Identifying road safety events in remotely operated vehicles

Abstract

According to several aspects, a method for identifying road safety events may include performing a measurement of one or more target vehicles with a sensor. The method may further include identifying a safety event based at least in part on the measurement of the one or more target vehicles. The method may further include performing an action based at least in part on the safety event.

Description

introduction

[0001] This description relates to systems and methods for identifying road safety events for a vehicle.

[0002] To increase occupant alertness and comfort, vehicles may be equipped with sensor and communication systems that enable communication between vehicles on the roadway. Communication systems can be used to transmit information between vehicles, such as location, direction, speed, and / or similar information. Such information can be used to detect road safety events, such as harsh braking or near-collisions. Vehicles may also be equipped with advanced driver assistance systems (ADAS), which allow the vehicle to notify the occupant and / or take actions based on information about road safety events. However, some vehicles are not equipped with communication systems and therefore may not be able to transmit information to other vehicles.Without information about the vehicle's location, heading, speed and / or similar, the performance and / or availability of ADAS system features may be limited.

[0003] Although the detection and communication systems and methods serve their purpose, there is a need for a new and improved system and method for identifying road safety events for a vehicle. Description

[0004] According to several aspects, a method for identifying road safety events is provided. The method may include performing a measurement of one or more target vehicles with a sensor. The method may further include identifying a safety event based at least in part on the measurement of the one or more target vehicles. The method may further include performing an action based at least in part on the safety event.

[0005] In another aspect of the present description, performing the measurement may further comprise performing the measurement of the one or more target vehicles. The sensor comprises at least one of the following elements: a host vehicle sensor of a host vehicle, a mobile device, and a roadside unit (RSU). The measurement of the one or more target vehicles comprises at least a target vehicle location of each of the one or more target vehicles and a target vehicle speed of each of the one or more target vehicles.

[0006] In another aspect of the present description, performing the measurement may further comprise performing the measurement of the one or more target vehicles by the sensor being the host vehicle sensor of the host vehicle.

[0007] In another aspect of the present description, performing the measurement may further comprise extrapolating at least one of the following: the target vehicle location and the target vehicle speed of a first target vehicle of the one or more target vehicles in response to determining that the first target vehicle is outside a field of view of the sensor. The target vehicle location and / or the target vehicle speed of the first target vehicle is extrapolated based at least in part on one or more previous measurements of the first target vehicle.

[0008] In another aspect of the present description, identifying the safety event may further comprise evaluating the measurement of the one or more target vehicles to identify a target-to-infrastructure safety event. Identifying the safety event may further comprise evaluating the measurement of the one or more target vehicles to identify a target-to-target safety event. Identifying the safety event may further comprise evaluating the measurement of the one or more target vehicles to identify an erratic driving safety event. Identifying the safety event may further comprise evaluating the measurement of the one or more target vehicles to identify an unobserved safety event.

[0009] In another aspect of the present description, evaluating the measurement of the one or more target vehicles to identify the target-to-infrastructure safety event may further comprise evaluating the measurement of the one or more target vehicles based at least in part on one or more traffic laws. Evaluating the measurement of the one or more target vehicles to identify the target-to-infrastructure safety event may further comprise identifying the target-to-infrastructure safety event in response to determining that at least one of the one or more target vehicles has violated the one or more traffic laws.

[0010] In another aspect of the present description, evaluating the measurement of the one or more target vehicles to identify the target-to-infrastructure safety event may further comprise calculating a time to collision between a first target vehicle and a second target vehicle of the one or more target vehicles based at least in part on the measurement of the one or more target vehicles. Evaluating the measurement of the one or more target vehicles to identify the target-to-infrastructure safety event may further comprise identifying the target-to-target safety event in response to determining that the time to collision is less than or equal to a predetermined time-to-collision threshold.

[0011] In another aspect of the present description, evaluating the measurement of the one or more target vehicles to identify the erratic driving safety event may further comprise executing a machine learning model for identifying erratic driving. The machine learning model for identifying erratic driving is configured to receive the measurement of the one or more target vehicles as input and identify the erratic driving safety event based at least in part on the measurement of the one or more target vehicles.

[0012] In another aspect of the present description, evaluating the measurement of the one or more target vehicles to identify the unobserved safety event may further comprise executing a machine learning model for identifying unobserved safety events. The machine learning model for identifying unobserved safety events is configured to receive the measurement of the one or more target vehicles as input and to identify the unobserved safety event based at least in part on the measurement of the one or more target vehicles. The unobserved safety event occurs outside the field of view of the sensor.

[0013] In another aspect of the present description, performing the action based at least in part on the safety event may further comprise providing an in-vehicle warning to an occupant. Performing the action based at least in part on the safety event may further comprise providing a navigation suggestion based at least in part on a number of safety events in a specific geographic area.

[0014] According to several aspects, a system for identifying road safety events for a host vehicle is provided. The system may include a remote server system having a server communication system. The system may further include a server controller electrically connected to the server communication system. The server controller is programmed to receive a measurement from one or more target vehicles using the server communication system. The server controller is further programmed to identify a safety event based at least in part on the measurement of the one or more target vehicles. The server controller is further programmed to perform an action based at least in part on the safety event.

[0015] In another aspect of the present description, in order to identify the safety event, the server controller is further programmed to evaluate the measurement of the one or more target vehicles to identify a target-to-infrastructure safety event. In order to identify the safety event, the server controller is further programmed to evaluate the measurement of the one or more target vehicles to identify a target-to-target safety event. In order to identify the safety event, the server controller is further programmed to evaluate the measurement of the one or more target vehicles to identify an erratic driving safety event. In order to identify the safety event, the server controller is further programmed to evaluate the measurement of the one or more target vehicles to identify an unobserved safety event.

[0016] In another aspect of the present description, to identify the safety event, the server controller is further programmed to evaluate the measurement of the one or more target vehicles based at least in part on one or more traffic laws. To identify the safety event, the server controller is further programmed to calculate a time to collision between a first target vehicle and a second target vehicle of the one or more target vehicles based at least in part on the measurement of the one or more target vehicles. To identify the safety event, the server controller is further programmed to identify the target-to-infrastructure safety event in response to determining that at least one of the one or more target vehicles has violated the one or more traffic laws.To identify the safety event, the server controller is further programmed to identify the target-to-target safety event in response to determining that the time to collision is less than or equal to a predetermined time to collision threshold.

[0017] In another aspect of the present description, the server controller is further programmed to execute an erratic driving identification machine learning model to evaluate the measurement of the one or more target vehicles and identify the safety event. The erratic driving identification machine learning model is configured to receive the measurement of the one or more target vehicles as input and identify the erratic driving safety event based at least in part on the measurement of the one or more target vehicles.

[0018] In another aspect of the present description, the server controller is further programmed to execute an unobserved safety event identification machine learning model to evaluate the measurement of the one or more target vehicles to identify the unobserved safety event. The unobserved safety event identification machine learning model is configured to receive the measurement of the one or more target vehicles as input and to identify the unobserved safety event based at least in part on the measurement of the one or more target vehicles.

