| CPC G06V 20/58 (2022.01) [B60W 40/105 (2013.01); H04W 88/10 (2013.01); B60W 2420/403 (2013.01); B60W 2420/408 (2024.01); B60W 2554/4041 (2020.02); B60W 2554/4049 (2020.02)] | 11 Claims |

|
1. An automobile vehicle visual wireless-based positioning system, comprising:
an automobile vehicle having a radio receiver and a transmitter;
a map containing candidate locations of access-points (APs) and access-point corresponding media-access-control (MAC) IDs, the map also identifying signal reflectors;
a vehicle on-board positioning system of the automobile vehicle collecting wireless positioning measurements from detected ones of the multiple Aps, the transmitter operating to transmit the wireless positioning measurements to a Cloud-Edge in real-time;
a wireless range sensor determining different multiple ranges of various detected APs visible to the automobile vehicle, wherein the multiple ranges for each of the various detected AP's includes a long-range measurement and a short-range measurement, and wherein the short-range measurement is shorter than the long-range measurement;
a MAC association process for associating a MAC ID with individual ones of the various detected APs at the different ranges;
a Line-of-Sight-No-Line-of-Sight (LOS-NLOS) association process performed on outputs from the MAC association process to resolve ambiguity between multiple AP locations to determine which identified AP is a real AP, the real AP defining an AP that does not include data from a reflection or data returned from one of the signal reflectors, wherein when one of the signal reflectors is disposed between a predicted automobile vehicle pose and a mapped AP location, then the long-range measurement is associated with that mapped AP such that the long-range measurement of the mapped AP defines a reflection, and when one of the signal reflectors does not fall between the predicted automobile vehicle pose and a mapped AP location, the short range measurements is associated with the mapped AP and the mapped AP defines a LOS feature;
an image collection feature identifying image data visible to the automobile vehicle;
an image feature extraction process receiving the image data to extract visual features from the image data;
a real-time feature matching process for matching the visual features with data from the map;
a data collection process, wherein vehicle data collected by the data collection process includes operating and location data from a vehicle inertial measurement unit (IMU). a vehicle wheel speed sensor (WSS), and a global positioning system (GPS) device; and
a filter receiving an output from the LOS-NLOS association process, an output from the real-time feature matching process element, and the vehicle data from the data collection process to generate an automobile vehicle pose.
|