A vehicle monitoring method and apparatus

Abstract

This invention discloses a vehicle monitoring method and apparatus. The method includes: collecting vehicle driving data; sending the driving data to an on-board computing main channel and an on-board safety brain computing channel connected to the vehicle, so that the monitoring opinions calculated by the on-board computing main channel and the on-board safety brain computing channel are cross-validated to obtain a first monitoring opinion; sending the driving data and the first monitoring opinion to the cloud, so that the cloud calculates based on the driving data and the first monitoring opinion to obtain a second monitoring opinion; receiving the first monitoring opinion and the second monitoring opinion, and changing the vehicle status according to the first monitoring opinion and / or the second monitoring opinion. Therefore, this invention improves the monitoring efficiency of regulatory departments, provides data support for accident investigation, and enhances vehicle driving safety and user experience.

Description

Technical Field

[0001] This invention relates to the field of intelligent vehicle monitoring, and further to a vehicle monitoring method and apparatus. Background Technology

[0002] With the development of intelligent vehicles, advanced autonomous driving has become an indispensable function of modern vehicles due to its convenience and safety. People are increasingly relying on driver assistance or autonomous driving functions to reduce the burden of driving and improve driving comfort and safety.

[0003] Traditional vehicle inspection and identification systems are already very comprehensive. However, for autonomous vehicles, due to the lack of effective regulatory methods and means by relevant departments or industries, and the difficulty in uniformly controlling industry quality levels, it is easy to cause difficulties in determining liability for accidents. Furthermore, for intelligent vehicles with problems, regulatory departments have low efficiency in supervising intelligent vehicles and cannot provide timely regulatory opinions. Summary of the Invention

[0004] To address the aforementioned technical problems, this invention provides a vehicle monitoring method and apparatus, which improves the efficiency of monitoring the driving status of intelligent vehicles by supervisors.

[0005] Specifically, the technical solution of the present invention is as follows:

[0006] A vehicle monitoring method includes the following steps:

[0007] Collect vehicle driving data;

[0008] The driving data is sent to the vehicle computing main channel and the vehicle safety brain computing channel connected to the vehicle terminal, so that the regulatory opinions calculated by the vehicle computing main channel and the vehicle safety brain computing channel are cross-validated to obtain a first regulatory opinion;

[0009] The driving data and the first regulatory opinion are sent to the cloud so that the cloud can calculate a second regulatory opinion based on the driving data and the first regulatory opinion.

[0010] Receive the first regulatory opinion and the second regulatory opinion, and change the vehicle status according to the first regulatory opinion and / or the second regulatory opinion.

[0011] By sending driving data to both the onboard computing main channel and the vehicle safety brain computing channel, the regulatory opinions calculated from these channels are cross-validated to arrive at a first regulatory opinion. The cloud then generates a second regulatory opinion based on the received driving data and the first regulatory opinion. The onboard unit adjusts the vehicle status according to the first and / or second regulatory opinions. This effectively monitors the driving status of intelligent vehicles, provides accurate data support for accident liability determination, and improves the safety of intelligent vehicles during operation and the user experience.

[0012] In some implementations, the step of sending the driving data to the vehicle-mounted main computing channel and the vehicle-mounted safety brain computing channel connected to the vehicle terminal, so that the regulatory opinions calculated by the vehicle-mounted main computing channel and the vehicle-mounted safety brain computing channel are cross-validated to obtain a first regulatory opinion, specifically includes the following steps:

[0013] The driving data is sent to the vehicle computing main channel and the vehicle safety brain computing channel connected to the vehicle terminal, so that the vehicle computing main channel calculates the third regulatory opinion, and the vehicle safety brain calculates the vehicle control result based on the driving data;

[0014] The vehicle control results are sent to the verifier of the vehicle safety brain so that the verifier can verify the vehicle control results and obtain the fourth regulatory opinion.

[0015] The third and fourth regulatory opinions are sent to the decision cross-validation module so that the cross-validation module can cross-validate the third and fourth regulatory opinions to arrive at the first regulatory opinion.

[0016] By cross-validating the third and fourth regulatory opinions, the first regulatory opinion was derived, further improving regulatory efficiency and accuracy.

[0017] In some implementations, sending the driving data and the first regulatory opinion to the cloud, so that the cloud can calculate a second regulatory opinion based on the driving data and the first regulatory opinion, specifically includes the following steps:

[0018] The driving data and the first regulatory opinion are sent to the cloud, so that the cloud can calculate the number of forward collision warnings, emergency braking, sharp turns, and abnormal following distance per thousand kilometers for the vehicle based on the driving data and the first regulatory opinion.

[0019] The vehicle's assisted driving capability or autonomous driving capability is assessed based on the calculation results, and the second regulatory opinion is derived.

[0020] The cloud-based system calculates vehicle performance indicators based on driving data and the first regulatory opinion, assesses the vehicle's assisted driving or autonomous driving capabilities, and generates a second regulatory opinion, further improving vehicle driving safety and comfort and providing more accurate data support for accident identification.

[0021] In some implementations, after sending the third and fourth regulatory opinions to a cross-validation module to cross-validate the third and fourth regulatory opinions and derive the first regulatory opinion, the method further includes the following step:

[0022] Determine whether the first regulatory opinion passes the cross-validation;

[0023] If the first regulatory opinion passes the cross-validation, the vehicle status is changed according to the first regulatory opinion;

[0024] If the first regulatory opinion fails the cross-validation, the third regulatory opinion shall represent the first regulatory opinion.

[0025] In some implementations, the steps include:

[0026] The third and fourth regulatory opinions will be sent to the cloud for data backup.

[0027] The backup of driving data and regulatory opinions provides more accurate data support for accident identification, facilitates the determination of accident liability, and reduces the burden on regulatory personnel.

[0028] In addition, the present invention also provides a vehicle monitoring device, comprising:

[0029] The data acquisition unit is used to collect vehicle driving data;

[0030] The first sending unit is used to send the driving data to the vehicle computing main channel and the vehicle safety brain computing channel connected to the vehicle terminal, so that the regulatory opinions calculated by the vehicle computing main channel and the vehicle safety brain computing channel can be cross-verified to obtain the first regulatory opinion;

[0031] The second sending unit is used to send the driving data and the first regulatory opinion to the cloud, so that the cloud can calculate and obtain the second regulatory opinion based on the driving data and the first regulatory opinion;

[0032] The receiving unit is configured to receive the first regulatory opinion and the second regulatory opinion, and change the vehicle status according to the first regulatory opinion and / or the second regulatory opinion.

[0033] In some implementations, the first transmitting unit specifically includes:

[0034] The first sending module is used to send the driving data to the vehicle computing main channel and the vehicle safety brain computing channel connected to the vehicle terminal, so that the vehicle computing main channel calculates the third regulatory opinion and the vehicle safety brain calculates the vehicle control result based on the driving data.

[0035] The second sending module is used to send the vehicle control result to the verifier of the vehicle safety brain, so that the verifier can verify the vehicle control result and obtain the fourth regulatory opinion.

