METHOD FOR DETECTING CONSTRUCTION SITE AREAS FOR A VEHICLE

Abstract

A method for detecting construction zones for a vehicle, comprising: receiving measurement data about an environment surrounding the vehicle using a vehicle sensor, wherein the measurement data comprise perception data of the environment and telemetry data of a plurality of remote vehicles in the environment; determining a starting point and an endpoint of a construction zone, at least partially, based on the measurement data, wherein the construction zone represents a plurality of road segments extending from the starting point to the endpoint; determining a lane relocation status for each of the plurality of road segments; determining a lane closure status for each of the plurality of road segments; determining a hard shoulder closure status for each of the plurality of road segments; and determining a speed limit for each of the plurality of road segments; characterized in that,that determining the lane relocation status, lane closure status, and hard shoulder closure status further comprises: determining a plurality of lateral lane density distributions, each of which corresponds to one of the plurality of lanes on one of the plurality of road segments of the construction area; determining the lane relocation status for each of the plurality of road segments at least partially based on the plurality of lateral lane density distributions; determining a lane closure status for each of the plurality of road segments at least partially based on the plurality of lateral lane density distributions.and determining the hard shoulder closure status for each of the multitude of road segments at least partially based on the multitude of lateral lane density distributions; wherein: (i) where determining the multitude of lateral lane density distributions further comprises: determining a multitude of total lateral density distributions at least partially based on the telemetry data, wherein each of the multitude of total lateral density distributions describes a spatial distribution of the multitude of distant vehicles within one of the multitude of road segments of the construction area, and separating the multitude of total lateral density distributions into the multitude of lateral lane density distributions using a Gaussian Mixing Model (GMM),wherein each of the plurality of lateral lane density distributions corresponds to one of the plurality of lanes within one of the plurality of road segments of the construction area, and / or (ii) wherein determining the hard shoulder closure status for each of the plurality of road segments further comprises: determining a high-density area on each of the plurality of lanes within each of the plurality of road segments, wherein the high-density area is an area within each of the plurality of lanes that has a lateral lane density distribution greater than or equal to a predetermined lateral density threshold; determining an average width of the high-density area on each of the plurality of lanes across the plurality of road segments; and determining a plurality of hard shoulder closure road segments.wherein the plurality of hard shoulder road segments is a subset of the plurality of road segments and wherein a width of the high-density area on at least one of the plurality of lanes on each of the plurality of hard shoulder road segments differs from the average width of the high-density area on the at least one of the plurality of lanes by a greater than or equal to a predetermined threshold for hard shoulder closure deviation, and determining the hard shoulder closure status for each of the plurality of hard shoulder road segments as a positive hard shoulder closure status, and / or (iii) wherein determining the speed limit for each of the plurality of road segments further comprises: determining a plurality of total speed density distributions at least partially based on the telemetry data,wherein each of the multitude of total velocity density distributions describes a velocity distribution of the multitude of distant vehicles within one of the multitude of road segments of the construction area, determining an average speed for each of the multitude of road segments based on the multitude of total velocity density distributions, generating a multitude of truncated total velocity density distributions by truncating each of the multitude of total velocity density distributions to a predetermined range around the average speed for each of the multitude of road segments, and determining the speed limit for each of the multitude of road segments as a truncated average speed for each of the multitude of road segments based on the multitude of truncated total velocity density distributions.

Description

INTRODUCTION

[0001] The present disclosure relates to systems and methods for navigation, route planning and wayfinding for vehicles and in particular to the acquisition, processing and verification of data relating to construction sites on roads.

[0002] To enhance occupant alertness and comfort, vehicles can be equipped with driver assistance systems (DAS) and / or automated driving systems. Automated driving systems can use various sensors to detect objects in the vehicle's surroundings and steer the vehicle to navigate through the environment to a predetermined destination. Both driver assistance systems and automated driving systems can also utilize vehicle positioning, determined using global navigation satellite systems (GNSS) in conjunction with globally oriented maps for navigation planning, route planning, lane detection, obstacle avoidance, and / or similar functions. Furthermore, vehicles can be equipped with the capability to receive electronically transmitted data feeds containing information about roadworks and / or construction zones on roads.However, due to changing road conditions, changing road construction plans, inaccuracies in data entry, and / or similar factors, data feeds providing information about roadworks may be outdated and / or inaccurate.

[0003] While current navigation, route and path planning systems and procedures fulfill their purpose, there is a need for a new and improved system and procedure for detecting construction site areas for a vehicle. SUMMARY

[0004] A method for detecting construction zones for a vehicle is provided according to several aspects. The method may include receiving measurement data about the vehicle's surroundings using a vehicle sensor. The measurement data includes perception data of the environment and telemetry data from a multitude of remote vehicles in the vicinity. The method may further include determining, at least in part, a start and end point of a construction zone based on the measurement data. The construction zone is represented as a multitude of road segments extending from the start point to the end point. The method may further include determining a lane relocation status for each of the multitude of road segments. The method may also include determining a lane closure status for each of the multitude of road segments.The procedure may also include determining the hard shoulder closure status for each of the numerous road segments. The procedure may also include determining the speed limit for each of the numerous road segments.

[0005] In another aspect of the present disclosure, determining the start and end points of the construction site area, at least partially based on perception data, may further include detecting a cluster of construction site objects in the vicinity. This cluster of construction site objects comprises a construction site traffic sign, a construction site road barrier, a construction site vehicle, and / or a construction site worker. Determining the start and end points of the construction site area may also include ascertaining these points at least partially based on the position of the cluster of construction site objects.Determining the starting and ending points of the construction area may further involve dividing the construction area into a multitude of road segments extending from the starting point to the end point of the construction area. Each of these multiple road segments has the same length.

[0006] In another aspect of the present disclosure, the detection of the cluster of construction site objects in the environment may include the detection of the cluster of construction site objects in the environment at least partially based on perception data using a DBSCAN algorithm (Density Based Spatial Clustering of Applications with Noise).

[0007] In another aspect of the present disclosure, determining the lane relocation status, lane closure status, and hard shoulder closure status may further include determining a plurality of lateral lane density distributions. Each of the plurality of lateral lane density distributions corresponds to one of the plurality of lanes for one of the plurality of road segments in the construction area. Determining the lane relocation status, lane closure status, and hard shoulder closure status may further include determining the lane relocation status for each of the plurality of road segments, at least partially, based on the plurality of lateral lane density distributions.Determining the lane relocation status, lane closure status, and hard shoulder closure status may further include determining the lane closure status for each of the many road segments, at least partially, based on the many lateral traffic density distributions.

[0008] In another aspect of the present disclosure, determining the multitude of lateral lane density distributions may further comprise determining a multitude of total lateral density distributions, at least partially, based on telemetry data. Each of the multitude of total lateral density distributions describes a spatial distribution of the multitude of distant vehicles within one of the multitude of road segments in the construction area. Determining the multitude of lateral lane density distributions may further comprise separating the multitude of total lateral density distributions into the multitude of lateral lane density distributions using a Gaussian mixing model (GMM). Each of the multitude of lateral lane density distributions corresponds to one of the multitude of lanes within one of the multitude of road segments in the construction area.

[0009] In another aspect of the present disclosure, determining the lane layout status for each of the plurality of road segments may further include determining a high-density area for each of the plurality of lanes within each of the plurality of road segments. The high-density area is an area within each of the plurality of lanes that exhibits a lateral lane density distribution greater than or equal to a predetermined lateral density threshold. Determining the lane layout status for each of the plurality of road segments may further include determining an average position of the high-density area for each of the plurality of lanes across the plurality of road segments.Determining the lane relocation status for each of the multitude of road segments may further include determining a multitude of lane-relocated road segments. The multitude of lane-relocated road segments is a subset of the multitude of road segments. A position of the high-density area on at least one of the multitude of lanes on each of the multitude of lane-relocated road segments deviates from the average position of the high-density area on the at least one of the multitude of lanes by greater than or equal to a predefined lane relocation deviation threshold. Determining the lane relocation status for each of the multitude of road segments may further include determining the lane relocation status for each of the multitude of lane-relocated road segments as a positive lane relocation status.

[0010] In another aspect of the present disclosure, determining the lane closure status for each of the multitude of road segments may further comprise determining an average lane density on each of the multitude of lanes across the multitude of road segments, at least partially based on the multitude of lateral lane density distributions. Determining the lane closure status for each of the multitude of road segments may further comprise determining a multitude of lane-closed road segments. The multitude of lane-closed road segments is a subset of the multitude of road segments.An average lane density of at least one of the multiple lanes on each of the multiple lane-closed road segments deviates from the average lane density of the at least one of the multiple lanes by a greater than or equal to a predefined threshold for a deviation from the lane closure. Determining the lane closure status for each of the multiple road segments may also include determining the lane closure status for each of the multiple lane-closed road segments as a positive lane closure status.

