Collaborative sensing metric map

By generating sensing metric maps and processing GNSS and cellular connection quality information, the connection problems caused by poor occlusion and signal coverage in vehicle navigation are solved, and navigation accuracy and communication stability are improved.

CN118936492APending Publication Date: 2024-11-12FORD GLOBAL TECH LLC
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410520180.X
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Priority Date
2023-05-09
Filing Date
2024-04-28
Publication Date
2024-11-12

AI Technical Summary

Technical Problem

The prior art is difficult to effectively deal with connection deterioration or obstruction caused by occlusion and poor signal coverage in vehicle navigation, affecting position accuracy and vehicle operation characteristics.

Method used

By generating sensing metric maps, collecting and processing Global Navigation Satellite System (GNSS) coverage quality, cellular connection quality and occlusion information, we generate collaborative sensing metric maps based on these data for navigating bypassing bad connection areas or optimizing vehicle operations .

Benefits of technology

Improves the navigation accuracy and reliability of the vehicle in a bad signal environment, ensures that the vehicle can accurately locate and avoid areas that affect connections, and enhances the communication stability between the vehicle and the user.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118936492A_ABST
    Figure CN118936492A_ABST
Patent Text Reader

Abstract

The present disclosure provides a "collaborative sensing metric map". A system and method for collaborative sensing metric map generation includes receiving a sensing metric data set from a first plurality of vehicles for each of a plurality of nodes of a region of interest having an assigned region. It is determined, for each node, whether a first threshold number of sensing metric data sets sufficient to provide sensing metrics for the node has been received in a previous predetermined window of time. Upon expiration of a predetermined period of time, a sensing metric map of the region of interest is provided to a second plurality of vehicles based on a sensing metric data set received in the previous predetermined time window.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present disclosure relates to systems and methods for collaborative sensing metric map generation. Background Art

[0002] Ground vehicles may include features that utilize satellite-based location information, occluder detection, and wireless connectivity (e.g., to remote or "cloud" servers, infrastructure nodes, user devices, etc.). Satellite and cellular wireless connectivity may degrade or be blocked at various locations for various reasons (such as obstructing objects, poor signal coverage at a location, etc.). Factors affecting connectivity (such as occluders, strength of cellular coverage, etc.) may change over time. For example, degraded or blocked connectivity or new occluders may affect the operation of features that rely on accurate knowledge of maps and / or location accuracy of the vehicle's location. Summary of the invention

[0003] The present disclosure provides for generating a sensing metric map of an area of ​​interest (e.g., an area in which a vehicle may operate). In this context, a sensing metric is data indicating the quality of a connection at a location, an indication of whether the vehicle's location is accurately known, detected obstructions, and / or any other signal of interest that may provide information about the operation of a vehicle at a location. Exemplary sensing metrics include whether cellular coverage exists at a location or its strength, the accuracy of location data at a location, and the presence of detected obstructions that may affect vehicle operation. In general, a sensing metric may be any data that may be used as an indication of vehicle connectivity, vehicle location accuracy, or the location of a vehicle relative to an obstruction. The vehicle may then be actuated based at least in part on the sensing metric map, such as navigating around obstructed areas or areas of poor connectivity when the operation depends on features of such connectivity, or allowing certain features only when the sensing metric meets certain thresholds.

[0004] In one or more embodiments, a system may include a computer having a processor and a memory, the memory storing instructions executable by the processor and programmed to: receive a sensing metric data set from a first plurality of vehicles for each of a plurality of nodes having an assigned area in an area of ​​interest; determine for each node whether a first threshold number of sensing metric data sets sufficient to provide sensing metrics for the node has been received in a last predetermined time window; and upon expiration of a predetermined time period, provide a sensing metric map of the area of ​​interest to a second plurality of vehicles based on the sensing metric data sets received in the last predetermined time window.

[0005] An embodiment may also include instructions for determining, for each node, whether a second threshold number of sensing metric data sets sufficient to mark the node as having a status of full has been received in the last predetermined time window.

[0006] In one embodiment, a smaller percentage of the sensing metrics in the sensing metric data set may be received from the vehicle for nodes whose status is marked as full in the sensing metric map.

[0007] In another embodiment, the sensing metric map may provide sensing metric data for nodes having at least the first threshold number of sensing metric data sets within the last predetermined time window.

[0008] In further embodiments, the sensing metric dataset may include indicators of global navigation satellite system (GNSS) coverage quality, cellular connection quality, and / or identified occluders.

[0009] In one embodiment, the sensing metric dataset may include indicators of global navigation satellite system (GNSS) coverage quality, cellular connection quality, and identified obstructions, and the maximum time gap between the recorded position of the vehicle and the generation of the sensing metric by the vehicle may be a predetermined number of milliseconds (e.g., 200ms).

[0010] In other embodiments, the GNSS coverage quality may be latitude, longitude, altitude, and geometric dilution of precision (GDOP), the cellular connection quality may be round trip time (RTT), reference signal strength indication (RSSI), and / or packet error rate (PER), and the identified obstructions may be true / false detections or probabilities of obstructions and sensor sources.

[0011] In another embodiment, the sensing metric data set may include a vehicle make, model, and year; and when sufficient sensing metric data sets are received for a specific node that defines specific node data within the predetermined time window for a vehicle of a specific make, model, and year, instructions may be included for performing the following operations: providing a sensing metric map of the area of ​​interest specific to the corresponding vehicle by replacing the generalized node data with the specific node data.

[0012] In one embodiment, the area of ​​interest may be a road segment or a parking area, and the nodes may be spaced apart within a predetermined range of meters (eg, spaced between 5m and 25m).

[0013] In other embodiments, the first predetermined time window and the predetermined time period may be preconfigurable days.

[0014] One or more embodiments of a method for collaborative sensing metric map generation may include: receiving a sensing metric data set from a first plurality of vehicles for each of a plurality of nodes having an assigned area in an area of ​​interest; determining for each node whether a first threshold number of sensing metric data sets sufficient to provide sensing metrics for the node has been received in a last predetermined time window; and upon expiration of a predetermined time period, providing a sensing metric map of the area of ​​interest to a second plurality of vehicles based on the sensing metric data sets received in the last predetermined time window.

[0015] An embodiment of the method may also include determining, for each node, whether a second threshold number of sensing metric data sets sufficient to mark the node as having a status of full has been received in the last predetermined time window.

[0016] In one embodiment, a smaller percentage of the sensing metrics in the sensing metric data set may be received from the vehicle for nodes whose status is marked as full in the sensing metric map.

[0017] In another embodiment, the sensing metric map may provide sensing metric data for nodes having at least the first threshold number of data points within the last predetermined time window.

[0018] In further embodiments, the sensing metric dataset may include indicators of global navigation satellite system (GNSS) coverage quality, cellular connection quality, and / or identified occluders.

[0019] In one embodiment, the sensing metric dataset may include indicators of global navigation satellite system (GNSS) coverage quality, cellular connection quality, and identified obstructions, and the maximum time gap between the recorded position of the vehicle and the generation of the sensing metric by the vehicle may be a predetermined number of milliseconds (e.g., 200ms).

[0020] In other embodiments, the GNSS coverage quality may be latitude, longitude, altitude, and geometric dilution of precision (GDOP), the cellular connection quality may be round trip time (RTT), reference signal strength indication (RSSI), and / or packet error rate (PER), and the identified obstructions may be true / false detections or probabilities of obstructions and sensor sources.

