HAZARD WARNING SYSTEM FOR A VEHICLE

Abstract

A computer-implemented procedure, when executed by data processing hardware, causes this hardware to perform operations. These operations include receiving radar data via a vehicle's radar system, identifying multipath clusters based on the radar data using a hazard warning algorithm, and estimating a local reflectance coefficient for one or more of the multipath clusters using the hazard warning algorithm. The operations also include comparing the local reflectance coefficient with a global reflectance coefficient stored by a hazard warning system using the hazard warning algorithm, identifying an anomaly based on this comparison, and updating a hazard list in the hazard warning algorithm with the identified anomaly.The processes also include assessing a hazard type based on the updated hazard list and issuing a warning stating the estimated hazard type using the hazard warning algorithm.

Description

INTRODUCTION

[0001] The information contained in this section serves to present the general context of the disclosure. Works of the inventors mentioned herein, insofar as they are described in this section, as well as aspects of the description that may not have been prior art at the time of filing, are neither expressly nor implicitly recognized as prior art with respect to the present disclosure.

[0002] The present disclosure relates generally to a hazard warning system for a vehicle.

[0003] Vehicles can be equipped with various warning systems to help drivers avoid potential collisions or impacts. Many vehicles, for example, are equipped with a front assist system that can detect objects in front of the vehicle, such as other vehicles. Front assist systems can use imaging systems like cameras, light detection and ranging (LiDAR), and radar. While front assist systems are useful for detecting a potential object or collision, they cannot predict potential hazards on the road or inform the driver about the type of road and the hazard. Furthermore, front assist systems do not utilize a static infrastructure to capture and project images of multiple points along the roadway. Therefore, there is a need for improved vehicle monitoring systems to better detect potential hazards along the roadway. SUMMARY

[0004] In some aspects, a computer-implemented procedure, when executed by the data processing hardware, causes that hardware to perform operations. These operations include receiving radar data via a vehicle's radar system, identifying multipath clusters based on the radar data using a hazard warning algorithm, and estimating a local reflectance coefficient for one or more of the multipath clusters using the hazard warning algorithm. The operations also include comparing the local reflectance coefficient with a global reflectance coefficient stored by a hazard warning system using the hazard warning algorithm, identifying an anomaly based on this comparison, and updating a hazard list in the hazard warning algorithm with the identified anomaly.The processes also include assessing a hazard type based on the updated hazard list and issuing a warning stating the estimated hazard type using the hazard warning algorithm.

[0005] The operations may optionally include estimating the reflection point position of radar data on a road surface using the hazard warning algorithm. The operations may also include identifying a road boundary based on the reflection point position. In some examples, identifying the road boundary may include identifying a road type. Optionally, identifying multipath clusters may include generating geometric layout criteria and identifying the multipath clusters that meet these criteria. In some cases, identifying multipath clusters may include generating an amplitude test and identifying the multipath clusters based on the amplitude test.The processes can also include generating weights for an estimated global reflectance coefficient based on a comparison of the local reflectance coefficient with the global reflectance coefficient. Furthermore, the processes can include updating the global reflectance coefficient based on the generated weights and updating the road surface type of the global reflectance coefficient.

[0006] Another aspect of a hazard warning system is that it comprises data processing hardware and storage hardware that communicates with the data processing hardware. The storage hardware holds instructions that, when executed on the data processing hardware, cause it to perform operations. These operations include receiving radar data from a vehicle's radar system, identifying multipath clusters based on the radar data using a hazard warning algorithm, and estimating a local reflection coefficient for one or more of the multipath clusters using the same algorithm.The processes also include comparing the local reflection coefficient with a global reflection coefficient stored by a hazard warning system using the hazard warning algorithm, identifying an anomaly based on this comparison, and updating the hazard warning algorithm's hazard list with the identified anomaly. The processes further include assessing a hazard type based on the updated hazard list and issuing a warning, specifying the assessed hazard type, using the hazard warning algorithm.

[0007] The operations may optionally include estimating the reflection point position of radar data on a road surface using the hazard warning algorithm. The operations may also include identifying a road boundary based on the reflection point position. In some examples, identifying the road boundary may involve identifying a road type. Optionally, identifying multipath clusters may involve establishing geometric layout criteria and identifying the multipath clusters that meet those criteria. In some cases, the multipath clusters may include a target and one or more ghost targets. In other examples, identifying multipath clusters may involve capturing a large number of road points across a static infrastructure.The processes can also include generating weights for an estimated global reflection coefficient based on a comparison of the local reflection coefficient with the global reflection coefficient. Furthermore, the processes can include updating the global reflection coefficient based on the generated weights.