[0019] In another aspect of the present description, the system further comprises a host vehicle system having a host vehicle communication system. The host vehicle system further comprises a host vehicle sensor. The host vehicle system further comprises a controller for the host vehicle electrically connected to the host vehicle communication system and the host vehicle sensor. The host vehicle controller is programmed to perform a measurement of one or more target vehicles using the host vehicle sensor. The one or more target vehicles are remote from the host vehicle. The host vehicle controller is further programmed to transmit the measurement of the one or more target vehicles to the remote server system using the host vehicle communication system.

[0020] In another aspect of the present description, the server controller is further programmed to send a security event message to the host vehicle via the server communication system to perform the action based at least in part on the security event. The security event message includes information about the security event. The host vehicle system may further include a host vehicle display electrically connected to the host vehicle controller. To perform the action based at least in part on the security event, the host vehicle controller is further programmed to receive the security event message from the remote server system using the host vehicle communication system.To perform the action based at least in part on the safety event, the host vehicle controller is further programmed to provide an in-vehicle warning to an occupant of the host vehicle using the host vehicle display based at least in part on the safety event message.

[0021] According to several aspects, a method for identifying road safety events is provided. The method may include performing a measurement of one or more target vehicles with a sensor. The sensor is remote from the one or more target vehicles. The sensor includes at least one of the following: a host vehicle sensor of a host vehicle, a mobile device, and a roadside unit (RSU). The measurement of the one or more target vehicles includes at least a target vehicle location of each of the one or more target vehicles and a target vehicle speed of each of the one or more target vehicles. The method may further include identifying a safety event based at least in part on the measurement of the one or more target vehicles.The safety event includes at least one of the following events: a target-to-infrastructure safety event, a target-to-target safety event, an irregular driving safety event, and an unobserved safety event. The method may further include performing an action based at least in part on the safety event.

[0022] In another aspect of the present description, performing the measurement may further comprise extrapolating at least one of the following: the target vehicle location and the target vehicle speed of a first target vehicle of the one or more target vehicles in response to determining that the first target vehicle is outside a field of view of the sensor. The target vehicle location and / or the target vehicle speed of the first target vehicle is extrapolated based at least in part on one or more previous measurements of the first target vehicle.

[0023] In another aspect of the present description, identifying the safety event may further comprise evaluating the measurement of the one or more target vehicles based at least in part on one or more traffic laws. Identifying the safety event may further comprise identifying the target-to-infrastructure safety event in response to determining that the first target vehicle violates the one or more traffic laws. Identifying the safety event may further comprise calculating a time to collision between the first target vehicle and a second target vehicle based at least in part on the measurement of the one or more target vehicles.Identifying the safety event may further include identifying the target-to-target safety event in response to determining that the time to collision is less than or equal to a predetermined time to collision threshold. Identifying the safety event may further include executing a machine learning model to identify erratic driving. The machine learning model to identify erratic driving is configured to receive the measurement of the one or more target vehicles as input and to identify the erratic driving safety event based at least in part on the measurement of the one or more target vehicles. Identifying the safety event may further include executing a machine learning model to identify unobserved safety events.The machine learning model for identifying unobserved safety events is configured to receive the measurement of the one or more target vehicles as input and to identify the unobserved safety event based at least in part on the measurement of the one or more target vehicles. The unobserved safety event occurs outside the field of view of the sensor.

[0024] Further areas of applicability will become apparent from the present description. It should be understood that the description and specific examples are for illustrative purposes only and are not intended to limit the scope of the present 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 this description in any way. Fig. 1 is a schematic diagram of a system for identifying road safety events according to an exemplary embodiment; Fig. 2 is a schematic diagram of a host vehicle system according to an exemplary embodiment; Fig. 3 is a flowchart of a method for identifying road safety events according to an exemplary embodiment; and Fig. 4 is a flowchart of a method for performing a measurement 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 uses.

[0027] In aspects of the present description, it is advantageous to collect data about vehicles on the roadway (e.g., location, direction, speed, and / or the like). In some aspects, it is possible to retrieve such data directly from vehicles using wireless communication systems. However, in aspects of the present description, some vehicles may not be equipped with the necessary sensor and / or communication capabilities to facilitate data collection. Therefore, the present description provides a new and improved system and method for identifying road safety events by enabling the collection of data about remote vehicles.

[0028] In Fig. 1, a system for identifying road safety events is illustrated and generally designated by the reference number 10. The system 10 generally includes a remote server system 12 and a host vehicle system 14 in a host vehicle 16. The system 10 is shown in the exemplary context of a roadway 18 having one or more target vehicles 20. It is understood that the roadway 18 may be any open route for the passage and transportation of vehicles (for example, streets, freeways, highways, boulevards, avenues, parkways, avenues, bridges, tunnels, and / or the like). In the Fig. 1, the one or more target vehicles 20 includes a first target vehicle 20a and a second target vehicle 20b. It should be understood that the one or more target vehicles 20 may include any number of vehicles traveling on the roadway 18. The one or more target vehicles 20 may be, for example, sport utility vehicles (SUVs), sedans, compact cars, trucks, commercial vehicles, and / or the like. In some examples, the one or more target vehicles may also include additional road users, such as pedestrians, bicycles, and / or the like.

[0029] The remote server system 12 includes a server controller 30 in electrical communication with a server database 32 and a server communications system 34. In one non-limiting example, the remote server system 12 is located in a server farm, data center, roadside unit (RSU), or the like, and is connected to the Internet.

[0030] The server controller 30 is used to perform a method 100 for identifying road safety events, as described below. The server controller 30 includes at least one server processor 36 and a non-transferable, computer-readable device or server medium 38. The server processor 36 may be a custom or off-the-shelf processor, a central processing unit (CPU), a graphics processing unit (GPU), an auxiliary processor among a plurality of processors connected to the server controller 30, a semiconductor-based microprocessor (in the form of a microchip or chipset), a macroprocessor, a combination thereof, or generally an instruction-executing device. The computer-readable device or server medium 38 may include volatile and non-volatile memory, for example, read-only memory (ROM), random access memory (RAM), and keep-alive memory (KAM).KAM is a persistent or non-volatile memory that can be used to store various operating variables while the server processor 36 is powered off. The computer-readable storage device or server medium 38 can be implemented using a variety of storage devices such as PROMs (programmable read-only memory), EPROMs (electrically PROMs), EEPROMs (electrically erasable PROMs), flash memory, or other electrical, magnetic, optical, or combination storage devices capable of storing data, some of which are executable instructions used by the server controller 30 to perform the method 100. The server controller 30 can also consist of multiple controllers in electrical communication with one another.

[0031] The server controller 30 is in electrical communication with the server database 32 and the server communication system 34. In an exemplary embodiment, the electrical communication is established, for example, via a CAN network, a FLEXRAY network, a local area network (e.g., Wi-Fi, Ethernet, and the like), a Serial Peripheral Interface (SPI) network, or the like. It is understood that various additional wired and wireless technologies and communication protocols for communicating with the server controller 30 are within the scope of the present description.