[0036] The third sending module is used to send the third regulatory opinion and the fourth regulatory opinion to the decision cross-validation module, so that the cross-validation module can cross-validate the third regulatory opinion and the fourth regulatory opinion to obtain the first regulatory opinion.

[0037] In some embodiments, the second transmitting unit specifically includes:

[0038] The fourth sending module is used to send the driving data and the first regulatory opinion to the cloud, so that the cloud can calculate the number of forward collision warnings, emergency braking, sharp turns and abnormal following distance per thousand kilometers of the vehicle based on the driving data and the first regulatory opinion;

[0039] The judgment module is used to judge the vehicle's assisted driving capability or autonomous driving capability based on the calculation results, and to arrive at the second regulatory opinion.

[0040] In some implementations, it also includes:

[0041] The judgment unit is used to determine whether the first regulatory opinion passes the cross-validation;

[0042] A first execution unit is configured to change the vehicle status according to the first regulatory opinion if the first regulatory opinion passes the cross-validation.

[0043] The second execution unit is configured to use the third regulatory opinion to represent the first regulatory opinion if the first regulatory opinion fails the cross-validation.

[0044] In some implementations, it also includes:

[0045] The third sending unit is used to send the third regulatory opinion and the fourth regulatory opinion to the cloud for data backup.

[0046] In addition, the present invention also provides a computer medium having a computer program stored thereon, wherein the program, when executed, implements the above-described vehicle monitoring method.

[0047] Compared with the prior art, the present invention has at least one of the following beneficial effects:

[0048] 1. The vehicle-mounted terminal sends driving data to both the main vehicle computing channel and the vehicle safety brain computing channel. The resulting regulatory opinions are cross-validated to derive a first regulatory opinion. The cloud-based terminal then derives a second regulatory opinion based on the received driving data and the first regulatory opinion. The vehicle-mounted terminal adjusts the vehicle status according to the first and / or second regulatory opinions. This effectively monitors the driving status of intelligent vehicles, provides accurate data support for accident liability determination, and improves the safety of intelligent vehicles during operation and the user experience.

[0049] 2. The on-board unit cross-validates the third and fourth regulatory opinions to arrive at the first regulatory opinion, further improving regulatory efficiency and accuracy. Backups of driving data and regulatory opinions provide more accurate data support for accident investigation, facilitating accident liability determination and reducing the burden on regulatory personnel.

[0050] 3. The cloud platform calculates vehicle performance indicators based on driving data and the first regulatory opinion, assesses the vehicle's assisted driving or autonomous driving capabilities, and generates a second regulatory opinion, further improving vehicle driving safety and comfort and providing more accurate data support for accident identification. Attached Figure Description

[0051] The preferred embodiments will now be described in a clear and easy-to-understand manner, in conjunction with the accompanying drawings, to further explain the above-mentioned characteristics, technical features, advantages, and implementation methods of the present invention.

[0052] Figure 1 This is a flowchart of an embodiment of a vehicle monitoring method according to the present invention;

[0053] Figure 2 This is a flowchart of an embodiment of a vehicle monitoring method according to the present invention;

[0054] Figure 3 This is a flowchart of an embodiment of a vehicle monitoring method according to the present invention;

[0055] Figure 4 This is a flowchart of another embodiment of a vehicle monitoring method of the present invention;

[0056] Figure 5 This is a structural diagram of one embodiment of a vehicle monitoring device according to the present invention;

[0057] Figure 6 This is a structural diagram of one embodiment of a vehicle monitoring device according to the present invention;

[0058] Figure 7 This is a structural diagram of one embodiment of a vehicle monitoring device according to the present invention;

[0059] Figure 8 This is a structural diagram of another embodiment of a vehicle monitoring device of the present invention.

[0060] Reference numerals: Acquisition unit 100; First sending unit 200; Judgment unit 300; First execution unit 400; Second execution unit 500; Second sending unit 600; Receiving unit 700; Third sending unit 800; First sending module 210; Second sending module 220; Third sending module 230; Fourth sending module 610; Judgment module 620. Detailed Implementation

[0061] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the specific implementation methods of the present invention will be described below with reference to the accompanying drawings. Obviously, the drawings described below are merely some embodiments of the present invention. For those skilled in the art, other drawings and other implementation methods can be obtained based on these drawings without any creative effort.

[0062] To keep the drawings concise, each figure only schematically shows the parts relevant to the invention, and these do not represent the actual structure of the product. Furthermore, to facilitate understanding, in some figures, only one of components with the same structure or function is schematically depicted, or only one is labeled. In this document, "one" not only means "only one," but can also mean "more than one."

[0063] It should also be further understood that the term “and / or” as used in this application specification and the appended claims means any combination of one or more of the associated listed items and all possible combinations, and includes such combinations.

[0064] In this document, it should be noted that, unless otherwise explicitly specified and limited, the terms "installation," "connection," and "linking" should be interpreted broadly. For example, they can refer to fixed connections, detachable connections, or integral connections; they can refer to mechanical connections or electrical connections; they can refer to direct connections or indirect connections through an intermediate medium; and they can refer to the internal communication between two components. Those skilled in the art can understand the specific meaning of the above terms in this invention based on the specific circumstances.

[0065] Furthermore, in the description of this application, the terms "first," "second," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0066] It should be noted that the above embodiments can be freely combined as needed. The above are merely preferred embodiments of the present invention. It should be pointed out that for those skilled in the art, several improvements and modifications can be made without departing from the principle of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

[0067] In one embodiment, such as Figure 1 As shown, the present invention provides a vehicle monitoring method, comprising:

[0068] S100 collects vehicle driving data.

[0069] Specifically, when an intelligent driving vehicle begins assisted driving or autonomous driving functions, the front-end data acquisition unit collects various driving data during the vehicle's operation, such as data from cameras, radar, V2X, GPS, GNSS, vehicle perception data, body data, power data, and map data.

[0070] S110 sends driving data to the vehicle-mounted main computing channel and the vehicle-mounted safety brain computing channel connected to the vehicle terminal, so that the regulatory opinions calculated by the vehicle-mounted main computing channel and the vehicle-mounted safety brain computing channel can be cross-validated to obtain the first regulatory opinion.

[0071] Specifically, the driving data is aggregated and sent to both the main vehicle computing channel and the vehicle safety brain computing channel. Upon receiving the vehicle driving data, both the main vehicle computing channel and the vehicle safety brain computing channel calculate their respective regulatory opinions. Let's assume the regulatory opinion calculated by the main vehicle computing channel is A, and the regulatory opinion calculated by the vehicle safety brain computing channel is B.

[0072] Then, regulatory opinions A and B are sent to the decision cross-validation module for cross-validation to arrive at the first regulatory opinion C.

[0073] Among them, regulatory opinions A, B and the first regulatory opinion C can be various regulatory opinions such as the vehicle's current driving plan, vehicle braking status, and vehicle power status.

[0074] S120, the driving data and the first regulatory opinion are sent to the cloud so that the cloud can calculate based on the driving data and the first regulatory opinion to obtain the second regulatory opinion.

