| CPC G08G 1/164 (2013.01) [G08G 1/0116 (2013.01); G08G 1/166 (2013.01)] | 20 Claims |
|
1. A system comprising:
one or more processors programmed or configured to:
receive data associated with road environment object-actor sensor based detection and classification predictions, IEEE 1609 standard Security Credential Management System (SCMS) cryptographically signed SAE J2735 standard Basic Safety Messages (BSM)/Cooperative Awareness Messages (CAM), and IEEE 1609 standard SCMS cryptographically signed SAE J3224 standard Sensor Data Sharing Messages (SDSM); and
determine run-time detection, classification, and tracking of object-actors in the road operating environment in relation to a system relative coordinate reference map,
wherein for the determining detection, classification, and tracking of object-actors, the one or more processors are programmed or configured to:
extract object-actor associated data in the received SCMS cryptographically signed SAE J2735 participant broadcasted Basic Safety Messages/Cooperative Awareness Messages from which an object-actor's pose is determined, wherein the received data includes, but is not limited to a reported object-actor's real-time kinematic GNSS corrected position, spatial dimensions, including a length, a width and/or a height, and the categorical-type classification of the object-actor, wherein the BSM/CAM extracted data is transformed into a format to store and retrieve the represented object-actor as an artifact within a system relative coordinate reference map;
extract object-actor associated data in received SCMS cryptographically signed SAE J3224 participant broadcast Sensor Data Sharing Messages (SDSM), wherein the received data may include an external observers' report of a sensed object-actor's position, category-type classification, timestamp of observation, and location in GNSS based global coordinates, and wherein the SDSM extracted data is transformed into a format to store and retrieve the represented object-actor as an artifact within a system relative coordinate reference map;
predict object-actors presence and pose present within the fields of view of the one or more sensors of the system; wherein the predicted object-actor output is sent to the system relative coordinate reference map as a predicted object-actor artifact;
determine the existence of an actual object-actor in the road environment associated with representative object-actor artifacts in the system relative coordinate reference map, wherein one or more procedures and/or machine learning models determine that two or more artifacts correspond to the same object-actor,
wherein a minimum of one of the two or more artifacts is associated with a received BSM/CAM data upon which one or more algorithms and or machine learning models establishes the existence of a relationship between two or more object-actor representative artifacts, wherein a matched pair or set of artifacts containing a BSM/CAM based artifact is reduced to a ground truth object-actor in the system reference map, and the match reference is applied to crossmatched artifacts to construct a ground truth object-actor artifact to reside in the applicable state within the system relative coordinate reference map, when no sensor associated object-actor artifacts are identified as a match to a BSM/CAM artifact the BSM/CAM is established as a ground truth perception object-actor,
wherein in the absence of a BSM/CAM associated artifact but there exists representative object-artifacts based on predicted perception data and/or SDSM messages, measure the artifacts' parameters in relation to each other with respect to the system relative coordinate system map wherein the module with one or more algorithms and or machine learning models establishes the existence of a match between two or more object-actor representative artifacts and determines confidence level of a crossmatch between two or more object-actor artifacts, where the parameters used to determine crossmatch include but are not limited to object-actor classification category-type, position, velocity, and acceleration;
determine confidence levels on object-actor predicted detection, classification, and tracking, wherein measurement of the accuracy of aggregate weighted prediction of object-actor detection classification and tracking over the course of preceding and the current run-time outputs with available BSM/CAM based object-actor data artifacts determines the error between predicted vs actual detection, classification, and tracking, wherein the measured accuracies are persisted in system memory for reference in subsequent run-time operation, wherein the measured accuracy established from received BSM/CAM data based artifacts is determined as an objective comparison to measure internal generated predicted perception, external generated SDSMs, and the aggregate combinations thereof against actual detection and classification, and tracking parameter values, wherein the system determines a confidence interval based on a priori and runtime updated thresholds of accuracy, wherein associated thresholds are comprised of parameter value ranges determined to meet statistically significant precision requirements that indicate low uncertainty about a predicted value and merit the use of the underlying predicted value for perception runtime use in a road environment, wherein the outputs are confidence intervals for the crossmatched object-actor's current reconciled state parameter values including indication of high confidence for the predicted object-actor associated state values or high-confidence that the system's perception is unable to detect, classify, and track object-actors within threshold range,
wherein with the ground truth or otherwise matched perception process predicted or SDSM reported object-actor precursor artifacts used to determine match are removed from the reference map, wherein the output of the matched artifacts with corresponding map update is an aggregate reconciled collection of run-time determined ground truth and high confidence detection, classification, and tracking of object-actors in the road environment, wherein the system relative coordinate reference map updates to reflect the determined state for subsequent system runtime use and/or external transmission of ground truth data; and
persist the matched object-actors artifacts as ground truth or high confidence determined object-actors in the system relative reference coordinate map which subsequently are logged with crossmatched and reconciled data including confidence level attributes associated with Basic Safety Messages/Cooperative Awareness Messages, Sensor Data Sharing Messages and road environment sensor-perception data.
|