[0032] The server database 32 is used to store information about one or more target vehicles 20, as explained in more detail below. Detailed road maps may also be stored in the server database 32, for example, including information about lane boundaries, road geometry, speed limits, traffic signs, and / or other relevant features. In an exemplary embodiment, the server database 32 includes one or more mass storage devices, such as hard disk drives, magnetic tape drives, magneto-optical disk drives, optical disks, solid-state drives, and / or additional devices capable of storing data in a permanent and machine-readable manner.In some examples, the one or more mass storage devices may be configured to provide redundancy in the event of hardware failure and / or data corruption, for example, by using a redundant array of independent disks (RAID). In one non-limiting example, the server controller 30 may execute software, such as a database management system (DBMS), that enables the organization of and access to the data stored on one or more mass storage devices. The server database 32 is in electrical communication with the server controller 30, as described above.

[0033] The server communication system 34 is used by the server controller 30 to communicate with other systems external to the remote server system 12. For example, the server communication system 34 includes capabilities for communicating with vehicles, infrastructure, other remote systems in a remote call center (e.g., ON-STAR from GENERAL MOTORS), and / or personal devices. In certain embodiments, the server communication system 34 is a wireless communication system configured to communicate over a wireless local area network (WLAN) using IEEE 802.11 standards or using cellular data communication (e.g., using GSMA standards such as SGP.02, SGP.22, SGP.32, and the like).Accordingly, the server communication system 34 may further include an embedded universal integrated circuit card (eUICC) configured to store at least one cellular connectivity configuration profile, such as an embedded subscriber identity module (eSIM) profile.

[0034] The server communication system 34 is further configured to communicate via a personal area network (e.g., BLUETOOTH), near-field communication (NFC), and / or any other type of radio frequency communication. However, additional or alternative communication methods, such as a dedicated short-range communication channel (DSRC) and / or mobile telecommunications protocols based on the 3rd Generation Partnership Project (3GPP) standards, are also considered within the scope of this description. DSRC channels refer to short- to medium-range, one-way or two-way wireless communication channels specifically designed for use in motor vehicles, as well as a set of protocols and standards. The 3GPP is a partnership between several standards organizations that develop protocols and standards for mobile telecommunications. The 3GPP standards are structured as "releases."Therefore, communication methods based on 3GPP versions 30, 15, 16 and / or future 3GPP versions fall within the scope of this description.

[0035] Accordingly, the server communication system 34 may include one or more antennas and / or communication transceivers for receiving and / or transmitting signals. The server communication system 34 is configured to wirelessly communicate information between the remote server system 12 and at least the host vehicle 16. It is understood that the server communication system 34 may be integrated with the server controller 30 (e.g., on the same circuit board with the server controller 30 or otherwise as part of the server controller 30) without departing from the scope of the present description. The server communication system 34 is in electrical communication with the server controller 30, as described above.

[0036] Fig. Figure 2 shows a schematic representation of the host vehicle system 14. The host vehicle system 14 is illustrated with the exemplary host vehicle 16. Although a passenger car is illustrated, the host vehicle 16 may be any type of vehicle without departing from the scope of this description. The host vehicle system 14 generally includes a controller 50, a host vehicle communication system 52, a host vehicle sensor 54, and a host vehicle display 56.

[0037] The host vehicle controller 50 is used in conjunction with the server controller 30 to implement the method 100 for identifying road safety events, as described below. The host vehicle controller 50 includes at least one host vehicle processor 58 and a non-transferable, computer-readable device or host vehicle medium 60. The host vehicle processor 58 may be a custom or off-the-shelf processor, a central processing unit (CPU), a graphics processing unit (GPU), an auxiliary processor among a plurality of processors connected to the host vehicle controller 50, a semiconductor-based microprocessor (in the form of a microchip or chipset), a macroprocessor, a combination thereof, or generally an instruction-executing device.The computer-readable device or host vehicle medium 60 may include volatile and non-volatile memory, such as read-only memory (ROM), random access memory (RAM), and keep-alive memory (KAM). KAM is persistent or non-volatile memory that can be used to store various operating variables while the host vehicle processor 58 is powered off. The computer-readable storage device or host vehicle medium 60 may be implemented using a variety of storage devices such as PROMs (programmable read-only memory), EPROMs (electrically PROMs), EEPROMs (electrically erasable PROMs), flash memory, or other electrical, magnetic, optical, or combination storage devices capable of storing data, some of which may be executable instructions used by the host vehicle controller 50 to control various systems of the host vehicle 16.The host vehicle controller 50 may also consist of multiple controllers that are electrically connected to one another. The host vehicle controller 50 may be connected to additional systems and / or controllers of the host vehicle 16 so that the host vehicle controller 50 can access data such as speed, acceleration, braking, and steering angle of the host vehicle 16.

[0038] The host vehicle controller 50 is in electrical communication with the host vehicle communication system 52, the host vehicle sensor 54, and the host vehicle display 56. In an exemplary embodiment, the electrical communication is established, for example, via a CAN network, a FLEXRAY network, a local area network (e.g., Wi-Fi, Ethernet, and the like), a serial peripheral interface (SPI) network, or the like. It is understood that various additional wired and wireless technologies and communication protocols for communicating with the host vehicle controller 50 are within the scope of the present description.

[0039] The host-vehicle communication system 52 is used by the host-vehicle controller 50 to communicate with other systems external to the host vehicle 16 (e.g., with the remote server system 12). For example, the host-vehicle communication system 52 includes capabilities for communicating with vehicles (“V2V” communication), infrastructure (“V2I” communication), remote systems at a remote call center (e.g., ON-STAR from GENERAL MOTORS), and / or personal devices. Generally, the term vehicle-to-everything (“V2X” communication) refers to communication between the host vehicle 16 and any remote system (e.g., vehicles, infrastructure, and / or remote systems). In certain embodiments, the host-vehicle communication system 52 is a wireless communication system configured to communicate over a wireless local area network (WLAN) using IEEE 802.11a / b / g / n.11 standards or using cellular data communication (for example, using GSMA standards such as SGP.02, SGP.22, SGP.32, and the like). Accordingly, the host vehicle communication system 52 may further include an embedded universal integrated circuit card (eUICC) configured to store at least one cellular connectivity configuration profile, for example, an embedded subscriber identity module (eSIM) profile.

[0040] The host vehicle communication system 52 is further configured to communicate via a personal area network (e.g., BLUETOOTH), near-field communication (NFC), and / or any other type of radio frequency communication. However, additional or alternative communication methods, such as a dedicated short-range communication channel (DSRC) and / or mobile telecommunications protocols based on the 3rd Generation Partnership Project (3GPP) standards, are also considered within the scope of this description. DSRC channels refer to short- to medium-range, one-way or two-way wireless communication channels specifically designed for use in motor vehicles, as well as a set of protocols and standards. The 3GPP is a partnership between several standards organizations that develop protocols and standards for mobile telecommunications. The 3GPP standards are structured as "releases."Therefore, communication methods based on 3GPP versions 50, 15, 16 and / or future 3GPP versions fall within the scope of this description.