[0075] Specifically, the cloud receives the first regulatory opinion C after cross-validation and the driving data of the vehicle when it is in autonomous or assisted driving mode. Based on the driving data and the first regulatory opinion C, it calculates various indicators of the vehicle's operation (such as the number of forward collision warnings per 1,000 kilometers, the number of emergency brakings, the number of sharp turns, and the abnormal following distance). Based on the calculated indicators, it determines whether the vehicle's performance needs to be improved and gives a corresponding second regulatory opinion based on the performance judgment result. For example, the second regulatory opinion can be "recall opinion, algorithm upgrade opinion, or other opinion".

[0076] S130, receive the first regulatory opinion and the second regulatory opinion, and change the vehicle status according to the first regulatory opinion and / or the second regulatory opinion.

[0077] Specifically, the vehicle receives a first regulatory opinion and a second regulatory opinion, and changes the vehicle status based on the first or second regulatory opinion, or the first and second regulatory opinions.

[0078] This embodiment, as a preferred embodiment, describes a scenario where, when an intelligent driving vehicle begins assisted driving or autonomous driving functions, the front-end data acquisition unit collects various driving data during the vehicle's operation, such as data from cameras, radar, V2X, GPS, GNSS, vehicle perception data, body data, power data, and map data. This driving data is then aggregated and sent to both the onboard computing main channel and the onboard safety brain computing channel. Upon receiving the vehicle driving data, both the onboard computing main channel and the onboard safety brain computing channel calculate their respective regulatory opinions. Assume that the regulatory opinion calculated by the onboard computing main channel is A, and the regulatory opinion calculated by the onboard safety brain computing channel is B.

[0079] The vehicle control result derived from the combined action of the internal decision-making, planning, and control modules in the main vehicle computing channel is regulatory opinion A. Regulatory opinion B is derived from the combined action of the decision-maker and verifier in the vehicle safety brain computing channel. Specifically, the decision-maker in the vehicle safety brain derives the vehicle control result based on the input driving data and sends this result to the verifier. The verifier stores road traffic regulations and defensive driving models. The control result is verified in the verifier to validate the regulatory and defensive driving functions, resulting in the optimal control result, which is regulatory opinion B calculated by the vehicle safety brain computing channel.

[0080] Then, A and B are sent to the decision cross-validation module for cross-validation to arrive at the first regulatory opinion C. The cloud-based system performs offline verification based on the results from the decision-maker and validator in the onboard safety brain, vehicle driving data, and the first regulatory opinion C, calculating relevant indicators such as the number of forward collision warnings, emergency braking, emergency turns, and abnormal following distance per 1000 kilometers. The cloud-based system then assesses the vehicle's driving performance based on these indicators and provides a second regulatory opinion (e.g., recall opinion, algorithm upgrade opinion, other opinions, etc.) based on the assessment results.

[0081] Furthermore, the vehicle controller can receive a first regulatory opinion and change the vehicle status according to the first regulatory opinion, or it can change the vehicle status according to a second regulatory opinion given by the cloud, or it can change the vehicle status according to both the first and second regulatory opinions simultaneously.

[0082] All regulatory opinions in this embodiment are simplified examples for ease of understanding; the actual situation is much more complex.

[0083] In one embodiment, the present invention provides a vehicle monitoring method, which, based on the above embodiment, involves sending the driving data to an on-board computing main channel and an on-board safety brain computing channel connected to the vehicle terminal, so that the monitoring opinions calculated by the on-board computing main channel and the on-board safety brain computing channel are cross-validated to obtain a first monitoring opinion, specifically including:

[0084] S111 sends driving data to the vehicle computing main channel and the vehicle safety brain computing channel connected to the vehicle terminal, so that the vehicle computing main channel can calculate the third regulatory opinion and the vehicle safety brain can calculate the vehicle control result based on the driving data.

[0085] S112, the vehicle control results are sent to the verifier of the vehicle safety brain so that the verifier can verify the vehicle control results and obtain a fourth regulatory opinion.

[0086] Specifically, the driving data is aggregated and sent to both the main vehicle computing channel and the vehicle safety brain computing channel. Upon receiving the vehicle driving data, both the main vehicle computing channel and the vehicle safety brain computing channel calculate their respective regulatory opinions. Assume the third regulatory opinion calculated by the main vehicle computing channel is A, and the fourth regulatory opinion calculated by the vehicle safety brain computing channel is B.

[0087] The third regulatory opinion, A, is derived from the vehicle control result obtained through the combined action of the internal decision-making, planning, and control modules of the onboard computing main channel. The fourth regulatory opinion, B, is derived through the combined action of the decision-maker and verifier in the onboard safety brain computing channel. Specifically, the decision-maker in the onboard safety brain calculates the vehicle control result based on the input driving data and sends this result to the verifier. The verifier stores road traffic regulations and defensive driving models. The control result is verified in the verifier to validate the regulatory and defensive driving functions, resulting in the optimal control result, which is the fourth regulatory opinion, B, calculated by the onboard safety brain computing channel.

[0088] S113, send the third and fourth regulatory opinions to the decision cross-validation module so that the cross-validation module can cross-validate the third and fourth regulatory opinions to obtain the first regulatory opinion.

[0089] Specifically, the third regulatory opinion A and the fourth regulatory opinion B are sent to the decision cross-validation module for cross-validation to arrive at the first regulatory opinion C.

[0090] In one embodiment, the present invention provides a vehicle monitoring method, which, based on the above embodiment, involves sending the driving data and the first monitoring opinion to the cloud, so that the cloud performs calculations based on the driving data and the first monitoring opinion to derive a second monitoring opinion, including:

[0091] S121, the driving data and the first regulatory opinion are sent to the cloud, so that the cloud can calculate the number of forward collision warnings, emergency braking, sharp turns and abnormal following distance per thousand kilometers of the vehicle based on the driving data and the first regulatory opinion.

[0092] S122, based on the calculation results, determine the vehicle's assisted driving capability or autonomous driving capability, and arrive at the second regulatory opinion.

[0093] Specifically, the first regulatory opinion C is obtained through cross-validation of the onboard computing main channel regulatory opinion A and the onboard brain computing channel regulatory opinion B. The cloud then receives this cross-validated first regulatory opinion C and performs offline verification based on the vehicle's driving data when autonomous driving is activated, the first regulatory opinion C, the decision-maker in the onboard safety brain, and the verifier results. This verification calculates relevant indicators such as the number of forward collision warnings, emergency braking, emergency turns, and abnormal following distance per 1000 kilometers. The cloud then judges the vehicle's driving performance based on these indicators and provides a second regulatory opinion (e.g., recall opinion, algorithm upgrade opinion, other opinions, etc.). For example, if the calculated indicators show that the vehicle's algorithm and map need updating, the second regulatory opinion is "The vehicle needs to update its algorithm and map." Or, if the calculated indicators indicate a braking problem, the second regulatory opinion is "The vehicle's brakes are damaged and it needs to be recalled for repair."

