Gm Global Technolgoy Operations, Inc.

Shengbing Jiang

Xinyu Du

Yilu Zhang

Wen-Chiao Lin

Chaitanya Sankavaram

Atul Nagose

Mutasim Abdurrahman Salman

Shiming Duan

Meng Jiang

Sandeep Menon

Shuqing Zeng

Youssef A Ghoneim

Erik B Golm

Steven W Holland

Jiyu Zhang

Xiaoyu Huang

Mutasim A Salman

Aaron B Bloom

Brian L Buck

Zifeng Peng

Paul Edward Krajewski

Jinsong Wang

Yao Hu

Prakash Mohan Peranandam

Varsha K Sadekar

Azeem Sarwar

Mohamed A Layouni

Qi Zhang

Rod Niner

Joshua J Sanchez

Natalie Ann Wienckowski

Zhongyu Yang

Katrina M Schultz

David Gumpert

Michael B Gastmeier

Prakash Mohan Peranadam

Aleksey Nogin

James K Thomas

Kevin A Cansiani

Rasoul Salehi

David A Frank

Michael A Sowa

Scott A McCullough

John J Flood, Iv

Matthew Darin

Muralikrishnan Kailasam

Dongyi Zhou

Janelle Kane Rolando

Kenneth P Orlando

Paul A Krajewski

Eric J Baur

Sidi Lu

Aaron D Motyl

A vehicle includes a system and method of operating the vehicle. The system includes a camera, a map database and a processor. The camera obtains camera data of a location of a road being traversed by the vehicle. The map database provides map data of the location of the road. The processor determines a first curvature of the road at the location from the camera data, determines a second curvature of the road at the location from the map data, identifies a mismatch between the first curvature and the second curvature at the location of the road, generates a case report for one of the map data and the camera data at the location upon occurrence of the mismatch, and adjusts one of the map data and a confidence level in the camera data for the location based on the case report.

Self adaptive enhancement for automated driving with map and camera issues

A system and method for diagnosing vehicle battery health using electrode potential estimation is presented. A first set of anode electrode potentials and a first set of cathode electrode potentials of a pristine vehicle battery cell are determined at a first charge rate. A second set of anode electrode potentials and a second set of cathode electrode potentials of a pristine vehicle battery cell are determined at a second charge rate. A determination of a set of optimized health indicators are made based on the first set of anode electrode potentials, the first set of cathode electrode potentials, the second set of anode electrode potentials, and the second set of cathode electrode potentials. Testing a vehicle battery is administered, based on the optimized health indicators, after a first number of cycles to determine a faulty one or more cells of the vehicle battery.

Vehicle battery health diagnostics by electrode potential estimation

A vehicle, and a system and method of navigating the vehicle. The system includes a camera and a processor. The camera obtains an image of a road upon which the vehicle is moving. The processor is configured to extract a feature of the road from the image, perform a lane detection algorithm to detect a set of lane markers in the road using the image and the feature, and move the vehicle along the road by tracking the set of lane markers.

Mitigation strategies for lane marking misdetection

A vehicle, system method for operating the vehicle is disclosed. The system includes a camera and a processor. The camera is configured to obtain a camera image of a road segment. The processor determines a location of a road edge for the road segment within the camera image, obtains a lane attribute for the road segment, generates a virtual lane mark for the road segment based on the road edge and the lane attribute, and moves the vehicle along the road segment by tracking the virtual lane mark.

Virtual lane mark generation

A process for local traffic approximation through analysis of cloud data is provided. The process includes, within a computerized traffic flow estimation controller of a host vehicle, operating programming to monitor a planned navigational route of the host vehicle, identify along the planned navigational route a road section including cross-traffic, monitor cloud data related to a mobile cellular device, analyze the cloud data to identify traffic posing a hazardous condition to the host vehicle within the road section, and generate a vehicle alert to a driver of the host vehicle based upon the identified traffic.

Process and system for local traffic approximation through analysis of cloud data

A system includes a first most probable cause (MPC) module, a second MPC module, and an integrated MPC module. The first MPC module is configured to determine a first most probable cause of an issue on a vehicle based on at least one service procedure for the vehicle. The second MPC module is configured to determine a second most probable cause of the issue based on repair data for other vehicles. The integrated MPC module is configured to determine an integrated most probable cause of the issue based on the first and second most probable causes.

System and method for determining most probable cause of vehicle fault using multiple diagnostic techniques

A first network device includes a transceiver, a memory and a control module. The transceiver receives an integrated model from a second network device that is separate from the first network device. The memory stores the integrated model and diagnostic trouble code data, most probable cause data, and least probable cause data, which have corresponding cause of issue indications for an issue of a vehicle. The control module while executing the integrated model: compares the cause of issue indications to determine whether the cause of issue indications are consistent such that a same cause of issue is indicated; in response to the cause of issue indications being consistent, displays the same cause of issue, and in response to the cause of issue indications being inconsistent and based on a set of conditions, displays a portion of health related information while refraining from displaying another portion of the health related information.