[0008] In other aspects, a vehicle hazard warning system comprises data processing hardware and storage hardware that communicates with the data processing hardware. The storage hardware holds instructions that, when executed on the data processing hardware, cause it to perform operations. These operations include receiving one or more input signals via the vehicle's radar system, identifying multipath clusters based on the one or more input signals using a hazard warning algorithm, and estimating a reflection point position on a road surface using the same algorithm.The processes also include identifying a road boundary based on the reflection point position, estimating a local reflection coefficient for one or more of the multipath clusters using the hazard warning algorithm, and comparing the local reflection coefficient with a global reflection coefficient stored by a hazard warning system. The processes further include identifying an anomaly based on the comparison of the local reflection coefficient with the global reflection coefficient, updating a hazard list of the hazard warning algorithm with the identified anomaly, estimating a hazard type based on the updated hazard list, and issuing a warning with the estimated hazard type using the hazard warning algorithm.

[0009] In some examples, the operations may optionally include generating weights for an estimated global reflection coefficient based on comparing the local reflection coefficient with the global reflection coefficient and updating the global reflection coefficient based on the generated weights. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] The drawings described herein serve only to illustrate selected arrangements and are not intended to limit the scope of the present disclosure. Fig. Figure 1 is a schematic representation of a vehicle equipped with a hazard warning system according to the present disclosure, Fig. Figure 2 is an exemplary block diagram of a hazard warning system according to the present disclosure, Fig. Figure 3 is a schematic representation of a vehicle equipped with a hazard warning system according to the present disclosure, wherein the vehicle is equipped with a radar system designed to detect a hazard and to drive on a roadway; Fig. Figure 4 is another exemplary block diagram of a hazard warning system according to the present disclosure, Fig. Figure 5 is a schematic representation of a radar system and the multipath effect of a hazard warning system according to the present disclosure, Fig. Figure 6 is an exemplary flowchart for a hazard warning system according to the present disclosure, and Fig. Figure 7 is an exemplary procedure for implementing a hazard warning system in accordance with the present disclosure.

[0011] Corresponding reference symbols identify corresponding parts in the drawings. DETAILED DESCRIPTION

[0012] Exemplary arrangements are now described in more detail with reference to the accompanying drawings. Since exemplary arrangements are provided, this is a careful disclosure that conveys the full scope of this disclosure to persons skilled in the art. Specific details are included, such as examples of specific components, devices, and processes, to provide a precise understanding of the embodiments of the present disclosure. It is obvious to persons skilled in the art that specific details need not be used, that exemplary embodiments can be embodied in many different forms, and that none of these should be interpreted as limiting the scope of the disclosure.

[0013] The terminology used herein serves only to describe certain exemplary arrangements and is not to be understood as restrictive. As used herein, the singular articles "a," "an," as well as "the," "a," and "an" can also include the plural forms unless the context clearly indicates otherwise. The terms "comprise," "comprehensive," "contain," and "exhibit" are inclusive and therefore specify the presence of properties, steps, processes, elements, and / or components, but do not exclude the presence or addition of one or more other properties, steps, processes, elements, and / or components and / or groups thereof.The procedures, processes, and processes described herein are not to be interpreted as necessarily requiring them to be carried out in the specific order explained or illustrated, unless they are expressly designated as the order of execution. Additional or alternative steps may be used.

[0014] When an element or layer is described as being "on" or "interacting with" another element or layer, or as being "connected" or "coupled" or "attached" to the same, it may be directly on or interacting with, connected with, coupled to, or attached to the other element or layer, or there may be intervening elements or layers. However, when an element is described as being "directly on" or "directly interacting with" another element or layer, or as being "directly connected" or "directly coupled" or "attached" to the same, there must be no intervening elements or layers. Other words used to describe the relationship between elements should be interpreted similarly (e.g.,“Between” as opposed to “directly between”, “neighboring” or “adjacent” as opposed to “directly adjacent” or “directly bordering”, etc.). As used herein, the term “and / or” includes all combinations of one or more of the related listed items.