[0094] In one embodiment, such as Figure 2 As shown, the present invention provides a vehicle supervision method. Based on the above embodiments, after sending the third and fourth supervision opinions to a cross-validation module to cross-validate the third and fourth supervision opinions and derive the first supervision opinion, the method further includes:

[0095] S200 determines whether the first regulatory opinion has passed cross-validation.

[0096] S210, if the first regulatory opinion passes cross-validation, the vehicle status shall be changed in accordance with the first regulatory opinion.

[0097] S220 If the first regulatory opinion fails to pass cross-validation, the third regulatory opinion shall be used to represent the first regulatory opinion.

[0098] Specifically, determine whether the first regulatory opinion C has passed cross-validation. If the first regulatory opinion C has passed cross-validation, then the first regulatory opinion C is the optimal regulatory opinion after cross-validation of A and B, and the vehicle status is changed according to the first regulatory opinion.

[0099] Furthermore, if the first regulatory opinion C fails cross-validation, then this first regulatory opinion C becomes the third regulatory opinion A calculated by the onboard computing main channel. Regulatory opinions A and B are sent to the onboard safety brain, and regulatory opinion A is sent to the vehicle controller. The onboard safety brain then sends regulatory opinions A and B, along with vehicle driving data, to the cloud for offline verification of regulatory opinions A and B.

[0100] This embodiment, as a preferred embodiment, describes a scenario where, when an intelligent driving vehicle begins assisted driving or autonomous driving functions, the front-end data acquisition unit collects various driving data during the vehicle's operation, such as data from cameras, radar, V2X, GPS, GNSS, vehicle perception data, body data, power data, and map data. This driving data is then aggregated and sent to both the onboard computing main channel and the onboard safety brain computing channel. Upon receiving the vehicle driving data, both the onboard computing main channel and the onboard safety brain computing channel calculate their respective regulatory opinions. Assuming the third regulatory opinion calculated by the onboard computing main channel is A, and the fourth regulatory opinion calculated by the onboard safety brain computing channel is B.

[0101] The third regulatory opinion, A, is derived from the vehicle control result obtained through the combined action of the internal decision-making, planning, and control modules of the onboard computing main channel. The fourth regulatory opinion, B, is derived through the combined action of the decision-maker and verifier in the onboard safety brain computing channel. Specifically, the decision-maker in the onboard safety brain calculates the vehicle control result based on the input driving data and sends this result to the verifier. The verifier stores road traffic regulations and defensive driving models. The control result is verified in the verifier to validate the regulatory and defensive driving functions, resulting in the optimal control result, which is the fourth regulatory opinion, B, calculated by the onboard safety brain computing channel. For example, let's assume that the third regulatory opinion, A, is "the vehicle travels forward 500 meters, then turns left and travels 400 meters to reach its destination," while the fourth regulatory opinion, B, is "the vehicle turns left and travels 300 meters, then turns right and travels 400 meters to reach its destination."

[0102] Then, A and B are sent to the decision cross-validation module for cross-validation to obtain the first regulatory opinion C, and it is determined whether the first regulatory opinion C passes cross-validation. If the first regulatory opinion C has passed cross-validation, then the first regulatory opinion C is the optimal regulatory opinion after A and B have passed cross-validation. For example, let's assume that the first regulatory opinion C is "the vehicle turns left and travels 400 meters, then turns right and travels 200 meters." By comparing regulatory opinions A and B, the first regulatory opinion C travels the shortest distance. Then, the first regulatory opinion C is sent to the vehicle safety brain and the vehicle controller. The vehicle safety brain will send the first regulatory opinion C and the vehicle driving data to the cloud so that the cloud can perform offline verification of the first regulatory opinion C. After receiving the first regulatory opinion C, the vehicle controller controls the vehicle to travel according to the driving plan of the first regulatory opinion C, that is, "the vehicle turns left and travels 400 meters, then turns right and travels 200 meters."

[0103] Furthermore, if the first regulatory opinion C fails cross-validation, then the first regulatory opinion C becomes the regulatory opinion A calculated by the onboard computing main channel. Regulatory opinions A and B are sent to the onboard safety brain, and regulatory opinion A is sent to the vehicle controller. The onboard safety brain sends regulatory opinions A and B, along with vehicle driving data, to the cloud for offline verification of these opinions. Upon receiving regulatory opinion A, the vehicle controller controls the vehicle's movement according to the driving plan outlined in regulatory opinion A, i.e., "the vehicle moves forward 500 meters, then turns left and moves 400 meters to reach its destination." In this embodiment, because each vehicle is manufactured by a different company and has different factory settings, each vehicle's onboard computing main channel is different. Therefore, when cross-validation fails, the vehicle is controlled according to the regulatory opinion provided by the vehicle's own onboard computing main channel. The onboard brain computing channel only plays a regulatory role, allowing the cloud to conduct vehicle performance tests using regulatory opinion B from the onboard brain computing channel and regulatory opinion A from the onboard computing main channel during subsequent vehicle testing, and to provide a second regulatory opinion D.

[0104] Furthermore, the cloud not only receives various driving data collected by the front-end data acquisition unit during vehicle operation, but also receives the first regulatory opinion C (if cross-validation passes) and the third regulatory opinion A (if cross-validation fails) from the main vehicle computing channel and the fourth regulatory opinion B (if the vehicle's brain computing channel fails). Based on the driving data, the optimal regulatory opinion C, the main vehicle computing channel regulatory opinion A (if cross-validation fails), and the vehicle's brain computing channel regulatory opinion B are verified offline to calculate the vehicle's driving performance and provide a regulatory opinion D.

[0105] From this, we can see that the cloud will provide regulatory opinions in three situations.

[0106] In the first scenario, the cloud platform calculates various performance metrics based on the vehicle's driving data when autonomous driving is activated. These metrics include, for example, the number of forward collision warnings, emergency braking, sharp turns, and abnormal following distance per 1000 kilometers, among others. Based on these calculated metrics, the cloud platform determines whether the vehicle's performance needs improvement and provides regulatory recommendations. These recommendations might include, "The vehicle has reached its maximum carrying capacity and needs to be recalled," or "The vehicle's algorithm is outdated and requires an update," or other similar recommendations.

[0107] In the second scenario, if the cross-validation between the onboard computing main channel regulatory opinion A and the onboard brain computing channel regulatory opinion B is successful, then the cloud receives the first regulatory opinion C after successful cross-validation. Assuming the first regulatory opinion C is "the vehicle turns left and travels 400 meters, then turns right and travels 200 meters," the cloud simulates the scenario based on the vehicle's driving data when autonomous driving is activated and the first regulatory opinion C, calculating various indicators of vehicle operation, such as the number of forward collision warnings per 1000 kilometers, the number of emergency brakings, the number of sharp turns, and abnormal following distance. Based on the calculated indicators, it determines whether the vehicle's performance needs improvement and provides a second regulatory opinion. If the simulation result is the same as the first regulatory opinion C, the regulatory opinion "First regulatory opinion C is not problematic" is given; if the simulation result differs from the first regulatory opinion C, a corresponding regulatory opinion is given. For example, if the simulation result is "First regulatory opinion C states that one road is under repair and an alternative road needs to be taken," and it is also calculated that the vehicle map has not been updated in a timely manner, then the second regulatory opinion is "First regulatory opinion C does not conform to the actual situation, and the vehicle map needs to be updated." If a braking problem occurs during vehicle operation, and the simulation result is "Scheme C of the first regulatory opinion: the vehicle cannot brake", then the second regulatory opinion is given: "The vehicle needs to be recalled for inspection".

