Map information diagnosis method and device, controller and vehicle

Abstract

The invention relates to a map information diagnosis method and device, a controller and a vehicle, and relates to the technical field of data processing. The method comprises the following steps: receiving map information of a vehicle; pre-diagnosing the map information and determining a pre-diagnosis result of the map information; wherein the pre-diagnosis comprises at least one of frame loss pre-diagnosis, continuity pre-diagnosis and invalid value pre-diagnosis, and the pre-diagnosis result comprises at least one of a frame loss pre-diagnosis result, a continuity pre-diagnosis result and an invalid value pre-diagnosis result; and determining a diagnosis result of the map information according to the pre-diagnosis result. By adopting the method, the fault diagnosis of the map information can be realized.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a map information diagnosis method, device, controller and vehicle. Background Art

[0002] With the development of vehicle technology, intelligent driving technology has emerged, such as L2-level intelligent assisted driving. Intelligent driving technology can sense the surrounding environment of the road by integrating multiple sensors, combining high-precision maps and high-precision positioning to achieve path planning, and control vehicle movement after making decisions. Intelligent driving technology can improve road traffic efficiency, reduce traffic accidents and casualties, improve vehicle operation efficiency, reduce driver labor intensity, reduce energy consumption and emissions, and improve travel comfort.

[0003] Fault diagnosis is a key part of intelligent driving technology. Fault diagnosis obtains relevant data of the vehicle's driving process for analysis, gives fault judgment results, and guides safe driving. Map information is one of the important perception information sources of L2-level intelligent assisted driving systems. It can provide vehicles with detailed information about the road ahead, facilitating effective path planning and control. However, existing intelligent driving assistance systems do not have a fault diagnosis method for map information. Summary of the invention

[0004] Based on this, it is necessary to provide a map information diagnosis method, device, controller and vehicle to address the above technical problems, which can realize fault diagnosis of map information.

[0005] In a first aspect, the present application provides a map information diagnosis method, the method comprising:

[0006] Receive map information of the vehicle;

[0007] Performing a pre-diagnosis on the map information and determining a pre-diagnosis result of the map information; wherein the pre-diagnosis includes at least one of a frame loss pre-diagnosis, a continuity pre-diagnosis, and an invalid value pre-diagnosis, and the pre-diagnosis result includes at least one of a frame loss pre-diagnosis result, a continuity pre-diagnosis result, and an invalid value pre-diagnosis result;

[0008] A diagnosis result of the map information is determined according to the pre-diagnosis result.

[0009] In one embodiment, the pre-diagnosis includes frame loss pre-diagnosis, and the pre-diagnosis result includes a frame loss pre-diagnosis result, wherein the pre-diagnosis of the map information and determining the pre-diagnosis result of the map information includes:

[0010] determining an actual reception time of the map information upon receipt of the map information;

[0011] determining a reception time difference between the actual reception time and the expected reception time of the map information;

[0012] The frame loss pre-diagnosis result of the map information is determined according to the receiving time difference and the time threshold.

[0013] In one embodiment, the pre-diagnosis includes frame loss pre-diagnosis, and the pre-diagnosis result includes a frame loss pre-diagnosis result, wherein the pre-diagnosis of the map information and determining the pre-diagnosis result of the map information includes:

[0014] In a case where the map information is not received and the duration of not receiving the map information does not exceed a first duration, determining an actual reception period of the map information according to the reception period of the map information;

[0015] In the case where the map information is not received and the duration of not receiving the map information exceeds a first duration, determining the actual receiving period of the map information according to a preset multiple of the receiving period; wherein the preset multiple is greater than 1;

[0016] The frame loss pre-diagnosis result of the map information is determined according to the expected receiving time of the map information, the actual receiving period and the time threshold.

[0017] In one embodiment, the method further comprises:

[0018] Recording the number of frame losses for which the pre-diagnosis result of frame loss is a frame loss fault;

[0019] The time threshold is adjusted according to the number of frame losses.

[0020] In one embodiment, the pre-diagnosis includes continuous pre-diagnosis, and the pre-diagnosis result includes continuous pre-diagnosis result, wherein the pre-diagnosis of the map information and determining the pre-diagnosis result of the map information includes:

[0021] Acquiring historical map information of the vehicle; wherein the actual receiving time of the historical map information is earlier than the actual receiving time of the map information;

[0022] determining an information difference between the map information and the historical map information;

[0023] A continuity pre-diagnosis result of the map information is determined according to the information difference and the information threshold.

[0024] In one embodiment, the map information includes a road type location, the information difference includes a road type location difference, the information threshold includes a location threshold, and determining the continuity pre-diagnosis result of the map information according to the information difference and a preset information threshold includes:

[0025] Acquiring longitudinal speed information of the vehicle;

[0026] determining a distance compensation amount according to the longitudinal vehicle speed information, the actual receiving time of the map information, and the actual receiving time of the historical map information;

[0027] A continuity pre-diagnosis result of the map information is determined according to the distance compensation amount, the road type position difference and the position threshold.

[0028] In one embodiment, the pre-diagnosis includes invalid value pre-diagnosis, and the pre-diagnosis result includes an invalid value pre-diagnosis result, wherein the pre-diagnosis of the map information and determining the pre-diagnosis result of the map information includes:

[0029] An invalid value pre-diagnosis result of the map information is determined according to the map information, a value range of the map information and a decision range of the intelligent assisted driving system of the vehicle for the map information.

[0030] In one embodiment, the pre-diagnosis includes at least one of a continuous pre-diagnosis and an invalid value pre-diagnosis, the pre-diagnosis result includes at least one of a continuous pre-diagnosis result and an invalid value pre-diagnosis result, and the pre-diagnosis of the map information and determining the pre-diagnosis result of the map information includes:

[0031] Acquiring longitudinal speed information of the vehicle;

[0032] At least one of a continuity pre-diagnosis result and an invalid value pre-diagnosis result of the map information is determined based on the longitudinal vehicle speed information, the map information and the long short-term memory neural network model.

[0033] In one embodiment, determining the diagnosis result of the map information according to the pre-diagnosis result includes:

[0034] Obtaining the number of fault items in the pre-diagnosis result;

[0035] When the number of fault items is greater than zero and less than or equal to a first fault threshold, determining that the diagnosis result of the map information is a minor fault;

[0036] When the number of fault items is greater than the first fault threshold and the number of fault items is less than a second fault threshold, determining that the diagnosis result of the map information is a moderate fault; wherein the first fault threshold is less than the second fault threshold;

[0037] When the number of fault items is greater than or equal to the second fault threshold, it is determined that the diagnosis result of the map information is a serious fault.

[0038] In a second aspect, the present application provides a map information diagnosis device, the device comprising:

[0039] A receiving module, used for receiving map information of the vehicle;

[0040] a pre-diagnosis module, configured to pre-diagnose the map information and determine a pre-diagnosis result of the map information; wherein the pre-diagnosis includes at least one of frame loss pre-diagnosis, continuity pre-diagnosis and invalid value pre-diagnosis, and the pre-diagnosis result includes at least one of frame loss pre-diagnosis result, continuity pre-diagnosis result and invalid value pre-diagnosis result;

[0041] A comprehensive diagnosis module is used to determine a diagnosis result of the map information according to the pre-diagnosis result.

[0042] In a third aspect, the present application provides a controller including a memory and a processor, wherein the memory stores a computer program, and the controller implements the steps of the above method when executing the computer program.

[0043] In a fourth aspect, the present application provides a vehicle, comprising a controller as described above.

