Abstract: A system and method for selectively reducing or filtering data provided by one or more vehicle mounted sensors before using that data to detect, track and/or estimate a stationary object located along the side of a road, such as a guardrail or barrier. According to one example, the method reduces the amount of data by consolidating, classifying and pre-sorting data points from several forward looking radar sensors before using those data points to determine if a stationary roadside object is present. If the method determines that a stationary roadside object is present, then the reduced or filtered data points can be applied to a data fitting algorithm in order to estimate the size, shape and/or other parameters of the object. In one example, the output of the present method is provided to automated or autonomous driving systems.

Abstract: A method of ordering memory access by an instruction cache of a central processing unit on a global memory device. A signal list of a link map file is extracted in the global memory device. Memory access traces relating to executed tasks are accessed from the signal list. Memory locations accessed in the global memory device from the access traces are identified. A correlation value for each pair of memory locations accessed in the global memory device is determined. Correlation values of the pairs of memory locations are determined, wherein the correlation values are computed based on a proximity of executable instructions utilizing the respective pair of memory locations. Accessed memory locations within the global memory device are reordered as a function of the determined correlation values. An executable file accessing the global memory device is modified.

Abstract: A system and method are provided for detecting remote vehicles relative to a host vehicle using wheel detection. The system and method include tracking wheel candidates based on wheel detection data received from a plurality of object detection devices, comparing select parameters relating to the wheel detection data for each of the tracked wheel candidates, and identifying a remote vehicle by determining if a threshold correlation exists between any of the tracked wheel candidates based on the comparison of select parameters.

Abstract: Examples of techniques for road feature detection using a vehicle camera system are disclosed. In one example implementation, a computer-implemented method includes receiving, by a processing device, an image from a camera associated with a vehicle on a road. The computer-implemented method further includes generating, by the processing device, a top view of the road based at least in part on the image. The computer-implemented method further includes detecting, by the processing device, lane boundaries of a lane of the road based at least in part on the top view of the road. The computer-implemented method further includes detecting, by the processing device, a road feature within the lane boundaries of the lane of the road using machine learning.

Abstract: A method and system are disclosed for tracking a remote vehicle which is driving in a lateral position relative to a host vehicle. Target data from two radar sensors are provided to an object detection fusion system. Wheels on the remote vehicle are identified as clusters of radar points with essentially the same location but substantially varying Doppler range rate values. If both wheels on the near side of the remote vehicle can be identified, a fusion calculation is performed using the wheel locations measured by both radar sensors, yielding an accurate estimate of the position, orientation and velocity of the remote vehicle. The position, orientation and velocity of the remote vehicle are used to trigger warnings or evasive maneuvers in a Lateral Collision Prevention (LCP) system. Radar sensor alignment can also be calibrated with an additional fusion calculation based on the same wheel measurement data.

Abstract: A method of determining a surface condition of a path of travel. A plurality of images is captured of a surface of the path of travel by an image capture device. The image capture device captures images at varying scales. A feature extraction technique is applied by a feature extraction module to each of the scaled images. A fusion technique is applied, by the processor, to the extracted features for identifying the surface condition of the path of travel. A road surface condition signal provide to a control device. The control device applies the road surface condition signal to mitigate the wet road surface condition.

Abstract: A positioning method includes acquiring global positioning system (GPS) position data associated with a mobile platform from a plurality of GPS satellites observable by the mobile platform. A set of wireless range measurements associated with the mobile platform and a plurality of wireless access points in communication with the mobile platform are acquired. The method further includes receiving, from a server communicatively coupled to the mobile platform over a network, wireless position data associated with the plurality of wireless access points. A corrected position of the mobile platform is determined based on the wireless position data, the wireless range measurements, and the GPS position data.

Abstract: A positioning method for a mobile platform includes acquiring GPS position data associated with the mobile platform from a plurality of GPS satellites observable by the mobile platform. A set of wireless range measurements associated with the mobile platform and a plurality of wireless access points in communication with the mobile platform are received (e.g., via time-of-flight measurements). Wireless position data associated with the plurality of wireless access points is received from a server communicatively coupled to the mobile platform over a network. A corrected position of the mobile platform based on the wireless position data, the wireless range measurements, and the GPS position data.

Abstract: A method and sensor system are disclosed for automatically determining object sensor position and alignment on a host vehicle. A radar sensor detects objects surrounding the host vehicle in normal operation. Static objects are identified as those objects with ground speed approximately equal to zero. Vehicle dynamics sensors provide vehicle longitudinal and lateral velocity and yaw rate data. Measurement data for the static objects—including azimuth angle, range and range rate relative to the sensor—along with the vehicle dynamics data, are used in a recursive geometric calculation which converges on actual values of the radar sensor's two-dimensional position and azimuth alignment angle on the host vehicle.

Abstract: A system and method are provided for detecting and identifying elongated objects relative to a host vehicle. The method includes detecting objects relative to the host vehicle using a plurality of object detection devices, identifying patterns in detection data that correspond to an elongated object, wherein the detection data includes data fused from at least two of the plurality of object detection devices, determining initial object parameter estimates for the elongated object using each of the plurality of object detection devices, calculating object parameter estimates for the elongated object by fusing the initial object parameter estimates from each of the plurality of object detection devices, and determining an object type classification for the elongated object by fusing the initial object parameter estimates from each of the plurality of object detection devices.