[0011] In another aspect of the present disclosure, determining the hard shoulder closure status for each of the plurality of road segments may further include determining a high-density area on each of the plurality of lanes within each of the plurality of road segments. The high-density area is an area within each of the plurality of lanes that exhibits a lateral lane density distribution greater than or equal to a predetermined lateral density threshold. Determining the hard shoulder closure status for each of the plurality of road segments may further include determining an average width of the high-density area on each of the plurality of lanes across the plurality of road segments.Determining the hard shoulder closure status for each of the multitude of road segments may further include determining a multitude of hard shoulder closure road segments. The multitude of hard shoulder closure road segments is a subset of the multitude of road segments. A width of the high-density area of ​​at least one of the multitude of lanes on each of the multitude of hard shoulder closure road segments deviates from the average width of the high-density area of ​​the at least one of the multitude of lanes by a greater than or equal to a predetermined threshold for hard shoulder closure deviation. Determining the hard shoulder closure status for each of the multitude of road segments may further include determining the hard shoulder closure status for each of the multitude of hard shoulder closure road segments as a positive hard shoulder closure status.

[0012] In another aspect of the present disclosure, determining the speed limit for each of the multitude of road segments may further comprise determining a multitude of overall speed density distributions, at least partially, based on telemetry data. Each of the multitude of overall speed density distributions describes a speed distribution of the multitude of remote vehicles within one of the multitude of road segments of the construction area. Determining the speed limit for each of the multitude of road segments may further comprise determining an average speed for each of the multitude of road segments based on the multitude of overall speed density distributions.Determining the speed limit for each of the multitude of road segments can further involve generating a multitude of truncated total speed density distributions by truncating each of the multitude of total speed density distributions to a predetermined range around the average speed for each of the multitude of road segments. Determining the speed limit for each of the multitude of road segments can further involve determining the speed limit for each of the multitude of road segments as a truncated average speed for each of the multitude of road segments based on the multitude of truncated total speed density distributions.

[0013] In another aspect of the present disclosure, the method further comprises transmitting the starting point and end point of the construction site area, the lane relocation status for each of the multitude of road segments, the lane closure status for each of the multitude of road segments, the hard shoulder closure status for each of the multitude of road segments and the speed limit for each of the multitude of road segments to a remote device.

[0014] A system for detecting construction zones is provided for vehicles, based on several aspects. The system may include a server system. This server system may include a server communication system and a server controller electrically connected to the server communication system. The server controller is programmed to receive measurement data about the environment using the server communication system. This measurement data includes perception data of the environment and telemetry data from numerous remote vehicles in the vicinity. The server controller is further programmed to determine, at least partially, the start and end points of a construction zone based on this measurement data. The construction zone represents a multitude of road segments extending from the start point to the end point.The server control is further programmed to determine a lane change status for each of the numerous road segments. The server control is further programmed to determine a lane closure status for each of the numerous road segments. The server control is further programmed to determine the hard shoulder closure status for each of the numerous road segments. The server control is further programmed to determine a speed limit for each of the numerous road segments.The server control is further programmed to transmit the starting point and end point of the construction area, the lane relocation status for each of the multitude of road segments, the lane closure status for each of the multitude of road segments, the hard shoulder closure status for each of the multitude of road segments, and the speed limit for each of the multitude of road segments to the multitude of remote vehicles using the server communication system.

[0015] In another aspect of the present disclosure, the server controller for determining the start and end points of the construction site area is further programmed to detect a cluster of construction site objects in the environment, at least partially, based on perception data using a DBSCAN algorithm (Density Based Spatial Clustering of Applications with Noise). The cluster of construction site objects includes a construction site traffic sign, a construction site road barrier, a construction site vehicle, and / or a construction site worker. The server controller is further programmed to determine the start and end points of the construction site area, at least partially, based on the position of the cluster of construction site objects.The server control system is further programmed to determine the start and end points of the construction area by dividing it into a multitude of road segments extending from the start and end points of the construction area. Each of these road segments has the same length.

[0016] In another aspect of the present disclosure, the server control for determining the lane relocation status for each of the plurality of road segments is further programmed to determine a plurality of lateral lane density distributions. Each of the plurality of lateral lane density distributions corresponds to one of the plurality of lanes on one of the plurality of road segments within the construction area. The server control for determining the lane relocation status for each of the plurality of road segments is further programmed to identify a high-density area on each of the plurality of lanes within each of the plurality of road segments.The high-density area is a region within each of the multitude of lanes that exhibits a lateral lane density distribution greater than or equal to a predefined lateral density threshold. The server controller is programmed to determine the lane-shift status for each of the multitude of road segments and to calculate an average position of the high-density area on each of the multitude of lanes across the multitude of road segments. The server controller is programmed to determine the lane-shift status for each of the multitude of road segments and to calculate a multitude of lane-shifted road segments. The multitude of lane-shifted road segments is a subset of the multitude of road segments.The position of a high-density area on at least one of the multiple lanes on each of the multiple lane-shifted road segments deviates from the average position of the high-density area of ​​the at least one of the multiple lanes by a greater than or equal to a predefined threshold for deviation from the lane shift. The server control is further programmed to determine the lane shift status for each of the multiple lane-shifted road segments such that it determines the lane shift status for each of the multiple lane-shifted road segments as a positive lane shift status.

[0017] In another aspect of the present disclosure, the server controller for determining the lane closure status for each of the plurality of road segments is further programmed to determine an average lane density on each of the plurality of lanes across the plurality of road segments, at least partially, based on the plurality of lateral lane density distributions. The server controller is further programmed to determine the lane closure status for each of the plurality of road segments by identifying a plurality of lane-closed road segments. The plurality of lane-closed road segments is a subset of the plurality of road segments.An average lane density of at least one of the multiple lanes on each of the multiple lane-closed road segments deviates from the average lane density of the at least one of the multiple lanes by a greater than or equal to a predefined threshold for a deviation from the lane closure. The server control is further programmed to determine the lane closure status for each of the multiple road segments such that it identifies the lane closure status for each of the multiple lane-closed road segments as a positive lane closure status.

[0018] In another aspect of the present disclosure, the server controller for determining the hard shoulder closure status for each of the plurality of road segments is further programmed to determine an average width of the high-density area on each of the plurality of lanes across the plurality of road segments. The server controller is further programmed to determine the hard shoulder closure status for each of the plurality of road segments and to identify a plurality of hard shoulder-closed road segments. The plurality of hard shoulder-closed road segments is a subset of the plurality of road segments.The width of the high-density area of ​​at least one of the multiple lanes on each of the multiple lane-closed road segments deviates from the average width of the high-density area of ​​the at least one of the multiple lanes by a greater than or equal to a predefined threshold for deviation from the hard shoulder closure. The server control is further programmed to determine the hard shoulder closure status for each of the multiple road segments such that it determines the hard shoulder closure status for each of the multiple road segments to be a positive hard shoulder closure status.

[0019] In another aspect of the present disclosure, the server control for determining the speed limit for each of the plurality of road segments is further programmed to determine a plurality of total speed density distributions, at least partially, based on the telemetry data. Each of the plurality of total speed density distributions describes a speed distribution of the first plurality of remote vehicles within one of the plurality of road segments of the construction zone. The server control for determining the speed limit for each of the plurality of road segments is further programmed to determine an average speed for each of the plurality of road segments based on the plurality of total speed density distributions.The server controller is programmed to determine the speed limit for each of the multitude of road segments and to generate a multitude of truncated total speed density distributions by truncating each of the multitude of total speed density distributions to a predetermined range around the average speed for each of the multitude of road segments. The server controller is further programmed to determine the speed limit for each of the multitude of road segments as a truncated average speed for each of the multitude of road segments based on the multitude of truncated total speed density distributions.

[0020] In another aspect of the present disclosure, the system further comprises a vehicle system. The vehicle system may include a vehicle sensor, a vehicle communication system, and a vehicle controller electrically connected to the vehicle sensor and the vehicle communication system. The vehicle controller is programmed to receive measurement data about the environment using the vehicle sensor. The vehicle controller is further programmed to transmit the measurement data to the server system using the vehicle communication system.

[0021] A method for detecting construction zones for a vehicle is provided according to several aspects. The method may include receiving measurement data about the vehicle's surroundings using a vehicle sensor. This measurement data includes perception data of the environment and telemetry data from a multitude of distant vehicles in the vicinity. The method may further include determining, at least in part, a starting point and an endpoint of a construction zone based on the measurement data. The construction zone represents a multitude of road segments extending from the starting point to the endpoint. The method may also include determining a multitude of lateral lane density distributions. Each of these distributions corresponds to one of the many lanes on one of the many road segments within the construction zone.The procedure may further include determining a lane relocation status for each of the numerous road segments, at least partially based on the numerous lateral lane density distributions. The procedure may further include determining a lane closure status for each of the numerous road segments, at least partially based on the numerous lateral lane density distributions. The procedure may further include determining a hard shoulder closure status for each of the numerous road segments, at least partially based on the numerous lateral lane density distributions. The procedure may further include determining a speed limit for each of the numerous road segments.The procedure may further include transmitting the starting point and end point of the construction area, the lane relocation status for each of the multitude of road segments, the lane closure status for each of the multitude of road segments, the hard shoulder closure status for each of the multitude of road segments and the speed limit for each of the multitude of road segments to a remote device.