[0044] The above-mentioned map information diagnosis method, device, controller and vehicle receive map information from the vehicle, pre-diagnose the map information and determine the pre-diagnosis result of the map information, and determine the diagnosis result of the map information based on the pre-diagnosis result, wherein the pre-diagnosis includes at least one of frame loss pre-diagnosis, continuity pre-diagnosis and invalid value pre-diagnosis, and the pre-diagnosis result includes at least one of frame loss pre-diagnosis result, continuity pre-diagnosis result and invalid value pre-diagnosis result. The map information diagnosis method realizes fault diagnosis of multiple dimensions of map information by performing frame loss pre-diagnosis, continuity pre-diagnosis and invalid value pre-diagnosis on map information, which helps to provide map information diagnosis input for the vehicle intelligent driving assistance system to make reasonable decisions, and can improve the safety of vehicle intelligent driving. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] FIG1 is a schematic diagram of a flowchart of a map information diagnosis method according to an embodiment;

[0046] FIG2 is a second flow chart of a map information diagnosis method according to an embodiment;

[0047] FIG3 is a third flow chart of a map information diagnosis method according to an embodiment;

[0048] FIG4 is a fourth flow chart of a map information diagnosis method according to an embodiment;

[0049] FIG5 is a fifth flow chart of a map information diagnosis method according to an embodiment;

[0050] FIG6 is a sixth flow chart of a map information diagnosis method according to an embodiment;

[0051] FIG. 7 is a seventh flow chart of a map information diagnosis method according to an embodiment;

[0052] FIG8 is a flowchart of a map information diagnosis method according to an embodiment of the present invention;

[0053] FIG9 is a block diagram of a map information diagnosis device according to an embodiment;

[0054] FIG. 10 is a diagram showing the internal structure of a controller in one embodiment. DETAILED DESCRIPTION

[0055] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0056] In one embodiment, as shown in FIG1 , a map information diagnosis method is provided, and this embodiment is illustrated by applying the method to a terminal. It is understandable that the method can also be applied to a server, and can also be applied to a system including a terminal and a server, and is implemented through the interaction between the terminal and the server. Exemplarily, the terminal includes an intelligent driving domain controller, for example, an L2-level intelligent driving domain controller, referred to as an L2 controller. For ease of description, the map information diagnosis method is applied to an L2 controller as an example to introduce map information diagnosis. In this embodiment, the method includes the following steps S102 to S106.

[0057] S102: Receive map information of the vehicle.

[0058] The vehicle's map information refers to geographic data related to the vehicle's location and driving. Map information can provide the vehicle with various information about the road ahead, facilitating effective path planning and control for the vehicle to achieve intelligent driving of the vehicle. For example, the L2 controller receives the vehicle's map information, which can be used as input information for the L2-level intelligent driving assistance system to achieve L2-level intelligent driving.

[0059] Exemplarily, the map information includes road parameter information and road type information. Among them, the road parameter information includes at least one of the longitudinal slope, lateral slope and road curvature of the road in front of the vehicle. In the embodiment of the present application, the longitudinal direction refers to the forward direction of the vehicle, and the lateral direction is the direction perpendicular to the longitudinal direction. The specific road type information includes at least one of the specific road type and road type position of the road in front of the vehicle. Among them, the specific road type includes ramps, tunnels or bridges, and can also be other road types other than the main road of the highway, which are not overly limited here. The road type position refers to the current distance between the specific road type and the vehicle. In the application, the L2 controller can receive different types of map information sent by different sensors on the vehicle.

[0060] Exemplarily, receiving map information of a vehicle includes: receiving a map message of the vehicle, the map message including map information, the map information including at least one of longitudinal slope, transverse slope, road curvature, specific road type and road type location. That is, the map information is transmitted in the form of a message. In the application, the L2 controller can receive map messages via the CAN (Controller Area Network) bus. It should be noted that the longitudinal slope, transverse slope, road curvature, specific road type and road type location can be transmitted separately in the form of a message, or multiple can be transmitted together in the form of a message, which can be specifically set according to factors such as the method of collecting map information, and is not limited here.

[0061] S104: Pre-diagnose the map information and determine the pre-diagnosis result of the map information, wherein the pre-diagnosis includes at least one of frame loss pre-diagnosis, continuity pre-diagnosis and invalid value pre-diagnosis, and the pre-diagnosis result includes at least one of frame loss pre-diagnosis result, continuity pre-diagnosis result and invalid value pre-diagnosis result.

[0062] Frame loss pre-diagnosis refers to the detection of whether the map information is received as expected. Accordingly, the frame loss pre-diagnosis result is used to indicate whether the map information is received as expected. The frame loss pre-diagnosis result includes frame loss failure or frame loss normal. Among them, frame loss failure indicates that the map information is not received as expected, and frame loss normal indicates that the map information is received as expected.

[0063] Continuity pre-diagnosis refers to the detection of whether continuous map information is received. Accordingly, the continuity pre-diagnosis result is used to indicate whether continuous map information is received. Continuity pre-diagnosis includes continuity failure or continuity normal. Among them, continuity failure indicates that continuous map information is not received, and continuity normal indicates that continuous map information is received.

[0064] Invalid value pre-diagnosis refers to the detection of whether the value of the received map information is valid. Accordingly, the invalid value pre-diagnosis result is used to indicate whether the value of the received map information is valid. The invalid value pre-diagnosis result includes invalid value failure or invalid value normal. Among them, invalid value failure indicates that the value of the received map information is invalid, and invalid value normal indicates that the value of the received map information is valid.

[0065] In the application, the L2 controller can perform frame loss pre-diagnosis on the map information and determine the frame loss pre-diagnosis result of the map information, and can also perform continuity pre-diagnosis on the map information and determine the continuity pre-diagnosis result of the map information, and can also perform invalid value pre-diagnosis on the map information and determine the invalid value pre-diagnosis result of the map information.

[0066] It should be noted that, for map information including one or more of longitudinal slope, transverse slope, road curvature, specific road type and road type position, frame loss, continuity and invalid value pre-diagnosis can be performed for each type of map information obtained, respectively, and the specific settings are made accordingly according to the type of information included in the map information, which is not limited here. For example, the map information includes longitudinal slope and transverse slope, and taking the pre-diagnosis including frame loss, continuity and invalid value pre-diagnosis as an example, frame loss, continuity and invalid value pre-diagnosis are performed for the longitudinal slope, and frame loss, continuity and invalid value pre-diagnosis are performed for the transverse slope.

[0067] S106: Determine a diagnosis result of the map information according to the pre-diagnosis result.

[0068] The diagnostic result of the map information is used to indicate whether the map information is faulty. The diagnostic results include map fault and map normal. Among them, map fault means that the map information is inaccurate or faulty and cannot be used for vehicle intelligent driving, that is, it cannot be used as input information for the L2 intelligent driving assistance system; map normal means that the map information is valid and accurate and can be used for vehicle intelligent driving, that is, it can be used as input information for the L2 intelligent driving assistance system.

[0069] Based on the above step S104, it can be known that the pre-diagnosis result includes at least one of a frame loss pre-diagnosis result, a continuity pre-diagnosis result and an invalid value pre-diagnosis result. Based on this, when the pre-diagnosis result includes one pre-diagnosis result such as a frame loss pre-diagnosis result, the diagnosis result of the map information is determined according to the frame loss pre-diagnosis result; when the pre-diagnosis result includes two pre-diagnosis results such as a frame loss pre-diagnosis result and a continuity pre-diagnosis result, the diagnosis result of the map information is determined according to the frame loss pre-diagnosis result and the continuity pre-diagnosis result; when the pre-diagnosis result includes all pre-diagnosis results, the diagnosis result of the map information is determined according to all pre-diagnosis results.

[0070] Exemplarily, the L2 controller receives a map message sent by the CAN bus, performs frame loss pre-diagnosis on the map message and determines a frame loss pre-diagnosis result of the map message, performs continuity pre-diagnosis on the map message and determines a continuity pre-diagnosis result of the map message, and performs invalid value pre-diagnosis on the map message and determines an invalid value pre-diagnosis result of the map message, thereby determining a diagnostic result of the map information based on the frame loss pre-diagnosis result, the continuity pre-diagnosis result and the invalid value pre-diagnosis result.

[0071] It should be noted that the above map information diagnosis method can adopt an online diagnosis method to perform online fault diagnosis on the map information in real time, which can meet the driving needs of the vehicle.