[0041] Accordingly, the host-vehicle communication system 52 may include one or more antennas and / or communication transceivers for receiving and / or transmitting signals, such as Cooperative Sensing Messages (CSMs). The host-vehicle communication system 52 is configured to wirelessly communicate information between the host vehicle 16 and another vehicle. Furthermore, the host-vehicle communication system 52 is configured to wirelessly communicate information between the host vehicle 16 and the infrastructure or other vehicles. Furthermore, the host-vehicle communication system 52 is configured to wirelessly communicate information between the host vehicle 16 and the remote server system 12.It is understood that the host vehicle communication system 52 may be integrated into the host vehicle controller 50 (e.g., on the same circuit board as the host vehicle controller 50 or otherwise as part of the host vehicle controller 50) without departing from the scope of the present description.

[0042] The host vehicle sensor 54 is used to collect information about the one or more target vehicles 20. In an exemplary embodiment, the host vehicle sensor 54 includes at least one perception sensor 62 and a global navigation satellite system (GNSS) 64.

[0043] The perception sensor 62 is used to perceive objects and / or measure distances in the environment of the host vehicle 16. In an exemplary embodiment, the perception sensor 62 includes at least one of the following components: a camera 68, a radar sensor 70, and a LiDAR (Light Detection and Ranging) sensor 72. The camera 68 is a perception sensor used to capture images and / or videos of the environment of the host vehicle 16. In an exemplary embodiment, the camera 68 includes a still and / or video camera positioned to capture the environment of the host vehicle 16. In one non-limiting example, the camera 68 includes a camera mounted inside the host vehicle 16, for example, in a headlight of the host vehicle 16, and visible through a windshield of the host vehicle 16.In another non-limited example, the camera 68 comprises a camera mounted outside the host vehicle 16, for example, on the roof of the host vehicle 16, and providing a view of the environment in front of the host vehicle 16.

[0044] In another exemplary embodiment, camera 68 is a surround-view camera system having a plurality of cameras (also known as satellite cameras) arranged to provide a view of the surroundings on all sides of host vehicle 16. In one non-limiting example, camera 68 includes a forward-facing camera (e.g., mounted in a grille of host vehicle 16), a rearward-facing camera (e.g., mounted on a tailgate of host vehicle 16), and two side-facing cameras (e.g., mounted below each of two side-view mirrors of host vehicle 16). In another non-limiting example, camera 68 also includes an additional rearview camera mounted near a high-mounted center brake light of host vehicle 16.

[0045] It is understood that camera systems with additional cameras and / or additional mounting locations fall within the scope of the present description. It should be further understood that cameras with various sensor types, such as charge-coupled device (CCD) sensors, complementary metal oxide semiconductor (CMOS) sensors, and / or high dynamic range (HDR) sensors, fall within the scope of the present description. Furthermore, cameras with various lens types, such as wide-angle lenses and / or narrow-angle lenses, also fall within the scope of the present description. The camera 68 is in electrical communication with the host vehicle controller 50, as described above.

[0046] The radar sensor 70 is used to detect and measure the distance, speed, and direction of objects (e.g., the one or more target vehicles 20) by transmitting radio waves and analyzing the reflections of the radio waves. In an exemplary embodiment, the radar sensor 70 includes a radar transmitter, a radar antenna, a radar receiver, and a radar signal processing unit. In one non-limiting example, the radar transmitter transmits radio frequency (RF) signals that travel through space until they encounter an object. The RF signals bounce off the surface of the object and return to the radar sensor 70. The radar receiver detects the reflected signals, and the radar signal processing unit analyzes the time delay, frequency shift, and amplitude of the returned RF signals to determine the distance, speed, and direction of the detected objects.The radar sensor 70 is, as described above, in electrical communication with the host vehicle controller 50.

[0047] The LiDAR sensor 72 is used for remote sensing and environmental mapping by emitting laser pulses and measuring the time it takes for the laser pulses to return to the LiDAR sensor 72 after hitting objects. In an exemplary embodiment, the LiDAR sensor 72 includes a LiDAR laser source, a LiDAR scanner or mirror, a LiDAR photodetector, and a LiDAR time-of-flight measurement system. In one non-limiting example, the LiDAR laser source emits laser pulses that travel toward the target area, and the LiDAR scanner steers these pulses in different 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 LiDAR laser source emitting the laser pulses and the LiDAR photodetector receiving the reflected laser pulses.The LiDAR sensor 72 is, as described above, in electrical communication with the host vehicle controller 50.

[0048] In another exemplary embodiment, the perception sensor 62 further includes a stereo camera with ranging capabilities. In one example, the perception sensor 62 is mounted inside the host vehicle 16, for example, in a headlight of the host vehicle 16, and provides a view through the windshield of the host vehicle 16. In another example, the perception sensor 62 is mounted outside the host vehicle 16, for example, on the roof of the host vehicle 16, overlooking the surroundings of the host vehicle 16. It is understood that various additional types of perception sensors, such as ultrasonic range sensors and / or time-of-flight sensors, are within the scope of the present description. The perception sensor 62 is in electrical communication with the host vehicle controller 50, as described above.

[0049] The GNSS 64 is used to determine the geographic location of the host vehicle 16. In an exemplary embodiment, the GNSS 64 is a global positioning system (GPS).

[0050] In one non-limiting example, the GPS includes a GPS receiving antenna (not shown) and a GPS controller (not shown) electrically connected to the GPS receiving antenna. The GPS receiving antenna receives signals from a plurality of satellites, and the GPS controller calculates the geographic location of the host vehicle 16 based on the signals received by the GPS receiving antenna.

[0051] In one exemplary embodiment, the GNSS 64 additionally includes a map. The map contains information about infrastructure such as municipal boundaries, roads, rail lines, sidewalks, buildings, and the like. Therefore, the geographic location of the host vehicle 16 is contextualized using the map information. In one non-limiting example, the map is retrieved from a remote source via a wireless connection. In another non-limiting example, the map is stored in a database of the GNSS 64.

[0052] It is understood that various additional types of satellite-based radio navigation systems, such as the Global Positioning System (GPS), Galileo, GLONASS, and the BeiDou Navigation Satellite System (BDS), are within the scope of the present description. It is understood that the GNSS 64 may be integrated into the host vehicle controller 50 (e.g., on the same circuit board as the host vehicle controller 50 or otherwise as part of the host vehicle controller 50) without departing from the scope of the present description.

[0053] In another exemplary embodiment, host vehicle sensor 54 further includes sensors to determine performance data about host vehicle 16. In one non-limiting example, host vehicle sensor 54 further includes at least one of an engine speed sensor, an engine torque sensor, an electric drive motor voltage and / or current sensor, an accelerator pedal position sensor, a brake position sensor, a coolant temperature sensor, a cooling fan speed sensor, and a transmission oil temperature sensor.