[0021] In one embodiment, the sensing metric data set may include a vehicle make, model, and year; and when sufficient sensing metric data sets are received for a specific node defining specific node data within the predetermined time window for a vehicle of a specific make, model, and year, it may include providing a sensing metric map of the area of ​​interest specific to the corresponding vehicle by replacing the generalized node data with the specific node data.

[0022] In another embodiment, the area of ​​interest may be a road segment or a parking area, and the nodes may be spaced apart within a predetermined range of meters (eg, spaced between 5m and 25m).

[0023] In other embodiments, the predetermined time window and the predetermined time period may be preconfigurable days. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figure 1 is an illustration of an exemplary system for collaborative sensing metric map generation.

[0025] Figure 2A is an exemplary illustration of a survey vehicle path through a nodal area of ​​an area of ​​interest being mapped.

[0026] Figure 2B is an exemplary flow chart of a vehicle survey process.

[0027] Figure 3 is an exemplary graph illustrating data collection for collaborative sensing metric map generation.

[0028] Figure 4 is an exemplary flow chart of a process for collaborative sensing metric map generation.

[0029] Figure 5A is an exemplary illustration of an autonomous vehicle path through a nodal area of ​​an area of ​​interest that has been mapped.

[0030] Figure 5B is an exemplary flow chart of a process for vehicles to use collaborative sensing to measure maps. DETAILED DESCRIPTION

[0031] refer to Figure 1 , the connected vehicle system 100 may provide communications between the vehicle 102 , a global navigation satellite system (GNSS) satellite 115 , and / or a central computer 120 .

[0032] The vehicle 102 is a set of components or parts used to perform a function or a set of operations in the vehicle 102, including hardware components, and typically also software and / or programming. The vehicle subsystem 106 typically includes a braking system, a propulsion system, and a steering system, as well as other subsystems, including but not limited to a body control system, a climate control system, a lighting system, and a human-machine interface (HMI) system that may include a head-up display (HUD), an instrument panel, and an infotainment system. The propulsion subsystem converts energy into rotation of the wheels of the vehicle 102 to propel the vehicle 102 forward and / or backward. The braking subsystem can slow down and / or stop the movement of the vehicle 102. The steering subsystem can control the yaw of the vehicle 102 as it moves, such as turning left and right, and maintaining a straight path.

[0033] The vehicle 102 may also include an advanced driver assistance system 105 (ADAS). The ADAS system 105 may include various driver assistance technologies (DAT) and autonomous vehicle (AV) technologies, such as lane keeping assist (LKA), lane centering assist (LCA), intelligent adaptive cruise control (iACC), automatic lane change, automatic parking assist, blind spot information system (BLIS), and autonomous valet parking (VaPa).

[0034] The computer including one or more vehicle computers 104 discussed herein (e.g., one or more electronic control units (ECUs)) and the central computer 120 includes a corresponding processor and memory. The computer memory may include one or more forms of computer-readable media and store instructions that can be executed by the processor for performing various operations (including operations as disclosed herein). For example, the computer may be a general-purpose computer with a processor and memory as described above, and / or an ECU, controller, etc. for a specific function or a set of functions, and / or a dedicated electronic circuit including an ASIC manufactured for a specific operation, such as an ASIC for processing sensor data and / or transmitting sensor data. In another example, the computer may include an FPGA (field programmable gate array), which is an integrated circuit manufactured to be configurable by a user. Typically, hardware description languages ​​such as VHDL (very high speed integrated circuit hardware description language) are used in electronic design automation to describe digital and mixed signal systems such as FPGAs and ASICs. For example, an ASIC is manufactured based on VHDL programming provided before manufacturing, and the logic components inside the FPGA can be configured based on, for example, VHDL programming stored in a memory electrically connected to the FPGA circuit. In some examples, a combination of a processor, an ASIC, and / or an FPGA circuit may be included in the computer.

[0035] The computer memory may be of any suitable type, for example, EEPROM, EPROM, ROM, Flash, hard drive, solid state drive, server, or any volatile or non-volatile medium. The memory may store data, such as the memory of an ECU. The memory may be a device separate from the computer, and the computer may retrieve information stored in the memory, for example, one or more computers 104 may obtain the data to be stored via a vehicle network 112 in the vehicle 102 (e.g., via an Ethernet bus, a CAN bus, a wireless network, etc.). Alternatively or in addition, the memory may be part of the computer, i.e., as a firmware of a memory or a programmable chip of the computer.

[0036] One or more vehicle computers 104 (e.g., one or more ECUs) may be included in a vehicle 102, which may be any suitable type of ground vehicle 102, such as a passenger car or commercial vehicle, such as a sedan, coupe, truck, sport utility vehicle, crossover, van, minivan, etc. As part of a driver assistance system or advanced driver assistance system (ADAS), the vehicle computer 104 may include programming to operate one or more of braking, propulsion (e.g., by controlling acceleration of the vehicle 102 and controlling power delivery therefrom by controlling one or more of an internal combustion engine (ICE), an electric motor, a hybrid ICE / electric propulsion device, etc.), steering, climate control, interior and / or exterior lights, etc. of the vehicle 102 and determine whether and when the computer controls such operations as compared to a human operator, such as by sending vehicle data over a vehicle network 112. Additionally, the vehicle computer 104 may be programmed to determine whether and when a human operator controls such operations.

[0037] The vehicle computer 104 may include or be communicatively coupled to (e.g., via a vehicle network 112, such as a communication bus as further described below) more than one processor, for example, the more than one processor is included in the sensors 108 and cameras 107 included in the vehicle 102, electronic controller units (ECUs), etc., for monitoring and / or controlling various vehicle components, such as a powertrain controller, a brake controller, a steering controller, etc. The computer is typically arranged for communication on the vehicle 102 communication network, which may include a bus in the vehicle 102, such as a controller area network (CAN), etc., and / or other wired and / or wireless mechanisms. Alternatively or in addition, in the case where the computer actually includes multiple devices, the vehicle network 112 can be used for communication between devices represented as computers in this disclosure.

[0038] The vehicle network 112 is a network via which messages can be exchanged between various devices in the vehicle 102. The vehicle computer 104 can generally be programmed to send and / or receive messages from other devices in the vehicle 102 (e.g., any or all of ECUs, sensors, cameras, actuators, components, communication modules, human-machine interfaces HMI, etc.) via the vehicle network 112. Additionally or alternatively, messages can be exchanged between various such other devices in the vehicle 102 via the vehicle network 112. In the case where the vehicle computer 104 includes multiple devices, the vehicle network 112 can be used for communication between devices represented as computers in the present disclosure. In some embodiments, the vehicle network 112 can be a network in which messages are communicated via a vehicle 102 communication bus. For example, the vehicle network 112 may include a CAN in which messages are communicated via a controller area network (CAN) bus, or a LIN in which messages are communicated via a local interconnect network (LIN) bus. In some embodiments, the vehicle network 112 may include a network in which messages are communicated using other wired communication technologies and / or wireless communication technologies (e.g., Ethernet, Wi-Fi, Bluetooth, ultra-wideband (UWB), etc.). In some embodiments, additional examples of protocols that can be used to communicate via the vehicle network 112 include, but are not limited to, Media Oriented Systems Transport (MOST), Time Triggered Protocol (TTP), and FlexRay. In some embodiments, the vehicle network 112 can represent a combination of multiple networks that may be of different types that support communication between devices in the vehicle 102. For example, the vehicle network 112 can include: CAN, where some devices in the vehicle 102 communicate via a CAN bus; and a wired or wireless local area network, where some devices in the vehicle 102 communicate according to Ethernet or WI-FI communication protocols.