[0072] The above-mentioned map information diagnosis method receives map information of the vehicle, pre-diagnoses the map information and determines the pre-diagnosis result of the map information, and determines the diagnosis result of the map information based on the pre-diagnosis result, wherein the pre-diagnosis includes at least one of frame loss pre-diagnosis, continuity pre-diagnosis and invalid value pre-diagnosis, and the pre-diagnosis result includes at least one of frame loss pre-diagnosis result, continuity pre-diagnosis result and invalid value pre-diagnosis result. The map information diagnosis method realizes fault diagnosis of multiple dimensions of map information by performing frame loss pre-diagnosis, continuity pre-diagnosis and invalid value pre-diagnosis on map information, which helps to provide map information diagnosis input for the vehicle intelligent driving assistance system to make reasonable decisions, and can improve the safety of vehicle intelligent driving.

[0073] In one embodiment, the pre-diagnosis includes frame loss pre-diagnosis, and the pre-diagnosis result includes a frame loss pre-diagnosis result, wherein, as shown in FIG. 2 , step S104 , pre-diagnosing the map information and determining the pre-diagnosis result of the map information, may include the following steps S202 to S206 .

[0074] S202: Determine the actual reception time of the map information when the map information is received.

[0075] The actual receiving time refers to the time when the map information is actually received. For example, when the L2 controller receives the map information, the actual receiving time of the map information is updated in real time.

[0076] S204: Determine a reception time difference between the actual reception time and the expected reception time of the map information.

[0077] In the embodiment of the present application, the reception time difference is recorded as T, where T represents the difference between the actual reception time and the expected reception time. The expected reception time refers to the time when the map information is expected to be received. The reception period refers to the period for receiving the map information. Exemplarily, the expected reception time of the map information is determined according to the reception period and the reception order of the map information.

[0078] For example, the L2 controller periodically receives map messages, so the expected reception time of the map message currently to be received can be determined according to the reception period and reception order of the map messages. For example, the reception period of the map message is Ts, and the L2 controller is initialized when powered on, and the timestamp of the first map message received is 0s, then the expected reception time of the second map message is Ts, and the expected reception time of the third map message is 2Ts, and so on.

[0079] S206: Determine a frame loss pre-diagnosis result of the map information according to the reception time difference and the time threshold.

[0080] The time threshold is pre-set and can be set according to the actual application scenario.

[0081] Exemplarily, the absolute value of the reception time difference is compared with the time threshold, and when the absolute value of the reception time difference exceeds the time threshold, the frame loss pre-diagnosis result of the map information is determined to be a frame loss fault, otherwise, it is determined to be normal frame loss.

[0082] In an embodiment of the present application, a frame loss parameter F1 is defined, and F1 represents the number of consecutive times that the absolute value of the received time difference exceeds the time threshold. F1 is a dynamically changing parameter. Exemplarily, the absolute value of the received time difference is compared with the time threshold. When the absolute value of the received time difference exceeds the time threshold, the frame loss parameter F1 is increased by one, and the frame loss parameter F1 after the increase is compared with the frame loss threshold. When the frame loss parameter F1 after the increase exceeds the frame loss threshold, the frame loss pre-diagnosis result of the map information is determined to be a frame loss fault, otherwise, it is determined to be normal. Moreover, after being determined as a frame loss fault, if there are multiple consecutive map information frame loss pre-diagnosis results that are normal, it is determined that the map information frame loss has returned to normal, and the frame loss parameter F1 is cleared. In this way, after being determined as a frame loss fault, continuous monitoring can be performed and the fault state can be exited after returning to normal, which is more flexible and intelligent.

[0083] The above-mentioned map information diagnosis method determines the actual reception time of the map information when the map information is received, and determines the reception time difference between the actual reception time and the expected reception time of the map information, and determines the frame loss pre-diagnosis result of the map information based on the reception time difference and the time threshold, thereby realizing the frame loss pre-diagnosis of the map information, so that the map information can be diagnosed based on the frame loss pre-diagnosis result. In this way, when there is a frame loss fault in the map information, the fault diagnosis result can be fed back in time and the cause of the fault can be analyzed, which helps to provide reliable map information diagnosis input for the vehicle intelligent driving assistance system to make reasonable decisions, and can improve the safety of vehicle intelligent driving.

[0084] In one embodiment, as shown in Figure 3, the pre-diagnosis includes frame loss pre-diagnosis, and the pre-diagnosis result includes a frame loss pre-diagnosis result. Step S104, pre-diagnosing the map information and determining the pre-diagnosis result of the map information, may include the following steps S302 to S306.

[0085] S302: When no map information is received and the duration of not receiving the map information does not exceed a first duration, determine an actual reception period of the map information according to the reception period of the map information.

[0086] The first duration is preset and can be set according to the actual application scenario. For example, the first duration is 3 receiving cycles, i.e. 3Ts. The actual receiving cycle is used to dynamically record the cumulative receiving time of map information. The actual receiving cycle can be understood as an internally set variable that changes dynamically with the growth of natural time.

[0087] Exemplarily, when the map information is not received and the duration of not receiving the map information does not exceed the first duration, the actual receiving period is dynamically adjusted according to the receiving period over natural time. For example, when the L2 controller has not actually received the map message and the duration of not receiving the map message does not exceed 3 receiving periods, i.e., 3Ts, the actual receiving period of the map message is accumulated by one receiving period Ts every time Ts passes.

[0088] S304: When no map information is received and the duration of not receiving the map information exceeds a first duration, determining an actual reception period of the map information according to a preset multiple of the reception period; wherein the preset multiple is greater than 1.

[0089] The preset multiple is a value greater than 1, for example, it may be 1.1, 1.2, 1.5, 2 or 2.5, etc., or it may be any other value greater than 1, and no further limitation is made here.

[0090] Exemplarily, when the map information is not received and the duration of not receiving the map information exceeds the first duration, the actual receiving period is dynamically adjusted according to the preset multiple of the receiving period over natural time. For example, the preset multiple is 1.5, and when the L2 controller actually has not received the map message, and the duration of not receiving the map message exceeds 3 receiving periods, i.e., 3Ts, the actual receiving period of the map message is accumulated by 1.5Ts every Ts.

[0091] It should be noted that the actual receiving cycle is a cumulative value. For example, if the map message receiving cycle is Ts, it is initialized when the L2 controller is powered on. For example, the timestamp of receiving the first map message is 0s, the actual receiving cycle is recorded as 0, and the first four map messages are received normally. After each Ts, the actual receiving cycle is accumulated by Ts. After receiving the first four map messages, the corresponding actual receiving cycle is 3Ts, and the expected receiving time of the fifth map message is 4Ts. If the L2 controller has not received the fifth message, when the duration does not exceed 3 receiving cycles, i.e. 3Ts, the actual receiving cycle will be accumulated by Ts every Ts. When the duration exceeds 3 receiving cycles, i.e. 3Ts, the actual receiving cycle will be accumulated by 1.5 times Ts every Ts until the fifth map message is received.

[0092] S306: Determine a frame loss pre-diagnosis result of the map information according to the expected reception time of the map information, the actual reception period and the time threshold.

[0093] Exemplarily, the duration difference between the actual receiving cycle and the expected receiving time is determined, and the absolute value of the duration difference is compared with the receiving time threshold. When the absolute value of the duration difference exceeds the receiving time threshold, the pre-diagnosis result of the frame loss of the map information is determined to be a frame loss fault, otherwise, it is determined to be normal frame loss. The expected receiving time is related to the receiving cycle of the map information. The specific relationship between the expected receiving time and the receiving cycle can be found in the previous description, which will not be repeated here.

[0094] The above-mentioned map information diagnosis method, when map information is not received and the duration of not receiving map information does not exceed the first duration, determines the actual receiving period of map information according to the receiving period; when map information is not received and the duration of not receiving map information exceeds the first duration, determines the actual receiving period of map information according to the preset multiple of the receiving period, and determines the frame loss pre-diagnosis result of map information according to the expected receiving time, the actual receiving period and the receiving time threshold. In the case that map information is not received, the method dynamically records the accumulated receiving time of map information by additionally setting the actual receiving period, and realizes the frame loss pre-diagnosis of map information according to the actual receiving period, so that the frame loss pre-diagnosis of map information can be realized even when the received map information is not received, and then the fault diagnosis of map information can be realized according to the frame loss pre-diagnosis result; in addition, when the duration of not receiving map information exceeds the first duration, the actual receiving period is dynamically adjusted by the preset multiple of the receiving period, which can accelerate the determination of whether there is a frame loss fault in the map information, improve the diagnosis rate of map information, can respond to the fault of map information more quickly, and improve the sensitivity to the existence of frame loss fault in the map information, thereby improving the reliability and accuracy of map information, which helps to further improve the safety of vehicle intelligent driving.