[0054] In another exemplary embodiment, host vehicle sensor 54 further includes additional sensors to determine information about the environment within host vehicle 16. In one non-limiting example, host vehicle sensor 54 further includes at least one seat occupancy sensor, a cabin air temperature sensor, a cabin motion detection sensor, a cabin camera, a cabin microphone, an occupant eye sensor, and / or the like.

[0055] In another exemplary embodiment, host vehicle sensor 54 further includes additional sensors for obtaining information about the environment of host vehicle 16. In one non-limiting example, host vehicle sensor 54 further includes at least one ambient air temperature sensor, a barometric pressure sensor, and / or the like. Host vehicle sensor 54 is in electrical communication with host vehicle controller 50, as described above.

[0056] The host vehicle display 56 is used to provide information to an occupant of the host vehicle 16. For the purposes of this description, the occupant includes a driver and / or a passenger of the host vehicle 16. In the Fig. In the exemplary embodiment illustrated in Figure 2, the host vehicle display 56 is a human-machine interface (HMI) located within the occupant's field of view and capable of displaying text, graphics, and / or images. It is understood that HMI display systems, including LCD displays, LED displays, and the like, are within the scope of the present description. Other exemplary embodiments in which the host vehicle display 56 is disposed in a rearview mirror are also within the scope of the present description.

[0057] In another exemplary embodiment, the host vehicle display 56 includes a head-up display (HUD) configured to provide information to the occupant by projecting text, graphics, and / or images onto the windshield of the host vehicle 16. The text, graphics, and / or images are reflected from the windshield of the host vehicle 16 and are visible to the occupant without requiring the occupant to look away from the roadway 18 in front of the host vehicle 16. In another exemplary embodiment, the host vehicle display 56 includes an augmented reality head-up display (AR-HUD). The AR-HUD is a type of HUD configured to augment the occupant's view of the roadway in front of the host vehicle 16 by overlaying text, graphics, and / or images onto physical objects surrounding the host vehicle 16 within the occupant's field of view.In an exemplary embodiment, the occupant may interact with the host vehicle display 56 using a human interaction device (HID), such as a touchscreen, an electromechanical switch, a capacitive switch, a rotary knob, and the like.

[0058] It is understood that additional systems for displaying information to the occupant of the host vehicle 16 are also within the scope of this description. The host vehicle display 56 is in electrical communication with the host vehicle controller 50, as described above.

[0059] Fig. 3 shows a flowchart of the method 100 for identifying road safety events. The method 100 begins in block 102 and proceeds to block 104. In block 104, a measurement is taken of at least one of the one or more target vehicles 20. In an exemplary embodiment, the measurement includes a target vehicle location of each of the one or more target vehicles and a target vehicle speed of each of the one or more target vehicles. In an exemplary embodiment, the measurement is taken with a sensor. In one non-limiting example, the sensor includes at least one of the following: the host vehicle sensor 54 of the host vehicle 16 (i.e., the host vehicle system 14), a mobile device (e.g., a smartphone, a smartwatch, a tablet, and / or the like), and / or a roadside unit (RSU). Taking the measurement is explained in more detail below.After block 104, the method 100 proceeds to block 106.

[0060] In block 106, the measurement is transmitted to the remote server system 12. In one exemplary embodiment, the host vehicle controller 50 uses the host vehicle communication system 52 to transmit the measurement to the remote server system 12 via the server communication system 34. In another exemplary embodiment, the mobile device uses a mobile device communication system to transmit the measurement to the remote server system 12 via the server communication system 34. In another exemplary embodiment, the RSU uses an RSU communication system to transmit the measurement to the remote server system 12 via the server communication system 34. In one non-limiting example, the server controller 30 receives the measurement via the server communication system 34 and stores the measurement in the server database 32. After block 106, the method 100 continues with blocks 108, 110, 112, and 114.

[0061] In block 108, the server controller 30 evaluates the measurement of the one or more target vehicles 20 to identify a target-to-infrastructure safety event. For the purposes of the present description, a target-to-infrastructure safety event describes an event in which a target vehicle 20 violates a traffic regulation involving road infrastructure. In one non-limiting example, the target-to-infrastructure safety event includes, for example, leaving the roadway 18 and / or a lane (e.g., crossing a lane line), driving the wrong way on a one-way street, disobeying a stop sign, yield sign, traffic signal, and / or other traffic signals, disobeying a red light, disobeying a no-turn zone, disobeying a speed limit, and / or the like.

[0062] In one exemplary embodiment, the server controller 30 first determines one or more traffic laws in effect on the roadway 18 to identify the target-to-infrastructure safety event. For the purposes of this description, the one or more traffic laws include, for example, the position and type of the travel lane, the permitted direction of travel of the lane / roadway, the position, type, and content of traffic signs, the position, type, and phase of traffic signals, speed limits, and / or the like. In one exemplary embodiment, the server controller 30 retrieves the one or more traffic laws from the server database 32. In another exemplary embodiment, the server controller 30 retrieves the one or more traffic laws from an external system (e.g., the Internet) using the server communication system 34.

[0063] After determining the one or more traffic laws applicable to roadway 18, server controller 30 evaluates the measurement received in block 106 based at least in part on one or more traffic laws. In one non-limiting example, server controller 30 compares the target vehicle location to the position of a lane line to identify a deviation from roadway 18 and / or a lane. In one non-limiting example, server controller 30 compares a direction of the target vehicle speed to the legal direction of travel on the lane / roadway to determine whether target vehicle 20 is traveling in the wrong direction on a one-way street.

[0064] In one non-limiting example, server controller 30 analyzes the target vehicle location and target vehicle speed over time in the vicinity of one or more traffic signs / signals to identify a stop sign violation, a yield sign violation, a traffic signal violation, a passing zone violation, and / or the like. In one non-limiting example, server controller 30 compares a magnitude of the target vehicle speed to the speed limit on roadway 18 to detect a speed limit violation.

[0065] It is understood that additional analysis of the measurement may be performed to identify other types of target-to-infrastructure security events without departing from the scope of the present description. It should be further understood that the server controller 30 may use signal processing techniques such as thresholding, filtering, pattern recognition, time-frequency analysis, statistical analysis, machine learning, and / or the like to identify the target-to-infrastructure security event without departing from the scope of the present description. After block 108, the method 100 proceeds to block 116.

[0066] If the target-to-infrastructure security event is not identified in block 116, the method 100 transitions to a standby state in block 118. If the target-to-infrastructure security event is identified in block 108, the method 100 transitions to block 120, as explained in more detail below.

