Gm Global Technolgoy Operations, Inc.

Dmitriy Feldman

Paul A Adam

Xiaofeng Frank Song

Robert Charles Baraszu

Amanpal S Grewal

Kevin Austin O'Dea

James Nicholas Nickolaou

Daniel Gandhi

Xian Zhang

Siva Chinthalapudi

Shuqing Zeng

Jeffrey S Parks

Tetyana V Mamchuk

Shaun C Bowman

Kevin K Hoang

Ibrahim Riba

Yadollah Sabri

Joseph R Abrash

Satish Rayarapu

Namai P Kumara

Benjamin T Llewellyn

Carlo LoChirco

Chinar Dhamija

Presented are intelligent vehicle systems providing AV/ADAS driving features with enhanced on-vehicle sensor operation for mixed-gradient pathways, methods for making/using such systems, and vehicles equipped with such systems. A method of operating a host vehicle includes a vehicle controller receiving gradient data indicating the host vehicle is traversing a mixed-gradient pathway. After receiving the gradient data, first and second on-vehicle sensors detect a target vehicle forward of the host vehicle on the mixed-gradient pathway. After detecting the target, the vehicle controller determines whether or not both sensors dropped the target vehicle. Responsive to the target vehicle being dropped, the vehicle controller determines if the target vehicle is reacquired by only the first sensor and not the second sensor. If so, the vehicle controller responsively transmits one or more command signals to one or more resident subsystems of the host vehicle to suppress an automated driving operation of the host vehicle.

Intelligent vehicle systems and control logic for mitigating sensor limitations on mixed gradient paths

A method and system for tracking attached objects for controlling a vehicle. The method includes receiving, by a processor, sensor data of an environment associated with the vehicle that includes an object. The method includes determining, based on the sensor data, whether the object corresponds to an attached object type, and determining whether the sensor data includes a second vehicle. The method includes determining an attached object region associated with the second vehicle based on a distance between the second vehicle and the vehicle, and determining whether a position of the object is within the attached object region. The method includes determining whether a difference between a velocity of the object and a vehicle velocity of the vehicle is within a velocity threshold based on the distance. The method includes determining that the object is an attached object and controlling the vehicle based on the determining.

Methods and systems for tracking of attached objects

A method for controlling operation of a motor vehicle includes an electronic controller receiving, e.g., from a vehicle-mounted sensor array, sensor data with dynamics information for a target vehicle and, using the received sensor data, predicting a lane assignment for the target vehicle on a road segment proximate the host vehicle. The electronic controller also receives map data with roadway information for the road segment; the controller fuses the sensor and map data to construct a polynomial overlay for a host lane of the road segment across which travels the host vehicle. A piecewise linearized road map of the host lane is constructed and combined with the predicted lane assignment and polynomial overlay to calculate a lane assignment for the target vehicle. The controller then transmits one or more command signals to a resident vehicle system to execute one or more control operations using the target vehicle's calculated lane assignment.

Automated driving systems and control logic for lane localization of target objects in mapped environments

An autonomous vehicle and a system and method of operating the autonomous vehicle. The system includes a sensor and a processor. The processor determines an effective observation area of the sensor, the effective observation area being affected by an extrinsic condition. The processor determines an available time for performing a lane change based on the effective observation area and performs the lane change based on the available time.

Extrinsic characterization of detection capability to support automated lane change

A full speed range adaptive cruise control system for a host vehicle includes a plurality of sensors that each generate a signal, a memory that includes executable instructions and a processor that executes the executable instructions. The executable instructions enable the processor to detect a target vehicle as being stopped along a route based upon the signals from the plurality of sensors, cause the host vehicle to stop at a distance from the target vehicle, detect the target vehicle moving along the route after the host vehicle has stopped based upon the signals from the plurality of sensors, determine whether a first predetermined period of time has elapsed since the host vehicle has stopped, determine whether a first predetermined condition is satisfied if the first predetermined period of time has elapsed, and cause the host vehicle to move if the system determines that the first predetermined condition is satisfied.

Full speed range adaptive cruise control for a vehicle

Presented are automated driving systems for intelligent vehicle control, methods for making/using such systems, and motor vehicles equipped with such automated driving systems. A method for executing an automated driving operation includes: determining path plan data for a subject motor vehicle, including current vehicle location and predicted route data; receiving, from a network of sensing devices, sensor data indicative of current object position and object dynamics of a target object; applying sensor fusion techniques to the received sensor data to determine a threat confidence value that is predictive of target object intrusion with respect to the vehicle's location and predicted route; determining if this threat confidence value is greater than a calibrated threshold value; and, responsive to the threat confidence value being greater than the calibrated threshold value, transmitting one or more command signals to one or more vehicle systems (e.g., powertrain, steering and/or brake system) to take preventive action.