[0022] In another aspect of the present disclosure, determining the start and end points of the construction site area may further include detecting a cluster of construction site objects in the surrounding area, at least partially, based on perception data using a DBSCAN algorithm (Density Based Spatial Clustering of Applications with Noise). The cluster of construction site objects includes a construction site traffic sign, a construction site road barrier, a construction site vehicle, and / or a construction site worker. Determining the start and end points of the construction site area may further include identifying the start and end points of the construction site area, at least partially, based on the position of the cluster of construction site objects.Determining the starting and ending points of the construction area may further involve dividing the construction area into a multitude of road segments extending from the starting point to the end point of the construction area. Each of these multiple road segments has the same length.

[0023] In another aspect of the present disclosure, determining the lane relocation status, lane closure status, and hard shoulder closure status may further include determining a high-density area on each of the plurality of lanes within each of the plurality of road segments. The high-density area is an area within each of the plurality of lanes that exhibits a lateral lane density distribution greater than or equal to a predetermined lateral density threshold. Determining the lane relocation status, lane closure status, and hard shoulder closure status may further include determining an average position of the high-density area on each of the plurality of lanes across the plurality of road segments.Determining the lane shift status, lane closure status, and hard shoulder closure status may further include determining a multitude of lane-shifted road segments. The multitude of lane-shifted road segments is a subset of the multitude of road segments. The position of the high-density area on at least one of the multitude of lanes on each of the multitude of lane-shifted road segments deviates from the average position of the high-density area on the at least one of the multitude of lanes by a greater than or equal to a predefined lane shift deviation threshold.Determining the lane relocation status, lane closure status, and hard shoulder closure status may further include determining the lane relocation status for each of the multiple lane relocation segments as a positive lane relocation status. Determining the lane relocation status, lane closure status, and hard shoulder closure status may further include determining an average lane density on each of the multiple lanes across the multiple road segments, at least partially based on the multiple lateral lane density distributions. Determining the lane relocation status, lane closure status, and hard shoulder closure status may further include determining a multiple of lane-closed road segments. The multiple of lane-closed road segments is a subset of the multiple road segments.An average lane density on at least one of the multiple lanes on each of the multiple lane-closed road segments deviates from the average lane density on the at least one of the multiple lanes by a greater than or equal to a predetermined threshold for a deviation from the lane closure. Determining the lane relocation status, lane closure status, and hard shoulder closure status may further include determining the lane closure status for each of the multiple lane-closed road segments as a positive lane closure status. Determining the lane relocation status, lane closure status, and hard shoulder closure status may further include determining an average width of the high-density area on each of the multiple lanes across the multiple road segments.Determining the lane relocation status, lane closure status, and hard shoulder closure status may further include identifying a multitude of hard shoulder closure road segments. The multitude of hard shoulder closure road segments is a subset of the multitude of road segments. The width of the high-density area on at least one of the multitude of lanes on each of the multitude of hard shoulder closure road segments deviates from the average width of the high-density area on the at least one of the multitude of lanes by a greater than or equal to a predefined hard shoulder closure deviation threshold.Determining the lane relocation status, lane closure status and hard shoulder closure status may also include determining the hard shoulder closure status for each of the many hard shoulder closed road sections as a positive hard shoulder closure status.

[0024] Further areas of application will become apparent from the description given herein. It is understood that the description and the specific examples serve only for illustration and are not intended to limit the scope of this disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] The drawings described herein are for illustrative purposes only and are not intended to limit the scope of the present disclosure in any way. Fig. Figure 1 shows a system for detecting construction site areas for a vehicle according to an exemplary embodiment in a schematic representation. Fig. Figure 2 shows a flowchart of the procedure for detecting construction site areas for a vehicle according to an exemplary embodiment. Fig. Figure 3 shows a first exemplary diagram of the lateral density according to an exemplary embodiment. Fig. Figure 4 shows a second exemplary diagram of the lateral density according to an exemplary embodiment. Fig. Figure 5A shows a flowchart of a procedure for determining a lane relocation status for each of a plurality of road segments according to an exemplary embodiment. Fig. Figure 5B shows an exemplary diagram of the lane relocation according to an exemplary embodiment. Fig. Figure 6 shows a flowchart of a procedure for determining a lane closure status for each of the multitude of road segments according to an exemplary embodiment. Fig. Figure 7 shows a flowchart of a procedure for determining a hard shoulder closure status for each of the multitude of road segments according to an exemplary embodiment. Fig. Figure 8A shows a flowchart of a procedure for determining a hard shoulder closure status for each of the multitude of road segments according to an exemplary embodiment. Fig. Figure 8B shows an exemplary diagram of the velocity distribution according to an exemplary embodiment. DETAILED DESCRIPTION

[0026] The following description is merely exemplary and is not intended to limit the present disclosure, application or use.

[0027] The advent of data feeds providing information about roadworks, such as the Work Zone Data Exchange (WZDx), offers opportunities for increased awareness of construction zones by vehicle occupants and optimized route planning for vehicle navigation systems and automatic route planning systems. However, due to changing road conditions, evolving road construction plans, inaccuracies in data input, and / or similar factors, data feeds providing information about roadworks can become outdated and / or inaccurate. Therefore, this disclosure provides a new and improved system and method for detecting construction zones for a vehicle, enabling the verification, correction, and / or updating of data feeds providing information about roadworks.

[0028] With reference to Fig. Figure 1 illustrates a system for detecting construction site areas for a vehicle and is generally designated by reference numeral 10. System 10 generally comprises a vehicle system 12 and a server system 14.

[0029] The vehicle system 12 is shown with an exemplary vehicle 16. Although a passenger car is illustrated, it should be noted that the vehicle 16 can be any type of vehicle without this deviating from the scope of the present disclosure. The vehicle system 12 generally comprises a vehicle control unit 18 and a plurality of vehicle sensors 20.

[0030] The vehicle control unit 18 is used to implement a method 100 for detecting construction site areas for a vehicle, as described below. The vehicle control unit 18 comprises at least one processor 22 and a non-transient computer-readable storage device or medium 24. The processor 22 can be a custom or commercially available processor, a central processing unit (CPU), a graphics processing unit (GPU), an auxiliary processor among several processors associated with the vehicle control unit 18, a semiconductor-based microprocessor (in the form of a microchip or chipset), a macroprocessor, a combination thereof, or generally an instruction-executing device.

[0031] The computer-readable storage device or medium 24 can include volatile and non-volatile memory, such as read-only memory (ROM), random-access memory (RAM), and keep-alive memory (KAM). A KAM is a persistent or non-volatile memory that can be used to store various operating variables while the processor 22 is turned off. The computer-readable storage device or medium 24 can be implemented using a number of storage devices, such as PROMs (programmable read-only memory), EPROMs (erasable PROMs), EEPROMs (electrically erasable PROMs), flash memory, or other electrical, magnetic, optical, or combined storage devices capable of storing data, some of which represents executable instructions used by the vehicle controller 18 to control various systems of the vehicle 16.

[0032] The vehicle control unit 18 can also comprise multiple control units that are electrically interconnected. The vehicle control unit 18 can be connected to additional systems and / or controls of the vehicle 16, enabling the vehicle control unit 18 to access data such as speed, acceleration, braking, and steering angle of the vehicle 16.

[0033] The vehicle control unit 18 is electrically connected to the plurality of vehicle sensors 20. In an exemplary embodiment, the electrical communication is established, for example, via a CAN network, a FLEXRAY network, a local area network (e.g., WiFi, Ethernet, etc.), an SPI (Serial Peripheral Interface) network, or the like. It is understood that various additional wired and wireless techniques and communication protocols for communication with the vehicle control unit 18 are within the scope of this disclosure. It is further understood that, within the scope of this disclosure, the electrical connection also includes the power and / or energy transfer between electrical devices (e.g., using conductive wires and / or wireless power transfer techniques).

[0034] The plurality of vehicle sensors 20 is used to acquire information relevant to the vehicle 16. In an exemplary embodiment, the plurality of vehicle sensors 20 comprises at least one perception sensor (e.g., a camera system 26, a LiDAR sensor 28, an ultrasonic distance sensor (not shown), a radar sensor (not shown), a time-of-flight sensor (not shown), and / or the like) and a vehicle communication system 30.

[0035] The camera system 26 is a perception sensor used to capture images and / or videos of the environment outside the vehicle 16. In one exemplary embodiment, the camera system 26 comprises a photo and / or video camera positioned to view the environment outside the vehicle 16. In a non-limiting example, the camera system 26 comprises a camera mounted inside the vehicle 16, for example, in the headliner of the vehicle 16, with a view through the windshield. In another non-limiting example, the camera system 26 comprises a camera mounted outside the vehicle 16, for example, on the roof of the vehicle 16, with a view of the environment in front of the vehicle 16.