[0108] In the third scenario, if the cross-validation between the vehicle-mounted computing main channel regulatory opinion A ("The vehicle travels forward 500 meters, then turns left and travels 400 meters to reach the destination") and the vehicle-mounted brain computing channel regulatory opinion B ("The vehicle turns left and travels 300 meters, then turns right and travels 400 meters to reach the destination") fails, the cloud receives both the vehicle-mounted computing main channel regulatory opinion A and the vehicle-mounted brain computing channel regulatory opinion B, simulates each opinion separately, and calculates various indicators of vehicle operation, such as the number of forward collision warnings per 1000 kilometers, the number of emergency brakings, the number of sharp turns, and the abnormal following distance. Based on the calculated indicators, it determines whether the vehicle's performance needs improvement and provides a second regulatory opinion. If the simulation result is the same as A, the regulatory opinion is "Regulatory opinion B is not the optimal route; the vehicle-mounted brain computing channel needs to update its algorithm or map." If the simulation result is the same as B, the regulatory opinion is "Regulatory opinion A is not the optimal route; the vehicle-mounted computing main channel needs to update its algorithm or map." If the simulation result is different from both regulatory opinions A and B, the appropriate regulatory opinion is given based on the actual situation. For example, if the simulation result is "the vehicle will send collision warnings to other vehicles under both regulatory opinions A and B", thus discovering that the vehicle collision warning mechanism is faulty, then the second regulatory opinion will be given: "the vehicle collision warning has a problem and needs to be recalled".

[0109] The regulatory opinions and various examples described in this embodiment are examples given for ease of understanding because the actual situation is very complex, and do not represent the actual operation of this embodiment.

[0110] In one embodiment, such as Figure 3 As shown, the present invention provides a vehicle monitoring method, comprising:

[0111] When an intelligent driving vehicle begins assisted driving or autonomous driving functions, the data acquisition unit aggregates data from cameras, radar, V2X, IMU, GPS, GNSS, vehicle body, power, maps, etc., and then sends the data to the onboard computer's main computing channel and the onboard safety brain's computing channel, respectively.

[0112] The vehicle-mounted computing main channel and the vehicle-mounted safety brain calculate the decision results respectively, and cross-validate the output results.

[0113] Once cross-validation is successful, the cross-validation decision results are temporarily stored in the security brain.

[0114] When cross-validation fails, the decision data in the vehicle computing main channel is sent to the vehicle actuator. The calculation results of the vehicle computing main channel and the calculation results of the safety brain are temporarily stored in the safety brain at the same time.

[0115] By using network communication, the data stored in the security brain is sent to the cloud for data backup.

[0116] In one embodiment, such as Figure 4 As shown, the present invention provides a vehicle monitoring method, comprising:

[0117] Once the intelligent driving vehicle is started and assisted driving or autonomous driving is activated, the data acquisition unit records and stores data from cameras, radar, V2X, IMU, GPS, GNSS, vehicle body, power, maps, etc.

[0118] The recorded data is uploaded to the cloud via wireless network.

[0119] The cloud computing system tracks indicators such as the number of forward collision warnings, emergency braking, emergency turns, and abnormal following distances per 100 kilometers for intelligent driving vehicles.

[0120] The driving performance of intelligent driving vehicles is judged based on calculated indicators.

[0121] Based on the assessment results, recommendations such as vehicle recall and algorithm upgrades were made.

[0122] In one embodiment, such as Figure 5 As shown, the present invention provides a vehicle monitoring device, including: a data acquisition unit 100, a first transmitting unit 200, a second transmitting unit 600, and a receiving unit 700.

[0123] The data acquisition unit 100 is used to collect vehicle driving data.

[0124] Specifically, when an intelligent driving vehicle begins assisted driving or autonomous driving functions, the data collection unit 100 collects various driving data during the vehicle's operation, such as data from cameras, radar, V2X, GPS, GNSS, vehicle perception data, vehicle body data, power data, and map data.

[0125] The first sending unit 200 is used to send driving data to the vehicle-mounted computing main channel and the vehicle-mounted safety brain computing channel connected to the vehicle terminal, so that the regulatory opinions calculated by the vehicle-mounted computing main channel and the vehicle-mounted safety brain computing channel can be cross-validated to obtain the first regulatory opinion.

[0126] Specifically, the first sending unit 200 aggregates the driving data and sends it to both the on-board computing main channel and the on-board safety brain computing channel. Upon receiving the vehicle driving data, the on-board computing main channel and the on-board safety brain computing channel calculate their respective regulatory opinions. Assume the regulatory opinion calculated by the on-board computing main channel is A, and the regulatory opinion calculated by the on-board safety brain computing channel is B.

[0127] Then, regulatory opinions A and B are sent to the decision cross-validation module for cross-validation to arrive at the first regulatory opinion C.

[0128] Among them, regulatory opinions A, B and the first regulatory opinion C can be various regulatory opinions such as the vehicle's current driving plan, vehicle braking status, and vehicle power status.

[0129] The second sending unit 600 is used to send the driving data and the first regulatory opinion to the cloud, so that the cloud can calculate the second regulatory opinion based on the driving data and the first regulatory opinion.

[0130] Specifically, the cloud receives the first regulatory opinion C sent by the second sending unit 600 and the driving data of the vehicle when it is in autonomous driving or assisted driving mode. Based on the driving data and the first regulatory opinion C, it calculates various indicators of the vehicle's operation (such as the number of forward collision warnings per 1,000 kilometers, the number of emergency brakings, the number of sharp turns, and the abnormal following distance). Based on the calculated indicators, it determines whether the vehicle's performance needs to be improved and gives a corresponding second regulatory opinion based on the performance judgment result. For example, the second regulatory opinion can be "recall opinion, algorithm upgrade opinion, or other opinions".

[0131] The receiving unit 700 is used to receive a first regulatory opinion and a second regulatory opinion, and to change the vehicle status according to the first regulatory opinion and / or the second regulatory opinion.

[0132] Specifically, the receiving unit 700 receives the first regulatory opinion and the second regulatory opinion, and changes the vehicle status according to the first or the second regulatory opinion, or the first and the second regulatory opinions.

[0133] This embodiment, as a preferred embodiment, involves the acquisition unit 100 collecting various driving data during the vehicle's operation when the intelligent driving vehicle begins its assisted driving or autonomous driving function. This data includes information from cameras, radar, V2X, GPS, GNSS, vehicle perception data, vehicle body data, power data, and map data. The first sending unit 200 then aggregates the driving data and sends it to both the onboard computing main channel and the onboard safety brain computing channel. Upon receiving the vehicle driving data, both the onboard computing main channel and the onboard safety brain computing channel calculate their respective regulatory opinions. Assume that the regulatory opinion calculated by the onboard computing main channel is A, and the regulatory opinion calculated by the onboard safety brain computing channel is B.