[0039] The vehicle computer 104, the user device 118, and / or the central computer 120 may communicate via the wide area network 116. In addition, the various computing devices discussed herein may communicate directly with each other, such as via direct radio frequency communication according to a protocol such as Bluetooth. For example, the vehicle 102 may include a communication module 110 for providing communications with devices and / or networks not included as part of the vehicle 102, such as, for example, GNSS satellites 115 and the wide area network 116. The communication module 110 may provide various communications, such as vehicle-to-vehicle (V2V), vehicle-to-infrastructure or outside (V2X), or vehicle-to-outside (including cellular communications (C-V2X)) wireless communications cellular, dedicated short range communications (DSRC), etc., generally providing communications to another vehicle or infrastructure via direct radio frequency communications, and / or generally providing communications to, for example, the central computer 120 via the wide area network 116. The communication module 110 may include one or more mechanisms by which the vehicle computer 104 may communicate, including any desired combination of wireless (e.g., cellular, wireless, satellite, microwave, and radio frequency) communication mechanisms and any desired network topology (or multiple topologies when multiple communication mechanisms are utilized). Exemplary communications provided via the module may include cellular, Bluetooth, IEEE 802.11, DSRC, Cellular V2X (CV2X), etc.

[0040] The vehicle 102 according to the present disclosure includes a plurality of cameras 107 and sensors 108 that can support driver assistance or ADAS functions. For example, the sensor 108 may include, but is not limited to, one or more wheel speed sensors, steering angle sensors, GNSS sensors, ultrasonic parking assistance sensors, short-range radars, medium-range radars, lidar sensors, light sensors, rain sensors, accelerometers, wheel torque sensors, inertial sensors, yaw rate sensors, etc., and the camera 107 may include, but is not limited to, a forward camera, a side camera, and a rear camera. The sensor 108 and the camera 107 may support functions that sometimes use cameras in conjunction with detailed map building data to detect lane lines, road curvature, parking lines, and obstructions. The sensor 108 and the camera 107 may also support lane keeping assist (LKA) or lane centering assist (LCA) functions using one or more cameras and steering angle sensors for detecting lane lines, or support driving assistance functions using one or more cameras, steering angle or position sensors, and driver monitoring system cameras (DMSC) for detecting lane lines or monitoring blind spots as part of BLIS. The sensors 108 and the camera 107 may also support an adaptive cruise control (ACC) function that uses wheel speed sensors / GNSS and / or cameras / lidars / mid-range radars to support an automatic following distance function. The sensors 108 and the camera 107 may also support an intelligent adaptive cruise control (iACC) function that uses accelerometers, wheel speed sensors / GNSS, cameras, and / or lidars / radars to support a cruise control function that changes the speed of the vehicle based on detected speed limits, acceleration, and road curvature. The sensors 108 and the camera 107 may support a parking assist function that uses wheel speed sensors, steering sensors, cameras, and / or ultrasonic sensors. The sensors 108 and the camera 107 may support, for example, autonomous steering features, valet parking features, speed control features, and / or some other features that use GNSS positioning, cameras, radars, lidars, ultrasonic sensors, and the like.

[0041] The central computer 120 may be connected to a map database 122. Data may be received by the central computer 120 from the communication modules 110 of the vehicles 102 via the wide area network 116 and stored in the database 122 for access and use by the central computer 120, such as for generating the collaborative sensing metric map disclosed herein. The data from the vehicle 102 may include global navigation satellite system (GNSS) data (longitude, latitude, altitude, geometric dilution of precision, etc.), cellular connection data (round trip time (RTT), reference signal strength indication (RSSI), packet error rate (PER), etc.), and occluder data (true / false detection or probability of specific objects (such as walls and pillars in a parking lot), as well as top clearance data, curb height data, etc.). Data from other vehicles may similarly be received by the central computer 120 via the wide area network 116 and stored in the map database 122. Data from one or more vehicles 102 may be used to generate a collaborative sensing metric map, as further described below. The collaborative sensing metric map may then be provided to the vehicle 102 to support various features (such as a valet parking feature) and provide sensor calibration information.

[0042] Referring to FIG2 , an example of sensing metric collection for collaborative sensing metric map generation of an area of ​​interest 200 is shown. A collaborative sensing metric map is a map of an area of ​​interest (such as a road segment or parking lot in which a vehicle 102 may operate) that is periodically generated based on data received (i.e., crowdsourced) from multiple vehicles within a recent time window. In addition to information about the location of lanes, curbs, parking spaces, ramps, entrances, exits, etc. of a standard navigation map, a sensing metric map in the context of the present disclosure also includes recent data indicating global navigation satellite system (GNSS) coverage quality, cellular connection quality, and / or identified obstructions. For example, for a latitude and longitude location on a collaborative sensing metric map, GNSS coverage quality may be indicated by geometric dilution of precision (GDOP, typically defined as Δ(output position) / Δ(measurement data) or the ratio of position error to range error, and indicating the effect of the geometry of the satellites used on the position error), cellular connection quality may be indicated by round trip time (RTT), reference signal strength indication (RSSI), and / or packet error rate (PER), and the location of an identified occluder (with optional sensor sources such as radar / lidar / ultrasonic / camera / etc.) at or near the location. Based on the collected sensing metric data collected for a location or area (as described below), the various data included in the map may be average values, means, sum scores, normalized values ​​relative to the mean, etc. of GDOP, RTT / RSSI, PER, and the presence or absence of an occluder for each node.

[0043] exist Figure 2AIn the present invention, an area of ​​interest 200 can be surveyed by a central computer 120, which defines a plurality of nodes 210-224 with assigned areas 230-244 to cover an area of ​​interest on a navigation map (such as a road segment of a parking area). As used herein, a "node" in an area of ​​interest is a geometric point within the area of ​​interest, and a corresponding assigned area is an area defined by a set of points (i.e., an area) that is closest to a particular node. Although shown as squares based on the illustrated grid-like spacing of the nodes 210-224, the associated areas 230-244 can take other shapes based on determining the area closest to a particular node. In addition, although shown as a regular grid with continuous nodes, the nodes 210-224 can be irregularly spaced, typically between 5 meters and 25 meters, and can be defined only for areas (i.e., road segments, parking lots, driveways, etc.) where the vehicle is expected to operate. It is possible for the nodes to be spaced less than 5 meters apart, but it has been found that when the nodes are less than 5 meters together, it is unreasonable to increase the granularity of the determined sensing metrics by increasing data collection and retention or storage. It is also possible for nodes to be more than 25 meters apart, but it has been found that distances between nodes greater than 25 meters may result in insufficient granularity for applications currently supported in vehicles 102 (i.e., there may be undetected blind spots therein). In general, nodes may be positioned in any suitable manner to ensure adequate coverage of an area of ​​interest. For example, a substantially evenly spaced grid of nodes may be used for large areas of interest, such as parking lots, additional or more closely spaced nodes may be used for irregular areas or high traffic areas, and nodes may be spaced apart along a road segment (such as along a centerline) in a manner that follows the curvature of the road segment.