[0015] The terms "first," "second," "third," etc., may be used herein to describe different elements, components, areas, layers, and / or sections. These elements, components, areas, layers, and / or sections should not be restricted by these terms. These terms may only be used to distinguish one element, component, area, layer, or section from another. Terms such as "first," "second," and other numerical terms do not imply any sequence or order unless the context clearly indicates otherwise.Thus, one could refer to a first element, a first component, a first area, a first layer or a first section, which are discussed below, as a second element, second component, second area, second layer or second section, without deviating from the lessons of the exemplary arrangements.

[0016] In this application, which includes the definitions below, the term "module" may be replaced by the term "circuit". The term "module" may refer to, be part of, or include: an application-specific integrated circuit (ASIC), a digital, analog, or mixed analog / digital discrete circuit, a digital, analog, or mixed analog / digital integrated circuit, a combinational logic circuit, a field-programmable gate array (FPGA), a processor (common, dedicated, or group) that executes code, a memory (common, dedicated, or group) that stores code executed by the processor, other suitable hardware components that provide the described functionality, or a combination of some or all of the above components, for example, in a system-on-a-chip.

[0017] The term "code," as used above, can include software, firmware, and / or microcode, and can refer to programs, routines, functions, classes, and / or objects. The term "shared processor" includes a single processor that executes some or all of the code from multiple modules. The term "group processor" includes a processor that, in combination with additional processors, executes some or all of the code from one or more modules. The term "shared memory" includes a single memory that stores some or all of the code from multiple modules. The term "group memory" includes a memory that, in combination with other memories, stores some or all of the code from one or more modules. The term "memory" is a subset of the term "computer-readable medium."The term "computer-readable medium" excludes transitory electrical and electromagnetic signals propagating through a medium and can therefore be considered a concrete and non-transient storage medium. Non-restrictive examples of non-transient storage include a concrete, computer-readable medium, including non-volatile memory, magnetic memory, and optical memory.

[0018] The devices and methods described in this application may be implemented in whole or in part by one or more computer programs executed by one or more processors. The computer programs comprise processor-executable instructions stored on at least one non-transitory, concrete, computer-readable medium. The computer programs may also include and / or be based on stored data.

[0019] A software application (i.e., a software resource) can refer to computer software that causes a computing device to perform a task. In some examples, a software application may be called an "application," "app," or "program." Examples of applications include system diagnostics applications, system administration applications, system maintenance applications, word processing applications, spreadsheet applications, messaging applications, media streaming applications, social networking applications, and gaming applications.

[0020] Non-transitory memory can be physical devices used for the temporary or permanent storage of programs (e.g., sequences of instructions) or data (e.g., program status information) for use by a computing device. Non-transitory memory can be volatile and / or non-volatile addressable semiconductor memory. Examples of non-volatile memory include flash memory and read-only memory (ROM) / programmable read-only memory (PROM) / erasable programmable read-only memory (EPROM) / electronic erasable programmable read-only memory (EEPROM) (e.g., typically used for firmware, such as boot programs). Examples of volatile memory include random-access memory (RAM), dynamic random-access memory (DRAM), static random-access memory (SRAM), phase-change memory (PCM), and floppy disks or tapes.

[0021] These computer programs (also referred to as programs, software, software applications, or code) comprise machine instructions for a programmable processor and may be written in a procedural and / or object-oriented high-level programming language and / or in assembly / machine language. As used herein, the terms "machine-readable medium" and "computer-readable medium" refer to computer program products of all kinds, non-transitory computer-readable media, devices, and / or equipment of all kinds (e.g., magnetic disk storage, optical disks, memory, programmable logic devices (PLDs)) for delivering machine instructions and / or data to a programmable processor, including a machine-readable medium that receives machine instructions as a machine-readable signal. The term "machine-readable signal" refers to any signal used to deliver machine instructions and / or data to a programmable processor.

[0022] Various implementations of the systems and techniques described herein can be realized in digital electronic and / or optical circuits, integrated circuits, specially designed ASICs (application-specific integrated circuits), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include execution in one or more computer programs that can be executed and / or interpreted on a programmable system comprising at least one programmable processor, which can be used for special or general purposes and is coupled such that it receives data and instructions from and transmits data and instructions to a storage system, as well as at least one input and at least one output device.

