Abstract: A system and method for calculating a virtual target path that is used to calculate an evasive steering path around a target object, such as a target vehicle, stopped in front of a subject vehicle. The method includes determining a potential field using a plurality of scan points that is a summation of two-dimensional Gaussian functions, where each Gaussian function has center defined by target object scan points and other object scan points. The method identifies a mesh grid in an X-Y plane where the mesh grid includes mesh grid points at locations where X and Y plane lines cross. The method identifies a local minimum point of the potential field for each X-plane line at each mesh grid point along the Y-plane crossing that X-plane line, where the local minimum point is a curve point. The method then connects the curve points to define the target path.

Abstract: A method for determining an actual trajectory of a vehicle using object detection data and vehicle dynamics data. An object detection system identifies point objects and extended objects in proximity to the vehicle, where the point objects are less than a meter in length and width. An updated vehicle pose is calculated which optimally transposes the point objects in the scan data to a target list of previously-identified point objects. The updated vehicle pose is further refined by iteratively calculating a pose which optimally transposes the extended objects in the scan data to a target model of previously-identified extended objects, where the iteration is used to simultaneously determine a probability coefficient relating the scan data to the target model. The updated vehicle pose is used to identify the actual trajectory of the vehicle, which is compared to a planned path in a collision avoidance system.

Abstract: A method of detecting and tracking objects for a vehicle traveling in a narrow space. Estimating a host vehicle motion of travel. Objects exterior of the vehicle are detected utilizing object sensing devices. A determination is made whether the object is a stationary object. A static obstacle map is generated in response to the detection of the stationary object detected. A local obstacle map is constructed utilizing the static obstacle map. A pose of the host vehicle is estimated relative to obstacles within the local obstacle map. The local object map is fused on a vehicle coordinate grid. Threat analysis is performed between the moving vehicle and identified objects. A collision prevention device is actuated in response to a collision threat detected.

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 method of calibrating multiple vehicle-based image capture devices of a vehicle. An image is captured by at least one image capture device. A reference object is identified in the captured image. The reference object has known world coordinates. Known features of the vehicle are extracted in the captured image. A relative location and orientation of the vehicle in world coordinates is determined relative to the reference object. Each of the multiple image capture devices is calibrated utilizing intrinsic and extrinsic parameters of the at least one image capture device as a function of the relative location and orientation of the vehicle in world coordinates.

Abstract: A method for calculating a virtual target path around a target object that includes providing scan points identifying detected objects and separating the scan points into target object scan points and other object scan points. The method identifies a closest scan point from the target object scan points and identifies a path point that is a predetermined safe distance from the closest scan point. The method determines a straight target line adjacent to the target object that goes through the path point, and determines a distance between the target line and each of the other objects and determines whether all of the distances are greater than a predetermined threshold distance. The method identifies curve points for each other object whose distance is less than the predetermined threshold distance, and identifies a curve path that connects the curve points to be the virtual target path using a quadratic polynomial function.

Abstract: A method of diagnosing a state of health of a vision-based lane sensing system. A first misalignment factor is calculated as a function of a vehicle lateral offset and a vehicle heading. A second misalignment factor is calculated as a function of a vehicle speed, an estimated curvature of an expected path of travel, a lane curvature, and the vehicle heading. Histograms are generated for the first and second misalignment factors. A probability of a state of health is determined. A determination is made whether the probability of the state of health is within a predetermined threshold. An angle misalignment of the vision system is estimated. The angle misalignment of the vision system is corrected in response to the determination that the probability of the state of health is within the predetermined threshold; otherwise a warning of a faulty lane sensing system is actuated.

Abstract: A method of autonomously convoying vehicles traveling along a route with a leader vehicle being in communication with at least one follower vehicle. The at least one follower vehicle receives a communication relating to a target offset position and route data. Tracking data is generated and derived from on-board sensing devices of the at least one follower vehicle that includes a traveled path of the leader vehicle sensed by the at least one follower vehicle. The route data is compared to the tracking data for identifying accuracy between the route data relative to the tracking data. An adjusted target offset position and a set of trajectory points that provides a trajectory path of travel from a current position of the at least one follower vehicle to the adjusted target offset position are determined based on the accuracy between the route data and the tracking data.

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 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: Methods and systems for determining a misalignment angle for a sensor in a vehicle are provided. The method, for example, may include, but is not limited to determining, by a processor, when an object detected in sensor data acquired by the sensor is a stationary object, and calculating, by the processor, the misalignment angle of the sensor based upon sensor data associated with the stationary object.