[0044] To collaboratively collect sensing metrics to generate a collaborative sensing metrics map (CSMM), vehicles 102 (among a plurality of such vehicles) may travel on a survey path 202 through node regions, in this example regions 240, 241, 242, 237, 238, 233, and 234 of nodes 220, 221, 222, 217, 218, 213, and 214 of interest for mapping. The sensing metrics collected on the survey path 202 by the computer 104 of the vehicle 102 may include, but are not limited to: vehicle brand / model / year, UTC time, sensing metrics selected from the following: round trip time, reference signal strength, packet error rate, detected GNSS-only 3-D position (latitude, longitude, altitude), dilution of precision (DOP), cellular coverage / provider and actual 3-D position using onboard sensors, detected occluders (true / false or probabilistic), and sensor source (camera / lidar / radar / ultrasonic). In order to know the location of nodes and / or node areas, the vehicle 102 will typically have an initial collaborative sensory metric map (CSMM) with defined nodes or a previously published CSMM with sensory metric data for defined nodes. The nodes in the CSMM can have a represented state, such as insufficient, sufficient, or full, as discussed below; the initial unpopulated CSMM can mark all nodes as "N / A" (not applicable because it only defines nodes) or insufficient. A later published CSMM can have nodes marked as insufficient, sufficient, or full, as discussed further below, to inform the vehicle 102 how to process the collected sensory metric data set.

[0045] When traveling through an area associated with a node, the sensors 108 and / or camera 107 of the vehicle 102 may sense or detect selected sensing metrics, such as GNSS data (longitude, latitude, altitude, geometric dilution of precision, etc.), cellular connectivity data (round trip time (RTT), reference signal strength indication (RSSI), packet error rate (PER), etc.), and occlusion data (e.g., a binary yes / no or true / false value or a probability indicating that an object has been detected in the area 230-244). In order for the cellular connectivity and occlusion data to be useful in generating a collaborative sensing metric map, the cellular connectivity and occlusion data should be collected at a vehicle location reported within a predetermined number of milliseconds (e.g., 200ms) by a position sensor that provides GNSS data indicating the vehicle location within the area of ​​the node. The vehicle 102 can time-stamp the collected data and can transmit the data to the central computer 120 immediately or within a set time period (such as 72 hours) to allow the vehicle 102 to transmit data when it is more convenient or efficient (such as when parked, connected to Wi-Fi, or during off-peak usage).

[0046] If a node has been marked as "F" or full due to having a full sensing metric dataset count based on the number of datasets collected for that node in a recent time window (e.g., 100 in the past 30 days), such as Figure 2A 220, 221, and 222, the computer 104 of the vehicle 102 may randomly eliminate a percentage of the sensed metrics transmitted to the central computer 120 in order to reduce bandwidth usage of the vehicle 102 and the central computer 120 and to reduce storage usage by the map database 122. For example, for the node 220 marked as full, the vehicle 102 may randomly eliminate 80% of the sensed metric data sets transmitted to the central computer 120 for the sensed metrics collected within the area 240. The full sensed metric data set count may be based on a predetermined number of sets of sensed metric data sets, such as greater than or equal to 100, collected from the vehicle within the last predetermined number of days, such as 30 days.

[0047] For nodes with sufficient sensed metric data set counts marked as "S" or sufficient, such as nodes 217 and 218 of FIG. 2, the computer 104 of the vehicle 102 can collect all sensed metric data sets and transmit them to the central computer 120 for storage in the map database 122. The sufficient sensed metric data set count can be based on collecting a predetermined number of sets of sensed metric data sets from the vehicle within the last predetermined first number of days (such as 30 days), such as greater than or equal to 10 but less than 100. The sufficient sensed metric data set count can also depend on the information in the sensed metric data set, because some sensed metrics (such as object detection) may have a freshness time that becomes outdated quickly. For nodes with insufficient sensed metric data set counts marked as "I" or insufficient, such as nodes 213 and 214 of FIG. 2, the computer 104 of the vehicle 102 can collect all sensed metric data sets and transmit them to the central computer 120 for storage in the map database 122. The insufficient sensed metric data set count can be based on collecting less than a predetermined number of sets of sensed metric data sets from the vehicle within the predetermined previous number of days (such as 30 days), such as less than 10. If a node has a status of insufficient, any available metrics may or may not be included in the published CSMM.

[0048] The vehicle 102 may also transmit its make, model, and year information along with the sensing metrics to allow for the generation and use of a collaborative sensing metric map with node data specific to a particular make / model / year when a sufficient number of sensing metric data sets are received from vehicles of a particular make / model / year for a particular node. This vehicle-specific granularity may be particularly useful since each vehicle make / model / year may have its own specific sensing suite and RF antenna.

[0049] Figure 2BAn example process 250 is shown for vehicle 102 to perform a survey.

[0050] The process 250 begins in box 252 where the computer 104 of the vehicle 102 obtains a CSMM populated with at least a description of the region of interest 200 and the region with its corresponding nodes.

[0051] In the next box 255 , the computer 104 determines the location of the vehicle 102 , for example from a GNSS-based sensor 108 , such as a GPS sensor.

[0052] In block 260, the computer 104 determines whether the location is within a node region of the CSMM's region of interest 200. If not, the process returns to block 255 to continue location monitoring.

[0053] If it is determined at block 260 that the location is within the CSMM node (i.e., yes), the process 250 moves to block 265 where the computer 104 collects sensing metrics. However, if the geometric dilution of precision (GDOP) of the GNSS positioning data is greater than 5, the location information is not considered to have sufficient accuracy to make the collected data valid. Therefore, the computer 104 may collect sensing metrics when the GDOP is 5 or less. Alternatively, the computer may collect sensing metrics and take further action on the data only when the GDOP is 5 or less.

[0054] In the next block 270, the computer 104 may consult the CSMM to determine whether the node associated with the GNSS-based location is designated as full. If not, then in block 275, the computer may transmit the sensed metric data set to the central computer 120. Furthermore, in some embodiments, the computer 104 may transmit the sensed data to the central computer 120 regardless of whether the node is designated as full on the received CSMM of the area of ​​interest 200. That is, block 270 may be skipped and the process 250 may proceed from block 265 to block 275.

[0055] If it is determined at block 270 that the node is designated as full, the computer 104 may randomly eliminate a specified percentage (typically a majority, such as 80%) of the data points in the sensed metric data set and transmit a specified percentage (typically a minority, such as 20%) of the data points in the sensed metric data set at block 280. Certain data may be excluded from being eliminated, for example, data such as timestamps and locations should not be eliminated because they are necessary to provide context to other data.

[0056] After transmitting the sensed metric data set in either box 275 or 280, the computer 104 determines whether the vehicle 102 has been turned off at box 285. If not, the process 250 returns to box 255. If the vehicle 102 is turned off, the process 250 ends.

[0057] Figure 3 shows the collection of data at a single node for use as in Figure 4 The generation includes an exemplary graph 300 of a collaborative sensing metric map of data for a plurality of nodes. Graph 300 plots sensing metric data set uploads for a node with sensing vehicles on the vertical axis and days on the horizontal axis. Thus, Figure 3 The days on which the vehicles 102 obtained a data set, labeled AQ, are shown for three respective vehicles 102 .