[0036] In another exemplary embodiment, the camera system 26 is a surround-view camera system comprising a plurality of cameras (also referred to as satellite cameras) arranged to provide a view of the surroundings on all sides of the vehicle 16. In one non-limiting example, the camera system 26 includes a forward-facing camera (e.g., mounted in a radiator grille of the vehicle 16), a rear-facing camera (e.g., mounted on a tailgate of the vehicle 16), and two side-facing cameras (e.g., mounted below each of the two side mirrors of the vehicle 16). In another non-limiting example, the camera system 26 further includes an additional rear-view camera mounted near a high-mounted center brake light of the vehicle 16.

[0037] It is understood that camera systems with additional cameras and / or additional mounting locations fall within the scope of this disclosure. It is further understood that various types of cameras, such as stereo cameras, infrared cameras, thermal imaging cameras, and / or the like, fall within the scope of this disclosure. As discussed above, the camera system 26 is electrically connected to the vehicle control unit 18.

[0038] The LiDAR sensor 28 is a perception sensor used for distance sensing and environmental mapping by emitting laser pulses and measuring the time it takes for the laser pulses to return to the LiDAR sensor 28 after striking objects. In an exemplary embodiment, the LiDAR sensor 28 comprises a LiDAR laser source, a LiDAR scanner or mirror, a LiDAR photodetector, and a LiDAR time-of-flight measurement system. In a non-restrictive example, the LiDAR laser source emits laser pulses that travel into the target area, and the LiDAR scanner directs these pulses in various directions. The emitted laser pulses interact with objects in the environment, and their reflections are detected by the LiDAR photodetector.The LiDAR time-of-flight measurement system calculates the distance to the objects based on the time between the emission of the laser pulses by the LiDAR laser source and the reception of the reflected laser pulses by the LiDAR photodetector. As discussed above, the LiDAR sensor 28 is electrically connected to the vehicle control unit 18.

[0039] The vehicle communication system 30 is used by the vehicle control unit 18 to communicate with other systems outside the vehicle 16. The vehicle communication system 30 includes, for example, functions for communication with vehicles (“V2V” communication), with infrastructure (“V2I” communication), with remote systems in a remote call center (e.g., GENERAL MOTORS ON-STAR), and / or with personal devices. In general, the term vehicle-to-everything communication (“V2X” communication) refers to communication between the vehicle 16 and any remote system (e.g., vehicles, infrastructure, and / or remote systems).

[0040] In certain embodiments, the vehicle communication system 30 is a wireless communication system designed to communicate via a wireless local area network (WLAN) using IEEE 802.11 standards or using radio data communication (e.g., using GSMA standards such as SGP.02, SGP.22, SGP.32, and the like). Accordingly, the vehicle communication system 30 may further comprise an embedded universal integrated circuit card (eUICC) designed to store at least one configuration profile for cellular connectivity, for example, an embedded subscriber identity module (eSIM) profile.

[0041] The vehicle communication system 30 is further designed to communicate via a personal network (e.g., Bluetooth), near-field communication (NFC), and / or any other type of radio frequency communication. Additional or alternative communication methods, such as Dedicated Short Range Communications (DSRC) channels and / or mobile telecommunications protocols based on the standards of the 3rd Generation Partnership Project (3GPP), are also considered within the scope of this disclosure. DSRC channels refer to one-way or two-way short- to medium-range wireless communication channels specifically designed for use in vehicles, as well as a corresponding set of protocols and standards. The 3GPP is a partnership of several standards organizations that develop protocols and standards for mobile telecommunications.3GPP standards are structured as "releases". Therefore, communication procedures based on 3GPP versions 14, 15, 16 and / or future 3GPP versions are covered within the scope of this disclosure.

[0042] Accordingly, the vehicle communication system 30 may include one or more antennas and / or communication transceivers for receiving and / or transmitting signals, such as Cooperative Sensing Messages (CSMs). The vehicle communication system 30 is designed to wirelessly transmit information between the vehicle 16 and another vehicle. Furthermore, the vehicle communication system 30 is designed to wirelessly transmit information between the vehicle 16 and the infrastructure or other vehicles. It is understood that the vehicle communication system 30 may be integrated into the vehicle controller 18 (e.g., on the same circuit board as the vehicle controller 18 or otherwise as part of the vehicle controller 18) without this deviating from the scope of this disclosure. As discussed above, the vehicle communication system 30 is electrically connected to the vehicle controller 18.

[0043] In another exemplary embodiment, the plurality of vehicle sensors 20 further comprises sensors for determining performance data and / or telemetry data about the vehicle 16. In a non-limiting example, the plurality of vehicle sensors 20 further comprises an engine speed sensor, an engine torque sensor, a voltage and / or current sensor of the electric drive motor, an accelerator pedal position sensor, a brake pedal position sensor, a coolant temperature sensor, a cooling fan speed sensor and / or a transmission oil temperature sensor.

[0044] In another exemplary embodiment, the plurality of vehicle sensors 20 further comprises sensors for determining information about an environment in the vehicle 16. In a non-limiting example, the plurality of vehicle sensors 20 further comprises at least a seat occupancy sensor, a passenger compartment air temperature sensor, a passenger compartment motion detection sensor, a passenger compartment camera, a passenger compartment microphone and / or the like.

[0045] In another exemplary embodiment, the plurality of vehicle sensors 20 further comprises sensors for acquiring information and / or telemetry data about an environment outside the vehicle 16. In a non-limiting example, the plurality of vehicle sensors 20 further comprises an ambient air temperature sensor, an air pressure sensor, and / or a global navigation satellite system (GNSS). The plurality of vehicle sensors 20 is, as discussed above, electrically connected to the vehicle control unit 18.

[0046] With further reference to Fig. Figure 1 illustrates the server system and is generally designated by reference numeral 14. The server system 14 comprises a server controller 50, which is electrically connected to a server database 52 and a server communication system 54. In a non-restrictive example, the server system 14 is located in a server farm, a data center, or the like, and is connected to the Internet via the server communication system 54.

[0047] The server controller 50 comprises at least one server processor 56 and a non-transient, computer-readable server storage device or medium 58. The description of the type and design given above for the vehicle controller 18 also applies to the server controller 50. In some examples, the server controller 50 may differ from the vehicle controller 18 in that the server controller 50 is capable of a higher processing speed, includes more memory, more inputs / outputs, and / or the like. In a non-restrictive example, the server processor 56 and the server media 58 of the server controller 50 are similar in structure and / or function to the processor 22 and the media 24 of the vehicle controller 18, as described above.

[0048] The server database 52 serves to store road maps that include, for example, information about lane markings, road geometry, speed limits, traffic signs, construction zones, and / or other relevant features. The server database 52 also serves to store crowdsourced perception and / or telematics data received from remote vehicles (e.g., vehicle 16). In an exemplary embodiment, the server database 52 comprises one or more mass storage devices, such as hard disk drives, magnetic tape drives, magneto-optical disk drives, optical disk drives, solid-state drives, and / or additional devices capable of storing data permanently and in a machine-readable format. In some examples, the one or more mass storage devices may be designed to provide redundancy in the event of a hardware failure and / or data corruption, e.g.,by using a redundant array of independent hard disks (RAID). In a non-restrictive example, the server controller can run 50 software applications, such as a database management system (DBMS), which allows data stored on one or more mass storage devices to be organized and accessed.

[0049] The server communication system 54 is used for communication with external systems, such as the vehicle control unit 18, via the vehicle communication system 30. In a non-restrictive example, the server communication system 54 is similar in structure and / or function to the vehicle communication system 30, as described above. In some examples, the server communication system 54 may differ from the vehicle communication system 30 in that the server communication system 54 is capable of transmitting signals with higher power, receiving signals more sensitively, transmitting with higher bandwidth, using additional transmit / receive protocols, and / or the like.

[0050] In an exemplary embodiment, the server system 14 serves to receive, store, and aggregate telemetry data from a plurality of remote vehicles. For the purposes of this disclosure, telemetry data includes data describing an operating state of the plurality of remote vehicles. In a non-limiting example, the telemetry data includes the vehicle location, vehicle speed, vehicle course, vehicle acceleration, vehicle type / size, and / or the like. For the purposes of this disclosure, the plurality of remote vehicles includes any vehicle (e.g., vehicle 16) operating in the vicinity.

[0051] In an exemplary embodiment, both the vehicle 16 and the multitude of remote vehicles continuously measure telemetry data and transmit the telemetry data to the server communication system 54. The server controller 50 aggregates the received telemetry data and stores it in the server database 52.

[0052] The server database 52 can then be queried to retrieve both current and historical telemetry data for vehicles at a specific location, time, type, and / or similar conditions. The server database 52 can also include detailed environmental maps with information on lane markings, road geometry, speed limits, traffic signs, construction zones, and / or other relevant features. The server controller 50 can then contextualize the received telemetry data using these detailed environmental maps.