Automated driving systems and control logic using sensor fusion for intelligent vehicle control

A system according to the principles of the present disclosure includes a current object position module, an expected position module, and an object position comparison module. The current object position module can determine a first position of an object with respect to a position of a vehicle based upon sensor data generated by a first object detection sensor within the vehicle and determines a second position of the object with respect to the position of the vehicle based upon sensor data generated by a second object detection sensor. The expected object position module can determine an expected position of the object with respect to the position of the vehicle based upon the first position of the object. The object position comparison module can determine whether at least one object detection sensor is improperly installed within the vehicle based upon comparing the second position of the object with the expected position.

System and method for detecting improper sensor installation within a vehicle to mitigate hazards associated with object detection

A system for a vehicle operating on a road includes a vehicle placement module that references, based on a geographic position of the vehicle, a road mapping database to identify a selected lane of the road where the vehicle is located. A lane assignment module (i) receives information indicating identification of an object in the road and (ii) determines a relative lane of the object with respect to the selected lane. A curvature plotting module determines a curvature line of the selected lane. An object placement module (i) determines a first distance value representing a shortest distance between the object and the curvature line and (ii) determines whether the relative lane of the object is the selected lane based on the first distance value and a lane width value. An alert generation module selectively generates an alert signal in response to the object being in the selected lane.

Systems and methods for providing relative lane assignment of objects at distances from the vehicle

A method for assessing operation of a navigation system onboard a vehicle is provided. The method determines a sensor-based lateral offset change using vehicle onboard sensor data; determines a second lateral offset change using navigation system data; computes a difference between the sensor-based lateral offset change and the second lateral offset change; performs secondary calculations using the difference to produce a result; and when the result is greater than a threshold error value, provides an error notification.

Methods and apparatus for evaluating operation of a vehicle onboard navigation system using lateral offset data

A front impact mitigation system for a host vehicle and a method for operating a front impact mitigation system. The front impact mitigation system can take into account the position of a rear object that trails the host vehicle to develop a modified front impact mitigation control signal that at least partially mitigates the likelihood of certain rear impact collisions between the rear object and the host vehicle when the host vehicle is responding to the presence of an impending leading obstacle. A modified front impact mitigation control signal may be developed to account for the speed of the host vehicle and the distance that the rear object trails the host vehicle.

Front impact mitigation system for a vehicle and method

A method is disclosed for improved target grouping of sensor measurements in an object detection system. The method uses road curvature information to improve grouping accuracy by better predicting a new location of a known target object and matching it to sensor measurements. Additional target attributes are also used for improved grouping accuracy, where the attributes includes range rate, target cross-section and others. Distance compression is also employed for improved grouping accuracy, where range is compressed in a log scale calculation in order to diminish errors in measurement of distant objects. Grid-based techniques include the use of hash tables and a flood fill algorithm for improved computational performance of target object identification, where the number of computations can be reduced by an order of magnitude.

Target grouping techniques for object fusion

A method and system for controlling a position of a vehicle relative to other vehicles on a road is provided. The method includes controlling a position of a host vehicle travelling in a lane of a road using an automated driving system and monitoring positions of one or more side vehicles located on either side of the host vehicle and traveling in adjacent lanes. The method further includes detecting a condition in which the host vehicle is or will be positioned in a blind spot of a side vehicle disposed on in an adjacent lane and adjusting the position of the host vehicle in response to the condition using the automated driving system such that the amount of time the host vehicle is or will be positioned in the blind spot of the side vehicle is reduced.

Method and system for controlling vehicle with automated driving system

Methods, systems, and vehicles are provided for localizing a vehicle. A sensor is configured to detect an object disposed in a generally upward direction from the vehicle while the vehicle is travelling. A processor is coupled to the sensor. The processor is configured to correlate the object with information from a map database, thereby generating a correlation, and determine a geographic location of the vehicle based on the correlation.

Vehicle localization

A vehicle system and method that can determine object sensor misalignment while a host vehicle is being driven, and can do so without requiring multiple sensors with overlapping fields-of-view. In an exemplary embodiment where the host vehicle is traveling in generally a straight line, the present method uses an object sensor to track the path of a stationary object as it moves through the sensor's field-of-view and compares the sensed object path to an expected object pat*h. If the sensed and expected paths of the stationary object deviate by more than some amount, then the method determines that the object sensor is skewed or otherwise misaligned.

Growing community of inventors

West Bloomfield, MI, United States of America

Dmitriy Feldman