[0058] In this example, data for nodes included in the collaborative sensing metric map of the present disclosure is updated by the central computer 120 and shared every 10 days based on the last previous 30 days of data in the map database 122, as indicated in Table 1 below:

[0059] Table 1

[0060]

[0061] In order for the sensing metric data set to be valid, the sensing metrics should be collected within a close time period (such as within 200ms) from when the vehicle position is determined, sent to the central computer 120 within a certain time period (such as 72 hours), and the error of the GNSS position determination should be within limits, such as having a GDOP of 5 or less, as discussed with respect to Table 2 below. In this example, 2 full sensing metric data sets are considered sufficient, and 8 or more full sensing metric data sets are considered full. The survey vehicle 120 can be provided with an initial map defining the node locations on the navigation map to associate a certain location with a node in the area of ​​interest and provide the sensing metric data set to the central computer 120. On the 10th day, the sensing metric data set A from vehicle 3 and the sensing metric data set B from vehicle 2 have been received (which is technically sufficient), but the data for 30 days is not yet available, so no collaborative sensing metric map (CSMM) with data from the node has been published. On day 20, sensed metric dataset C from vehicle 2 and sensed metric dataset D from vehicle 1 have also been received (which would be sufficient), except that 30 days of data are not yet available, so no CSMM with data from this node has been published. On day 30, a first CSMM with data for this node is published based on sensed metric datasets A, B, C, and D. Although 30 days is used as an example, the time window of the first CSMM should be sufficient to provide a minimum fidelity or quality of the sensed metrics. The time window is configurable and can be fixed or dynamically change over time, such as based on the amount of data collected or the percentage of nodes with sufficient data.

[0062] Similarly, on the 40th day, a second CSMM with data for the node is published based on the sensing metric datasets C, D, E, and F. On the 50th day, a third CSMM with data for the node is published based on the sensing metric datasets D, E, and F. On the 60th day, a fourth CSMM with data for the node is published based on the sensing metric datasets E and F. On the 70th day, a fifth CSMM with data for the node is published based on the sensing metric datasets E and F, but the node is considered insufficient because there is no sensing metric dataset from the previous 30 days. As shown in Table 1, when insufficient data is available in a given time window, the window can be extended to obtain a minimum number of samples.

[0063] On the 80th day, the sixth CSMM with data for the node is released based on the sensing metric datasets G, H, I and J. On the 90th day, the seventh CSMM with data for the node is released based on the sensing metric datasets G, H, I, J, K, L, M and N, and the node is marked as full. In fact, when there are sufficient samples in a given time window, the node attribute is marked as "full" so that when the vehicle submits data to the central map generator, a certain percentage of each additional sensing metric is randomly eliminated (e.g., PARM4 percentage, see Table 2). Therefore, on the 100th day, the eighth CSMM is released based on the full sensing metric datasets G, H, I, J, K, L, M and N and the partially uploaded sensing metric datasets O and P. On the 110th day, the ninth CSMM is released based on the full sensing metric datasets K, L, M, N and Q and the partially uploaded sensing metric datasets O and P. Since the node has less than 8 full sensing metric datasets, it is considered sufficient. In this manner, updating of the CSMM occurs in a manner that balances over-sharing and under-sharing of sensed metrics and allows the CSMM to reflect current conditions that may change over time.

[0064] In practice, since the RF environment around a parking lot or road segment may change due to many factors, including but not limited to construction or foliage growth, the sensed metrics or sensed metrics may change over time. The collaborative sensed metric map generation performed by the central computer 120 of the present disclosure can create a map with nodes that represent their location, cellular coverage, GNSS quality, and other sensed attributes. The central computer 120 updates the CSMM with fresh data over time by filtering the latest sensed data with the highest quality. If enough fresh data is available, the central computer 120 marks the sensed metric map node attributes as having insufficient or full or sufficient data, and can create CSMMs by vehicle brand / model / year, etc.

[0065] Updating the CSMM with a sensed metric data set from a recent time window (e.g., the past 30 days) every certain number of days (e.g., every 10 days) provides a fresh sensed metric map that provides updated sensed metrics for operation of the vehicle 102. Limiting the sensed metric data set to a partial data set when a node is marked as "full" helps the vehicle 102 minimize data usage of the communication module 110 and keeps the data memory load on the map database 122 low by allowing old sensed metric data to be deleted.

[0066] If a sufficient number of sensing metric datasets (for a sufficient number of nodes) can be aggregated for a specific make / model / year of vehicles using a certain sensing suite, then the CSMM can be customized for a specific vehicle make / model / year. Such customized CSMMs can help provide more relevant maps for individual vehicle types because the sensing metrics may be affected by on-board sensors that are specific to the make / model / year. The CSMM can be customized for a specific vehicle make / model / year by using only sensing metric datasets for a specific vehicle make / model / year or by weighting such sensing metric datasets higher for the customized CSMM. On the other hand, aggregated data from different vehicle types may have poor predictive power or limited value for individual vehicles with different sensing suites or capabilities compared to the survey vehicle.

[0067] CSMM can enhance the operation of the vehicle 102 by providing: after parking, the user will be able to communicate with their vehicle and know where their vehicle is because the vehicle can navigate around parking spaces or routes with poor cellular or GNSS coverage; provide drop-off and pickup points to be reliably or accurately located without significantly deviating from their true location; ensure that the vehicle can communicate with the user if an unexpected problem occurs by navigating around areas of poor coverage; and allow the experience during one driving session to help inform future driving sessions and be helpful to other vehicle users.

[0068] Implementations of processes for collaborative sensing metric map generation according to the present disclosure may operate based on an exemplary set of parameters for collecting sensing metrics as set forth in Table 2. Although specific values ​​are suggested, other suitable values ​​may be used without departing from the scope of the present disclosure.

[0069] Table 2

[0070]

[0071]

[0072] As shown in the example of Table 2, the first parameter PARM1 specifies the minimum defined distance between nodes of the area of ​​interest to be used for CSMM-based map generation. In this example, it is set to 5 meters. The second parameter PARM2 specifies the maximum defined distance between nodes of the area of ​​interest to be used for CSMM-based map generation. In this example, it is set to 25 meters. The central computer 120 can define the location of the nodes to cover the area of ​​interest, and the radius of PARM2 around each node can overlap. The sensing metric data set can be assigned to the nearest node based on the location.

[0073] The third parameter PARM3 specifies the maximum allowed time gap between the recorded position at the survey vehicle and the generation of the sensed metrics. In this example, it is set to 200 milliseconds so that the sensed metrics will be appropriately correlated with the position. PARM3 can be changed based on the acceptable position accuracy of the sensed metric data. The fourth parameter PARM4 specifies the percentage of random sensed metric data points from the data set that are eliminated by the survey vehicle in the event that the nearest / associated node has a full buffer and is marked as full. In this example, it is set to 80%. PARM4 can be changed based on the desired reduction in storage requirements.

[0074] As further shown in Table 2, the fifth parameter PARM5 specifies the time window for generating the sensed metrics of the published CSMM. In this example, it is set to 30 days. The sixth parameter PARM6 specifies the time period for generating the next CSMM. In this example, it is set to 10 days. PARM5 and PARM6 can be changed based on the expected or acceptable freshness and data transmission requirements of the CSMM published by balancing. The seventh parameter PARM7 specifies the minimum number of sensed metric data sets for each node for publishing the sensed metrics as sufficient. In this example, it is set to 10 sensed metric data sets. The eighth parameter PARM8 specifies the number of sensed metric data sets for each node for making the node status full. In this example, it is set to 100 sensed metric data sets. PARM7 and PARM8 can be changed based on empirical data about the number of data sets required to achieve the desired quality. The ninth parameter PARM9 specifies the maximum time that the sensed metric data set is unloaded from the survey vehicle to the central computer 120 before it is considered expired. In this example, it is set to 72 hours, but can be set to any suitable length of time to achieve the desired freshness of the data set. The tenth parameter PARM10 specifies the geometric dilution of precision (GDOP) for the GNSS position accuracy. In this example, the threshold GDOP is set to 5, and the GDOP of a valid data set must be 5 or less to be considered a valid data set to be sent to the central computer 120. Although a GDOP of 5 is generally considered a minimum accuracy level, if increased accuracy is desired, PARM10 can be set lower, for example.

