Delphi Technologies, Inc.

Hrl Laboratories, LLC

Aptiv Technologies Limited

Hughes Aircraft Company

Raytheon Company

Aptiv Technologies Ag

Hughes Electronics Corporation

Hughes Aircraft

David Aaron Schwartz

Jan Konried Schiffmann

David B Shu

Bin Jia

Lap-Wai Chow

Kumar Vishwajeet

Philip G Rosen

Sana Sarfraz

Yu Liu

James J Radigan

Lisa R Hamilton

Yuri Owechko

Mike Daily

Roy M Matic

Jan Siegemund

Krzysztof Wojtek Przytula

Nianxia Cao

Susan Chen

Amith Somanath

Anuradha Mangalgiri

Susan Yu-Ping Chen

John A Harding

Xumin Zhu

Henrik Clasen

This document describes techniques for performing track associations at least partially based on low confidence detections. For object trackers, which rely on measurement detections that are associated with a reported confidence, there is no direct tradeoff between a true positive track rate and a false positive track rate that applies to improving the accuracy of state estimates of tracks. To increase the true positive track rate while reducing the false positive track rate, a parameter is maintained for each track. Referred to as Probability of Existence (PoE), it is an estimate of likelihood that a real object exists with a true state that approximates an estimated state for that track. By considering PoE in combination with the reported confidence in the measurement detections being used, object tracking using radar and other sensors technologies is improved, so real-objects are reported more-quickly and accurately, and false objects are reported less often.

Track associations at least partially based on low confidence detections

This document describes radar tracking with model estimates augmented by radar detections. An example tracker analyzes information derived using radar detections to enhance radar tracks having object measurements estimated from directly analyzing data cubes with a model (e.g., a machine-learning model). High-quality tracks with measurements to objects of importance can be quickly produced with the model. However, the model only estimates measurements for classes of objects its training or programming can recognize. To improve estimated measurements from the model, or even in some cases, to convey additional classes of objects, the tracker separately analyzes detections. Detections that consistently align to objects recognized by the model can update model-derived measurements conveyed initially in the tracks. Consistently observed detections that do not align to existing tracks may be used to establish new tracks for conveying more classes of objects than the model can recognize.

Radar tracking with model estimates augmented by radar detections

This document describes techniques, apparatuses, and systems for a grid-based road model with multiple layers. An example road-perception system generates a roadway grid representation that includes multiple cells. The road-perception system uses data from multiple information sources to generate a road model that includes multiple layers. Each layer represents a roadway attribute of each cell in the grid and includes one or more layer hypotheses. In this way, the described techniques and systems can provide an accurate and reliable road model and quantify uncertainty therein.

Grid-based road model with multiple layers

This document describes techniques and systems to make determinations of lane-type and roadway hypotheses in a road model. The road-perception system can fuse various forms of evidence to determine lane-type hypotheses and respective belief masses associated with the lane-type hypotheses. The road-perception system the computes, using the belief masses, a belief parameter and a plausibility parameter associated with the lane-type hypotheses. One or more roadway hypotheses are then determined using the lane-type hypotheses. The road-perception system then uses the respective belief parameter and plausibility parameter associated with the lane-type hypotheses to compute a belief parameter and a plausibility parameter associated with the roadway hypotheses. In this way, the described techniques and systems can provide an accurate and reliable road model with quantified uncertainty.

Lane-type and roadway hypotheses determinations in a road model

An illustrative example method is for estimating a friction characteristic of a surface beneath a vehicle that has a plurality of wheels contacting the surface. The method includes determining a wheel speed of at least one of the wheels, determining a velocity of the at least one of the wheels separately from determining the wheel speed, determining a wheel slip of the at least one of the wheels based on the determined wheel speed and the determined velocity, and determining the friction characteristic based on the determined wheel slip. Determining the velocity separately from the wheel speed is accomplished using at least one detector that provides an output corresponding to a range rate, such as a RADAR or LIDAR detector.

Driving surface friction characteristic determination

In accordance with one embodiment, a radar system with auto-alignment suitable for use in an automated vehicle is provided. The system includes a radar-sensor, a speed-sensor, and a controller. The radar-sensor is used to detect objects present in a field-of-view proximate to a host-vehicle on which the radar-sensor is mounted. The radar-sensor is operable to determine a measured-range-rate (dRm), a measured-azimuth-angle (Am), and a measured-elevation-angle (Em) to each of at least three objects present in the field-of-view. The speed-sensor is used to determine a measured-speed (Sm) of the host-vehicle. The controller is in communication with the radar-sensor and the speed-sensor. The controller is configured to simultaneously determine a speed-scaling-error (Bs) of the measured-speed, an azimuth-misalignment (Ba) of the radar-sensor, and an elevation-misalignment (Be) of the radar-sensor based on the measured-range-rate, the measured-azimuth-angle, and the measured-elevation-angle to each of the at least three objects, while the host-vehicle is moving.

