Abstract: An autonomous driving merge management system includes an autonomous driving control device and an intention decision management system. The management system includes a candidate strategy subsystem generating a plurality of candidate driving strategies, a merging vehicle behavior recognition subsystem predicting a merging intention of a merging vehicle; an intention-based interactive prediction subsystem predicting future merging scenarios between the host vehicle and merging vehicle as a function of inputs by the merging vehicle behavior recognition subsystem and inputs by the candidate strategy subsystem, and a cost function-based evaluation subsystem determining a cost for each future merging scenario generated by the intention-based interactive prediction subsystem. A processor selects a merge strategy of the host vehicle based on intention-based prediction results and cost function-based evaluation results.

Abstract: A process for identifying a vehicle driver according to a pre-determined hierarchy. The process includes determining, in a first determination act, whether a first sub-process, of a group of multiple sub-processes, can be used to identify the vehicle driver. The first sub-process is pre-determined to be a most reliable sub-process of the group for identifying the vehicle driver. The process also includes determining, in a second determination act, only if the first determination act has a negative result, whether a second sub-process of the group can be used to identify the vehicle driver. The second sub-process is pre-determined to be a second-most reliable sub-process of the group for identifying the vehicle driver.

Abstract: A method and system for estimating the state of health of an object sensing fusion system. Target data from a vision system and a radar system, which are used by an object sensing fusion system, are also stored in a context queue. The context queue maintains the vision and radar target data for a sequence of many frames covering a sliding window of time. The target data from the context queue are used to compute matching scores, which are indicative of how well vision targets correlate with radar targets, and vice versa. The matching scores are computed within individual frames of vision and radar data, and across a sequence of multiple frames. The matching scores are used to assess the state of health of the object sensing fusion system. If the fusion system state of health is below a certain threshold, one or more faulty sensors are identified.

Abstract: A method for selecting an anchor lane for tracking in a vehicle lane tracking system. Digital map data and leading vehicle trajectory data are used to predict lane information ahead of a vehicle. Left and right lane boundary markers are also detected, where available, using a vision system. The lane marker data from the vision system is combined with the lane information from the digital map data and the leading vehicle trajectory data in a lane curvature fusion calculation. The left and right lane marker data from the vision system are also evaluated for conditions such as parallelism and sudden jumps in offsets, while considering the presence of entrance or exit lanes as indicated by the map data. An anchor lane for tracking is selected based on the evaluation of the vision system data, using either the fused curvature calculation or the digital map and leading vehicle trajectory data.

Abstract: A system and method for providing calibration and de-warping for ultra-wide FOV cameras. The method includes estimating intrinsic parameters such as the focal length of the camera and an image center of the camera using multiple measurements of the near optical axis object points and a pinhole camera model. The method further includes estimating distortion parameters of the camera using an angular distortion model that defines an angular relationship between an incident optical ray passing an object point in an object space and an image point on an image plane that is an image of the object point on the incident optical ray. The method can include a parameter optimization process to refine the parameter estimation.

Abstract: A method for map-aided vision-based lane sensing. The method includes receiving map information corresponding to a current geographic position of a vehicle on a roadway. The map information includes the number of lanes on the roadway. Information about the number of lanes crossed by the vehicle on the roadway is received. It is determined which of the lanes on the roadway is currently occupied by the vehicle based on the map information and the number of lanes crossed by the vehicle on the roadway.

Abstract: A method of guiding a vehicle to a region for initiating a parallel parking maneuver. A region of feasible starting locations for successfully performing a parallel parking maneuver is determined by a processor. A position of the vehicle relative to the region of feasible starting locations is determined. A determination is made whether the vehicle is in a zero heading position. The vehicle is guided along an initial target path by controlling a steering actuator until the vehicle is in a zero heading position relative to the road of travel in response to the vehicle is not in the zero heading position. A planned path is generated that includes two arc-shaped trajectories extending between the vehicle at the zero heading position and a position within the region of feasible starting locations as determined by the processor. The steering actuator is controlled to follow the planned path to the feasible region.