[0134] The vehicle control result derived from the combined action of the internal decision-making, planning, and control modules in the main vehicle computing channel is regulatory opinion A. Regulatory opinion B is derived from the combined action of the decision-maker and verifier in the vehicle safety brain computing channel. Specifically, the decision-maker in the vehicle safety brain derives the vehicle control result based on the input driving data and sends this result to the verifier. The verifier stores road traffic regulations and defensive driving models. The control result is verified in the verifier to validate the regulatory and defensive driving functions, resulting in the optimal control result, which is regulatory opinion B calculated by the vehicle safety brain computing channel.

[0135] Then, the first sending unit 200 sends A and B to the decision cross-validation module for cross-validation, thereby deriving the first regulatory opinion C. The cloud performs offline verification based on the decision-maker and validator results from the vehicle safety brain sent by the second sending unit 600, vehicle driving data, and the first regulatory opinion C, calculating relevant indicators such as the number of forward collision warnings, emergency braking, emergency turns, and abnormal following distance per 1000 kilometers. The cloud judges the vehicle's driving performance based on these indicators and provides a second regulatory opinion (e.g., recall opinion, algorithm upgrade opinion, other opinions, etc.) based on the judgment results.

[0136] Furthermore, the receiving unit 700 can receive the first regulatory opinion and change the vehicle status according to the first regulatory opinion, or change the vehicle status according to the second regulatory opinion given by the cloud, or change the vehicle status simultaneously according to the first and second regulatory opinions.

[0137] All regulatory opinions in this embodiment are simplified examples for ease of understanding; the actual situation is much more complex.

[0138] In one embodiment, such as Figure 6 As shown, the present invention provides a vehicle monitoring device. Based on the above embodiments, the first sending unit 200 specifically includes: a first sending module 210, a second sending module 220, and a third sending module 230.

[0139] The first sending module 210 is used to send driving data to the vehicle computing main channel and the vehicle safety brain computing channel connected to the vehicle terminal, so that the vehicle computing main channel can calculate the third regulatory opinion and the vehicle safety brain can calculate the vehicle control result based on the driving data.

[0140] The second sending module 220 sends the vehicle control results to the verifier of the vehicle safety brain so that the verifier can verify the vehicle control results and obtain the fourth regulatory opinion.

[0141] Specifically, the first sending module 210 aggregates the driving data and sends it to both the on-board computing main channel and the on-board safety brain computing channel. Upon receiving the vehicle driving data, the on-board computing main channel and the on-board safety brain computing channel calculate their respective regulatory opinions. Assume the third regulatory opinion calculated by the on-board computing main channel is A, and the fourth regulatory opinion calculated by the on-board safety brain computing channel is B.

[0142] The third regulatory opinion, A, is derived from the vehicle control result obtained through the combined action of the internal decision-making, planning, and control modules of the onboard computing main channel. The fourth regulatory opinion, B, is derived through the combined action of the decision-maker and verifier in the onboard safety brain computing channel. Specifically, the decision-maker in the onboard safety brain derives the vehicle control result based on the input driving data, and the second sending module 220 sends this control result to the verifier. The verifier stores road traffic regulations and defensive driving models. The control result is verified in the verifier to validate the regulatory and defensive driving functions, and the optimal control result is derived. This optimal control result is the fourth regulatory opinion, B, calculated by the onboard safety brain computing channel.

[0143] The third sending module 230 is used to send the third regulatory opinion and the fourth regulatory opinion to the decision cross-validation module, so that the cross-validation module can cross-validate the third regulatory opinion and the fourth regulatory opinion to obtain the first regulatory opinion.

[0144] Specifically, the third sending module 230 sends the third regulatory opinion A and the fourth regulatory opinion B to the decision cross-validation module for cross-validation, thereby obtaining the first regulatory opinion C.

[0145] In one embodiment, such as Figure 7As shown, the present invention provides a vehicle monitoring device. Based on the above embodiments, the second sending unit 600 specifically includes: a fourth sending module 610 and a judgment module 620.

[0146] The fourth sending module 610 is used to send the driving data and the first regulatory opinion to the cloud, so that the cloud can calculate the number of forward collision warnings, emergency braking, sharp turns, and abnormal following distance per thousand kilometers of the vehicle based on the driving data and the first regulatory opinion.

[0147] The judgment module 620 is used to judge the vehicle's assisted driving capability or autonomous driving capability based on the calculation results, and to arrive at the second regulatory opinion.

[0148] Specifically, the first regulatory opinion C is obtained through cross-validation of the onboard computing main channel regulatory opinion A and the onboard brain computing channel regulatory opinion B. Then, the fourth sending module 610 sends the first regulatory opinion C to the cloud. The cloud performs offline verification based on the vehicle's driving data when autonomous driving is activated, the first regulatory opinion C, the decision-maker in the onboard safety brain, and the verifier results, calculating relevant indicators such as the number of forward collision warnings, emergency braking, emergency turning, and abnormal following distance per 1000 kilometers. The judgment module 620 judges the vehicle's driving performance based on the relevant indicators and gives a second regulatory opinion (such as recall opinion, algorithm upgrade opinion, or other opinions) based on the judgment results. For example, if the calculated indicators show that the vehicle's algorithm and map need to be updated, the second regulatory opinion is given: "The vehicle needs to update its algorithm and map." Or, if the calculated indicators show that the vehicle's braking has a problem, the second regulatory opinion is given: "The vehicle's brakes are damaged and need to be recalled for repair."

[0149] In one embodiment, such as Figure 8 As shown, the present invention provides a vehicle monitoring method, which, based on the above embodiments, further includes: a judgment unit 300, a first execution unit 400, and a second execution unit 500.

[0150] Judgment unit 300 is used to determine whether the first regulatory opinion has passed cross-validation.

[0151] The first execution unit 400 is used to change the vehicle status according to the first regulatory opinion if the first regulatory opinion passes cross-validation.

[0152] The second execution unit 500 is used to replace the first regulatory opinion with a third regulatory opinion if the first regulatory opinion fails to pass cross-validation.

[0153] Specifically, the judgment unit 300 determines whether the first regulatory opinion C has passed cross-validation. If the first regulatory opinion C has passed cross-validation, then the first regulatory opinion C is the optimal regulatory opinion after cross-validation of A and B, and the first execution unit 400 changes the vehicle status according to the first regulatory opinion.

[0154] Furthermore, the second execution unit 500 is configured to, if the first regulatory opinion C fails cross-validation, then the first regulatory opinion C becomes the third regulatory opinion A calculated by the on-board computing main channel. The third regulatory opinion A and regulatory opinion B are sent to the on-board safety brain, and the third regulatory opinion A is sent to the vehicle controller. The on-board safety brain then sends the third regulatory opinions A and B, along with vehicle driving data, to the cloud for offline verification of the third regulatory opinions A and B.