[0067] In block 110, the server controller 30 evaluates the measurement of the one or more target vehicles 20 to identify a target-to-target safety event. For the purposes of the present description, a target-to-target safety event describes an event in which two or more target vehicles 20 are involved in an unsafe driving situation. By way of non-limiting example, the target-to-target safety event includes, for example, a collision between two or more target vehicles 20, a near-collision between two or more target vehicles 20, an aggressive maneuver (e.g., hard braking, hard acceleration, hard cornering, aggressive lane change) involving two or more target vehicles 20, close following (i.e., a close following distance) between two or more target vehicles 20, and / or the like.

[0068] In an exemplary embodiment, the server controller 30 calculates a time-to-collision (TTC) between the two or more target vehicles 20 (e.g., the first target vehicle 20a and the second target vehicle 20b) to identify the target-to-target safety event. For the purposes of this description, the time-to-collision (TTC) quantifies an estimated time required for the first target vehicle 20a to collide with the second target vehicle 20b (i.e., until the first target vehicle 20a and the second target vehicle 20b reach a common point in space based on their trajectories).

[0069] As one non-limiting example, to calculate the TTC, the server controller 30 determines a first trajectory of the first target vehicle 20a (i.e., a future path of the first target vehicle 20a) based at least in part on a first target vehicle speed and a first target vehicle location of the first target vehicle 20a. The server controller 30 further determines a second trajectory of the second target vehicle 20b (i.e., a future path of the second target vehicle 20b) based at least in part on a second target vehicle speed and a second target vehicle location of the second target vehicle 20b. The server controller 30 then evaluates the first trajectory and the second trajectory to determine whether the first trajectory intersects the second trajectory. If the first trajectory and the second trajectory do not intersect, the TTC is considered infinite.

[0070] When the first trajectory and the second trajectory intersect, the server controller 30 determines a distance between the first target vehicle 20a and the second target vehicle 20b based at least in part on the first target vehicle location and the second target vehicle location. The server controller 30 then determines a relative speed between the first target vehicle 20a and the second target vehicle 20b based at least in part on a magnitude of the first target vehicle speed and a magnitude of the second target vehicle speed.

[0071] To determine the TTC, the server controller 30 divides the distance between the first target vehicle 20a and the second target vehicle 20b by the relative speed between the first target vehicle 20a and the second target vehicle 20b. In one non-limiting example, the target-to-target safety event is identified when the TTC is less than or equal to a predetermined time-to-collision threshold (e.g., three seconds).

[0072] It is understood that additional analysis of the measurement may be performed to identify other types of target-to-target security events without departing from the scope of the present description. It should be further understood that the server controller 30 may use signal processing techniques such as thresholding, filtering, pattern recognition, time-frequency analysis, statistical analysis, machine learning, and / or the like to identify the target-to-target security event without departing from the scope of the present description. After block 110, the method 100 proceeds to block 122.

[0073] If the target-to-target security event is not identified in block 110, the method 100 proceeds to the standby state in block 118. If the target-to-target security event is identified in block 110, the method 100 proceeds to block 120, as explained in more detail below.

[0074] In block 112, the server controller 30 evaluates the measurement of the one or more target vehicles 20 to identify an erratic driving safety event. For the purposes of this description, an erratic driving safety event describes a situation or event involving an unpredictable and erratic driving safety event that poses a potential risk to road users. As a non-limiting example, an erratic driving safety event includes an abrupt lane change, sudden acceleration or deceleration, aggressive driving behavior, and / or other erratic driving patterns. In an exemplary embodiment, the server controller 30 uses a machine learning model for identifying erratic driving to identify the erratic driving safety event.

[0075] As a non-limiting example, the machine learning model for identifying erratic driving comprises multiple layers, including an input layer and an output layer, as well as one or more hidden layers. The input layer receives the measurement taken in block 104 as input. The input is then passed to the hidden layers. Each hidden layer applies a transformation (e.g., a nonlinear transformation) to the data and passes the result to the next hidden layer, up to the last hidden layer. The output layer generates a classification of erratic driving safety events.For the purposes of this description, the classification of driving safety disturbances includes, for example, the classification “no event” (i.e., no erratic driving behavior is determined), the classification “abrupt lane change,” the classification “abrupt speed change,” the classification “aggressive driving behavior,” and / or similar.

[0076] To train the machine learning model for identifying erratic driving, a dataset with inputs and the corresponding classification of erratic driving safety events is used. The algorithm is trained by adjusting the internal weights between the nodes in each hidden layer to minimize the prediction error. During training, an optimization technique (e.g., gradient descent) is used to adjust the internal weights and reduce the prediction error. The training process is repeated with the entire dataset until the prediction error is minimized, and the resulting trained model is then used to classify new input data.

[0077] After sufficient training of the machine learning model to identify erratic driving, the algorithm is able to accurately and precisely determine the classification of erratic driving safety events based on the measurements taken in block 104. By adjusting the weights between the nodes in each hidden layer during training, the algorithm "learns" to recognize patterns in the measurement data that indicate the classification of the erratic driving safety event.

[0078] It is understood that additional analysis of the measurement may be performed to identify other types of erratic driving safety events without exceeding the scope of the present description. It is further understood that the server controller 30 may use signal processing techniques such as thresholding, filtering, pattern recognition, time-frequency analysis, statistical analysis, and / or the like to identify the erratic driving safety event without exceeding the scope of the present description. After block 112, the method 100 proceeds to block 124.

[0079] In block 124, if the irregular driving safety event was not identified in block 112 (i.e., the classification of the irregular driving safety event is "no event"), the method 100 transitions to the standby state in block 118. If the irregular driving safety event is identified in block 112, the method 100 transitions to block 120, as explained in more detail below.

[0080] In block 114, the server controller 30 evaluates the measurement of the one or more target vehicles 20 to identify an unobserved safety event. For the purposes of this description, the unobserved safety event describes a situation or event that occurs outside the field of view of the sensor (e.g., the host vehicle sensor 54) and poses a potential hazard to road users. In one non-limiting example, the unobserved safety event includes one of the target-to-infrastructure safety events described above, between target-to-target safety events, and / or during irregular driving safety events.

[0081] For example, a near-collision may occur well in front of the host vehicle 16 on the roadway 18 outside the field of view of the host vehicle sensor 54, but the host vehicle sensor 54 may observe reactions of other target vehicles 20 within the field of view of the host vehicle sensor 54 to the near-collision. Therefore, even without directly observing the unobserved safety event, information about the unobserved safety event may be obtained from the measurement taken in block 104. In an exemplary embodiment, the server controller 30 uses a machine learning model for identifying unobserved safety events to identify the unobserved safety event.

[0082] In one non-limiting example, the machine learning model for identifying unobserved safety events comprises multiple layers, including an input layer and an output layer, as well as one or more hidden layers. The input layer receives the measurement taken in block 104 as input. In an exemplary embodiment, the input may also include additional information, such as telemetry data, ADAS (Advanced Driver Assistance System) data, and / or crash data / alerts from external sources. The inputs are then passed to the hidden layers. Each hidden layer applies a transformation (e.g., a nonlinear transformation) to the data and passes the result to the next hidden layer, up to the last hidden layer. The output layer generates a classification of unobserved safety events.