[0075] When the vehicle 102 downloads the CSMM, it will receive the position and status of each node, where the status is set to full, sufficient, or insufficient. When conducting a survey, the vehicle 102 collects GNSS position samples and associated sensing metrics at various points along its path. In the case of a collaborative survey conducted by multiple vehicles, almost all nodes may have sufficient or full sensing metric dataset data buffers for generating CSMMs. When uploading a sensing metric dataset for a node, the vehicle 102 can use its own status to determine the amount of data to upload, and when the status is full, the amount of data can be reduced by PARM4% (e.g., 80% is randomly removed). If GNSS coverage is lost for more than PARM3 seconds during the survey or if the GDOP is above the threshold PARM10, the associated sensing metric dataset will not be selected for upload because it indicates an unreliable GNSS position.

[0076] After every PARM5 days, a new and up-to-date collaborative sensing metric map (CSMM) can be generated for each combination of vehicle brand / model / year and sensing metric. This can be based on combining all sensing metric data sets submitted from one or more survey multiple sources. For each node defining the CSMM, the valid associated sensing metric data set should be recorded within half PARM2 meters (data bins) of the node location (to ensure association with the nearest node). When generating the CSMM, there should be at least PARM7 sensing metric data sets collected for a given node in the past PARM6 days to set the sensing metric freshness to true (buffer is sufficient). If there is no such number of samples, the time window can be extended backward until at least PARM7 samples are available, whereby the sensing metric freshness is set to false (buffer is insufficient) or the state is marked as sufficient. Otherwise, if there is no such number (i.e., PARM7) of sensing metric data sets with the minimum count, the sensing metric state of the node is empty (i.e., assuming no survey). If for a given node, more than PARM8 sensing metric data sets are available over time in the past PARM5 days, the sensing metric freshness layer or state is marked as full (buffer is full). After the CSMM is generated, the next iteration is issued after PARM4 days.

[0077] Even if a vehicle 102 does not have features that can use a CSMM, it can still download the latest CSMM and, if it has enough sensors and transceivers to provide reliable data, can be used to collect a sensed metric dataset. The GNSS or cellular antenna and onboard sensors of the vehicle 102 may be unique to its make / model / year. In the case where there are enough sensed metric datasets, the generated CSMM may be based on a filter of the vehicle make / model / year. In the case where there is insufficient data for a particular vehicle, the sensed metric dataset may be aggregated with other vehicle makes / models / years to generate a CSMM.

[0078] The vehicle 102 may be able to specify its location with varying degrees of accuracy, depending on, for example, the sensor data used to determine the location, such as GNSS only; GNSS + camera odometry; GNSS + inertial measurement unit (IMU); etc. A source of location data in a sensory metric data set may be provided and included in the CSMM, and the vehicle 102 may record a location based on GNSS only and / or based on any of its additional capabilities.

[0079] As described above, the sensing metric(s) data set collected by the vehicle 102 along the survey path 202 may include, but are not limited to: vehicle make / model / year, UTC time, sensing metric(s): round trip time / reference signal strength, packet error rate, detected pure GNSS 3-D position (latitude, longitude, altitude), dilution of precision (DOP), cellular coverage / provider, actual 3-D position using onboard sensors, detected occluders (true / false or probabilistic), sensor source (camera / lidar / radar / ultrasonic).

[0080] about Figure 4 , an exemplary process 400 for generating and / or updating a collaborative sensing metric map is shown. Although disclosed in a particular order in the examples, it should be understood that some of the various steps may be performed in a different order or simultaneously in some cases without departing from the present disclosure.

[0081] In the first box 405, the central computer 120 defines a new CSMM for the area of ​​interest. In order to define the new CSMM, the central computer 120 can define node locations and / or node areas for the area of ​​interest (such as a parking lot or a road section), and the node locations and / or node areas will be mapped to generate a collaborative sensing metric map (CSMM) according to the present disclosure. The node locations can be regularly, irregularly, or a combination thereof spaced within a predetermined range. In one example, the minimum distance between nodes is 5 meters and the maximum distance between nodes is 25 meters, so as to balance the map granularity and data storage requirements. For example, the node locations and areas can be defined based on user input to the central computer 120. In another example, the node locations and / or areas can be defined in the following manner: executing program instructions to divide the area of ​​interest into regular areas to the extent allowed by the shape of the area of ​​interest (e.g., rectangles or squares of the same size), and placing the corresponding nodes in the area, for example, in the center position of the corresponding area.

[0082] In the next block 410, the central computer 120 receives sensing measurements, also referred to as sensing measurement data sets as described above, from a vehicle 102 in the plurality of vehicles 102 for the defined node as the vehicle 102 operates and moves through the area associated with the node. As described above, such a vehicle 102 performs this operation while traveling on the survey path 202. The central computer 120 may receive the sensing measurement data sets by any suitable means, such as via the wide area network 116.

[0083] In block 415 , the central computer 120 determines the associated nodes for the sensed metric data set received in block 410 based on information in the sensed metric data set, such as a location (longitude, latitude, altitude) or a node identifier determined by the vehicle 102 .

[0084] In the next block 420, the central computer 120 stores the sensed metric data set based on its associated node as determined in block 415. In one embodiment, the received sensed metric data set may be stored in the map database 122. Although described with respect to one vehicle 102 traveling through one node area, the central computer 120 iteratively performs the operations of blocks 410, 415, and 420 for multiple node areas with multiple vehicles 102. In addition, the sensed metric data sets received in block 410 may be collected, stored, and batch-transmitted to the central computer 120 by the vehicle 102 at a later time to allow the vehicle 102 to use the communication bandwidth for other purposes during operation, and to transmit the sensed metric data sets during off-peak hours or during periods when the vehicle 102 is parked or not operating (e.g., within 72 hours of collection).

[0085] In box 425, the central computer 120 determines whether to publish a new CSMM. In one embodiment, this can be based on determining that a period of time has passed, such as 10 days, to publish a new CSMM. This periodicity can be determined based on an estimate of the frequency with which the sensory metric data may change in the area of ​​interest. In another embodiment, the central computer 120 may only publish a CSMM if a threshold number of nodes are marked as "sufficient" or "full" by executing box 430 before box 425. In addition, the central computer 120 may require that a specified time window (e.g., 30 days) has passed so that the data to be collected as described in box 410 has been collected. If the determination at box 425 is no, the process returns to box 410 to continue receiving sensory metric data sets from the vehicle. If so, the process 400 proceeds to box 430 (or to box 440 if box 430 has been executed).

[0086] In block 430, the central computer 120 determines the corresponding status of the node for which the data set has been stored in block 420. For example, as explained above, based on a comparison of the number of sensed metric data sets received for the node with a first threshold and / or a second threshold within a specified time window (e.g., the past thirty days), the node status may be unavailable (N / A indicates that no data has been previously received for the node), insufficient, sufficient, or full. In one example, a node with a number of stored sensed metric data sets that meets or exceeds a first threshold (e.g., 10) may be determined to be sufficient, a node with a number of stored sensed metric data sets below the first threshold may be determined to be insufficient, and a node with a number of stored sensed metric data sets that meets or exceeds a second threshold (e.g., 100) may be determined to be full. In another example, the node status determined in block 430 may be a percentage of the amount of data storage describing the sensed metrics used for the node, for example, the data storage for the node may be 0% full (or used), 20% full, 50% full, 100% full, etc.