[0053] In another exemplary embodiment, the server system 14 further serves to receive, transmit, and / or store information about traffic and / or road construction work. In a non-limiting example, the server database 52 comprises one or more construction site area records corresponding to the construction sites. For the purposes of this disclosure, a construction site area is an area in the surroundings where construction work is taking place that affects the flow of traffic on the roadway. In a non-limiting example, the one or more construction site area records may include fields containing a position of the construction site area (e.g., a start and end point of the construction site area), a status of the construction site area (e.g., active construction site area, inactive construction site area, and / or the like), a time frame of the construction site area (e.g.,Work start date, work end date, working hours, and / or the like), details about any impact of the work zone on traffic flow (e.g., information about lane / road closures), and / or the like. It is understood that the one or more work zone records may include any number of fields and be stored in any format (e.g., in a machine-readable format such as JSON, GeoJSON, XML, and / or the like) and / or conform to any standard or specification, such as the Work Zone Data Exchange (WZDx) specification or the Connected Work Zone (CWZ) standard supported by the United States Department of Transportation (USDOT).

[0054] In one exemplary embodiment, the one or more construction site area data records are provided by direct data input into the server system 14. In another exemplary embodiment, the one or more construction site area data records are received from an external system via the server communication system 54. Due to changing road conditions, changing road construction plans, inaccuracies in data input, and / or the like, the one or more construction site area data records may be outdated and / or inaccurate. Therefore, the present disclosure provides a method 100 for detecting construction sites, which can be used to update and / or correct the one or more construction site area data records, as discussed in more detail below.

[0055] With reference to Fig. Figure 2 provides a flowchart of Method 100 for detecting construction site areas for a vehicle. Method 100 begins in Block 102 and continues with Blocks 104 and 106. In Block 104, the vehicle controller 18 of the vehicle system 12 uses one or more of the plurality of vehicle sensors 20 to receive measurement data about the environment outside the vehicle 16. In one exemplary embodiment, the camera system 26 is used to capture one or more images of the environment. In another exemplary embodiment, the LiDAR sensor 28 is used to measure distances to one or more objects in the environment. In a non-limiting example, the measurement data includes camera images, LiDAR measurements, or environmental maps and / or the like. After Block 104, Method 100 continues with Block 108.

[0056] In block 108, the vehicle control unit 18 of the vehicle system 12 uses the vehicle communication system 30 of the vehicle system 12 to transmit the measurement data acquired in block 104 to the server communication system 54 of the server system 14. In an exemplary embodiment, the measurement data is transmitted to the internet via a cellular data connection. After block 108, the method 100 continues with block 110.

[0057] In block 110, the server controller 50 of the server system 14 receives the measurement data transmitted in block 108 using the server communication system 54. The server controller 50 then analyzes the measurement data to detect a cluster of construction site objects in the vicinity. For the purposes of this disclosure, a construction site object includes any object in the vicinity that indicates the presence of construction work affecting the flow of traffic on a roadway in the vicinity. Examples of construction site objects may include road signs indicating construction sites (e.g., road signs inscribed with "CAUTION CONSTRUCTION SITE," road signs of a specific color intended to indicate a construction site, and / or the like), road barriers indicating construction sites (e.g., construction cones, construction buoys, temporary barriers), and construction site vehicles (e.g.,Vehicles with flashing lights or reflectors, heavy equipment such as cranes, excavators or dump trucks and / or the like) and / or construction site workers (e.g. persons near the lane, persons wearing warning clothing, persons carrying out road work, and / or the like).

[0058] Within the scope of this disclosure, a cluster of construction site objects means a plurality of construction site objects arranged in the environment in such a way that they are mutually reachable under certain predetermined conditions. In a non-restrictive example, the predetermined conditions may include the maximum distance between construction site objects, the maximum lateral offset between construction site objects, the maximum angle between construction site objects, and / or the like.

[0059] In one exemplary embodiment, the server controller 50 detects a cluster of construction site objects in the vicinity based on the measurement data. In a non-restrictive example, the server controller 50 uses a data clustering algorithm, such as DBSCAN (Density Based Spatial Clustering of Applications with Noise), as discussed in "A Density-Based Algorithm for Discovering Clusters" by Ester et al. (Proceedings of the Second International Conference on Knowledge Discovery and Data Mining, pp. 226-231, Aug. 1996), the entire content of which is hereby incorporated by reference. It is understood that alternative or additional data clustering algorithms, such as...Distributed DBSCAN (DDBSCAN), k-means, agglomerative clustering, mean-shift, Gaussian mixture models, spectral clustering, affinity propagation, balanced iterative reduction and clustering using hierarchies (BIRCH), ordering points to identify the clustering structure (OPTICS), fuzzy c-means and / or the like can be used without departing from the scope of this disclosure. After block 110, method 100 continues with block 112.

[0060] In Block 112, the server controller 50 determines a start point and an end point of a construction zone. For the purposes of this disclosure, a construction zone is an area in the environment where construction work is taking place that affects the flow of traffic on the roadway. In an exemplary embodiment, the start point and the end point are determined at least partially based on the cluster of construction zone objects identified in Block 110. In a non-restrictive example, the start point and the end point are determined such that they are located at construction zone objects at two extremes of the cluster (e.g., the start point is located at the position of the westernmost construction zone object in the cluster, and the end point is located at the position of the easternmost construction zone object in the cluster).In another non-restrictive example, the starting point and endpoint are determined such that they are located at two of the most distant site area objects in the cluster (e.g., by determining a distance between each possible combination of two site area objects in the cluster and selecting the starting and endpoints based on the combination of two site area objects with the greatest distance between them). After Block 112, Procedure 100 continues with Block 114.

[0061] In Block 114, the server controller 50 divides the construction site area into a multitude of road segments. These multiple road segments, taken together, extend from the starting point to the endpoint of the construction site area defined in Block 112. In one exemplary embodiment, the construction site area is divided into a multitude of equally sized road segments of a predetermined length (e.g., one hundred meters). In another exemplary embodiment, the construction site area is divided into a multitude of equally sized road segments whose length is determined based on the total length of the construction site area (e.g., each road segment has a length that is ten percent of the total length of the construction site area).In another exemplary embodiment, the plurality of road segments is dimensioned such that the construction area comprises a predetermined number of road segments (e.g., ten road segments). In another exemplary embodiment, the entire construction area is represented by a single road segment if the total length of the construction area is less than a predetermined minimum length (e.g., one hundred meters). It is understood that various additional methods for dividing the construction area into a plurality of road segments, including methods that result in road segments of different lengths, are within the scope of this disclosure. In one exemplary embodiment, the starting point and the end point of the construction area determined in Block 112, as well as data identifying the plurality of road segments (e.g.,(A start and end point of each of the numerous road segments) are stored in server database 52 for later use. After block 114, procedure 100 continues with block 116, as described in more detail below.

[0062] In block 106, the server controller 50 of the server system 14 receives telemetry data from the multitude of remote vehicles in the environment outside of vehicle 16 using the server communication system 54. As discussed above, both vehicle 16 and the multitude of remote vehicles continuously measure telemetry data and transmit this data to the server communication system 54. In block 106, the server controller 50 aggregates the received telemetry data and stores it in the server database 52. After block 106, the procedure 100 continues with block 116.

[0063] In block 116, the server controller 50 determines a plurality of lateral total density distributions. Each of these plurality of lateral total density distributions describes a spatial distribution of the plurality of distant vehicles within one of the plurality of road segments of the construction area. In an exemplary embodiment, the plurality of lateral total density distributions is determined based on the most recent historical telemetry data received in block 106 and / or retrieved from the server database 52. In a non-restrictive example, the vehicle positions are aggregated from the most recent historical telemetry data to generate a probability density function that describes the probability of finding one of the plurality of distant vehicles at any given lateral offset within each of the plurality of road segments.

[0064] With reference to Fig. Figure 3 shows a first exemplary diagram 60 of lateral density. This first exemplary diagram 60 of lateral density includes an x-axis 62a, which indicates a position on the roadway (e.g., an offset relative to a left edge of the roadway), and a y-axis 62b, which indicates a magnitude of vehicle density. The first exemplary diagram 60 of lateral density further includes boxes that denote lanes of the roadway, e.g., a first lane 64a, a second lane 64b, and a third lane 64c. The first exemplary diagram 60 of lateral density further includes an exemplary total lateral density distribution 66 for one of the multitude of road segments. The exemplary lateral total density distribution 66 shows a higher density in the second lane 64b and the third lane 64c compared to the first lane 64a, which may indicate a closure or other obstruction on the first lane 64a.With renewed reference to . Fig. 2 continues procedure 100 after block 116 with block 118.

[0065] In block 118, the server controller 50 separates each of the multiple total lateral density distributions determined in block 116 into a multiple of lateral lane density distributions. Each of these multiple lateral lane density distributions corresponds to one of a multiple of lanes on one of the multiple road segments of the construction site area. In an exemplary embodiment, the server controller 50 uses a Gaussian mixing model (GMM) to separate each of the multiple total lateral density distributions determined in block 116 into a multiple of lateral lane density distributions.

