A driver assistance apparatus includes an external camera disposed at a vehicle so as to have an outer field of view of the vehicle, configured to obtain image data on the outer field of view of the vehicle; an internal camera disposed inside the vehicle to grasp a drivers gaze on board the vehicle, configured to obtain the drivers gaze data; and a controller including at least one processor configured to process the image data and the gaze data. The controller may be configured to grasp the driver's gaze based on the gaze data, and based on a determination that the driver is in a careless condition, to control at least one of a control timing of a steering device and a lateral distance limit value for operating the steering device to be changed.

In various examples, surface profile estimation and bump detection may be performed based on a three-dimensional (3D) point cloud. The 3D point cloud may be filtered in view of a portion of an environment including drivable free-space, and within a threshold height to factor out other objects or obstacles other than a driving surface and protuberances thereon. The 3D point cloud may be analyzed—e.g., using a sliding window of bounding shapes along a longitudinal or other heading direction—to determine one-dimensional (1D) signal profiles corresponding to heights along the driving surface. The profile itself may be used by a vehicle—e.g., an autonomous or semi-autonomous vehicle—to help in navigating the environment, and/or the profile may be used to detect bumps, humps, and/or other protuberances along the driving surface, in addition to a location, orientation, and geometry thereof.

Embodiments of the present disclosure are directed to lane marker prediction for occluded lane markers. Image data from one or more sensors of a vehicle is received by a processor of a control system. The image data includes a roadway from a route being navigated by the vehicle and lane marker information. If there are not enough lane markers captured in the lane marker information to produce a threshold look-ahead horizon of the roadway ahead of the vehicle, a longest lane marker ahead of the vehicle from the lane marker information is selected. A curvature tangent to the longest lane marker is computed and predictive lane markers are generated based on the curvature tangent. The vehicle is steered based on the predictive lane markers ahead of the vehicle generated from the curvature tangent.

A device for assisting in the driving of a motor vehicle includes a line detector for detecting the boundary line of a traffic lane, a setup module capable of establishing a virtual lane from the line detected, a monitoring module capable of monitoring the risk of the motor vehicle leaving the virtual lane established. The device also includes a module for acquiring an image representing a relevant object. The setup module includes a first map containing values of a position of a virtual-lane boundary according to a lateral shift of the relevant object in the acquired image.

Systems and methods for providing real-time feedback to a driver of a vehicle based on real-time datasets is disclosed. The systems and methods include obtaining one or more sets of real-time data associated with a vehicle. Performing one or more operations on the set of real-time data, wherein the one or more operations are based on the set of real-time data. Generating, a feedback alert based on results of the one or more operations and one or more detected real-time behaviors of the vehicle. Providing the feedback alert for presentation at a user interface on-board the vehicle. The real-time data may include contextual data, environmental data, operating data, data for a plurality of drivers, or combinations thereof.

A method for assigning a number of lanes and a direction of travel on a path includes receiving location data including a plurality of location points, projecting the plurality of location points on to an aggregation axis perpendicular to a centerline of the vehicle path, grouping the plurality of location points as projected onto the aggregation axis into one or more clusters, and determining the number of vehicle lanes of the vehicle path based on a count of the one or more clusters.

Systems and methods for situational behavior of an autonomous vehicle are disclosed. In one aspect, an autonomous vehicle includes at least one perception sensor configured to generate perception data indicative of at least one other vehicle on a roadway, a non-transitory computer readable medium, and a processor. The processor is configured to determine that the other vehicle is violating one or more rules of the roadway based on the perception data, tag the other vehicle as a non-compliant driver, and modify control of the autonomous vehicle in response to tagging the other vehicle as a non-compliant driver.

A method and system for road condition monitoring including receiving roadway data from connected vehicles in response to a third party request. The connected vehicles include sensors for capturing the roadway data. The method and system include determining a roadway condition based on the roadway data and calculating a data price based on the roadway condition and the roadway data. Further, the method and system include controlling access to the roadway data according to the data price.

A display control device includes a display that is configured to display information, a detector that is configured to detect a partition line for partitioning a lane on a road on which a vehicle is present, and a display controller that is configured to cause the display to display the partition line detected by the detector variably, and the display controller is configured to change a length of the partition line which is displayed by the display on the basis of a detection distance of the detector.

A list of images is received. The images were captured by a sensor of an ADV chronologically while driving through a driving environment. A first image of the images is identified that includes a first object in a first dimension (e.g., larger size) detected by an object detector using an object detection algorithm. In response to the detection of the first object, the images in the list are traversed backwardly in time from the first image to identify a second image that includes a second object in a second dimension (e.g., smaller size) based on a moving trail of the ADV represented by the list of images. The second object is then labeled or annotated in the second image equivalent to the first object in the first image. The list of images having the labeled second image can be utilized for subsequent object detection during autonomous driving.