Abstract: A method for allocating forces among the corners of a vehicle having a redundant actuator suite includes determining a set of desired forces at the center of gravity of the vehicle, and allocating the set of desired forces among the corners of the vehicle as virtual control commands using a controller. The method also includes mapping the virtual control commands at the corners to actual or true control commands at the corners, and controlling a plurality of actuators at the corners using the actual or true control commands. The actuators may include friction brakes and wheel motors. Mapping the virtual control commands may include using a Least Squares formulation. Control of the actuators may be prioritized with respect to each other using weighting matrices. A vehicle includes a controller having actuators and a controller configured for executing the above method.

Abstract: A vehicle obstacle detection system includes an imaging system for capturing objects in a field of view and a radar device for sensing objects in a substantially same field of view. The substantially same field of view is partitioned into an occupancy grid having a plurality of observation cells. A fusion module receives radar data from the radar device and imaging data from the imaging system. The fusion module projects the occupancy grid and associated radar data onto the captured image. The fusion module extracts features from each corresponding cell using sensor data from the radar device and imaging data from the imaging system. A primary classifier determines whether an extracted feature extracted from a respective observation cell is an obstacle.

Abstract: A method for selecting an anchor lane for tracking in a vehicle lane tracking system. Digital map data and leading vehicle trajectory data are used to predict lane information ahead of a vehicle. Left and right lane boundary markers are also detected, where available, using a vision system. The lane marker data from the vision system is combined with the lane information from the digital map data and the leading vehicle trajectory data in a lane curvature fusion calculation. The left and right lane marker data from the vision system are also evaluated for conditions such as parallelism and sudden jumps in offsets, while considering the presence of entrance or exit lanes as indicated by the map data. An anchor lane for tracking is selected based on the evaluation of the vision system data, using either the fused curvature calculation or the digital map and leading vehicle trajectory data.

Abstract: A method of determining functionality of a vision-based imaging system for a vehicle includes capturing images by the vision-based imaging system. The images include landmarks that are identified in multiple images for distinguishing displacement of landmarks between the images. Edge maps for each of the images are generated. Like regions of at least two edge maps are compared for distinguishing displacement of a landmark between the at least two edge maps. Each pixel location of a first edge map is compared with a same pixel location of a second edge map for determining whether each compared pixel location has a different intensity value. An aggregate number of pixel locations having a different intensity value between the at least two edge maps is determined and compared to a threshold. An error message is generated in response to the aggregate number being less than the threshold.

Abstract: A method for dynamically registering a graphic upon a cropped image obtained from a camera device includes capturing an original image obtained from the camera device. Intrinsic calibration information for the camera device, extrinsic information for the camera device and vehicle information are monitored. The cropped image is generated based on cropping parameters to exclude undesirable content from the original image. The intrinsic calibration information is adjusted based on a relationship to the cropping parameters. The graphic is dynamically registered upon the cropped image based on the adjusted intrinsic calibration information for the camera device, the monitored extrinsic information for the camera device and the monitored vehicle information.

Abstract: A system and method for providing lane sensing on a vehicle by detecting roadway lane-markers, where the system employs multiple cameras providing images around the vehicle. The method includes detecting left-side and right-side lane boundary lines in the camera images, and then determining whether the lane boundary lines in the images are aligned from one image frame to a next image frame and are aligned from image to image. If the boundary lines are not aligned, then calibration of one or more of the cameras is performed, and if the lines are aligned, then a model fitting process is used to specifically identify the location of the boundary lines on the roadway.