[0083] For the purposes of this description, the classification of unobserved safety events includes, for example, the "no event" classification (i.e., no unobserved safety event is identified), the "unobserved target-to-infrastructure" classification, the "unobserved target-to-target" classification, the "unobserved erratic driving" classification, and / or the like. It is understood that the classification of unobserved safety events may also include more specific classifications (e.g., a classification of unobserved near-collision) without departing from the scope of this description. It should further be understood that the output layer may generate additional information, such as a predicted location of the unobserved safety event and / or a confidence in the classification of the unobserved safety event.

[0084] To train the machine learning model for identifying unobserved security events, a dataset with inputs and the corresponding classification of unobserved security events is used. The algorithm is trained by adjusting the internal weights between the nodes in each hidden layer to minimize the prediction error. During training, an optimization technique (for example, gradient descent) is used to adjust the internal weights and reduce the prediction error. The training process is repeated with the entire dataset until the prediction error is minimized, and the resulting trained model is then used to classify new input data.

[0085] After sufficient training of the machine learning model to identify unobserved security events, the algorithm is able to accurately and precisely determine the classification of unobserved security events based on the measurements taken in block 104. By adjusting the weights between the nodes in each hidden layer during training, the algorithm "learns" to recognize patterns in the measurement data that indicate the classification of the unobserved security event.

[0086] It is understood that additional analysis of the measurement may be performed to identify other types of unobserved security events without departing from the scope of the present description. It should be further understood that the server controller 30 may use signal processing techniques, such as thresholding, filtering, pattern recognition, time-frequency analysis, statistical analysis, and / or the like, to identify the unobserved security event without departing from the scope of the present description. After block 114, the method 100 proceeds to block 126.

[0087] In block 126, if the unobserved safety event is not identified in block 114 (i.e., the classification of the unobserved safety event is the "no event" classification), the method 100 transitions to the standby state in block 118. If the unobserved safety event is identified in block 114, the method 100 transitions to block 120.

[0088] At block 120, the server controller 30 performs a first action based at least in part on the security event. In an exemplary embodiment, the first action includes transmitting a security event message to the host vehicle 16.As one non-limiting example, the safety event message includes at least one of the following: information about the target-to-infrastructure safety event identified in block 108 (i.e., a location, type, severity, and / or the like), information about the target-to-target safety event identified in block 110 (i.e., location, type, severity, and / or the like), information about the irregular driving safety event classification determined in block 112 (i.e., location, type, severity, and / or the like), and / or information about the unobserved safety event classification determined in block 114 (i.e., location, type, severity, and / or the like). The safety event message also includes a geographic location for each of the above-mentioned safety events.In an exemplary embodiment, server controller 30 uses server communication system 34 to transmit the security event message. The security event message is received by host vehicle controller 50 via host vehicle communication system 52.

[0089] In another exemplary embodiment, the security event message also includes statistical information about security events in a specific geographic area (e.g., a one-mile radius) near the host vehicle 16. In one non-limiting example, the statistical information includes, for example, a frequency of occurrence of security events, a number of security events, a geographic density of security events, and / or the like.

[0090] In another exemplary embodiment, at block 120, the server controller 30 stores the safety event message in the server database 32. In one non-limiting example, the safety event message is later retrieved for analysis purposes to improve road infrastructure and / or road safety, create regional road risk assessments, and / or the like. After block 120, the method 100 proceeds to block 128.

[0091] In block 128, the host vehicle controller 50 performs the first action based at least in part on the safety event. In an exemplary embodiment, the first action further includes using the host vehicle communication system 52 to receive the safety event message transmitted in block 120. In an exemplary embodiment, the host vehicle controller 50 uses the host vehicle display 56 to provide the occupant of the host vehicle 16 with an in-vehicle warning based at least in part on the safety event message. For example, the host vehicle controller 50 may use the host vehicle display 56 to display a warning using text, images, icons, and / or the like.In one non-limiting example, the alert includes text describing the type, location, severity, and / or the like of the security event included in the security event message transmitted in block 120.

[0092] In another exemplary embodiment, the host vehicle controller 50 uses the GNSS 64 to determine a navigation suggestion based at least in part on a number of security events within a specific geographic area. In one non-limiting example, the host vehicle controller 50 uses the GNSS 64 to calculate a navigation route based at least in part on the statistical information about security events in the specific geographic area. For example, the navigation route may be configured to avoid geographic areas with a high density or frequency of security events. After block 128, the method 100 transitions to the standby state at block 118.

[0093] In an exemplary embodiment, the method 100 is repeatedly restarted at block 102. In one non-limiting example, the method 100 is restarted with a timer, for example, every three hundred milliseconds.

[0094] In Fig.4 illustrates a flowchart of an exemplary embodiment 104a of block 104 (i.e., a method for performing a measurement). The exemplary embodiment 104a begins in block 302. As described above, the measurement is performed using a sensor. In one non-limiting example, the sensor includes at least one of the following: the host vehicle sensor 54 of the host vehicle system 14, a mobile device (e.g., a smartphone, a smartwatch, a tablet, and / or the like), and / or a roadside unit (RSU). The exemplary embodiment 104a is explained with reference to an exemplary embodiment in which the sensor is the host vehicle sensor 54. It should be understood that the following method steps are also applicable to a mobile device and / or a roadside unit (RSU).

[0095] In block 302, the host vehicle controller 50 selects a selected target vehicle. In one non-limiting example, the selected target vehicle may be one of the target vehicles 20 (e.g., the first target vehicle 20a or the second target vehicle 20b). After block 302, the exemplary embodiment 104a proceeds to block 304.

[0096] In block 304, the host vehicle controller 50 determines whether the selected target vehicle is within the field of view of the host vehicle sensor 54. For example, if the host vehicle sensor 54 includes only a forward-facing camera and the selected target vehicle is located behind the host vehicle 16, the selected target vehicle is not within the field of view of the host vehicle sensor 54. If the selected target vehicle is not within the field of view of the host vehicle sensor 54, the example embodiment 104a proceeds to block 306. If the selected target vehicle is within the field of view of the host vehicle sensor 54, the example embodiment 104a proceeds to block 308, as explained in more detail below.

[0097] In block 306, the host vehicle controller 50 extrapolates at least one of the following: the target vehicle location of the selected target vehicle and the target vehicle speed of the selected target vehicle in response to determining that the selected target vehicle is outside the field of view of the host vehicle sensor 54. In an exemplary embodiment, the host vehicle controller 50 uses a time-series prediction method to predict (i.e., extrapolate) future values ​​of the target vehicle location of the selected target vehicle and the target vehicle speed of the selected target vehicle based on one or more past measurements of the selected target vehicle stored in the host vehicle media 60 and / or the server database 32.

[0098] For example, in one non-limiting example, the time series prediction method includes an autoregressive integrated moving average (ARIMA), exponential smoothing, and / or machine learning models for predicting / extrapolating time series data. In one non-limiting example, the extrapolations of the selected target vehicle's target vehicle location and the selected target vehicle's target vehicle speed are assigned a decreasing confidence value based on the time elapsed since the last ground truth measurement was received (i.e., since the selected target vehicle was last within the field of view of the host vehicle sensor 54).