[0095] It should be noted that, according to the previous records, map information may include at least one of longitudinal slope, lateral slope, road curvature, specific road type and road type location. In this regard, frame loss pre-diagnosis can be performed for each type of map information and the corresponding frame loss pre-diagnosis result can be determined. The frame loss pre-diagnosis process can be specifically referred to the relevant records of the method shown in Figures 2 and 3, which will not be repeated here.

[0096] In one embodiment, the map information diagnosis method may further include: recording the number of frame loss times when the frame loss pre-diagnosis result is a frame loss fault, and adjusting the time threshold according to the number of frame loss times, wherein the number of frame loss times indicates the cumulative number of times when the frame loss pre-diagnosis result of the map information is determined to be a frame loss fault.

[0097] Exemplarily, the adjusted time threshold is less than the time threshold before adjustment, and the adjusted time threshold is greater than or equal to the time upper limit, wherein the time upper limit is a preset fixed value. In this way, in the case of a frame loss fault, by adjusting the time threshold, it is easier to diagnose whether the map information has a frame loss fault, thereby increasing the sensitivity to the map information having a frame loss fault, thereby increasing the reliability and accuracy of the map information, and helping to further improve the safety of the vehicle.

[0098] Exemplarily, the change of the time threshold conforms to the change trend of the exponential function, which can be expressed as y1=a1^x1, where y1 represents the time threshold, x1 represents the number of frame losses, and 0<a1<1. When the number of frame losses of the frame loss fault is small, the time threshold does not change much, and as the number of frame losses increases, the time threshold changes rapidly in a direction that is easy to be judged as a frame loss fault. At the same time, an upper limit of the time is set to avoid being too sensitive to faults and causing frequent fault reports.

[0099] In the embodiment of the present application, the number of frame losses is recorded as E1. Exemplarily, each time the pre-diagnosis result of frame loss of the map information is determined to be a frame loss fault, the number of frame losses E1 is increased by one accordingly. In the application, the map information diagnosis method may further include: in the case where the pre-diagnosis result of frame loss of the map information is a frame loss fault, recording the cause of the frame loss fault, and determining whether the number of frame losses E1 after increasing by one exceeds the frame loss threshold. If so, troubleshooting and fault clearing are performed through the host computer, and the use of the intelligent driving assistance system is prohibited. The intelligent driving assistance system can only be restored after the fault is restored to avoid safety hazards in the system due to map information. Among them, the recorded number of frame losses and the cause of the frame loss fault can only be cleared by the host computer.

[0100] In one embodiment, the pre-diagnosis includes continuous pre-diagnosis, and the pre-diagnosis result includes continuous pre-diagnosis result, wherein, as shown in FIG. 4 , step S104 , pre-diagnosing the map information and determining the pre-diagnosis result of the map information, may include the following steps S402 to S406 .

[0101] S402: Acquire historical map information of the vehicle, wherein the actual receiving time of the historical map information is earlier than the receiving time of the map information.

[0102] In this embodiment, the map information can be understood as the map information that needs to be received currently. The historical map information refers to the map information that is received earlier than the map information. Exemplarily, the historical map information is the map information received once before the map information, or in other words, the historical map information is adjacent to the reception time of the map information. Exemplarily, the historical map information includes at least one of the historical longitudinal slope, historical transverse slope, historical road curvature, historical specific road type and historical road type position of the road ahead of the vehicle.

[0103] S404: Determine the information difference between the map information and the historical map information.

[0104] Exemplarily, the information difference includes at least one of a longitudinal slope difference, a transverse slope difference, a road curvature difference, a specific road type difference and a road type position difference, wherein the longitudinal slope difference represents the difference between the map information and the historical map information in the dimension of longitudinal slope, the transverse slope difference represents the difference between the map information and the historical map information in the dimension of transverse slope, the road curvature difference represents the difference between the map information and the historical map information in the dimension of road curvature, the specific road type difference represents the difference between the map information and the historical map information in the dimension of specific road type, and the road type position represents the difference between the map information and the historical map information in the dimension of road type position.

[0105] For example, if the map information includes the longitudinal slope, the transverse slope, the road curvature, the specific road type and the road type location, the longitudinal slope difference between the longitudinal slope and the historical longitudinal slope, the transverse slope difference between the transverse slope and the historical transverse slope, the road curvature difference between the road curvature and the historical road curvature, the specific road type difference between the specific road type and the historical specific road type, and the road type position difference between the road type location and the historical road type location are determined respectively.

[0106] S406: Determine a continuity pre-diagnosis result of the map information according to the information difference and the information threshold.

[0107] Exemplarily, the absolute value of the information difference is compared with the information threshold, and when the absolute value of the information difference exceeds the information threshold, the continuity pre-diagnosis result of the map information is determined to be a continuity failure, otherwise, it is determined to be normal continuity.

[0108] In another exemplary embodiment, a discontinuity parameter F2 is defined, and the discontinuity parameter F2 is used to indicate the number of consecutive times that the absolute value of the information difference exceeds the information threshold. In an exemplary embodiment, the absolute value of the information difference is compared with the information threshold. When the absolute value of the information difference exceeds the information threshold, the discontinuity parameter F2 is increased by one, and the discontinuity parameter F2 after the increase is compared with the continuity threshold. When the discontinuity parameter F2 after the increase exceeds the continuity threshold, the continuity pre-diagnosis result of the map information is determined to be a continuity failure, otherwise, it is determined to be normal continuity.

[0109] In the application, after being determined as a discontinuity fault, if the continuity pre-diagnosis results corresponding to the multiple map information continuously received are all normal continuity, it is determined that the discontinuity fault of the map information has been restored to normal, and the discontinuity parameter F2 is cleared.

[0110] The above-mentioned map information diagnosis method obtains historical map information of the vehicle, wherein the actual reception time of the historical map information is earlier than the reception time of the map information, determines the information difference between the map information and the historical map information, and determines the continuity pre-diagnosis result of the map information based on the information difference and the information threshold, thereby realizing the continuity pre-diagnosis of the map information, so that the diagnosis result of the map information can be determined based on the continuity pre-diagnosis result of the map information, and the fault diagnosis of the map information can be realized. In this way, when there is a continuous fault in the map information, the fault situation can be fed back in time and the cause of the fault can be analyzed to obtain more accurate map information, thereby improving the reliability and accuracy of the vehicle map information, helping to provide map information diagnosis input for the vehicle intelligent driving assistance system to make reasonable decisions, and can improve the precise control and safety of the vehicle intelligent driving.

[0111] In one embodiment, the map information includes a road type position, the information difference includes a road type position difference, and the road type position difference refers to the difference between the road type position of the map information and the historical road type position of the historical map information. The information threshold includes a position threshold. As shown in FIG5 , step S406, determining the continuity pre-diagnosis result of the map information according to the information difference and the preset information threshold, may include the following steps S502 to S506.

[0112] S502: Obtaining longitudinal speed information of the vehicle.

[0113] The longitudinal vehicle speed information refers to the vehicle speed information in the forward direction of the vehicle. Exemplarily, the longitudinal vehicle speed information is the longitudinal vehicle speed corresponding to the actual reception time of the map information, or the longitudinal vehicle speed information is the longitudinal average vehicle speed between the actual reception time of the map information and the historical reception time of the historical map information. In the application, the longitudinal vehicle speed information can be determined according to the actual situation, and no excessive restrictions are made here.

[0114] S504: Determine a distance compensation amount according to the longitudinal vehicle speed information, the actual receiving time of the map information, and the actual receiving time of the historical map information.

[0115] Exemplarily, the time difference between the actual receiving time of the map information and the actual receiving time of the historical map information is determined, and the distance compensation amount is determined according to the longitudinal vehicle speed information and the time difference. Exemplarily, the distance compensation amount is the product of the longitudinal vehicle speed information and the time difference.