[0155] This embodiment, as a preferred embodiment, involves the acquisition unit 100 collecting various driving data during the vehicle's operation when the intelligent driving vehicle begins its assisted driving or autonomous driving function. This data includes information from cameras, radar, V2X, GPS, GNSS, vehicle perception data, vehicle body data, power data, and map data. The first sending unit 200 then aggregates the driving data and sends it to both the onboard computing main channel and the onboard safety brain computing channel. Upon receiving the vehicle driving data, both the onboard computing main channel and the onboard safety brain computing channel calculate their respective regulatory opinions. Assuming the third regulatory opinion calculated by the onboard computing main channel is A, and the fourth regulatory opinion calculated by the onboard safety brain computing channel is B.

[0156] The third regulatory opinion, A, is derived from the vehicle control result obtained through the combined action of the internal decision-making, planning, and control modules of the onboard computing main channel. The fourth regulatory opinion, B, is derived through the combined action of the decision-maker and verifier in the onboard safety brain computing channel. Specifically, the decision-maker in the onboard safety brain calculates the vehicle control result based on the input driving data and sends this result to the verifier. The verifier stores road traffic regulations and defensive driving models. The control result is verified in the verifier to validate the regulatory and defensive driving functions, resulting in the optimal control result, which is the fourth regulatory opinion, B, calculated by the onboard safety brain computing channel. For example, let's assume that the third regulatory opinion, A, is "the vehicle travels forward 500 meters, then turns left and travels 400 meters to reach its destination," while the fourth regulatory opinion, B, is "the vehicle turns left and travels 300 meters, then turns right and travels 400 meters to reach its destination."

[0157] Then, A and B are sent to the decision cross-validation module for cross-validation to obtain the first regulatory opinion C. The judgment unit 300 determines whether the first regulatory opinion C has passed the cross-validation. The first execution unit 400 is used to determine whether the first regulatory opinion C has passed the cross-validation if it has. If so, the first regulatory opinion C is the optimal regulatory opinion after the cross-validation of A and B. For example, let's assume that the first regulatory opinion C is "the vehicle turns left and travels 400 meters, then turns right and travels 200 meters". By comparing regulatory opinions A and B, the first regulatory opinion C has the shortest distance. Then, the first regulatory opinion C is sent to the vehicle safety brain and the vehicle controller. The vehicle safety brain will send the first regulatory opinion C and the vehicle driving data to the cloud so that the cloud can perform offline verification of the first regulatory opinion C. After receiving the first regulatory opinion C, the receiving unit 700 controls the vehicle to drive according to the driving plan of the first regulatory opinion C, that is, "the vehicle turns left and travels 400 meters, then turns right and travels 200 meters".

[0158] Furthermore, the second execution unit 500 is used to, if the first regulatory opinion C fails cross-validation, then the first regulatory opinion C becomes the regulatory opinion A calculated by the on-board computing main channel. Regulatory opinions A and B are sent to the on-board safety brain, and regulatory opinion A is sent to the vehicle controller. The second sending unit 600 sends regulatory opinions A and B, along with vehicle driving data, to the cloud for offline verification of regulatory opinions A and B. Upon receiving regulatory opinion A, the vehicle controller controls the vehicle's movement according to the driving plan outlined in regulatory opinion A, i.e., "the vehicle travels forward 500 meters, then turns left and travels 400 meters to reach the destination." In this embodiment, since each vehicle is manufactured by a different company and has different factory settings, the on-board computing main channel of each vehicle is different. Therefore, when cross-validation fails, the vehicle is controlled according to the regulatory opinion given by the on-board computing main channel carried by the vehicle itself. The on-board brain computing channel only plays a regulatory role so that in the subsequent vehicle testing process, the cloud will use the regulatory opinion B given by the on-board brain computing channel and the regulatory opinion A given by the on-board computing main channel to conduct vehicle performance testing and give a second regulatory opinion D.

[0159] Furthermore, the cloud not only receives various driving data collected by the collection unit 100 during vehicle operation, but also receives the first regulatory opinion C (if cross-validation passes) and the third regulatory opinion A (if cross-validation fails) from the on-board computing main channel and the fourth regulatory opinion B (if the on-board brain computing channel fails). Based on the driving data, the optimal regulatory opinion C, the on-board computing main channel regulatory opinion A (if cross-validation fails), and the on-board brain computing channel regulatory opinion B are verified offline to calculate the vehicle's driving performance and provide a regulatory opinion D.

[0160] From this, we can see that the cloud will provide regulatory opinions in three situations.

[0161] In the first scenario, the cloud platform calculates various performance metrics based on the vehicle's driving data when autonomous driving is activated. These metrics include, for example, the number of forward collision warnings, emergency braking, sharp turns, and abnormal following distance per 1000 kilometers, among others. Based on these calculated metrics, the cloud platform determines whether the vehicle's performance needs improvement and provides regulatory recommendations. These recommendations might include, "The vehicle has reached its maximum carrying capacity and needs to be recalled," or "The vehicle's algorithm is outdated and requires an update," or other similar recommendations.

[0162] In the second scenario, if the cross-validation between the onboard computing main channel regulatory opinion A and the onboard brain computing channel regulatory opinion B is successful, then the cloud receives the first regulatory opinion C after successful cross-validation. Assuming the first regulatory opinion C is "the vehicle turns left and travels 400 meters, then turns right and travels 200 meters," the cloud simulates the scenario based on the vehicle's driving data when autonomous driving is activated and the first regulatory opinion C, calculating various indicators of vehicle operation, such as the number of forward collision warnings per 1000 kilometers, the number of emergency brakings, the number of sharp turns, and abnormal following distance. Based on the calculated indicators, it determines whether the vehicle's performance needs improvement and provides a second regulatory opinion. If the simulation result is the same as the first regulatory opinion C, the regulatory opinion "First regulatory opinion C is not problematic" is given; if the simulation result differs from the first regulatory opinion C, a corresponding regulatory opinion is given. For example, if the simulation result is "First regulatory opinion C states that one road is under repair and an alternative road needs to be taken," and it is also calculated that the vehicle map has not been updated in a timely manner, then the second regulatory opinion is "First regulatory opinion C does not conform to the actual situation, and the vehicle map needs to be updated." If a braking problem occurs during vehicle operation, and the simulation result is "Scheme C of the first regulatory opinion: the vehicle cannot brake", then the second regulatory opinion is given: "The vehicle needs to be recalled for inspection".