[0023] The processes and logical flows described in this description can be executed by one or more programmable processors, also known as data processing hardware, which run one or more computer programs to perform functions by acting on input data and producing outputs. The processes and logic flows can also be executed by specialized logic circuits, such as an FPGA (Field Programmable Gate Array) or an ASIC (Application Specific Integrated Circuit). Processors suitable for executing a computer program include, for example, general-purpose and specialized microprocessors, as well as one or more processors in all types of digital computers. Generally, a processor receives instructions and data from read-only memory, random-access memory, or both.The essential elements of a computer are a processor for executing instructions and one or more storage devices for storing instructions and data. Generally, a computer also includes one or more mass storage devices for storing data, such as magnetic, magneto-optical, or optical disks, or is functionally connected to them to receive data from or transmit data to them, or both. However, a computer does not necessarily have to have such devices. Computer-readable media suitable for storing computer program instructions and data include all forms of non-volatile memory, media, and storage devices, including, for example, semiconductor memory devices such as EPROM, EEPROM, and flash memory devices; magnetic disks such as internal hard disks or removable disks; magneto-optical disks; and CD-ROM and DVD-ROM disks.The processor and memory can be supplemented by or integrated into special logic circuits.

[0024] To enable interaction with a user, one or more aspects of the disclosure may be executed on a computer with a display device, such as a CRT (cathode ray tube) or LCD (liquid crystal display) monitor or a touchscreen, to display information to the user, and optionally a keyboard and pointing device, such as a mouse or trackball, with which the user can input data into the computer. Other types of devices may also be used to enable interaction with the user; for example, the user may receive any form of sensory feedback, such as visual, auditory, or tactile feedback, and user input may be received in any form, including acoustic, verbal, or tactile input.Furthermore, a computer can interact with a user by sending and receiving documents to a device used by the user, e.g., by sending web pages to a web browser on a user's client device in response to requests received from the web browser.

[0025] With reference to Fig. 1-5 comprises a hazard warning system 10 and a controller 12 designed with a hazard warning algorithm 14. The controller 12 can be designed as part of a vehicle 100 equipped with the hazard warning system 10. The vehicle 100 can also be equipped with a radar system 110 for acquiring radar data 112. The radar data 112 may, for example, contain a current image 114. The radar system 110 is communicatively connected to a static infrastructure 200 to receive a multitude of road points 202, which generally correspond to the current image 114 acquired by the radar system 110. For example, the radar system 110 is designed to query the multitude of road points 202 from the static infrastructure 200 in order to acquire at least some of the radar data 112.

[0026] The radar system 110 queries the radar data 112 received from the static infrastructure 200 and the road points 202 of a roadway 102. The radar system 110 can acquire the radar data 112 from reflections off the road surface 104 of the roadway 102, which is described in more detail below. The reflected static infrastructure 200 can store data relating to the roadway 102. For example, the reflected static infrastructure 200 can store a road type 106 of the roadway 102, which can be communicated via and used by the radar system 110. The radar system 110 can transmit the road type 106 to the hazard warning algorithm 14, which is described in more detail below. The hazard warning algorithm 14 receives the radar data 112 from the radar system 110 and can estimate a reflection point position 116 of the radar data on the road surface 104.Furthermore, the hazard warning system 10 can determine a road boundary 108 of the roadway 102 and the reflection coefficient 32 based on the reflection point position 116.

[0027] The hazard warning algorithm 14 is executed by the data processing hardware 16 of the controller 12. The controller 12 also includes memory hardware that communicates with the data processing hardware 16. The memory hardware stores instructions which, when executed on the data processing hardware 16, cause the hardware 16 to perform the operations described herein. The hazard warning algorithm 14 is designed to detect a multipath effect 20 based on the radar data 112. The multipath effect 20 can be used by the hazard warning algorithm 14 to identify multipath clusters 22 based on the radar data 112. As described in more detail below, the multipath clusters 22 can be used to identify a hazard 24 and the road type 106 of the carriageway 102, and the hazard warning algorithm 14 can issue a warning 26 to a driver of the vehicle 100. The hazard 24 can be, for example, a collision with a roadway 100. B., without being limited to an oil slick, a pothole and / or other obstacle or object on the roadway 102 that may affect the trajectory of the vehicle 100. The warning message 26 may alert the driver to the hazard 24 identified by the multi-route clusters 22.