[0116] S506: Determine a continuity pre-diagnosis result of the map information according to the distance compensation amount, the road type position difference and the position threshold.

[0117] Exemplarily, the sum of the distance compensation amount and the road type position difference is determined and recorded as the compensation position; the compensation position is compared with the position threshold, and when the compensation position exceeds the position threshold, the continuity pre-diagnosis result of the map information is determined to be a road type position failure, otherwise, it is determined that the road type position is normal.

[0118] In another exemplary embodiment, the discontinuity parameter F2 includes a position discontinuity parameter F21, and the compensation position is compared with the position threshold. When the compensation position exceeds the position threshold, the position discontinuity parameter F21 is increased by one, and the position discontinuity parameter F21 after the increase is compared with the position continuity threshold. When the position discontinuity parameter F21 after the increase exceeds the position continuity threshold, the continuity pre-diagnosis result of the map information is determined to be a continuity failure, otherwise, it is determined to be normal continuity.

[0119] It is understandable that during the driving process of the vehicle, the distance between the vehicle and the specific road ahead changes in real time. In this regard, in the embodiment of the present application, by obtaining the longitudinal speed information of the vehicle, and determining the distance compensation amount according to the longitudinal speed information, the actual receiving time of the map information and the actual receiving time of the historical map information, and determining the continuity pre-diagnosis result of the map information according to the distance compensation amount, the road type position difference and the position threshold, based on this, in the process of judging the specific road type position, the longitudinal speed information of the vehicle is also considered, and the forward distance of the vehicle in each receiving cycle is calculated for compensation, so as to avoid the misdiagnosis of the road type position under different driving scenarios of the vehicle (such as different longitudinal speed information), improve the accuracy of the continuity pre-diagnosis result of the map information, and thus improve the diagnostic accuracy of the map information.

[0120] In one embodiment, the map information diagnosis method may further include: recording the number of times the continuity pre-diagnosis result is a continuity fault, and adjusting the information threshold according to the continuity number and / or adjusting the continuity threshold according to the continuity number. The continuity number indicates the cumulative number of times the continuity pre-diagnosis result of the map information is determined to be a continuity fault.

[0121] Exemplarily, the adjusted information threshold is less than the information threshold before adjustment, and the adjusted information threshold is greater than or equal to the information upper limit, wherein the information upper limit is a preset fixed value. Exemplarily, the adjusted continuity threshold is less than the continuity threshold before adjustment, and the adjusted continuity threshold is greater than or equal to the continuity upper limit, wherein the continuity upper limit is a preset fixed value. In this way, in the event of a continuity fault, by adjusting the information threshold and / or the continuity threshold, it is easier to diagnose whether there is a continuity fault in the map information later, thereby increasing the sensitivity to the existence of continuity faults in the map information, thereby increasing the reliability and accuracy of the map information, and helping to further improve the safety of the vehicle.

[0122] Exemplarily, the changes of the information threshold and the continuity threshold are in accordance with the change trend of the exponential function, which can be expressed as y2=a2^x2, where y2 represents the information threshold or the continuity threshold, x2 represents the number of continuity, 0<a2<1, and the a2 corresponding to the information threshold and the continuity threshold can be the same or different. When the number of continuity faults is small, the information threshold and the continuity threshold do not change much, and as the number of continuity faults increases, the information threshold and the continuity threshold change rapidly in a direction that is easy to be judged as a continuity fault. At the same time, the information upper limit and the continuity upper limit are set to avoid being too sensitive to faults and causing frequent fault reports.

[0123] In the embodiment of the present application, the number of continuity is recorded as E2. Exemplarily, each time the continuity pre-diagnosis result of the map information is determined to be a continuity fault, the continuity number E2 is increased by one accordingly. In the application, the map information diagnosis method may also include: in the case where the continuity pre-diagnosis result of the map information is a continuity fault, recording the cause of the continuity fault, and determining whether the continuity number E2 after increasing by one exceeds the continuity threshold. If so, troubleshooting and fault clearing are performed through the host computer, and the use of the intelligent driving assistance system is prohibited. The intelligent driving assistance system can only be restored after the fault is restored to avoid safety hazards in the system due to map information. Among them, the recorded continuity times and continuity fault causes can only be cleared by the host computer.

[0124] In one embodiment, pre-diagnosis includes invalid value pre-diagnosis, and the pre-diagnosis result includes an invalid value pre-diagnosis result, wherein step S104, pre-diagnosing the map information and determining the pre-diagnosis result of the map information, includes: the step of determining the invalid value pre-diagnosis result of the map information based on the map information, the value range of the map information and the decision range of the vehicle's intelligent assisted driving system for the map information.

[0125] The value range is pre-set and can be set according to the vehicle driving scenario. For example, in the application scenario of the L2-level intelligent driving assistance system, the main highway is the main road. For this, in the map information: the longitudinal slope value range can be [-20%, 20%], the transverse slope value range can be [-5%, 5%], the road curvature value range can be [0, 0.1] / m, the specific road type is a predetermined value type (customized according to needs, including but not limited to ramps, tunnels and bridges, etc.), and the road type location value range is [0, 10]km.

[0126] The vehicle's intelligent assisted driving system has a preset decision range for map information, which can be set according to the vehicle's driving scenario. For example, the L2-level intelligent driving assistance system has a preset decision range for map information of 0 to 10 km ahead of the vehicle.

[0127] Exemplarily, when it is determined that the map information is a frame loss fault, the invalid value pre-diagnosis result of the map information is determined to be an invalid value fault. In another exemplary embodiment, when the value of the map information exceeds the value range, the invalid value pre-diagnosis result of the map information is determined to be an invalid value fault. In another exemplary embodiment, the map information is received in the form of a map message, and when the map message does not meet the message encoding rule, the invalid value pre-diagnosis result of the map information is determined to be an invalid value fault. In another exemplary embodiment, when the value of the map information meets the value range but does not meet the decision range, the invalid value pre-diagnosis result of the map information is determined to be an invalid value fault.

[0128] As another example, an invalid value parameter F3 is defined, and when the value of the map information does not satisfy the value range but satisfies the decision range, the invalid value parameter F3 is increased by one, and when the invalid value parameter F3 exceeds the invalid threshold, the invalid value pre-diagnosis result of the map information is determined to be an invalid value fault; and after being determined to be an invalid value fault, if the invalid value pre-diagnosis results of multiple map information continuously received are that the invalid value is normal, it is determined that the invalid value fault of the map information has returned to normal, and the invalid value parameter F3 is cleared to zero.

[0129] For example, the L2 controller receives a map message including a longitudinal slope. The longitudinal slope 6 km ahead of the vehicle is 30%, which exceeds [-20%, 20%]. However, the vehicle's L2 driving assistance system needs to consider the map information within 8 km ahead of the vehicle to make a decision. At this time, the invalid value parameter F3 corresponding to the longitudinal slope is increased by one, and it is determined whether the invalid value parameter F3 after the increase exceeds the invalid threshold. If so, it is determined that the map message is invalid. At the same time, it is determined that the invalid value pre-diagnosis result of the map message is an invalid value fault. After that, if the invalid value pre-diagnosis results of multiple map messages received continuously are normal, it is determined that the invalid value fault of the map message has returned to normal, and the invalid value parameter F3 is cleared.

[0130] The above-mentioned method for diagnosing map information determines the invalid value pre-diagnosis result of the map information based on the map information, the value range of the map information and the decision range of the vehicle's intelligent assisted driving system for the map information, thereby realizing the invalid value pre-diagnosis of the map information, and then the diagnosis result of the map information can be determined based on the invalid value pre-diagnosis result to realize the fault diagnosis of the map information, and in the case of an invalid value fault in the map information, the invalid value fault situation can be fed back in time and the cause of the fault can be analyzed to obtain more accurate map information, thereby improving the reliability and accuracy of the vehicle's map information, helping to provide map information diagnosis input for the vehicle's intelligent driving assistance system to make reasonable decisions, and can improve the precise control and safety of the vehicle's intelligent driving.