Automated vehicle radar system with auto-alignment for azimuth, elevation, and vehicle speed-scaling-error

An object detection system for an automated vehicle includes a radar, a camera, and a controller. The radar detects a cluster of targets characterized by a radar-distance (x) from the host-vehicle. The camera renders an image of an object and a lane-marking present in the area. The controller is configured to determine an equation that is a function of a longitudinal-distance from the host-vehicle and corresponds to the lane-marking, determine a first-optical-angle (&#x3b8;) based on a first-image-distance between a reference-point on the object and a spot on the image indicated by the equation where the longitudinal-distance is equal to the radar-distance, determine a lateral-distance (Dist_LM) between the object and the lane-marking based on the first-optical-angle and the radar-distance, and determine a first-lateral-offset (y) between the object and a longitudinal-axis of the host-vehicle based on the lateral-distance and a first-value of the equation where the longitudinal-distance is equal to the radar-distance.

Automated vehicle object detection system with camera image and radar data fusion

A method and apparatus are presented for performing wavelet transforms, post transform processing and inverse wavelet transforms whereby hardware complexity is reduced and processor performance is enhanced by performing the forward and inverse wavelet transformations and post transform processing in variable precision arithmetic. Optimal decreases in the operational arithmetic precision of different wavelet scale coefficients, multiplication and weighting operations, and other operations, results in reduced computational complexity, increased speed, and in some cases better signal to noise ratios.

Variable precision wavelets

An improved probabilistic lane assignment method for detected objects in the scene forward of a host vehicle. Road/lane model parameters, preferably including an angular orientation of the host vehicle in its lane, are estimated from host vehicle sensor systems, taking into account measurement uncertainty in each of the constituent parameters. A probabilistic assignment of the object's lane is then assessed based on the road/lane model parameters and object measurements, again taking into account measurement uncertainty in both the road/lane model and object measurements. According to a first embodiment, the probabilistic assignment is discrete in nature, indicating a confidence or degree-of-belief that the detected object resides in each of a number of lanes. According to a second embodiment, the probabilistic assignment is continuous in nature, providing a lateral separation distance between the host vehicle and the object, and a confidence or degree-of-belief in the lateral separation distance.

Probabilistic lane assignment method

A method of lane marker detection and detection fitting is provided for lane tracking. A lane marker is modeled and split into left and right steps. A filter response is calculated from a cumulative row sum, and normalized for filter pixel size, lane marker brightness and road brightness. A lane marker response is peak detected for positive and negative peaks and checked for having a magnitude above a threshold and being a local peak in a five point neighborhood. A Hough transform is extended to multiple planes to use lane marker features to determine a best line. Lane marker features include a mean and variance of lane marker brightness, lane marker width, lane marker parallelism to a host vehicle direction of travel, and consistence with a predicted lane marker characteristic. A closest lane marker line to a host vehicle is identified, and refitted to account for any curvature.

Lane marker detection and fitting methods

A method for estimating unknown parameters (pan angle (&#x3c8;), instantaneous tilt angle (&#x3c4;) and road geometry of an upcoming road segment) for a vehicle object detection system. The vehicle object detection system is preferably a forward looking, radar-cued vision system having a camera, a radar sensor and an processing unit. The method first estimates the pan angle (&#x3c8;), then corrects the coordinates from a radar track so that pan angle (&#x3c8;) can be treated as zero, and finally solves a least squares problem that determines best estimates for instantaneous tilt angle (&#x3c4;) and road geometry. Estimating these parameters enables the vehicle object detection system to identify, interpret and locate objects in a more accurate and efficient manner.

Method for estimating unknown parameters for a vehicle object detection system

Lane marker coordinate data obtained from a previous frame of a vehicle vision system is projected into the current video frame based on measured translation and rotation of the host vehicle. The projected lane marker coordinate data is consolidated with lane marker coordinate data from the current video frame for lane detection or display applications.

Lane marker projection method for a motor vehicle vision system

A method, apparatus, and computer program product are provided for calculating an indicator of operator distraction for an equipment operator. First, distraction-correlated indicator information from devices around an operator is received. Next, a distraction level is estimated. Subsequently, an output is produced indicative of the distraction level to facilitate a threat assessment decision. Additional operations may include grouping information into complex task types comprising sets of related activities. Next, an elapsed time is determined since the start of the first activity in a complex task. The delay since the most recent activity in the complex task is compared with a minimum task quiescent period. When the delay exceeds the minimum task quiescent period, the elapsed time and the delay are reset. Also, during the performance of a complex task, the type and the elapsed time of the complex task are correlated with other information to facilitate a threat assessment decision.

Method and apparatus for calculating an operator distraction level

A method and an apparatus are presented for selectively locking controls from operators operating equipment. The invention actively detects when an operator accesses a control for which lockout is desired. After detection, the invention locks the control to prevent the operator from operating the control. Thus, operators are permitted selective access to controls. The active detection of when an operator is accessing a control is performed by first generating a signal, which is passed to a plate, where it is then coupled through the operator to a receiver. The signal is detected at a signal detector attached with a control so the control can react to the signal. In an automotive situation, the plate may be in a vehicle seat, with the signal coupling through a driver or passenger upon actuation of a control. Based on the signal received, the function of the control may be eliminated, altered, or reduced.

Growing community of inventors

Moorpark, CA, United States of America

David Aaron Schwartz