least one available parking space based on the parking space data, determining a plurality of target positions between the current location and the selected parking space, calculating, in response to the selecting of the selected parking space and based on the plurality of target positions, the optimum route, including calculating trajectories of the first vehicle along an entire route between the current location and the selected parking space, and controlling the first vehicle to travel from the current location to the selected parking space.

Abstract: A method for operating a driver assistance system for a vehicle includes capturing a video feed of an external environment of the vehicle and transmitting the video feed to an Electronic Control Unit (ECU) of the vehicle. Subsequently, a designated speed limit for the vehicle at a current location of the vehicle is determined. The method further includes extracting context information of the external environment from the video feed and comparing the context information to the designated speed limit to create a contextual speed limit. A user is notified of the vehicle of the contextual speed limit. The context information designates a specific environment that the vehicle is located in based upon one or more of: first warning information that informs the user of unsafe driving conditions, first guidance information that provides directional information to the user, and objects located in the specific environment of the vehicle.

Abstract: A method for operating a driver assistance system for a vehicle includes capturing a video feed of an external environment of the vehicle, receiving coordinates and a navigational speed limit from a signal connection identifying a location of the vehicle, transmitting the video feed and the coordinates to an Electronic Control Unit of the vehicle, and extracting a detected speed limit from the video feed of the external environment of the vehicle. The method further includes comparing the detected speed limit to the navigational speed limit to create a fusion speed limit and notifying a user of the vehicle of the fusion speed limit.

Abstract: Methods and systems for autonomously controlling a first vehicle with a forward vehicle intends to park. An image sensor is mounted to the first vehicle and is configured to generate image data associated with a scene surrounding the first vehicle, wherein the scene includes the forward vehicle located ahead of the first vehicle. A processor is mounted to the first vehicle and communicatively coupled to the image sensor. The processor is programmed to process the image data to identify a plurality of parking spaces, a first roadway lane adjacent to the plurality of parking spaces, and a second roadway lane adjacent to the first roadway lane. The processor determines a speed of the forward vehicle, and classifies the forward vehicle as intending to park based on sensed conditions. In response to the forward vehicle being classified as intending to park, the processor issues commands to maneuver the vehicle accordingly.

Abstract: A method for operating a driver assistance system for a vehicle includes capturing a video feed of an external environment of the vehicle, receiving coordinates and a navigational speed limit from a signal connection identifying a location of the vehicle, transmitting the video feed and the coordinates to an Electronic Control Unit of the vehicle, and extracting a detected speed limit from the video feed of the external environment of the vehicle. The method further includes comparing the detected speed limit to the navigational speed limit to create a fusion speed limit and notifying a user of the vehicle of the fusion speed limit.

Abstract: A method for operating a driver assistance system for a vehicle includes capturing a video feed of an external environment of the vehicle and transmitting the video feed to an Electronic Control Unit (ECU) of the vehicle. Subsequently, a designated speed limit for the vehicle at a current location of the vehicle is determined. The method further includes extracting context information of the external environment from the video feed and comparing the context information to the designated speed limit to create a contextual speed limit. A user is notified of the vehicle of the contextual speed limit. The context information designates a specific environment that the vehicle is located in based upon one or more of: first warning information that informs the user of unsafe driving conditions, first guidance information that provides directional information to the user, and objects located in the specific environment of the vehicle.

Abstract: Method for perception blockage prediction and supervision for performing information cloud localization in an ego vehicle based on an information cloud map and a sensor information cloud generated based on sensor information provided by at least one environment sensor of the ego vehicle. The method comprises perceiving a surrounding of the ego vehicle. The method comprises detecting and localizing at least one object in the surrounding of the ego vehicle, which is not contained in the information cloud map. The method comprises determining a future obstruction of at least one part of the information cloud map for the at least one environment sensor of the ego vehicle based on the localization of the at least one object detected in the surrounding of the ego vehicle. The method comprises generating a warning in case the future obstruction of the at least one part of the information cloud map has been determined.