[0087] In one embodiment, the central computer 120 may determine that a node is a certain percentage less than 100% full, and may then store the sensed metric data for the node such that the storage for the node is 100% full. If the amount of new data is large enough that it will cause the node to be more than 100% full, the computer 120 may discard older data for the node, even if the older data was received within a specified time window, in favor of the new data, e.g., the sensed metrics for the node may be maintained on a first-in, first-out (FIFO) basis. Alternatively or in addition, when the amount of new data for a node will cause the node to have or exceed a full state, the central computer 120 may, for example, randomly discard data received for the node such that the node does not exceed the amount of data specified for the full state. In another embodiment, when the node state or buffer is full, the survey vehicle may randomly reduce the amount of data in the reported sensed metric data set by a percentage greater than 50%, such as 80%, in order to reduce the storage load at the map database 122.

[0088] In block 440, the central computer 120 may calculate a sensing metric for each node of the region of interest based on the stored sensing metric data set received in a recent time window (e.g., 30 days). Based on the collected sensing metric data collected for each node region, the sensing metric may include an average, mean, sum score, variance, or normalized value relative to the mean of values ​​of GDOP, RTT / RSSI, PER, and presence or absence of an occluder for each node.

[0089] In block 445, the central computer 120 publishes a new CSMM for the latest time window. The CSMM will include the status (N / A, Insufficient, Sufficient, or Full) and the sensing metrics calculated at block 440 for each node in the region of interest.

[0090] If sufficient data is available for a specific vehicle brand / model / year with substantially the same sensor suite, a CSMM may be provided for vehicles of the same type (which means vehicles with the same or similar sensing suites, such as vehicles of the same brand, model, and / or year), and the central computer 120 may filter the sensing metric data set based on the vehicle brand / model / year and publish a vehicle-specific CSMM. Thus, the CSMM may be customized for the sensing suite and antenna of a specific vehicle or type of vehicle and may allow higher quality data to be used for the operation of the vehicle.

[0091] After publishing the new CSMM in block 445 , the central computer 120 may return to block 410 to continue receiving sensory metric data sets for subsequent CSMMs.

[0092] After publishing a new CSMM in box 445, the central computer 120 may also move to box 450 and delete or otherwise discard the stored sensed metric data sets that fall outside the recent time window. For example, sensed metric data sets older than 30 days when a new CSMM is published may be deleted from the map database 122 to reduce the storage requirements of the system and retain only the most recent data that reflects the current situation. In an embodiment in which data for the past 30 days is published every 10 days, for situations in which a node does not have enough data in the 30-day time window, when the next CSMM is published, deleting the data at the time of publication allows access to 40 days worth of data, and the central computer 120 extends the time window to include older data for use with the node. After box 435, the process 400 ends.

[0093] about Figure 5A , an exemplary region of interest 200 is shown including a vehicle path 502 through the node regions 230 - 244 of the region of interest 200 .

[0094] Based on the data provided by the CSMM for the area of ​​interest 200, the vehicle 102 can plot a path 502 through the areas 240, 241, 242, 237, 232, and 233 for the vehicle computer 104 and / or a human operator to actuate the steering, propulsion, and braking subsystems to move the vehicle 102 along the path 502, possibly stopping (e.g., parking) in the area 234. In this way, the vehicle 102 can navigate around the areas 230, 238, 239, and 244 that have sensing metrics indicating poor GNSS, poor cellular connectivity, or detected obstacles determined by the CSMM (i.e., "bad metrics"). The bad metrics may, for example, be related to nearby objects (such as foliage, buildings, or recent construction) that interfere with the GNSS or cellular signals received by the vehicle 102 or are not reliably sensed by the vehicle sensors 108 and the camera 107. By navigating around these areas, the vehicle 102 can reliably operate autonomously, such as during autonomous valet parking, and maintain good contact with the user via the user device 118 .

[0095] Figure 5B An example process 250 is shown for operating the vehicle 102 using the CSMM.

[0096] The process 550 begins and in a first block 552 , the vehicle 102 receives a published CSMM from the central computer 120 , such as via transmission over the wide area network 116 .

[0097] In the next box 555, the computer 104 of the vehicle 102 determines the location of the vehicle 102 based on the GNSS based sensor 108 (such as a GPS sensor).

[0098] In the next block 560, the computer 104 determines whether the location is within the CSMM's region of interest 200. If not, the process returns to block 555 to continue location monitoring.

[0099] If it is determined at block 560 that the location is within a CSMM node, the process 550 moves to block 565 where the computer 104 identifies regions of the node(s) having poor sensing metrics. Such regions may be determined in any suitable manner, such as by having insufficient sensing metric data, suboptimal GNSS accuracy (e.g., closer to a GDOP of 5), no / suboptimal / poor cellular connectivity, and / or detected obstacles, etc.

[0100] In the next block 570 , the computer 104 may plot a vehicle path to navigate around areas of poor sensing metrics.

[0101] In block 575 , the computer 104 or user may operate the vehicle 102 to follow the mapped vehicle path.

[0102] In the next box 580, the computer 104 determines whether the vehicle 102 has been turned off. If not, the process 550 returns to the box 555 to continue iterating. If the vehicle 102 is turned off, the process 550 ends.

[0103] Although disclosed above with respect to certain implementations, various other implementations are possible without departing from the present disclosure.The operations, systems, and methods described herein should always be implemented and / or performed in accordance with applicable owner / user manuals and / or safety guidelines.

[0104] The use of "in response to," "based on," and "upon determining..." herein indicates a causal relationship, not just a temporal relationship. In addition, unless otherwise expressly indicated herein, all terms used in the claims are intended to be given their ordinary and customary meanings as understood by those skilled in the art. Unless a claim recites an express limitation to the contrary, the use of singular articles such as "a / kind," "the," etc. should be interpreted as reciting one or more of the indicated elements.

[0105] In the accompanying drawings, the same or similar reference numerals indicate the same or similar elements. In addition, some or all of these elements may be changed. With respect to the media, processes, systems, methods, etc. described herein, it should be understood that although the steps of such processes, etc. have been described as occurring in a particular order, unless otherwise specified or as can be seen from the context, such processes may be practiced in the case where the steps are performed in an order other than the order described herein. Similarly, it should also be understood that certain steps may be performed simultaneously, other steps may be added, or certain steps described herein may be omitted. In other words, the description of the process herein is provided for the purpose of illustrating certain embodiments and should never be construed as limiting the present disclosure.

[0106] The present disclosure has been described in an illustrative manner, and it should be understood that the terminology which has been used is intended to be in the nature of words of description rather than limitation. In light of the above teachings, many modifications and variations of the present disclosure are possible, and the present disclosure may be practiced in other ways than specifically described.

[0107] According to the present invention, a system is provided, which has a computer, the computer including a processor and a memory, the memory storing instructions executable by the processor, the processor being programmed to: receive a sensing metric data set from a first plurality of vehicles for each of a plurality of nodes having an assigned area in an area of ​​interest; determine for each node whether a first threshold number of sensing metric data sets sufficient to provide sensing metrics for the node has been received in a last predetermined time window; and upon expiration of a predetermined time period, provide a sensing metric map of the area of ​​interest to a second plurality of vehicles based on the sensing metric data sets received in the last predetermined time window.

[0108] According to an embodiment, the invention also features instructions for determining, for each node, whether a second threshold number of sensing metric data sets sufficient to mark the node as having a status of full has been received in the last predetermined time window.