[0131] In one embodiment, the map information diagnosis method may further include: obtaining the number of invalid values ​​for which the invalid value pre-diagnosis result is an invalid value fault, and adjusting the receiving invalid threshold according to the number of invalid values. The number of invalid values ​​indicates the cumulative number of times that the invalid value pre-diagnosis result of the map information is determined to be an invalid value fault. Exemplarily, the adjusted invalid threshold is less than the invalid threshold before adjustment, and the adjusted invalid threshold is greater than or equal to the invalid upper limit, wherein the invalid upper limit is a pre-set fixed value. In this way, in the case of an invalid value fault, by adjusting the invalid threshold, it is easier to diagnose the invalid value fault of the map information later, and the sensitivity of the invalid value fault is improved. Exemplarily, the change of the invalid threshold conforms to the change trend of the exponential function, which can be expressed by an expression of y3=a3^x3, wherein y3 represents the invalid threshold, x3 represents the number of invalid values, and 0<a3<1. When the number of invalid values ​​of the invalid value fault is small, the invalid threshold does not change much, and as the number of invalid values ​​increases, the invalid threshold changes rapidly in a direction that is easy to be judged as a fault abnormality, and the invalid upper limit is set at the same time to avoid being too sensitive to the fault and causing frequent fault reporting.

[0132] In the embodiment of the present application, the number of invalid values ​​is recorded as E3. Exemplarily, each time the invalid value pre-diagnosis result of the map information is determined to be an invalid value fault, the number of invalid values ​​E3 is increased by one. In the application, the map information diagnosis method may also include: in the case where the invalid value pre-diagnosis result of the map information is an invalid value fault, recording the cause of the invalid value fault, and determining whether the number of invalid values ​​E3 after adding one exceeds a preset threshold value. If so, troubleshooting and fault clearing are performed through the host computer, and the use of the intelligent driving assistance system is prohibited. The intelligent driving assistance system can only be restored after the fault is restored to avoid safety hazards in the system due to map information. Among them, the recorded number of continuity and continuity fault causes can only be cleared by the host computer.

[0133] In one embodiment, the pre-diagnosis includes at least one of a continuous pre-diagnosis and an invalid value pre-diagnosis, and the pre-diagnosis result includes at least one of a continuous pre-diagnosis result and an invalid value pre-diagnosis result. As shown in FIG6 , step S104, pre-diagnosing the map information and determining the pre-diagnosis result of the map information, may include the following steps S602 and S604.

[0134] S602: Obtaining longitudinal speed information of the vehicle.

[0135] Step S602 is the same as the aforementioned step S502. For details, please refer to the aforementioned related content and will not be repeated here.

[0136] S604: Determine at least one of a continuity pre-diagnosis result and an invalid value pre-diagnosis result of the map information according to the longitudinal vehicle speed information, the map information and the long short-term memory neural network model.

[0137] The long short-term memory neural network model is pre-set, and the long short-term memory neural network model takes map information and longitudinal vehicle speed information as input, and the output result is at least one of the continuity pre-diagnosis result and the invalid value pre-diagnosis result of the current map information.

[0138] Exemplarily, the number of hidden layer neurons in the long short-term memory neural network model can be taken as twice the number of input layer neurons + 1, or can be flexibly adjusted depending on the specific problem. The activation functions of the hidden layer and output layer of the model are taken as Sigmoid functions. The ordinary long short-term memory neural network back propagation method is used for training. The map information and longitudinal vehicle speed information are transmitted to the trained long short-term memory neural network model in real time on the actual vehicle, and the neural network model is used to determine whether the map information has continuity faults and invalid value faults.

[0139] The sample set required for the training of the LSTM neural network model can be taken from the data collected during the vehicle's driving on the highway. For example, the sample set can include 10,000 kilometers of data for each type of terrain, such as plains, hills, and mountains. Each type of terrain includes a variety of rich types of data such as straight roads and curves, as well as a variety of longitudinal vehicle speed information, such as 60-100km / h, and includes specific types of roads such as tunnels, ramps, and bridges. In this way, the diagnostic accuracy of the LSTM neural network model can be improved.

[0140] The above-mentioned map information diagnosis method obtains the longitudinal speed information of the vehicle, and determines at least one of the continuity pre-diagnosis result and the invalid value pre-diagnosis result of the map information based on the longitudinal speed information, the map information and the long short-term memory neural network model, that is, the neural network model is used to pre-diagnose the two dimensions of continuity and invalid value of the map information, and then the diagnosis result of the map information can be determined based on the continuity pre-diagnosis result and / or the invalid value pre-diagnosis result, so as to realize fault diagnosis of the map information, improve the reliability and accuracy of the vehicle map information, help provide map information diagnosis input for the vehicle intelligent driving assistance system to make reasonable decisions, and improve the precise control and safety of the vehicle intelligent driving.

[0141] In the embodiment of the present application, for the convenience of description and distinction, the aforementioned frame loss pre-diagnosis, continuity pre-diagnosis and invalid value pre-diagnosis of map information without using the long short-term memory neural network model can be collectively referred to as rule-based pre-diagnosis, and the corresponding pre-diagnosis results are respectively referred to as frame loss pre-diagnosis, first continuity pre-diagnosis result and first invalid value pre-diagnosis result, and the result determined by using the long short-term memory neural network model to pre-diagnose the map information is called the second continuity pre-diagnosis result and the second invalid value pre-diagnosis result. Based on this, step S106 can include: determining the diagnosis result of the map information according to the frame loss pre-diagnosis, the first continuity pre-diagnosis result, the first invalid value pre-diagnosis result, the second continuity pre-diagnosis result and the second invalid value pre-diagnosis result. In this way, the rule-based strategy and the intelligent algorithm-based strategy are combined to perform dynamic comprehensive judgment on the map information, which improves the rationality and accuracy of fault diagnosis and helps to further improve vehicle driving safety.

[0142] In one embodiment, as shown in FIG. 7 , step S106 , determining the diagnosis result of the map information according to the pre-diagnosis result, includes the following steps S702 to S708 .

[0143] S702: Obtain the number of fault items in the pre-diagnosis result.

[0144] In an embodiment of the present application, the pre-diagnosis results may include three pre-diagnosis results based on rules (respectively, frame loss pre-diagnosis, first continuity pre-diagnosis result, and first invalid value pre-diagnosis result), and two pre-diagnosis results based on a long short-term memory neural network model (respectively, second continuity pre-diagnosis result and second invalid value pre-diagnosis result), totaling five pre-diagnosis results.

[0145] The number of fault items refers to the total number of items determined as faults in the five pre-diagnosis results. For example, if the five pre-diagnosis results include the frame loss pre-diagnosis result being frame loss normal, the first continuity pre-diagnosis result being continuity fault, the first invalid value pre-diagnosis result being invalid value fault, the second continuity pre-diagnosis result being continuity fault, and the second invalid value pre-diagnosis result being invalid value fault, the number of fault items in the map information is 4.

[0146] S704: When the number of fault items is greater than zero and less than or equal to the first fault threshold, determine that the diagnosis result of the map information is a minor fault.

[0147] A minor fault indicates that the map information has a fault and the fault problem is minor. The first fault threshold is preset and can be set according to the actual scenario. For example, the first fault threshold is 1, that is, when the number of fault items is equal to 1, the map information is determined to have a minor fault.

[0148] S706: When the number of fault items is greater than the first fault threshold and less than the second fault threshold, determine that the diagnosis result of the map information is a moderate fault; wherein the first fault threshold is less than the second fault threshold.

[0149] A moderate fault indicates that the map information has a fault and the fault problem is moderate. The second fault threshold is preset and can be set according to the actual scenario. For example, the second fault threshold is 4, that is, when the number of fault items is greater than 1 and less than 4 (such as the number of fault items is 2 or 3), the map information is determined to be a moderate fault.

[0150] S708: When the number of fault items is greater than or equal to the second fault threshold, determine that the diagnosis result of the map information is a serious fault.

[0151] A serious fault indicates that the map information has a fault, and the fault problem is serious. For example, the second fault threshold is 4, that is, when the number of fault items is 4 or 5, the map information is determined to have a serious fault.

[0152] It should be noted that, when the number of fault items is zero, the diagnosis result of the map information is determined to be normal.