[0066] The GMM represents each of the multitude of lateral total density distributions as a mixture of the multitude of lateral lane density distributions. Each of the multitude of lateral lane density distributions is defined by a mean vector, a covariance matrix, and a set of mixing coefficients that determine the weight of each of the multitude of lateral lane density distributions in the GMM. The GMM is trained, for example, with an expectation-maximization algorithm (EM algorithm) that iteratively adjusts the mean vector, the covariance matrix, and the mixing coefficients of each of the multitude of lateral lane density distributions until the GMM exactly represents one of the multitude of lateral total density distributions. This process is repeated until each of the multitude of lateral total density distributions is exactly represented by a subset of the multitude of lateral lane density distributions.

[0067] With reference to Fig. Figure 4 shows a second exemplary diagram of lateral density 70. This second exemplary diagram 70 of lateral density includes the x-axis 62a, which indicates a position on the roadway (e.g., an offset relative to a left edge of the roadway), and the y-axis 62b, which indicates the magnitude of the vehicle density. The second exemplary diagram 70 of lateral density further includes boxes that designate lanes of the roadway, e.g., the first lane 64a, the second lane 64b, and the third lane 64c. The second exemplary diagram 70 of lateral density also includes the exemplary total lateral density distribution 66 for one of the multitude of road segments.

[0068] The second exemplary diagram 70 of the lateral density further comprises a first exemplary lateral lane density distribution 72a, corresponding to the first lane 64a, a second exemplary lateral lane density distribution 72b, corresponding to the second lane 64b, and a third exemplary lateral lane density distribution 72c, corresponding to the third lane 64c. The first exemplary lateral lane density distribution 72a has a first mean 74a, the second exemplary lateral lane density distribution 72b has a second mean 74b, and the third exemplary lateral lane density distribution 72c has a third mean 74c.As discussed above, the first exemplary lateral lane density distribution 72a, the second exemplary lateral lane density distribution 72b and the third exemplary lateral lane density distribution 72c are determined on the basis of the exemplary total lateral density distribution 66, using, for example, a Gaussian mixture model (GMM) trained using an expectation maximization algorithm (EM algorithm).

[0069] Furthermore, a high-density area is defined on each of the multitude of lanes within each of the multitude of road segments. In a non-restrictive example, the high-density area is an area within each of the multitude of lanes that exhibits a lateral lane density distribution greater than or equal to a predefined lateral density threshold. In another non-restrictive example, the high-density area is defined relative to the mean of each of the multitude of lateral lane density distributions, for example, as an area that lies within plus or minus one standard deviation of the mean.

[0070] In the second exemplary diagram 70 of the lateral density, the first lane 64a has a first high-density area 76a, determined based on the first exemplary lateral lane density distribution 72a; the second lane 64b has a second high-density area 76b, determined based on the second exemplary lateral lane density distribution 72b; and the third lane 64c has a third high-density area 76c, determined based on the third exemplary lateral lane density distribution 72c. The first high-density area 76a is centered on the first mean 74a in such a way that a position of the first high-density area 76a is defined as the position of the first mean 74a.The second high-density region 76b is centered on the second mean 74b in such a way that a position of the second high-density region 76b is defined as the position of the second mean 74b. The third high-density region 76c is centered on the third mean 74c in such a way that a position of the third high-density region 76c is defined as the position of the third mean 74c.

[0071] The width of the first high-density region 76a is defined as the width 78a of the first high-density region. The width of the second high-density region 76b is defined as the width 78b of the second high-density region. The width of the third high-density region 76c is defined as the width 78c of the third high-density region. With further reference to Fig. 2 continues procedure 100 after block 118 with blocks 120, 122, 124 and 126.

[0072] In block 120, the server controller 50 determines a lane relocation status for each of the plurality of road segments. Within the scope of this disclosure, the lane relocation status comprises either a positive lane relocation status or a negative lane relocation status. The positive lane relocation status indicates that a lane relocation has occurred within a road segment. Within the scope of this disclosure, a lane relocation is a lateral displacement of a lane of a carriageway due to road construction work. In a non-restrictive example, a lane relocation includes moving the first lane of a northbound highway across a median strip to the first lane of a southbound highway. The determination of the lane relocation status for each of the plurality of road segments is discussed in more detail below.Following block 120, procedure 100 continues with block 128, as will be discussed in more detail below.

[0073] In Block 122, the server controller 50 determines a lane closure status for each of the multiple road segments. Within the scope of this disclosure, the lane closure status comprises either a positive lane closure status or a negative lane closure status. The positive lane closure status indicates that a lane closure has occurred within a road segment. Within the scope of this disclosure, a lane closure is the closure or blocking of a lane of a roadway due to road construction work. The determination of the lane closure status for each of the multiple road segments is discussed in more detail below. Following Block 122, the method 100 continues with Block 128, as discussed in more detail below.

[0074] In Block 124, the server controller 50 determines a hard shoulder closure status for each of the multiple road segments. Within the scope of this disclosure, the hard shoulder closure status comprises either a positive hard shoulder closure status or a negative hard shoulder closure status. The positive hard shoulder closure status indicates that a hard shoulder closure has occurred within a road segment. Within the scope of this disclosure, a hard shoulder closure is the closure or blocking of a hard shoulder of a carriageway or the narrowing of a carriageway due to roadworks. The determination of the hard shoulder closure status for each of the multiple road segments is discussed in more detail below. Following Block 124, the procedure 100 continues with Block 128, as discussed in more detail below.

[0075] In Block 126, the server controller 50 determines a speed limit for each of the multiple road segments. For the purposes of this disclosure, the speed limit is a permissible speed for driving on the road segment, based on legal regulations, environmental conditions, and / or road conditions. The determination of the speed limit for each of the multiple road segments is discussed in more detail below. Following Block 126, the procedure 100 continues with Block 128.

[0076] In block 128, the server controller 50 receives one or more construction site area data records, as discussed above with regard to the server system 14. In an exemplary embodiment, the one or more construction site area data records are received from authorities such as state governments, local authorities, municipalities, road maintenance depots, and / or the like. The one or more construction site area data records are stored in the server database 52 for later retrieval. After block 128, the procedure 100 continues with block 130.

[0077] In block 130, the server controller 50 queries the server database 52 to retrieve construction site area data records that have start points and / or end points in the vicinity (e.g., within a predefined distance or radius) of the start and end points of the construction site area determined in block 112. The server controller 50 then compares the data in the retrieved construction site area data records with the information determined in blocks 112, 120, 122, 124, and 126.If discrepancies are detected between the retrieved construction site area records and the information obtained in blocks 112, 120, 122, 124 and 126, the retrieved construction site area records will be updated at least partially based on the information obtained in blocks 112, 120, 122, 124 and 126, and the updated construction site area records will then be transmitted back to the source of the construction site area records (i.e., state governments, local governments, municipalities, road maintenance depots and / or the like) using Server Communication System 54.

[0078] In a non-restrictive example, the position of the construction area (i.e., the start and end points of the construction area) contained in the retrieved construction area data records may differ from the start and end points of the construction area determined in Block 112. Therefore, the retrieved construction area data record is updated to reflect the start and end points of the construction area determined in Block 112 and sent back to the source of the retrieved construction area data record for storage, processing, and / or redistribution to other systems (e.g., the multitude of remote vehicles).In another, non-restrictive example, the information contained in the retrieved construction zone datasets regarding lane shifting, lane closure, hard shoulder closure, and / or speed limits may differ from the information regarding lane shifting, lane closure, hard shoulder closure, and / or speed limits obtained from blocks 120, 122, 124, and 126. Therefore, the retrieved construction zone dataset is updated to reflect the lane shifting, lane closure, hard shoulder closure, and / or speed limit information obtained from blocks 120, 122, 124, and 126 and transmitted back to the source of the retrieved construction zone dataset for storage, processing, and / or redistribution to other systems or remote devices (e.g., the multitude of remote vehicles).After block 130, procedure 100 continues with block 132 to enter a standby state.

[0079] In one exemplary embodiment, the method 100 repeatedly leaves the ready state 132 and restarts in block 102. In a non-restrictive example, the method 100 is restarted after a timer, e.g., every three hundred milliseconds.

[0080] With reference to Fig. Figure 5A shows a flowchart of an exemplary embodiment 500 of Block 120 (i.e., a method for determining a lane relocation status for each of the plurality of road segments). The exemplary embodiment 500 of Block 120 begins in Block 502. With reference to Fig. 5A and with further reference to Fig. 4. Server control 50 in block 502 determines the high-density area on each of the multitude of lanes within each of the multitude of road segments (e.g., the first high-density area 76a, the second high-density area 76b, and the third high-density area 76c), as above with reference to Fig. 4 is discussed. In one non-restrictive example, the high-density area is a region within each of the plurality of lanes that has a lateral lane density distribution greater than or equal to a predetermined lateral density threshold. In another non-restrictive example, the high-density area is defined relative to the mean of each of the plurality of lateral lane density distributions, for example, as a region that lies within plus or minus one standard deviation of the mean. Following Block 502, Exemplary Embodiment 500 transitions from Block 120 to Block 504.