[0028] The multipath clusters 22 comprise a target 22a and one or more ghost targets 22b-d. The multipath clusters 22 are partially identified by the radar system 110 from the multitude of detected road points 202 of the static infrastructure 200. The radar system 110 receives signals 28, 28a-n from the target 22a and from ghost targets 22b-d, so that the radar data 112, communicated via the hazard warning algorithm 14, report multiple targets 22a-d based on the signals 28, 28a-n. The hazard warning algorithm 14 is equipped with a multi-image reflection coefficient estimator 30, which is designed to determine and extract information about the road surface 104 from the ghost targets 22b-d when a reference signal 28a originates from the target 22a.

[0029] The multi-image reflection coefficient estimator 30 is a real-time estimator for reflection coefficients 32, 32a-n that utilizes information transmitted by a multitude of paths 34, 34a-n of the multi-path clusters 22. For example, the multitude of paths 34, 34a-n includes a direct-direct path 34a, an indirect-direct path 34b, a direct-indirect path 34c, and an indirect-indirect path 34d. The direct-direct path 34a leads to the target and back to radar system 110. Each of the indirect-direct paths 34b, the direct-indirect paths 34c, and the indirect-indirect paths 34d represents the ghost targets 22b-d. The multi-image reflection coefficient estimator 30 uses the information transmitted by the direct path 34a and the indirect paths 34b-d to estimate the respective reflection coefficients 32.When the signals 28, 28a-n are transmitted in the direction of the target 22a, the direct path 34a is defined, and the multi-image reflection coefficient estimator 30 uses the direct path 34a as a reference to extract information from the indirect paths 34b-d, which contain information about the reflection coefficients 32, 32a-n.

[0030] Hazard warning algorithm 14 uses geometric arrangement criteria 36 to identify the multipath clusters 22. For example, hazard warning algorithm 14 generates the geometric arrangement criteria 36 and identifies the multipath clusters that meet the geometric arrangement criteria 36. The geometric arrangement criteria 36 include an elevation E 34a of the direct-indirect route 34a, an elevation E 34d of the indirect-indirect route 34d, a height H 22a of target 22a, a height H 110 of radar system 110, a range R 34dof the indirect-indirect path 34d and a range R 34a of the direct-indirect path 34a. The multipath clusters 22 are compared with the geometric layout criteria 36 to identify the clusters 22 that meet the criteria 36, ​​which are described in more detail below. The geometric layout criteria 36 are used to align the radar system 110 and the target 22a relative to the road surface 104. The hazard warning algorithm 14 evaluates the multipath clusters 22 and paths 34, 34a-d to determine whether the target path 34a (i.e., the direct-direct path 34a) and the indirect-indirect path 34d meet the geometric layout criteria 36.

[0031] Once the hazard warning algorithm 14 has identified the target path 34a and the indirect-indirect path 34d based on the geometric arrangement criteria 36, ​​the hazard warning algorithm 14 works to identify the indirect-direct path 34b and the direct-indirect path 34c. The ghost targets 22b, 22c can be referred to as intermediate ghost targets 22b, 22c, and the corresponding paths 34b, 34c as intermediate paths 34b, 34c. The target path 34a is the shortest path between the radar system 110 and the target 22a, and the indirect-indirect path 34d is the longest path between the radar system 110 and the target 22a, via the ghost target 22d. The hazard warning algorithm 14 searches between the target path 34a and the indirect-indirect path 34d to determine whether the intermediate paths 34b, 34c each contain an area R 34b , R 34cexhibiting a position that falls in the middle of the area between target 22a and ghost target 22d. The first ghost target 22b has the same elevation E 22a like target 22a, and the second ghost target 22c has the same elevation E 22d like the ghost target 22d.

[0032] Hazard warning algorithm 14 uses the range resolution to distinguish between target 22a and the ghost target 22d. The intervening ghost targets 22b and 22c represent the average between the ranges R. 22a , R 22dof target 22a and ghost target 22d. At low resolution, the hazard warning algorithm 14 uses only the individual detection of target 22a and ghost target 22d. In this case, the hazard warning algorithm 14 identifies a single ghost target 22b, 22c. To verify the ghost targets 22b, 22c, the hazard warning algorithm 14, at a sufficiently high elevation resolution, performs an amplitude test 38 to determine the amplitudes 40, 40a-d of the multipath clusters 22. The amplitude test 38 is used to check the relationship between the ghost targets 22b-d and target 22a relative to the road surface 104. The amplitude ratio 40, 40a-d is between zero (0) and one (1). The relationship between the intermediate targets 22b, 22c is one (1). If the ratio of the amplitudes 40, 40a-d matches, the hazard warning algorithm 14 determines that all ghost targets 22b-d originate from the same source (i.e., target 22a).