[0109] According to an embodiment, a smaller percentage of the sensing metrics in the sensing metric data set is received from the vehicle for nodes whose status is marked as full in the sensing metric map.

[0110] According to an embodiment, the sensing metric map provides sensing metric data for nodes having at least the first threshold number of sensing metric data sets within the last predetermined time window.

[0111] According to an embodiment, the sensing metric data set includes indicators of Global Navigation Satellite System (GNSS) coverage quality, cellular connection quality, and / or identified occluders.

[0112] According to an embodiment, the sensing metric dataset comprises indicators of Global Navigation Satellite System (GNSS) coverage quality, cellular connection quality, and identified obstructions; and wherein the maximum time gap between a recorded position of a vehicle and generation of sensing metrics by the vehicle is a predetermined number of milliseconds.

[0113] According to an embodiment, the GNSS coverage quality is latitude, longitude, altitude and geometric dilution of precision (GDOP), the cellular connection quality is round trip time (RTT), reference signal strength indication (RSSI) and / or packet error rate (PER), and the identified obstructions are true / false detections or probabilities of obstructions and sensor sources.

[0114] According to an embodiment, the sensing metric data set includes a vehicle brand, model and year; and when sufficient sensing metric data sets are received for a specific node that defines specific node data within the predetermined time window for a vehicle of a specific brand, model and year, it includes instructions for performing the following operations: providing a sensing metric map of the area of ​​interest specific to the corresponding vehicle by replacing the generalized node data with the specific node data.

[0115] According to an embodiment, the area of ​​interest is a road segment or a parking area, and the nodes are spaced apart within a predetermined range of meters.

[0116] According to an embodiment, the last predetermined time window and the predetermined period are configurable days.

[0117] According to the present invention, a method for collaborative sensing metric map generation includes: receiving a sensing metric data set from a first plurality of vehicles for each of a plurality of nodes having an assigned area in an area of ​​interest; determining for each node whether a first threshold number of sensing metric data sets sufficient to provide sensing metrics for the node has been received in a last predetermined time window; and upon expiration of a predetermined period, providing a sensing metric map of the area of ​​interest to a second plurality of vehicles based on the sensing metric data sets received in the last predetermined time window.

[0118] In one aspect of the invention, the method comprises determining, for each node, whether a second threshold number of sensing metric data sets sufficient to mark the node as having a status of full has been received in the last predetermined time window.

[0119] In one aspect of the invention, a smaller percentage of the sensing metrics in the sensing metric data set is received from vehicles for nodes whose status is marked as full in the sensing metric map.

[0120] In one aspect of the invention, the sensing metric map provides sensing metric data for nodes having at least the first threshold number of data points within the last predetermined time window.

[0121] In one aspect of the invention, the sensing metric data set includes indicators of Global Navigation Satellite System (GNSS) coverage quality, cellular connection quality, and / or identified occluders.

[0122] In one aspect of the invention, the sensing metric data set includes indicators of Global Navigation Satellite System (GNSS) coverage quality, cellular connection quality, and identified obstructions; and wherein the maximum time gap between a recorded position of a vehicle and the generation of sensing metrics by the vehicle is a predetermined number of milliseconds.

[0123] In one aspect of the invention, the GNSS coverage quality is latitude, longitude, altitude and geometric dilution of precision (GDOP), the cellular connection quality is round trip time (RTT), reference signal strength indication (RSSI) and / or packet error rate (PER), and the identified obstructions are true / false detections or probabilities of obstructions and sensor sources.

[0124] In one aspect of the present invention, the sensing metric data set includes a vehicle brand, model and year; and when sufficient sensing metric data sets are received for a specific node that defines specific node data within the predetermined time window for a vehicle of a specific brand, model and year, a sensing metric map of the area of ​​interest specific to the corresponding vehicle is provided by replacing the generalized node data with the specific node data.

[0125] In one aspect of the invention, the area of ​​interest is a road segment or a parking area, and the nodes are spaced apart within a predetermined range of meters.

[0126] In one aspect of the present invention, the last predetermined time window and the predetermined period are configurable days.

Claims

1. A method for collaborative sensing metric map generation, wherein include: receiving a sensed metric data set from a first plurality of vehicles for each of a plurality of nodes having an assigned area for an area of ​​interest; determining, for each node, whether a first threshold number of sensing metric data sets sufficient to provide sensing metrics for the node has been received in a previous predetermined time window; as well as Upon expiration of the predetermined time period, a sensory metric map of the area of ​​interest is provided to a second plurality of vehicles based on the sensory metric data sets received in the last predetermined time window.

2. The method according to claim 1, further comprising: include: A determination is made for each node whether a second threshold number of sensing metric data sets sufficient to mark the node as having a status of full has been received in the last predetermined time window. 3 . The method of claim 2 , wherein a smaller percentage of the sensing metrics in the sensing metric data set is received from the vehicle for nodes whose status is marked as full in the sensing metric map. 4 . The method of claim 1 , wherein the sensing metric map provides sensing metric data for nodes having at least the first threshold number of data points within the last predetermined time window.

5. The method of claim 1, wherein the sensing metric data set includes indicators of global navigation satellite system (GNSS) coverage quality, cellular connection quality, and / or identified occluders.

6. The method of claim 1, wherein the sensing metric data set includes indicators of global navigation satellite system (GNSS) coverage quality, cellular connection quality, and identified occluders; and Wherein a maximum time gap between a recorded position of a vehicle and generation of a sensed metric by said vehicle is a predetermined number of milliseconds.

7. The method of claim 6, wherein the GNSS coverage quality is latitude, longitude, altitude, and geometric dilution of precision (GDOP), the cellular connection quality is round trip time (RTT), reference signal strength indication (RSSI), and packet error rate (PER), and the identified obstructions are true / false detections or probabilities of obstructions and sensor sources.

8. The method of claim 1, wherein the sensory metric data set includes a vehicle make, model, and year; and When sufficient sensed metric data sets are received for a specific make, model and year of vehicle for a specific node defining specific node data within the predetermined time window, a sensed metric map of the area of ​​interest specific to the corresponding vehicle is provided by replacing the generalized node data with the specific node data.

9. The method of claim 1, wherein the area of ​​interest is a road segment or a parking area, and the nodes are spaced apart within a predetermined range of meters.

10. The method of claim 1, wherein the predetermined time window and the predetermined time period are configurable days.

11. The method of claim 3, wherein the sensing metric map provides sensing metric data for nodes having at least the first threshold number of data points within the last predetermined time window.

12. The method of claim 3, wherein the sensing metric data set includes indicators of Global Navigation Satellite System (GNSS) coverage quality, cellular connection quality, and / or identified occluders.

13. The method of claim 3, wherein the sensing metric data set includes indicators of global navigation satellite system (GNSS) coverage quality, cellular connection quality, and identified occluders; and Wherein a maximum time gap between a recorded position of a vehicle and generation of a sensed metric by said vehicle is a predetermined number of milliseconds.

14. The method of claim 13, wherein the GNSS coverage quality is latitude, longitude, altitude, and geometric dilution of precision (GDOP), the cellular connection quality is round trip time (RTT), reference signal strength indication (RSSI), and / or packet error rate (PER), and the identified obstructions are true / false detections or probabilities of obstructions and sensor sources.

15. A system comprising a computer, the computer comprising a processor and a memory storing instructions executable by the processor, the processor being programmed to perform the method according to any one of claims 1 to 14.