Abstract: A system and method for correcting bias and angle misalignment errors in the angle rate and acceleration outputs from a 6-DOF IMU mounted to a vehicle. The method includes providing velocity and estimation attitude data in an inertial frame from, for example, a GNSS/INS, and determining an ideal acceleration estimation and an ideal rate estimation in a vehicle frame using the velocity and attitude data. The method then determines the IMU bias error and misalignment error using the ideal acceleration and rate estimations and the angle rate and acceleration outputs in an IMU body frame from the IMU.

Abstract: A system and method are provided for detecting remote vehicles relative to a host vehicle using wheel detection. The system and method include tracking wheel candidates based on wheel detection data received from a plurality of object detection devices, comparing select parameters relating to the wheel detection data for each of the tracked wheel candidates, and identifying a remote vehicle by determining if a threshold correlation exists between any of the tracked wheel candidates based on the comparison of select parameters.

Abstract: A system and method for correcting bias and angle misalignment errors in the angle rate and acceleration outputs from a 6-DOF IMU mounted to a vehicle. The method includes providing velocity and estimation attitude data in an inertial frame from, for example, a GNSS/INS, and determining an ideal acceleration estimation and an ideal rate estimation in a vehicle frame using the velocity and attitude data. The method then determines the IMU bias error and misalignment error using the ideal acceleration and rate estimations and the angle rate and acceleration outputs in an IMU body frame from the IMU.

Abstract: A method for autonomously aligning a tow hitch ball on a towing vehicle and a trailer drawbar on a trailer through a human-machine interface (HMI) assisted visual servoing process. The method includes providing rearview images from a rearview camera. The method includes touching the tow ball on a display to register a location of the tow ball in the image and touching the drawbar on the display to register a location of a target where the tow ball will be properly aligned with the drawbar. The method provides a template pattern around the target on the image and autonomously moves the vehicle so that the tow ball moves towards the target. The method predicts a new location of the target as the vehicle moves and identifies the target in new images as the vehicle moves by comparing the previous template pattern with an image patch around the predicted location.

Abstract: An active vision system includes an image capture device for capturing images in a region exterior of a vehicle and a headlamp control unit for controlling a vehicle headlamp beam for illuminating an environment exterior of a vehicle. The headlamp control unit is configured to selectively illuminate between making a path of travel of a road visible to a driver of the vehicle and making the region exterior of the vehicle visible for capturing images by the image capture device. The headlamp control unit utilizes a duty cycle for controlling a first cycle time that the headlamp beam illuminates the path of travel for making the road visible to the driver and for controlling a second cycle time that the headlamp beam makes the captured region visible for capturing images by the image capture device.

Abstract: A method of ordering memory access by an instruction cache of a central processing unit on a global memory device. A signal list of a link map file is extracted in the global memory device. Memory access traces relating to executed tasks are accessed from the signal list. Memory locations accessed in the global memory device from the access traces are identified. A correlation value for each pair of memory locations accessed in the global memory device is determined. Correlation values of the pairs of memory locations are determined, wherein the correlation values are computed based on a proximity of executable instructions utilizing the respective pair of memory locations. Accessed memory locations within the global memory device are reordered as a function of the determined correlation values. An executable file accessing the global memory device is modified.

Abstract: A method of partitioning tasks on a multi-core ECU. A signal list of a link map file is extracted in a memory. Memory access traces relating to executed tasks are obtained from the ECU. A number of times each task accesses a memory location is identified. A correlation graph between the each task and each accessed memory location is generated. The correlation graph identifies a degree of linking relationship between each task and each memory location. The correlation graph is re-ordered so that the respective tasks and associated memory locations having greater degrees of linking relationships are adjacent to one another. The tasks are partitioned into a respective number of cores on the ECU. Allocating tasks and memory locations among the respective number of cores is performed as a function of substantially balancing workloads with minimum cross-core communication among the respective cores.

Abstract: Methods and systems are provided for detecting an object. In one embodiment, a method includes: receiving, by a processor, image data from an image sensor; receiving, by a processor, radar data from a radar system; processing, by the processor, the image data from the image sensor and the radar data from the radar system using a deep learning method; and detecting, by the processor, an object based on the processing.

Abstract: An embodiment contemplates a method of calibrating multiple image capture devices of a vehicle. A plurality of image capture devices having different poses are provided. At least one of the plurality of image capture devices is identified as a reference device. An image of a patterned display exterior of the vehicle is captured by the plurality of image capture devices. The vehicle traverses across the patterned display to capture images at various instances of time. A processor identifies common landmarks of the patterned display between each of the images captured by the plurality of image capture devices and the reference device. Images of the patterned display captured by each of the plurality of image devices are stitched using the identified common landmarks. Extrinsic parameters of each image capture device are adjusted relative to the reference device based on the stitched images for calibrating the plurality of image capture devices.

Abstract: A rear cross traffic avoidance system includes an object detection device sensing remote objects rearward of a host vehicle. An object classifier distinguishes a remote dynamic object from remote static objects. The object classifier identifies a shape of the dynamic object. A tracking system tracks the remote dynamic object. A processor determines the remote object being on an intersecting path to the remote vehicle. The processor determines a warning threat assessment as a function of a time to intersect between the host vehicle and the remote dynamic object. The processor determines a brake threat assessment in response to an actuated warning of a collision. A brake actuation system actuates a braking operation for mitigating the collision.