[0033] With further reference to Fig. In steps 1-5, the multi-image reflection coefficient estimator 30 is used to distinguish between a local reflection coefficient 32a and a global reflection coefficient 32b. The multi-image reflection coefficient estimator 30 also improves the estimation accuracy of both the global reflection coefficient 32b and the local reflection coefficient 32a. The reflection coefficients 32, 32a-n are calculated from the signals 28, 28a-n associated with the target 22a and the ghost targets 22b-d. Using the multipath clusters 22, the multi-image reflection coefficient estimator 30 identifies which signal 28a originates from the target 22a and which signals 28b-d originate from the ghost targets 22b-d.For example, the multi-image reflectance coefficient estimator 30 can use reflection points 118, acquired from previous images as part of the radar data 112, to estimate the reflection point position 116 of the radar data 112 on the road surface 104, as mentioned above. The hazard warning algorithm 14 receives a signal 28a corresponding to the target 22a when the road surface 104 (i.e., a reflectance surface) is present, and also receives the signals 28b-d corresponding to the ghost targets 22b-d. The multi-image reflectance coefficient estimator 30 is able to recognize that the signals 28 originate from the same target 22a, so that the target 22a is the source of the ghost targets 22b-d. The hazard warning algorithm 14 is designed to extract information about the road surface 104 from the ghost targets 22b-d by evaluating the signal 28a from target 22a.

[0034] The current image 114 from the radar data 112 represents a time window and is received by the hazard warning algorithm 14 as input 50. The inputs 50 can also correspond to the signals 28 and the previously detected hazards 24, which may be stored as part of a hazard lookup table 60 in the memory hardware 18. The inputs 50 are received by the hazard warning algorithm 14 and used with the multi-image reflection coefficient estimator 30 to estimate the reflection point 118 on the road surface 104 for each multipath cluster 22. Based on the reflection point 118, the multi-image reflection coefficient estimator 30 estimates the local reflection coefficient 32a for one or more of the multi-path clusters 22. To evaluate the reflection coefficient 32, the multi-image reflection coefficient estimator 30 uses a multi-image approach to estimate the local reflection coefficient 32a.The multiple image approach improves the accuracy of the estimation of the local and global reflection coefficients 32a, 32b.

[0035] The local reflectance coefficient 32a is compared with the global reflectance coefficient 32b. The global reflectance coefficient 32b can be stored in the memory hardware 18 and used by the hazard warning algorithm 14 for comparison with the estimated local reflectance coefficient 32a. The global reflectance coefficient 32b contains information about the type of road surface 33. The hazard warning algorithm 14 can be designed to detect a change in the global reflectance coefficient 32b and, accordingly, a change in the road surface type 33 in order to issue the warning 26. For example, the road surface type 33 may change from a concrete road to a dirt road or a gravel road, which may cause the hazard warning algorithm 14 to issue a warning 26 informing a driver or controller of the change.

[0036] In some cases, comparing the local reflection coefficient 32a with the global reflection coefficient 32b can result in an anomaly 62. The anomaly 62 causes the local reflection coefficient 32a to be classified as a hazard 24 and entered into the hazard tracker 64 of the hazard warning algorithm 14. The hazard tracker 64 comprises a kinematic tracker 64a and a semantic tracker 64b. The hazard tracker 64 assigns the anomaly 62 to a hazard list 66 of the hazard lookup table 60 to identify a hazard type 68. If the anomaly 62 matches one of the hazards 24 on the hazard list 66, the hazard warning algorithm 14 updates the hazard 24 on the hazard list 66 and identifies the hazard type 68. For example, the hazard tracker 64 can check the hazard lookup table 60 using the reflection coefficient 32 to determine the hazard type 68.Once hazard type 68 is identified, the hazard warning algorithm 14 issues warning 26, which identifies hazard 24 for the driver of vehicle 100. If anomaly 62 does not match a hazard 24 from hazard list 66, the hazard warning algorithm 14 triggers a new hazard 24.