[0153] Among them, the fault levels of map information are from low to high, namely, minor fault, moderate fault, and severe fault. When the map information is judged to be a certain fault level, if it further meets a higher fault level, it will continue to enter the higher fault level state. If part of the fault returns to normal after entering the high fault level, in order to improve safety, it will not return to the low fault level at this time, and can only return to the fault-free state when all faults no longer exist.

[0154] In the application, after the L2 controller determines the diagnostic results of the map information, it can output the diagnostic results to the L2 driving assistance algorithm for decision-making control, and record the fault information to facilitate subsequent fault cause analysis and diagnostic repair.

[0155] The above-mentioned map information diagnosis method obtains the number of fault items in the pre-diagnosis result, and determines that the diagnosis result of the map information is a minor fault when the number of fault items is greater than zero and less than or equal to the first fault threshold; determines that the diagnosis result of the map information is a moderate fault when the number of fault items is greater than the first fault threshold and less than the second fault threshold; and determines that the diagnosis result of the map information is a severe fault when the number of fault items is greater than or equal to the second fault threshold, thereby realizing fault level identification of map information, so as to perform decision-making control and diagnostic maintenance according to different fault levels, and helping to improve the safety and reliability of the vehicle.

[0156] In one embodiment, as shown in FIG. 8 , a map information diagnosis method is provided, which is described by taking the method applied to an L2 controller of a vehicle as an example. The method includes the following steps S802 to S812 .

[0157] S802: Receive a map message and longitudinal vehicle speed information of the vehicle.

[0158] The map message includes a longitudinal slope message, a transverse slope message, a road curvature message, a road type message and a type position message, wherein the longitudinal slope message includes the longitudinal slope of the road ahead of the vehicle, the transverse slope message includes the transverse slope of the road ahead of the vehicle, the road curvature message includes the curvature of the road ahead of the vehicle, the road type message includes the specific road type of the road ahead of the vehicle, and the type position message includes the distance between the vehicle and the specific road type ahead.

[0159] S804: Perform frame loss pre-diagnosis on the map message according to the time threshold and determine the frame loss pre-diagnosis result of the map message, perform continuity pre-diagnosis on the map message according to the information threshold and the continuity threshold and determine the first continuity pre-diagnosis result of the map information, perform invalid value pre-diagnosis on the map message according to the value range, decision range and invalid threshold and determine the first invalid value pre-diagnosis result of the map information.

[0160] S806: Determine a second continuity pre-diagnosis result and a second invalid value pre-diagnosis result of the map message according to the map message, the longitudinal vehicle speed information and the long short-term memory neural network model.

[0161] S808: Determine a diagnosis result of the map message according to the frame loss pre-diagnosis result, the first continuity pre-diagnosis result, the first invalid value pre-diagnosis result, the second continuity pre-diagnosis result, and the second invalid value pre-diagnosis result.

[0162] S810: Adjust the time threshold according to the number of frame loss faults for which the frame loss pre-diagnosis result is a frame loss fault, adjust the information threshold and the continuity threshold according to the number of consecutive times for which the first continuity pre-diagnosis result is a continuity fault, and adjust the value range, decision range and invalid threshold according to the number of invalid times for which the first invalid value pre-diagnosis result is an invalid value fault, so as to diagnose the subsequently received map messages according to the adjusted thresholds.

[0163] S812: When the diagnosis results of the subsequent multiple map messages received are normal, exit the fault state.

[0164] The process from step S804 to step S812 can be found in the above related introduction and will not be repeated here.

[0165] The above-mentioned map information diagnosis method performs online pre-diagnosis on the three aspects of frame loss, continuity and invalid values ​​of map messages based on preset rules, provides map information diagnosis input for the driving assistance system to make reasonable decisions, and performs secondary pre-diagnosis on the two aspects of continuity and invalid values ​​of map messages based on the long short-term memory neural network model, and combines the rule-based pre-diagnosis results with the model-based pre-diagnosis results, and dynamically adjusts the various thresholds involved in the rule-based pre-diagnosis process based on the number of historical faults, thereby improving the rationality and accuracy of fault diagnosis, and can continuously monitor after being judged as a fault and exit the fault state under reasonable circumstances, which is more flexible and intelligent.

[0166] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0167] Based on the same inventive concept, the embodiment of the present application also provides a map information diagnosis device for implementing the map information diagnosis method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more map information diagnosis device embodiments provided below can refer to the limitations on the map information diagnosis method above, and will not be repeated here.

[0168] In one embodiment, as shown in FIG9 , a map information diagnosis device 900 is provided, comprising: a receiving module 901, a pre-diagnosis module 902 and a comprehensive diagnosis module 903. The receiving module 901 is used to receive the map information of the vehicle. The pre-diagnosis module 902 is used to pre-diagnose the map information and determine the pre-diagnosis result of the map information; wherein the pre-diagnosis includes at least one of frame loss pre-diagnosis, continuity pre-diagnosis and invalid value pre-diagnosis, and the pre-diagnosis result includes at least one of frame loss pre-diagnosis result, continuity pre-diagnosis result and invalid value pre-diagnosis result. The comprehensive diagnosis module 903 is used to determine the diagnosis result of the map information according to the pre-diagnosis result.

[0169] In one embodiment, the pre-diagnosis module 902 includes a first pre-diagnosis unit 9021, which is used to determine the actual reception time of the map information when the map information is received, determine the reception time difference between the actual reception time and the expected reception time of the map information, and determine the frame loss pre-diagnosis result of the map information based on the reception time difference and the time threshold.

[0170] In one embodiment, the first pre-diagnosis unit 9021 is also used to determine the actual receiving period of the map information based on the receiving period when the map information is not received and the duration of not receiving the map information does not exceed the first duration; and to determine the actual receiving period of the map information based on a preset multiple of the receiving period when the map information is not received and the duration of not receiving the map information exceeds the first duration; wherein the preset multiple is greater than 1; and determine the frame loss pre-diagnosis result of the map information based on the expected receiving time of the map information, the actual receiving period and the time threshold.

[0171] In one embodiment, the map information diagnosis device 900 further includes a historical fault memory module 904, which is used to record the number of frame losses for which the pre-diagnosis result of frame loss is a frame loss fault, and adjust the time threshold according to the number of frame losses.

[0172] In one embodiment, the first pre-diagnosis unit 9021 is also used to obtain historical map information of the vehicle; wherein the actual reception time of the historical map information is earlier than the actual reception time of the map information; determine the information difference between the map information and the historical map information; and determine the continuity pre-diagnosis result of the map information based on the information difference and the information threshold.

[0173] In one embodiment, the first pre-diagnosis unit 9021 is also used to obtain the longitudinal speed information of the vehicle; determine the distance compensation amount based on the longitudinal speed information, the actual reception time of the map information and the actual reception time of the historical map information; and determine the continuity pre-diagnosis result of the map information based on the distance compensation amount, the road type position difference and the position threshold.

[0174] In one embodiment, the first pre-diagnosis unit 9021 is further used to determine the invalid value pre-diagnosis result of the map information based on the map information, the value range of the map information and the decision range of the vehicle's intelligent assisted driving system for the map information.

[0175] In one embodiment, the pre-diagnosis module 902 includes a second pre-diagnosis unit 9022, which is used to obtain longitudinal vehicle speed information of the vehicle; and determine at least one of a continuity pre-diagnosis result and an invalid value pre-diagnosis result of the map information based on the longitudinal vehicle speed information, the map information and the long short-term memory neural network model.

[0176] In one embodiment, the comprehensive diagnosis module 903 is also used to obtain the number of fault items in the pre-diagnosis result; when the number of fault items is greater than zero and less than or equal to a first fault threshold, the diagnosis result of the map information is determined to be a minor fault; when the number of fault items is greater than the first fault threshold and less than the second fault threshold, the diagnosis result of the map information is determined to be a moderate fault; wherein the first fault threshold is less than the second fault threshold; when the number of fault items is greater than or equal to the second fault threshold, the diagnosis result of the map information is determined to be a severe fault.