[0081] In block 504, server control 50 determines an average position of the high-density area on each lane across the numerous road segments. As above, with reference to Fig. As discussed in section 4, in a non-restrictive example, the first high-density area 76a for a single road segment is centered on the first mean 74a in such a way that a position of the first high-density area 76a is defined as the position of the first mean 74a. The second high-density area 76b is centered on the second mean 74b in such a way that a position of the second high-density area 76b is defined as the position of the second mean 74b. The third high-density area 76c is centered on the third mean 74c in such a way that a position of the third high-density area 76c is defined as the position of the third mean 74c.

[0082] To determine the average position of the high-density area on each lane across the multitude of road segments, the position of the high-density area on each lane is averaged across all of the multitude of road segments. In a non-restrictive example, the average position of the high-density area on each lane across the multitude of road segments is normalized to a known roadside location based on detailed maps in such a way that bends or curves in the road do not affect the average position of the high-density area on each lane across the multitude of road segments. Following Block 504, Exemplary Embodiment 500 transitions from Block 120 to Block 506.

[0083] In block 506, the server controller 50 determines a plurality of lane-aligned road segments. The plurality of lane-aligned road segments is a subset of the plurality of road segments. In an exemplary embodiment, each lane-aligned road segment from the plurality of road segments is one from the plurality of road segments, wherein a position of the high-density area on at least one of the plurality of lanes deviates from the average position of the high-density area of ​​the at least one of the plurality of lanes by a greater than or equal to a predetermined threshold value for the deviation from the lane alignment.In another exemplary embodiment, each of the multiple lane-laid road segments is one of the multiple road segments, wherein a distance between a position of the high-density area on a first lane of the multiple lanes and a position of the high-density area on a second lane of the multiple lanes deviates from an average distance by a greater than or equal to a predetermined threshold for deviation from the distance.

[0084] With reference to Fig. Figure 5B shows an example diagram 80 of the lane relocation. The example diagram 80 of the lane relocation includes an x-axis 82a that shows a road segment (i.e., rising from left to right such that points near the left side of the x-axis 82a represent road segments near the starting point of the construction area and points near the right side of the x-axis 82a represent road segments near the end point of the construction area). The example diagram 80 of the lane relocation also includes a y-axis 82b that indicates the position relative to a road edge.

[0085] Exemplary diagram 80 of the lane relocation further comprises a first curve 84a, illustrating changes in the position of the high-density area across the multitude of road segments for a first exemplary lane, and a second curve 84b, illustrating changes in the position of the high-density area across the multitude of road segments for a second exemplary lane. The average position of the high-density area on the first exemplary lane is indicated by a first dashed line 86a. The multitude of lane-relocated road segments are indicated by a first dashed box 86b, which includes road segments where the position of the high-density area for the first exemplary lane (i.e.,the first curve 84a) deviates from the average position of the high-density area on the first exemplary lane (i.e., the first dashed line 86a) by at least one exemplary threshold for deviation from the lane realignment 86c. With renewed reference to . Fig. In 5A, the exemplary embodiment 500 transitions from block 120 to block 506 to block 508.

[0086] In Block 508, the lane relocation status determined in Block 506 is identified as the positive lane relocation status for each of the multiple lane-relocated road segments. Following Block 508, Exemplary embodiment 500 of Block 120 is completed, and Method 100 continues as discussed above.

[0087] With reference to Fig. Figure 6 shows a flowchart of an exemplary embodiment 600 of Block 122 (i.e., a method for determining a lane closure status for each of the plurality of road segments). The exemplary embodiment 600 of Block 122 begins in Block 602. In Block 602, the server controller 50 determines an average lane density on each of the plurality of lanes across the plurality of road segments. In an exemplary embodiment, the average lane density on a given lane of a given road segment is equal to the mean of the lateral lane density distribution corresponding to the given lane and the given road segment. With reference to Fig. 4. In a non-restrictive example, the average lane density on the first lane 64a in a section is determined as the first mean value 74a. To determine the average lane density on each of the many lanes across the many road sections, the average lane density on each of the many lanes across the many road sections is averaged. With renewed reference to Fig. In section 6, exemplary embodiment 600 transitions from block 122 to block 602 to block 604.

[0088] In block 604, the server controller 50 determines a plurality of lane-closed road segments. The plurality of lane-closed road segments is a subset of the plurality of road segments. In one exemplary embodiment, each lane-closed road segment from the plurality of road segments is one from the plurality of road segments, wherein the average lane density differs from the average lane density of at least one lane from the plurality of lanes across the plurality of road segments, determined in block 602, by a greater than or equal to a predetermined threshold for the deviation from the lane closure. In another exemplary embodiment, each lane-closed road segment from the plurality of road segments is one from the plurality of road segments, wherein the average lane density differs from a historical average lane density (e.g.,(determined on the basis of the processing of historical telemetry data stored in server database 52) by a greater than or equal to the specified threshold for deviation from the lane closure. After block 604, exemplary embodiment 600 transitions from block 122 to block 606.

[0089] In Block 606, the lane closure status determined in Block 604 is identified as the positive lane closure status for each of the multiple lane-closed road segments. Following Block 606, Exemplary embodiment 600 of Block 122 is completed, and Method 100 continues as discussed above.

[0090] With reference to Fig. Figure 7 shows a flowchart of an exemplary embodiment 700 of Block 124 (i.e., a method for determining a hard shoulder closure status for each of the plurality of road segments). The exemplary embodiment 700 of Block 124 begins in Block 702. With reference to Fig. 7 and with further reference to Fig. 4. Server control 50 in block 702 determines the high-density area on each of the multitude of lanes within each of the multitude of road segments (e.g., the first high-density area 76a, the second high-density area 76b, and the third high-density area 76c), as above with reference to Fig. 4 is discussed. In one non-restrictive example, the high-density area is a region within each of the plurality of lanes that has a lateral lane density distribution greater than or equal to a predetermined lateral density threshold. In another non-restrictive example, the high-density area is defined relative to the mean of each of the plurality of lateral lane density distributions, for example, as a region that lies within plus or minus one standard deviation of the mean. Following Block 702, Exemplary Embodiment 700 transitions from Block 124 to Block 704.

[0091] In block 704, server control 50 determines an average width of the high-density area on each lane across the numerous road segments. As above, with reference to Fig. As discussed in section 4, in an example for a single road segment, the width 78a of the first high-density area, the width 78b of the second high-density area, and the width 78c of the third high-density area depend on the specified threshold for lateral density. In another, non-restrictive example, the width 78a of the first high-density area, the width 78b of the second high-density area, and the width 78c of the third high-density area depend on a specified width around the mean of each of the multitude of lateral lane density distributions, e.g., plus or minus one standard deviation from the mean.

[0092] To determine the average width of the high-density area on each lane across the multitude of road segments, the width of the high-density area on each lane is averaged across all of the multitude of road segments. Following Block 704, exemplary embodiment 700 transitions from Block 124 to Block 706.

[0093] In block 706, the server controller 50 determines a plurality of hard shoulder road segments. The plurality of hard shoulder road segments is a subset of the plurality of road segments. In an exemplary embodiment, each hard shoulder road segment from the plurality of road segments is one from the plurality of road segments, wherein the width of the high-density area on at least one of the plurality of lanes deviates from the average width of the high-density area on the at least one of the plurality of lanes determined in block 704 by a greater than or equal to a predetermined threshold for the deviation from the hard shoulder closure.This is because closing the hard shoulder can actually lead to a narrowing of the lanes, as objects on the hard shoulder cause vehicle occupants to tend to drive in a narrower area of ​​the adjacent lanes. Therefore, the same procedure discussed above for determining the hard shoulder closure status can also be used to determine a lane narrowing status. Following Block 706, Exemplary Embodiment 700 transitions from Block 124 to Block 708.

[0094] In Block 708, the hard shoulder closure status determined in Block 706 is identified as the positive hard shoulder closure status for each of the multiple hard shoulder road segments. Following Block 708, Exemplary Implementation 700 of Block 124 is completed, and Method 100 continues as discussed above.

[0095] With reference to Fig. Figure 8A shows a flowchart of an exemplary embodiment 800 of Block 126 (i.e., a method for determining a hard shoulder closure status for each of the plurality of road segments). The exemplary embodiment 800 of Block 126 begins in Block 802. In Block 802, the server controller 50 determines a plurality of total velocity density distributions, at least partially, based on the telemetry data received in Block 106 and / or the historical telemetry data stored in the server database 52. Each of the plurality of total velocity density distributions describes a velocity distribution of the plurality of remote vehicles within one of the plurality of road segments of the construction area.

[0096] With reference to Fig. Figure 8B shows an exemplary diagram 90 of the speed distribution. The exemplary diagram 90 of the speed distribution includes an x-axis 92a, which indicates the speed (e.g., in kilometers per hour), and a y-axis 92b, which indicates the frequency (i.e., the number of vehicles traveling at each speed within one of the many road segments of the construction area). The exemplary diagram 90 of the speed distribution further includes an exemplary speed distribution 94. With renewed reference to Fig. In 8A, the exemplary embodiment 800 passes from block 126 to block 802 to block 804.