Abstract: A lane tracking system for tracking the position of a vehicle within a lane includes a camera configured to provide a video feed representative of a field of view and a video processor configured to receive the video feed from the camera and to generate latent video-based position data indicative of the position of the vehicle within the lane. The system further includes a vehicle motion sensor configured to generate vehicle motion data indicative of the motion of the vehicle, and a lane tracking processor. The lane tracking processor is configured to receive the video-based position data, updated at a first frequency; receive the sensed vehicle motion data, updated at a second frequency; estimate the position of the vehicle within the lane from the sensed vehicle motion data; and fuse the video-based position data with the estimate of the vehicle position within the lane using a Kalman filter.

Abstract: A method and system may determine the estimated location of a vehicle, measure a location of an object relative to the vehicle using a sensor associated with the vehicle, and determine an updated vehicle location using the measured relative object location in conjunction with previously stored object locations. The estimated vehicle location may be determined using a system different from that associated with the sensor, for example a GPS system. The object location may be measured relative to a sub-map corresponding to the location of the vehicle.

Abstract: A system and method for fusing the outputs from multiple LiDAR sensors on a vehicle. The method includes providing object files for objects detected by the sensors at a previous sample time, where the object files identify the position, orientation and velocity of the detected objects. The method also includes receiving a plurality of scan returns from objects detected in the field-of-view of the sensors at a current sample time and constructing a point cloud from the scan returns. The method then segments the scan points in the point cloud into predicted clusters, where each cluster initially identifies an object detected by the sensors. The method matches the predicted clusters with predicted object models generated from objects being tracked during the previous sample time. The method creates new object models, deletes dying object models and updates the object files based on the object models for the current sample time.

Abstract: A system and method for fusing the outputs from multiple LiDAR sensors on a vehicle that includes cueing the fusion process in response to an object being detected by a radar sensor and/or a vision system. The method includes providing object files for objects detected by the LiDAR sensors at a previous sample time, where the object files identify the position, orientation and velocity of the detected objects. The method projects object models in the object files from the previous sample time to provide predicted object models. The method also includes receiving a plurality of scan returns from objects detected in the field-of-view of the sensors at a current sample time and constructing a point cloud from the scan returns. The method then segments the scan points in the point cloud into predicted scan clusters, where each cluster identifies an object detected by the sensors.

Abstract: A method and system for computing lane curvature and a host vehicle's position and orientation relative to lane boundaries, using image data from forward-view and rear-view cameras and vehicle dynamics sensors as input. A host vehicle includes cameras at the front and rear, which can be used to detect lane boundaries such as curbs and lane stripes, among other purposes. The host vehicle also includes vehicle dynamics sensors including vehicle speed and yaw rate. A method is developed which computes lane curvature and the host vehicle's position relative to a lane reference path, where the lane reference path is derived from the lane boundaries extracted from a fusion of the front and rear camera images. Mathematical models provided in the disclosure include a Kalman filter tracking routine and a particle filter tracking routine.

Abstract: A method of detecting and tracking objects using multiple radar sensors. Objects relative to a host vehicle are detected from radar data generated by a sensing device. The radar data includes Doppler measurement data. Clusters are formed, by a processor, as a function of the radar data. Each cluster represents a respective object. Each respective object is classified, by the processor, as stationary or non-stationary based on the Doppler measurement data of each object and a vehicle speed of the host vehicle. Target tracking is applied, by the processor, on an object using Doppler measurement data over time in response to the object classified as a non-stationary object; otherwise, updating an occupancy grid in response to classifying the object as a stationary object.

Abstract: A method and system may operate a coupled range imager and intensity imager to obtain a sequence of at least two automatically registered images, each automatically registered image including concurrently acquired range data and intensity data with regard to an imaged scene. The registered range and intensity data is analyzed to yield an estimated motion of an element of an imaged object of the imaged scene.

Abstract: Methods and systems for dynamically prioritizing target areas to monitor around a vehicle are provided. The system, for example, may include, but is not limited to a sensor, a global positioning system receiver, and a processor communicatively coupled to the sensor and the global positioning system receiver. The processor is configured to determine a location of the vehicle and based upon data from the global positioning system receiver, determine a projected path the vehicle is traveling upon, prioritize target areas based upon the determined location, heading and the projected path, and analyze data from the sensor based upon the prioritized target areas.

Abstract: A method for calculating a virtual target path around a target object that includes providing scan points identifying detected objects and separating the scan points into target object scan points and other object scan points. The method identifies a closest scan point from the target object scan points and identifies a path point that is a predetermined safe distance from the closest scan point. The method determines a straight target line adjacent to the target object that goes through the path point, and determines a distance between the target line and each of the other objects and determines whether all of the distances are greater than a predetermined threshold distance. The method identifies curve points for each other object whose distance is less than the predetermined threshold distance, and identifies a curve path that connects the curve points to be the virtual target path using a quadratic polynomial function.