[0163] In the third scenario, if the cross-validation between the vehicle-mounted computing main channel regulatory opinion A ("The vehicle travels forward 500 meters, then turns left and travels 400 meters to reach the destination") and the vehicle-mounted brain computing channel regulatory opinion B ("The vehicle turns left and travels 300 meters, then turns right and travels 400 meters to reach the destination") fails, the cloud receives both the vehicle-mounted computing main channel regulatory opinion A and the vehicle-mounted brain computing channel regulatory opinion B, simulates each opinion separately, and calculates various indicators of vehicle operation, such as the number of forward collision warnings per 1000 kilometers, the number of emergency brakings, the number of sharp turns, and the abnormal following distance. Based on the calculated indicators, it determines whether the vehicle's performance needs improvement and provides a second regulatory opinion. If the simulation result is the same as A, the regulatory opinion is "Regulatory opinion B is not the optimal route; the vehicle-mounted brain computing channel needs to update its algorithm or map." If the simulation result is the same as B, the regulatory opinion is "Regulatory opinion A is not the optimal route; the vehicle-mounted computing main channel needs to update its algorithm or map." If the simulation result is different from both regulatory opinions A and B, the appropriate regulatory opinion is given based on the actual situation. For example, if the simulation result is "the vehicle will send collision warnings to other vehicles under both regulatory opinions A and B", thus discovering that the vehicle collision warning mechanism is faulty, then the second regulatory opinion will be given: "the vehicle collision warning has a problem and needs to be recalled".

[0164] The regulatory opinions and various examples described in this embodiment are examples given for ease of understanding because the actual situation is very complex, and do not represent the actual operation of this embodiment.

[0165] In one embodiment, the present invention provides a computer medium storing a computer program thereon, which, when executed by a processor, can implement the vehicle monitoring method as described in the foregoing embodiments. That is, when part or all of the technical solutions contributing to the prior art in the foregoing embodiments of the present invention are embodied in a computer software product, the aforementioned computer software product is stored in a computer-readable storage medium. The computer-readable storage medium can be any physical device or equipment capable of carrying computer program code, such as a USB flash drive, portable hard disk, magnetic disk, optical disk, computer memory, read-only memory, random access memory, etc.

[0166] It should be noted that the above embodiments can be freely combined as needed. The above are merely preferred embodiments of the present invention. It should be pointed out that for those skilled in the art, several improvements and modifications can be made without departing from the principle of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

Claims

1. A vehicle monitoring method, characterized in that, Including the following steps: Collect vehicle driving data; The driving data is sent to the vehicle computing main channel and the vehicle safety brain computing channel connected to the vehicle terminal, so that the regulatory opinions calculated by the vehicle computing main channel and the vehicle safety brain computing channel are cross-validated to obtain the first regulatory opinion; The driving data and the first regulatory opinion are sent to the cloud so that the cloud can calculate a second regulatory opinion based on the driving data and the first regulatory opinion. Receive the first regulatory opinion and the second regulatory opinion, and change the vehicle status according to the first regulatory opinion and / or the second regulatory opinion.

2. The vehicle monitoring method according to claim 1, characterized in that, The process of sending the driving data to the vehicle-mounted main computing channel and the vehicle-mounted safety brain computing channel connected to the vehicle terminal, so that the regulatory opinions calculated by the vehicle-mounted main computing channel and the vehicle-mounted safety brain computing channel are cross-validated to obtain a first regulatory opinion, specifically includes the following steps: The driving data is sent to the vehicle computing main channel and the vehicle safety brain computing channel connected to the vehicle terminal, so that the vehicle computing main channel calculates the third regulatory opinion, and the vehicle safety brain calculates the vehicle control result based on the driving data; The vehicle control results are sent to the verifier of the vehicle safety brain so that the verifier can verify the vehicle control results and generate a fourth regulatory opinion. The third and fourth regulatory opinions are sent to the decision cross-validation module so that the cross-validation module can cross-validate the third and fourth regulatory opinions to arrive at the first regulatory opinion.

3. The vehicle monitoring method according to claim 1, characterized in that, The step of sending the driving data and the first regulatory opinion to the cloud, so that the cloud can calculate and derive a second regulatory opinion based on the driving data and the first regulatory opinion, specifically includes the following steps: The driving data and the first regulatory opinion are sent to the cloud, so that the cloud can calculate the number of forward collision warnings, emergency braking, sharp turns, and abnormal following distance per thousand kilometers for the vehicle based on the driving data and the first regulatory opinion. The vehicle's assisted driving capability or autonomous driving capability is assessed based on the calculation results, and the second regulatory opinion is derived.

4. The vehicle monitoring method according to claim 2, characterized in that, After sending the third and fourth regulatory opinions to the cross-validation module to cross-validate the third and fourth regulatory opinions and derive the first regulatory opinion, the method further includes the following steps: Determine whether the first regulatory opinion passes the cross-validation; If the first regulatory opinion passes the cross-validation, the vehicle status is changed according to the first regulatory opinion; If the first regulatory opinion fails the cross-validation, the third regulatory opinion shall represent the first regulatory opinion.

5. The vehicle monitoring method according to any one of claims 2 and 4, characterized in that, Including the following steps: The third and fourth regulatory opinions will be sent to the cloud for data backup.

6. A vehicle monitoring device, characterized in that, include: The data acquisition unit is used to collect vehicle driving data. The first sending unit is used to send the driving data to the vehicle computing main channel and the vehicle safety brain computing channel connected to the vehicle terminal, so that the regulatory opinions calculated by the vehicle computing main channel and the vehicle safety brain computing channel can be cross-verified to obtain the first regulatory opinion; The second sending unit is used to send the driving data and the first regulatory opinion to the cloud, so that the cloud can calculate and obtain the second regulatory opinion based on the driving data and the first regulatory opinion; The receiving unit is configured to receive the first regulatory opinion and the second regulatory opinion, and change the vehicle status according to the first regulatory opinion and / or the second regulatory opinion.

7. The vehicle monitoring device according to claim 6, characterized in that, The first sending unit specifically includes: The first sending module is used to send the driving data to the vehicle computing main channel and the vehicle safety brain computing channel connected to the vehicle terminal, so that the vehicle computing main channel calculates the third regulatory opinion and the vehicle safety brain calculates the vehicle control result based on the driving data. The second sending module is used to send the vehicle control result to the verifier of the vehicle safety brain, so that the verifier can verify the vehicle control result and obtain a fourth regulatory opinion. The third sending module is used to send the third regulatory opinion and the fourth regulatory opinion to the decision cross-validation module, so that the cross-validation module can cross-validate the third regulatory opinion and the fourth regulatory opinion to obtain the first regulatory opinion.

8. The vehicle monitoring device according to claim 6, characterized in that, The second transmitting unit specifically includes: The fourth sending module is used to send the driving data and the first regulatory opinion to the cloud, so that the cloud can calculate the number of forward collision warnings, emergency braking, sharp turns and abnormal following distance per thousand kilometers of the vehicle based on the driving data and the first regulatory opinion; The judgment module is used to judge the vehicle's assisted driving capability or autonomous driving capability based on the calculation results, and to arrive at the second regulatory opinion.

9. The vehicle monitoring device according to claim 7, characterized in that, Also includes: The judgment unit is used to determine whether the first regulatory opinion passes the cross-validation; A first execution unit is configured to change the vehicle status according to the first regulatory opinion if the first regulatory opinion passes the cross-validation. The second execution unit is configured to use the third regulatory opinion to represent the first regulatory opinion if the first regulatory opinion fails the cross-validation.

10. The vehicle monitoring device according to any one of claims 7 and 9, characterized in that, Also includes: The third sending unit is used to send the third and fourth regulatory opinions to the cloud for data backup.

Images