[0037] Hazard warning algorithm 14 uses hazard tracker 64 to identify the previously detected hazard 24 and link it to the newly identified hazard 24. Hazard warning algorithm 14 attempts to link the current hazard 24 with the previously tracked hazard 24 by using hazard tracker 64. For example, kinematic tracker 64a is used to link the current hazard 24 with the location of the previously located hazard 24. Semantic tracker 64b is used to link the current hazard with the reflection coefficient of the previously located hazard 24.

[0038] In some cases, comparing the local reflection coefficient 32a with the global reflection coefficient 32b does not yield anomaly 62. The hazard warning algorithm 14 can use the absence of anomaly 62 to improve the accuracy of estimating the global reflection coefficient 32b of the roadway 102. For example, the hazard warning algorithm 14 can use the global reflection coefficient 32b to classify the road type 106 and report this to the driver of vehicle 100. In some cases, the controller 12 can communicate with a back-office server 300 ( Fig. 1) to which the hazard warning algorithm 14 can transmit the warning 26 and / or the road type 106 determined by comparing the local reflection coefficient 32a with the global reflection coefficient 32b. In some examples and arrangements, the hazard warning algorithm 14 can be executed and implemented by the back-office server 300, and the warning 26 and the road type 106 are transmitted to the control unit 12 of the vehicle 100 for communication with the driver of the vehicle 100.

[0039] Hazard warning algorithm 14 generates weights 70 for an estimated global reflection coefficient 32c based on a comparison of the local reflection coefficient 32a with the global reflection coefficient 32b. Hazard warning algorithm 14 uses an alpha-beta filter 72 to generate the weights 70. The weights 70 are generated based on the comparison of the local reflection coefficient 32a with the global reflection coefficient 32b and are used for an updated, estimated global reflection coefficient 32c. The weights 70 can be calculated, for example, using a function based on factors such as the signal-to-noise ratio (SRV), the number of peak values ​​used for the estimate, and the difference between the local reflection coefficients 32a. The weights 70 can be calculated using the following example equation: wi=GSRVWNPeaksWρdiff where W SNRFor the SRV weighting 70a, W NPeaks for the number of peak values ​​70b and W ρdiff For the distance weighting of the local reflectance coefficient 70c. The SRV weightings 70a assign a higher weight to points with a high SRV. The higher the SRV, the more accurate the point. The higher number of peak values ​​70b in a cluster 22 leads to a high estimate of the local reflectance coefficient 32a, which results in a high weighting in the overall estimate. The weightings of the local reflectance coefficient 70c can show a large difference, which indicates the presence of a hazard rather than information about the road surface. The large difference leads to a lower associated weighting 70. Conversely, if all values ​​of the local reflectance coefficient 32a show significant differences, this indicates a change in the road surface 104.

[0040] The weights 70 generated by the alpha-beta filter 72 improve the accuracy of the hazard warning algorithm 14's estimation of the reflection coefficients 32. The weights 70 can range from zero (0) to one (1), so a weight 70 of zero (0) indicates that the hazard warning algorithm 14 should rely on the previous reflection coefficient 32 rather than the current one. A weight 70 of one (1) indicates that the current reflection coefficient 32 is exact and the hazard warning algorithm 14 can disregard the previous reflection coefficient 32. The estimate is improved by the hazard warning algorithm 14, which uses the previous reflection coefficient 32 of hazard 24 and the new, measured reflection coefficient 32 of hazard 24 to calculate a new, updated global reflection coefficient 32b.