[0099] In another exemplary embodiment, the host vehicle controller 50 extrapolates the target vehicle location of the selected target vehicle and the target vehicle speed of the selected target vehicle, assuming that a rate of change of the target vehicle location and a rate of change of the target vehicle speed of the selected target vehicle remain constant. After a predetermined period of time has elapsed since the last ground truth measurement, the prediction (i.e., the extrapolation) of the target vehicle location of the selected target vehicle and the target vehicle speed of the selected target vehicle is considered invalid and discarded. After block 306, the exemplary embodiment 104a proceeds to block 310, as explained in more detail below.

[0100] In block 308, the host vehicle controller 50 uses the host vehicle sensor 54 to perform the measurement of the selected target vehicle (e.g., the first target vehicle 20a or the second target vehicle 20b) in response to determining that the selected target vehicle is within the field of view of the host vehicle sensor 54. As described above, the measurement includes at least a target vehicle location and a target vehicle speed of the selected target vehicle. After block 308, the exemplary embodiment 104a proceeds to block 310.

[0101] In block 310, the host vehicle controller 50 updates the location of the selected target vehicle in memory. In an exemplary embodiment, the projected target vehicle location of the selected target vehicle and the projected target vehicle speed of the selected target vehicle determined in block 306 are stored on the host vehicle media 60 and / or in the server database 32. As previously mentioned, the projected target vehicle location of the selected target vehicle and the projected target vehicle speed of the selected target vehicle may include a confidence value that decreases with the time elapsed since the last ground truth measurement of the selected target vehicle.In another exemplary embodiment, the target vehicle location of the selected target vehicle and the target vehicle speed of the selected target vehicle measured in block 308 are stored on the host vehicle media 60 and / or in the server database 32. As described above, the target vehicle location of the selected target vehicle and the target vehicle speed of the selected target vehicle measured in block 308 may later be retrieved from the host vehicle media 60 and / or the server database 32 to perform extrapolation in block 306. After block 310, the exemplary embodiment 104a proceeds to block 312.

[0102] If not all target vehicles 20 in the exemplary embodiment 104a have been selected at block 312, the exemplary embodiment 104a returns to block 302 to select a next selected target vehicle. If all target vehicles 20 in the exemplary embodiment 104a have been selected, the exemplary embodiment 104a is completed, and the method 100 continues as described above.

[0103] The system 10 and method 100 of the present description provide several advantages. By using the host vehicle system 14 of the host vehicle 16, equipped with the host vehicle sensor 54, to collect data about target vehicles 20, data about safety events associated with the target vehicles 20 can be captured even if the target vehicles 20 do not have measurement and / or wireless communication capabilities. According to the present description, the system 10 and method 100 can be applied using a plurality of host vehicles, thereby allowing large amounts of measurement data about unconnected target vehicles to be aggregated by the remote server system 12. Therefore, the remote server system 12 can fuse data from multiple host vehicles to achieve a high degree of measurement coverage of the roadway 18.The fused data can be used with advanced driver assistance systems (ADAS) to provide occupants with important information about safety events on the roadway 18. The fused data can be used with global navigation satellite systems (GNSS) to adjust the navigation route based on road safety events 18. The fused data can also be used to improve road infrastructure and / or road safety, create regional road traffic risk assessments, and / or similar purposes.

[0104] The description of the present disclosure is merely exemplary, and variations that do not depart from the gist of the present disclosure are intended to be within the scope of the present disclosure. Such variations are not to be regarded as a departure from the spirit and scope of the present description.

Claims

[1] A method for identifying road safety incidents, the method comprising: Carrying out a measurement of one or more target vehicles with a sensor; Identifying a security event based at least in part on the measurement of the one or more target vehicles; and Performing an action based at least in part on the security event. [2] The method of claim 1, wherein performing the measurement further comprises: Performing the measurement of the one or more target vehicles, wherein the sensor comprises at least one of the following elements: a host vehicle sensor of a host vehicle, a mobile device, and a roadside unit, RSU, wherein the measurement of the one or more target vehicles comprises at least a target vehicle location of each of the one or more target vehicles and a target vehicle speed of each of the one or more target vehicles. [3] The method of claim 2, wherein performing the measurement further comprises: Performing the measurement of the one or more target vehicles, wherein the sensor is the host vehicle sensor of the host vehicle. [4] The method of claim 2, wherein performing the measurement further comprises: Extrapolating at least one of the following: the target vehicle location and the target vehicle speed of a first target vehicle of the one or more target vehicles in response to determining that the first target vehicle is outside a field of view of the sensor, wherein the target vehicle location and / or the target vehicle speed of the first target vehicle is extrapolated based at least in part on one or more previous measurements of the first target vehicle. [5] The method of claim 1, wherein identifying the security event further comprises: Evaluating the measurement of the one or more target vehicles to identify a target-to-infrastructure security event; Evaluating the measurement of the one or more target vehicles to identify a target-to-target security event; Evaluating the measurement of the one or more target vehicles to identify an irregular driving safety event; and Evaluating the measurement of the one or more target vehicles to identify an unobserved safety event. [6] The method of claim 5, wherein evaluating the measurement of the one or more target vehicles to identify the target-to-infrastructure security event further comprises: Evaluating the measurement of the one or more target vehicles based at least in part on one or more traffic regulations, and Identifying the target-to-infrastructure safety event in response to determining that at least one of the one or more target vehicles has violated the one or more traffic regulations. [7] The method of claim 5, wherein evaluating the measurement of the one or more target vehicles to identify the target-to-infrastructure security event further comprises: Calculating a time to collision between a first target vehicle and a second target vehicle of the one or more target vehicles based at least in part on the measurement of the one or more target vehicles; and Identifying the target-to-target safety event in response to determining that the time to collision is less than or equal to a predetermined time to collision threshold. [8] The method of claim 5, wherein evaluating the measurement of the one or more target vehicles to identify the irregular driving safety event further comprises: Executing a machine learning model to identify erratic driving, the machine learning model to identify erratic driving configured to receive the measurement of the one or more target vehicles as input and to identify the erratic driving safety event based at least in part on the measurement of the one or more target vehicles. [9] The method of claim 5, wherein evaluating the measurement of the one or more target vehicles to identify the unobserved safety event further comprises: Executing a machine learning model to identify unobserved safety events, wherein the machine learning model to identify unobserved safety events is configured to receive the measurement of the one or more target vehicles as an input and to identify the unobserved safety event based at least in part on the measurement of the one or more target vehicles, and wherein the unobserved safety event occurs outside a field of view of the sensor. [10] The method of claim 1, wherein performing the action based at least in part on the security event further comprises: Providing an in-vehicle warning to an occupant; and Providing a navigation suggestion based at least in part on the number of security events in a specific geographic area.

Images