Abstract: A vehicle capable of autonomous driving includes a lane detection system. The lane detection system is trained to predict lane lines using training images. The training images are automatically processed by a training module of the lane detection system in order to create ground truth data. The ground truth data is used to train the lane detection system to predict lane lines that are occluded in real-time images of roadways. The lane detection system predicts lane lines of a roadway in a real-time image even though the lane lines maybe indiscernible due to objects on the roadway or due to the position of the lane lines being in the horizon.

Abstract: A modeling system trains computer models for an autonomous control system using computer simulated models of objects. The objects may be vehicles, and the computer simulated models may be virtual models of vehicles simulated by computer software. Since the vehicle models are computer simulated, various characteristics of the vehicle can be easily obtained by the modeling system. The various types of data may include geometric information of the vehicle, views of the vehicle from different perspectives, and the like. The modeling system can easily generate and label a large amount of training data using the characteristics of the computer simulated vehicles. The modeling system can use the training data to train computer models for the autonomous control system.

Abstract: A vehicle capable of autonomous driving includes a lane detection system. The lane detection system is trained to predict lane lines using training images. The training images are automatically processed by a training module of the lane detection system in order to create ground truth data. The ground truth data is used to train the lane detection system to predict lane lines that are occluded in real-time images of roadways. The lane detection system predicts lane lines of a roadway in a real-time image even though the lane lines maybe indiscernible due to objects on the roadway or due to the position of the lane lines being in the horizon.

Abstract: A method of predicting a trajectory of a target vehicle with respect to an ego vehicle includes receiving a first image having a target object representing a target vehicle on a road from a camera mounted on the ego vehicle, generating a bounding box associated with the target vehicle, the bounding box surrounding a contour of the target object, extracting tire contact information of the target object with a road surface from the first image, wherein each tire contact information represents coordinates, in the first image, of contact between a corresponding tire and the road, mapping the plurality of tire contact information from the first image to a bird's eye view image of the first image, and calculating the trajectory, with reference to a moving direction of the ego vehicle, of the target object using the mapped tire contact information on the bird's eye view image.

Abstract: A modeling system trains computer models for an autonomous control system using computer simulated models of objects. The objects may be vehicles, and the computer simulated models may be virtual models of vehicles simulated by computer software. Since the vehicle models are computer simulated, various characteristics of the vehicle can be easily obtained by the modeling system. The various types of data may include geometric information of the vehicle, views of the vehicle from different perspectives, and the like. The modeling system can easily generate and label a large amount of training data using the characteristics of the computer simulated vehicles. The modeling system can use the training data to train computer models for the autonomous control system.

Abstract: A region (e.g., a portion) of a full-size image is selected for analysis by a vision inference model. The region of the image may be dynamically selected for the image based on environmental characteristics of the image. These environmental characteristics may include semantic information about the environment that may be determined from a previous image of the environment, road structure information, control information, and motion information. These environmental characteristics may thus describe expected areas of interest in the image. The selected region of the full-size image is resized to a size compatible with a vision inference model which identifies semantic information about the current image. This semantic information may then be used to select a region of a subsequent image.

Abstract: A vehicle capable of autonomous driving includes a lane detection system. The lane detection system is trained to predict lane lines using training images. The training images are automatically processed by a training module of the lane detection system in order to create ground truth data. The ground truth data is used to train the lane detection system to predict lane lines that are occluded in real-time images of roadways. The lane detection system predicts lane lines of a roadway in a real-time image even though the lane lines maybe indiscernible due to objects on the roadway or due to the position of the lane lines being in the horizon.