Abstract: A system and method for providing lane sensing on a vehicle by detecting roadway lane-markers, where the system employs a surround view camera system providing a top-down view image around the vehicle. The method includes detecting left-side and right-side lane boundary lines in the top-down view image, and then determining whether the lane boundary lines in the image are aligned from one image frame to a next image frame and are aligned from image to image in the top-down view image. If the boundary lines are not aligned, then calibration of one or more of the cameras is performed, and if the lines are aligned, then a model fitting process is used to specifically identify the location of the boundary lines on the roadway.

Abstract: A turn assist system for a vehicle includes a transceiver configured to receive data corresponding to the location and motion of a nearby vehicle, a GPS receiver configured to generate location data representative of the location of the vehicle, a vehicle motion sensor configured to monitor one or more motion parameters of the vehicle, and a processor. The processor may be configured to: receive the location data and the vehicle motion data; maintain a plurality of motion paths within a database; map the location of the adjacent vehicle to one of the plurality of motion paths using the received data; and determine if the adjacent vehicle will obstruct the forward motion of the vehicle.

Abstract: A method, system and computer readable medium to autonomously keep a vehicle in a lane. The method including, engaging a lane centering system configured to maintain the vehicle within the lane, at a specified lane position. Further engaging a lane keeping system when the lane centering system fails to keep the vehicle within the lane, the lane keeping system configured to return the vehicle to the lane, when the vehicle leaves or is leaving the lane. And, applying a cost function to determine the nature of engagement of the lane keeping system to return the vehicle to the lane.

Abstract: A lane controller system installed on a vehicle may include components for self-diagnosing malfunctions on the vehicle. The system may include a desired path generator for generating a desired path that keeps the vehicle within a road lane; a steering controller for providing steering a steering correction to keep the vehicle within the road lane; a vehicle state estimator for estimating the state of the vehicle; a lane marking detector for detecting position of road lane markings; a path predictor for predicting a path actively followed by the vehicle; a virtual dynamics module for modeling the anticipated path of the vehicle following input of the steering controller; a comparer that compares the results of actual steering corrections applied with those predicted by the virtual dynamics module, and a diagnostic system that determines a root cause of malfunctions, based on the comparison by the comparer.

Abstract: A method, for controlling direction of a vehicle as desired in connection with operation of an autonomous driving maneuver using selectively, independently and/or in combination, multiple electrical park brakes (EPBs) and multiple hydraulic brakes (HBs). The method includes determining a total brake force needed for redirecting the vehicle in a pre-determined manner, and determining whether an applicable EPB can provide the total brake force needed. The method further includes providing, if it is determined that the applicable EPB can provide the total brake force needed, a brake command instructing the applicable EPB to apply the total brake force. The method also includes determining, if it is determined that the EPB is alone insufficient, an optimal fusion of the EPBs and the HBs, including two front and two rear HBs, two rear EPBs, and in some embodiments, also two front EPBs.

Abstract: Method for controlling a vehicle to maintain a desired position on a roadway includes monitoring roadway information behind the vehicle using a rearward detection device and monitoring vehicle sensor information. Frontward positional information is projected based on rearward positional information obtained from the monitored roadway information behind the vehicle. Forward roadway curvature is estimated based on the vehicle sensor information. Roadway information ahead of the vehicle is modeled based on the projected frontward positional information and the estimated forward roadway curvature to determine desired vehicle positional information. Future vehicle positional information is predicted with respect to the modeled roadway information based on the monitored vehicle sensor information and the estimated forward roadway curvature.

Abstract: A lane tracking system for a vehicle includes a front steering controller, a rear steering controller, and a lane tracking processor. The front steering controller is configured to rotate a front wheel of the vehicle through a front steering angle in response to a front steering torque command, and the rear steering controller is configured to rotate a rear wheel of the vehicle through a rear steering angle in response to a rear steering torque command. The lane tracking processor is configured to determine a desired course of the vehicle along a roadway, estimate a trajectory of the vehicle based on sensed vehicle motion, compute an error between the determined desired course and the estimated trajectory, and provide a front steering torque command to the front steering controller, and a rear steering torque command to the rear steering controller to minimize the computed error.