[0041] With the following reference to Fig. Figure 6 shows an example flowchart for the hazard warning system 10. At 600, the hazard warning system 10 receives input 50 and at 602 finds the multipath clusters 22. At 604, the hazard warning algorithm 14 estimates the reflection point positions 116. At 606, the hazard warning algorithm 14 determines whether road boundaries 108 are present. If not, at 608, the hazard warning algorithm 14 determines whether the multipath clusters 22 are complete. If the multipath clusters 22 are not yet complete, the hazard warning algorithm 14 returns at 604 to estimating the reflection point positions. If the multipath clusters 22 are complete, at 610, the hazard warning algorithm 14 updates the global reflection coefficient 32b. If there are 108 multipath cluster reflection points in the road boundaries, the hazard warning algorithm 14 estimates a local reflection coefficient 32a for each cluster at 612.The hazard warning algorithm 14 then determines at step 614 whether there is a difference between the local reflection coefficient 32a and the global reflection coefficient 32b. If there is no difference, the hazard warning algorithm 14 calculates the weights 70 for estimating the global reflection coefficient 32b at step 616 and proceeds with steps 608 and 610. If there is a difference between the local reflection coefficient 32a and the global reflection coefficient 32b, the hazard warning algorithm 14 updates the hazard 24 at step 618 based on the hazard list 66. The hazard warning algorithm 14 estimates the hazard type 68 at step 620 and issues a warning 26 at step 622.

[0042] With the following reference to Fig.Figure 7 shows an exemplary procedure 700 for the hazard warning system 10. At 702, the hazard warning system 10 receives radar data 112 from a vehicle's radar system 110 and, at 704, identifies multipath clusters 22 based on the radar data 112 using a hazard warning algorithm 14. At 706, the hazard warning algorithm 14 estimates a reflection point position 116 on a road surface 104 and, at 708, identifies a road boundary 108 based on the reflection point position 116. At 710, the hazard warning algorithm 14 estimates a local reflection coefficient 32b for one or more of the multipath clusters 22 and, at 712, compares the local reflection coefficient 32a with a global reflection coefficient 32b stored by the hazard warning system 10. The hazard warning algorithm 14 identifies an anomaly 62 at 714 based on the comparison of the local reflection coefficient 32a with the global reflection coefficient 32b.At 716, a hazard list 66 of the hazard warning algorithm 14 is updated with the identified anomaly 62. Based on the updated hazard list 66, the hazard warning algorithm 14 estimates a hazard type 68 at 718 and issues a warning 26 with the estimated hazard type 68 at 720.

[0043] A number of interpretations have been described. However, it is understood that various modifications can be made without departing from the spirit and scope of the revelation. Accordingly, other interpretations also fall within the scope of the following claims.

[0044] The foregoing description of the embodiments serves for illustration and description purposes. It makes no claim to be complete or to limit the disclosure. Individual elements or features of a particular embodiment are generally not limited to that embodiment, but are interchangeable and may be used in a selected embodiment, even if they are not specifically shown or described. They may also be modified in many ways. Such modifications are not to be considered a departure from the disclosure, and all such modifications are intended to be contained within the scope of the disclosure. legend

[0045] In the drawing figures, N stands for no and Y for yes.

Claims

[1] A computer-implemented procedure which, when executed by the data processing hardware, causes that hardware to perform operations which include: Receiving radar data via a vehicle's radar system, Identifying multipath clusters based on radar data using a hazard warning algorithm, Estimating a local reflection coefficient for one or more multipath clusters using the hazard warning algorithm, Comparing the local reflection coefficient using the hazard warning algorithm with a global reflection coefficient stored by a hazard warning system, Identifying an anomaly based on comparing the local reflection coefficient with the global reflection coefficient. Updating a hazard list of the hazard warning algorithm with the identified anomaly, Estimating a hazard type based on the updated hazard list, and Issuing a warning with the estimated hazard type using the hazard warning algorithm. [2] Method according to claim 1, further comprising estimating a reflection point position of the radar data on a road surface using the hazard warning algorithm. [3] Method according to claim 2, further comprising identifying a road boundary based on the reflection point position. [4] Method according to claim 3, wherein identifying the road boundary includes identifying a road type. [5] Method according to claim 1, wherein the identification of the multipath clusters comprises generating geometric layout criteria and identifying the multipath clusters that satisfy the geometric layout criteria. [6] Method according to claim 1, wherein identifying the multipath clusters comprises generating an amplitude test and identifying the multipath clusters based on the amplitude test. [7] Method according to claim 1, wherein the identification of the multipath clusters comprises capturing a plurality of road points via a static infrastructure. [8] Method according to claim 1, wherein weights for an estimated global reflection coefficient are generated on the basis of comparing the local reflection coefficient with the global reflection coefficient. [9] The method of claim 8, further comprising updating the global reflection coefficient based on the generated weights and updating the road surface type of the global reflection coefficient. [10] Hazard warning system of a vehicle designed to carry out the method according to claim 1.

Images