[0097] In block 804, the server controller 50 determines an average speed for each of the multitude of road segments, at least partially, based on the multitude of overall speed density distributions. In an exemplary embodiment, the average speed for one of the multitude of road segments is determined using a weighted average based on the frequency of each speed. With further reference to Fig. 8B further includes the exemplary diagram 90 of the speed distribution, as well as a second dashed line 96a, which indicates the average speed for one of the many road segments. With renewed reference to Fig. In 8A, the exemplary embodiment 800 passes from block 126 to block 804 to block 806.

[0098] In block 806, server controller 50 generates a multitude of truncated total velocity density distributions by truncating each of the multitude of total velocity density distributions to a predetermined range around the average velocity determined in block 804. In one non-restrictive example, the predetermined range is plus or minus ten kilometers per hour. In another non-restrictive example, the predetermined range is plus or minus thirty kilometers per hour. Referring again to Fig. 8B further includes the exemplary diagram 90 of the velocity distribution, and a second dashed box 96b, which shows an exemplary abbreviated overall velocity density distribution. With renewed reference to Fig. In 8A, the exemplary embodiment 800 transitions from block 126 to block 806 to block 808.

[0099] In Block 808, the server controller 50 determines the speed limit for each of the plurality of road segments as a truncated average speed. In an exemplary embodiment, the truncated average speed is determined using a weighted average based on the frequency of each speed within the truncated overall speed density distribution for each of the plurality of road segments. Following Block 808, the exemplary embodiment 800 of Block 126 is completed, and the method 100 continues as discussed above.

[0100] System 10 and Method 100 of this disclosure offer several advantages. System 10 and Method 100 can be used to verify, correct, and / or update electronically transmitted construction site area datasets or data feeds, such as WZDx construction site area datasets and / or the like. System 10 and Method 100 enable the crowdsourcing of perception and telemetry data from multiple vehicles and their processing using Server System 14. The starting and ending points of construction site areas are determined using clustering techniques based on the perception data obtained through crowdsourcing. The status of traffic lanes, including lane shifts, lane closures, lane narrowings, hard shoulder closures, and speed limits, is determined based on a statistical analysis of the telemetry data obtained through crowdsourcing.Accordingly, the reliability and accuracy of electronically transmitted information on road construction works and construction site areas on roads can be increased using System 10 and Procedure 100.

[0101] The description of the present revelation is merely exemplary, and variations that do not deviate from the main point of the present revelation are to be considered within the scope of the present revelation. Such variations are not to be understood as a departure from the spirit and scope of the present revelation. QUOTES INCLUDED IN THE DESCRIPTION

[0000] This list of documents cited by the applicant was automatically generated and is included solely for the reader's convenience. The list is not part of the German patent or utility model application. The DPMA accepts no liability for any errors or omissions. Zitierte Nicht-Patentliteratur

[0000] A Density-Based Algorithm for Discovering Clusters“ von Ester et al. (Proceedings of the Second International Conference on Knowledge Discovery and Data Mining, S. 226-231, Aug. 1996

[0059]

Claims

[1] Method for detecting construction site areas for a vehicle, the method comprising: Receiving measurement data about an environment surrounding the vehicle using a vehicle sensor, wherein the measurement data includes perception data of the environment and telemetry data from a multitude of remote vehicles in the environment, Determining a starting point and an endpoint of a construction site area, at least partially based on measurement data, wherein the construction site area represents a multitude of road segments extending from the starting point to the endpoint, Determining a lane relocation status for each of the numerous road segments, Determining a lane closure status for each of the many road segments, Determining a hard shoulder closure status for each of the many road sections and Determining a speed limit for each of the many road sections. [2] Method according to claim 1, wherein determining the starting point and the end point of the construction site area further comprises: Detecting a cluster of construction site objects in the vicinity, at least partially based on perception data, wherein the cluster of construction site objects includes a construction site traffic sign, a construction site road barrier, a construction site vehicle and / or a construction site worker, Determining the starting point and the end point of the construction site area, at least partially, based on the position of the cluster of construction site area objects and Dividing the construction site area into a multitude of road segments extending from the starting point to the end point of the construction site area, each of the multitude of road segments being of the same length. [3] Method according to claim 2, wherein the detection of the cluster of construction site area objects in the surroundings comprises: Detection of the cluster of construction site objects in the surrounding area, at least partially based on perception data, using a DBSCAN algorithm (Density Based Spatial Clustering of Applications with Noise). [4] Method according to claim 1, wherein determining the lane relocation status, the lane closure status and the hard shoulder closure status further comprises: Determining a multitude of lateral lane density distributions, where each of the multitude of lateral lane density distributions corresponds to one of the multitude of lanes on one of the multitude of road sections of the construction area, Determining the lane relocation status for each of the multitude of road segments, at least partially based on the multitude of lateral lane density distributions, Determining a lane closure status for each of the multitude of road segments, at least partially based on the multitude of lateral lane density distributions and Determining the hard shoulder closure status for each of the multitude of road segments, at least partially based on the multitude of lateral lane density distributions. [5] Method according to claim 4, wherein determining the plurality of lateral lane density distributions further comprises: Determine a multitude of lateral total density distributions, at least partially based on telemetry data, wherein each of the multitude of lateral total density distributions describes a spatial distribution of the multitude of remote vehicles within one of the multitude of road segments of the construction site area, and Separating the multitude of lateral total density distributions into the multitude of lateral lane density distributions using a Gaussian mixture model (GMM), where each of the multitude of lateral lane density distributions corresponds to one of the multitude of lanes within one of the multitude of road segments of the construction area. [6] The method of claim 4, wherein determining the lane relocation status for each of the plurality of road segments further comprises: Determining a high-density area on each of the multitude of lanes within each of the multitude of road segments, wherein the high-density area is an area within each of the multitude of lanes that has a lateral lane density distribution greater than or equal to a predetermined lateral density threshold, Determining an average position of the high-density area on each of the many lanes across the many road segments, Determining a plurality of lane-shifted road segments, wherein the plurality of lane-shifted road segments is a subset of the plurality of road segments, and wherein a position of the high-density area on at least one of the plurality of lanes on each of the plurality of lane-shifted road segments deviates from the average position of the high-density area on the at least one of the plurality of lanes by a greater than or equal to a predetermined threshold for deviation from lane shifting, and Determining the lane relocation status for each of the many lane-relocated road segments as a positive lane relocation status. [7] The method of claim 4, wherein determining the lane closure status for each of the plurality of road segments further comprises: Determining an average lane density on each of the multitude of lanes across the multitude of road segments, at least partially based on the multitude of lateral lane density distributions, Identifying a plurality of lane-closed road segments, wherein the plurality of lane-closed road segments is a subset of the plurality of road segments, and wherein an average lane density on at least one of the plurality of lanes on each of the plurality of lane-closed road segments deviates from the average lane density on the at least one of the plurality of lanes by a greater than or equal to a predetermined threshold for deviation from the lane closure, and Determine the lane closure status for each of the many lane-closing road segments as a positive lane closure status. [8] The method of claim 4, wherein determining the hard shoulder closure status for each of the plurality of road sections further comprises: Determining a high-density area on each of the multitude of lanes within each of the multitude of road segments, wherein the high-density area is an area within each of the multitude of lanes that has a lateral lane density distribution greater than or equal to a predetermined lateral density threshold, Determining an average width of the high-density area on each of the many lanes across the many road segments, Identifying a plurality of hard shoulder road segments, wherein the plurality of hard shoulder road segments is a subset of the plurality of road segments, and wherein the width of the high-density area on at least one of the plurality of lanes on each of the plurality of hard shoulder road segments deviates from the average width of the high-density area on the at least one of the plurality of lanes by a greater than or equal to a predetermined threshold for deviation from hard shoulder closure, and Determine the hard shoulder closure status for each of the many hard shoulder road sections as a positive hard shoulder closure status. [9] The method of claim 1, wherein determining the speed limit for each of the plurality of road segments further comprises: Determining a multitude of total velocity density distributions, at least partially based on telemetry data, wherein each of the multitude of total velocity density distributions describes a velocity distribution of the multitude of remote vehicles within one of the multitude of road sections of the construction area, Determining an average speed for each of the many road segments based on the many total speed density distributions, Generating a multitude of truncated total velocity density distributions by truncating each of the multitude of total velocity density distributions to a predetermined range around the average speed for each of the multitude of road segments, and Determining the speed limit for each of the multitude of road segments as a truncated average speed for each of the multitude of road segments based on the multitude of truncated total speed density distributions. [10] Method according to claim 1, further comprising: Transmitting the starting and ending points of the construction area, the lane relocation status for each of the multitude of road segments, the lane closure status for each of the multitude of road segments, the hard shoulder closure status for each of the multitude of road segments, and the speed limit for each of the multitude of road segments to a remote device.

Images