[0177] In the application, the map information diagnosis device 900 includes a receiving module 901, a first pre-diagnosis unit 9021, a second pre-diagnosis unit 9022, a comprehensive diagnosis module 903, and a historical fault memory module 904. The first pre-diagnosis unit 9021 performs fault pre-diagnosis on the map information based on rules, and the second pre-diagnosis unit 9022 performs fault pre-diagnosis on the map information based on a neural network module. The historical fault memory module 904 combines historical fault information, and the comprehensive diagnosis module 903 performs fault synthesis on the pre-diagnosis results of the first pre-diagnosis unit 9021 and the second pre-diagnosis unit 9022, and reasonably exits the fault state when the conditions are met.

[0178] The above-mentioned map information diagnosis device 900 receives the map information of the vehicle through the receiving module 901, pre-diagnoses the map information and determines the pre-diagnosis result of the map information through the pre-diagnosis module 902, and determines the diagnosis result of the map information according to the pre-diagnosis result through the comprehensive diagnosis module 903, wherein the pre-diagnosis includes at least one of frame loss pre-diagnosis, continuity pre-diagnosis and invalid value pre-diagnosis, and the pre-diagnosis result includes at least one of frame loss pre-diagnosis result, continuity pre-diagnosis result and invalid value pre-diagnosis result. The map information diagnosis method realizes fault diagnosis of various dimensions of map information by performing frame loss pre-diagnosis, continuity pre-diagnosis and invalid value pre-diagnosis on map information, which helps to provide map information diagnosis input for the vehicle intelligent driving assistance system to make reasonable decisions, and can improve the safety of vehicle intelligent driving.

[0179] Each module in the above-mentioned map information diagnosis device can be implemented in whole or in part by software, hardware or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute the operations corresponding to each module.

[0180] In one embodiment, a controller is provided, for example, the controller may be an L2 controller. The internal structure diagram of the controller may be shown in FIG10. The controller includes a processor, a memory, and a network interface connected via a system bus. The processor of the controller is used to provide computing and control capabilities. The memory of the controller includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the controller is used to store map information, pre-diagnosis results, and diagnostic results. The network interface of the controller is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, a map information diagnosis method is implemented.

[0181] Those skilled in the art will understand that the structure shown in FIG. 10 is merely a block diagram of a partial structure related to the scheme of the present application, and does not constitute a limitation on the controller to which the scheme of the present application is applied. The specific controller may include more or fewer components than shown in the figure, or combine certain components, or have a different arrangement of components.

[0182] In one embodiment, a controller is provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps of the aforementioned map information diagnosis method when executing the computer program.

[0183] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps of the aforementioned map information diagnosis method are implemented.

[0184] In one embodiment, a computer program product is provided, including a computer program, which implements the steps of the aforementioned map information diagnosis method when executed by a processor.

[0185] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties.

[0186] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.

[0187] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0188] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A map information diagnosis method, characterized in that: The method comprises: Receive map information of the vehicle; Performing a pre-diagnosis on the map information and determining a pre-diagnosis result of the map information; wherein the pre-diagnosis includes at least one of a frame loss pre-diagnosis, a continuity pre-diagnosis, and an invalid value pre-diagnosis, and the pre-diagnosis result includes at least one of a frame loss pre-diagnosis result, a continuity pre-diagnosis result, and an invalid value pre-diagnosis result; A diagnosis result of the map information is determined according to the pre-diagnosis result.

2. The method according to claim 1, characterized in that The pre-diagnosis includes frame loss pre-diagnosis, and the pre-diagnosis result includes a frame loss pre-diagnosis result, wherein the pre-diagnosis of the map information and determining the pre-diagnosis result of the map information includes: determining an actual reception time of the map information upon receipt of the map information; determining a reception time difference between the actual reception time and the expected reception time of the map information; The frame loss pre-diagnosis result of the map information is determined according to the receiving time difference and the time threshold.

3. The method according to claim 1, characterized in that The pre-diagnosis includes frame loss pre-diagnosis, and the pre-diagnosis result includes a frame loss pre-diagnosis result, wherein the pre-diagnosis of the map information and determining the pre-diagnosis result of the map information includes: In a case where the map information is not received and the duration of not receiving the map information does not exceed a first duration, determining an actual reception period of the map information according to the reception period of the map information; In the case where the map information is not received and the duration of not receiving the map information exceeds a first duration, determining the actual receiving period of the map information according to a preset multiple of the receiving period; wherein the preset multiple is greater than 1; The frame loss pre-diagnosis result of the map information is determined according to the expected reception time of the map information, the actual reception period and the time threshold.

4. The method according to claim 2, characterized in that: The method further comprises: Recording the number of frame losses for which the pre-diagnosis result of frame loss is a frame loss fault; The time threshold is adjusted according to the number of frame losses.

5. The method according to claim 1, characterized in that The pre-diagnosis includes continuous pre-diagnosis, and the pre-diagnosis result includes continuous pre-diagnosis result, wherein the pre-diagnosis of the map information and determining the pre-diagnosis result of the map information includes: Acquiring historical map information of the vehicle; wherein the actual receiving time of the historical map information is earlier than the actual receiving time of the map information; determining an information difference between the map information and the historical map information; A continuity pre-diagnosis result of the map information is determined according to the information difference and the information threshold.

6. The method according to claim 5, characterized in that The map information includes a road type location, the information difference includes a road type location difference, the information threshold includes a location threshold, and determining the continuity pre-diagnosis result of the map information according to the information difference and a preset information threshold includes: Acquiring longitudinal speed information of the vehicle; determining a distance compensation amount according to the longitudinal vehicle speed information, the actual receiving time of the map information, and the actual receiving time of the historical map information; A continuity pre-diagnosis result of the map information is determined according to the distance compensation amount, the road type position difference and the position threshold.

7. The method according to claim 1, characterized in that The pre-diagnosis includes an invalid value pre-diagnosis, and the pre-diagnosis result includes an invalid value pre-diagnosis result, wherein the pre-diagnosis of the map information and determining the pre-diagnosis result of the map information includes: An invalid value pre-diagnosis result of the map information is determined according to the map information, a value range of the map information and a decision range of the intelligent assisted driving system of the vehicle for the map information.

8. The method according to any one of claims 1 to 7, characterized in that: The pre-diagnosis includes at least one of a continuous pre-diagnosis and an invalid value pre-diagnosis, the pre-diagnosis result includes at least one of a continuous pre-diagnosis result and an invalid value pre-diagnosis result, and the pre-diagnosis of the map information and determining the pre-diagnosis result of the map information includes: Acquiring longitudinal speed information of the vehicle; At least one of a continuity pre-diagnosis result and an invalid value pre-diagnosis result of the map information is determined based on the longitudinal vehicle speed information, the map information and the long short-term memory neural network model.

9. The method according to any one of claims 1 to 7, characterized in that: The determining the diagnosis result of the map information according to the pre-diagnosis result includes: Obtaining the number of fault items in the pre-diagnosis result; When the number of fault items is greater than zero and less than or equal to a first fault threshold, determining that the diagnosis result of the map information is a minor fault; When the number of fault items is greater than the first fault threshold and the number of fault items is less than a second fault threshold, determining that the diagnosis result of the map information is a moderate fault; wherein the first fault threshold is less than the second fault threshold; When the number of fault items is greater than or equal to the second fault threshold, it is determined that the diagnosis result of the map information is a serious fault.

10. A map information diagnosis device, characterized in that: The device comprises: A receiving module, used for receiving map information of the vehicle; a pre-diagnosis module, configured to pre-diagnose the map information and determine a pre-diagnosis result of the map information; wherein the pre-diagnosis includes at least one of frame loss pre-diagnosis, continuity pre-diagnosis and invalid value pre-diagnosis, and the pre-diagnosis result includes at least one of frame loss pre-diagnosis result, continuity pre-diagnosis result and invalid value pre-diagnosis result; A comprehensive diagnosis module is used to determine a diagnosis result of the map information according to the pre-diagnosis result.

11. A controller, comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: When the controller executes the computer program, the steps of the method according to any one of claims 1 to 9 are implemented.

12. A vehicle, characterized in that: The vehicle includes the controller of claim 11.

Images