Selective health information reporting systems including integrated diagnostic models providing least and most possible cause information

A system includes a diagnostic step module and an optimal diagnostic procedure module. The diagnostic step module is configured to identify diagnostic steps of a service procedure to be performed to diagnose a root cause of a fault on a vehicle based on a diagnostic trouble code identifying the fault, and identify a cost associated with performing each of the diagnostic steps. The optimal diagnostic procedure module is configured to determine an order in which to perform the diagnostic steps that minimizes the cost of diagnosing the fault, and output an optimal diagnostic procedure that indicates the diagnostic steps and the order in which to perform the diagnostic steps.

System and method for generating diagnostic procedure for vehicle fault based on most probable causes

A mirror assembly includes a mirror housing and a mirror. The mirror is supported by the mirror housing. The mirror has an outer reflective surface. The mirror is bendable between a flat shape and a fisheye shape. The mirror assembly further includes an actuator assembly coupled to the mirror. Upon actuation, the actuator assembly is configured to bend the mirror between the flat shape and the fisheye shape to adjust a field of view of the mirror.

Shape changing mirror

Methods and systems to implement sensor fusion to determine collision potential for a vehicle include identifying a specific intersection that the vehicle is approaching, and identifying collision potential scenarios associated with one or more paths through the specific intersection. Each collision potential scenario defines a risk of a collision between the vehicle and an object in a specified area. A weight with which one or more information sources of the vehicle are considered is adjusted for each collision potential scenario such that a highest weight is given to one or more of the one or more information sources that provide most relevant and reliable information about the specified area. Sensor fusion is implemented based on the adjusting the weight of the one or more information sources and performing detection based on the sensor fusion, and an alert is provided or actions are implemented according to the detection.

Sensor fusion based on intersection scene to determine vehicle collision potential

A method and system of diagnosing and suggesting least probable faults for an exhibited vehicle failure. The method includes initiating a vehicle health management (VHM) algorithm to monitor a state of health (SOH) for at least one vehicle component at each vehicle operating event over a predetermined time period. The VHM algorithm determines at least one of a Green SOH, a Yellow SOH, and a Red SOH designation with a confidence level for the at least one vehicle component; calculating a number of Green SOH designations (N) over the predetermined time period; and upon an exhibited vehicle failure, providing a least probable cause indication for the at least one component when a set of conditions are met. The set of conditions includes (i) Nis equal to or greater than a predetermined number of Green SOH designations and (ii) no Yellow SOH and Red SOH designations are present.

Method of enhanced component failure diagnosis for suggesting least probable fault

A system and method for determining the presence of a hidden hazard may include identification of an operational scene for a host vehicle, and identification of an operational situation for the host vehicle. Information from a plurality of proximity sensors is collected and classified. A plurality of hidden hazard presence probabilities corresponding to the information from each of the plurality of proximity sensors, the operational scene, the operational situation, and at least one of a comparative process and a dynamic neural network process are estimated. A fusion process may be performed upon the plurality of hidden hazard presence probabilities to determine the presence of a hidden hazard.

Hidden hazard situational awareness

A control system for identifying and responding to effective system changes in a monitored system includes data collection, change identification, classifier construction, effective system change and parameter adjustment modules. The data collection module tracks parameters of the monitored system. The change identification module, based on the parameters, identifies: during training, performance changes and first system changes; and post training, a set of performance changes and second system changes. The classifier construction module, based on the performance changes and the first system changes construct a performance-system change classifier module. The performance-system change classifier module, based on the set of performance changes, determines possible system changes and respective probability values. The effective system change module, based on the second and possible system changes, determines effective system changes and respective probability values. The parameter adjustment module controls an actuator of the monitored system based on the effective system changes and the probability values.

Data-driven approach for effective system change identification

A method of root cause diagnosis of fault data from a vehicle includes identifying a first vehicle fault and selecting from field repair data a vehicle feature corresponding to the identified first vehicle fault. The method also includes identifying from the field repair data an effective repair of the identified first vehicle fault. The method additionally includes training and testing via a machine learning algorithm, a labor code classifier using the identified effective repair of the first vehicle fault and the selected vehicle feature corresponding to the identified first vehicle fault. The method also includes identifying and classifying, using the trained classifier, indistinguishable labor codes. Furthermore, the method includes communicating the identified and classified indistinguishable labor codes for diagnosing a root cause of real time first vehicle fault data. A computer-readable medium storing an executable computer algorithm for performing the root cause diagnosis of vehicle fault data is also envisioned.

Vehicle fault root cause diagnosis

A system includes control modules, a low-voltage communications bus, e.g., a CAN bus of a vehicle, a voltage sensor that measures a bus voltage and outputs 2.5-3.5 VDC high-data and 1.5-2.5 VDC low-data, and a host electronic control unit (ECU). The host ECU detects a recoverable fault using a data pattern in the bus voltage data when the data is outside of a calibrated range, and recalibrates the sensor. Recalibration may be by adjustment to a scaling factor and/or a bias value. Non-recoverable 'stuck-at-fault'-type or 'out-of-range'-type faults may be detected using the pattern, as may be a ground offset fault. A method includes measuring the bus voltage using the sensor, comparing the output data to a range to detect the fault, and isolating a sensor fault as a recoverable fault using the data pattern when the data is outside of the range. The sensor is then be recalibrated.

Analog-to-digital fault detection, isolation, and mitigation for a low-voltage communications network

Growing community of inventors

Rochester Hills, MI, United States of America

Shengbing Jiang