A vehicle time synchronization method, device and medium

Abstract

The present invention discloses a vehicle time synchronization method, device and medium, which are applicable to the field of autonomous driving technology. According to the precise time and pulse-per-second signal, multiple sensors in each actuator are time synchronized to obtain sampling data of multiple sensors; the sampling data are analyzed and processed to obtain the execution results of each actuator; the execution results of each actuator are predicted to the same time to complete the time synchronization of the vehicle. In addition to completing the time synchronization of multiple sensors inside the actuator, the time synchronization between actuators is also realized, so that after the sensor is time synchronized, the subsequent sampling data of the sensor is analyzed and processed by the actuator to obtain the execution results of each actuator, and then the software synchronization based on the execution results of the actuator is predicted to the same time, all based on the same time reference, thereby improving the accuracy of time synchronization between multiple actuators, and greatly improving the safety and effectiveness of the autonomous driving redundant multi-executor technology.

Description

Technical Field

[0001] The present invention relates to the field of autonomous driving technology, and in particular to a vehicle time synchronization method, device and medium. Background Art

[0002] At present, while the technology of autonomous driving brings convenience to people's lives, it also poses a greater challenge to safety. The endogenous safety technology of autonomous driving that has emerged in China in recent years realizes dynamic heterogeneous redundant construction by configuring multiple heterogeneous redundant perception and decision-making units on the car, and makes decisions by comparing the information of multiple perception and decision-making units, which can achieve the effect of integrated enhancement of the functional safety and network security of the perception and decision-making units of autonomous driving.

[0003] Since the sensors used in each actuator are not completely consistent, they may include one or more sensors such as cameras, millimeter-wave radars, and lidars. In order to improve the accuracy of perception decision results (execution results), different sensor synchronization algorithms are usually used in the actuator to solve the problem. The execution results of the existing actuators for the same environment are also different. Due to the different frequencies of different actuators, there are a large number of execution results at different times that are difficult to compare. In addition, since the existing time synchronization methods are mainly used between multiple sensors, after the clock source is synchronized, the execution results after the sensor data is processed by the synchronization algorithm, the data processing time, and the transmission time of the processing results may all cause time deviations. At this time, time synchronization is not performed again, thereby reducing the accuracy of time synchronization between multiple actuators, further affecting the effectiveness of autonomous driving multi-executor technology and the safety of autonomous driving vehicles.

[0004] Therefore, how to improve the accuracy of multi-executable time synchronization is an issue that those skilled in the art urgently need to solve. Summary of the invention

[0005] The purpose of the present invention is to provide a vehicle time synchronization method, device and medium to improve the accuracy of multi-executable time synchronization.

[0006] In order to solve the above technical problems, the present invention provides a vehicle time synchronization method, comprising:

[0007] Obtain the standard time and pulse-per-second signal of the vehicle-mounted satellite navigation, and calibrate the precise time according to the standard time and pulse-per-second signal;

[0008] According to the precise time and the pulse-per-second signal, multiple sensors in each actuator are synchronized to obtain sampling data of multiple sensors;

[0009] Analyze and process the sampled data to obtain the execution results of each execution body;

[0010] The execution results of each actuator are predicted to the same time to complete the time synchronization of the vehicle.

[0011] Preferably, calibrating the accurate time according to the standard time and the pulse per second signal includes:

[0012] Parse the standard time to get UTC time;

[0013] Calibrate based on the second pulse signal and UTC time to get accurate time.

[0014] Preferably, the multiple sensors in each execution body are synchronized according to the precise time and the pulse per second signal to obtain the sampling data of the multiple sensors, including:

[0015] Calibrate the local time of each actuator according to the precise time and the second pulse signal to obtain the local calibration time;

[0016] Each actuator is controlled to synchronize multiple sensors in the respective actuator according to the local calibration time and the pulse per second signal to obtain sampling data.

[0017] Preferably, the local time of each execution body is calibrated according to the precise time and the second pulse signal to obtain the local calibration time, which specifically includes:

[0018] Send the precise time to each executor, and record the moment when the sending is completed as the first moment;

[0019] Determine whether each executive has a pulse per second signal interface;

[0020] If it does not exist, the difference time is sent to the execution body without the second pulse signal interface, wherein the difference time is the difference between the first time and the precise time;

[0021] Controlling the execution body with the pulse-per-second signal interface to calibrate with the precise time according to the pulse-per-second signal to obtain the first local calibration time of the execution body with the pulse-per-second signal interface to complete hardware synchronization;

[0022] The execution body without the second pulse signal interface is controlled to record the moment of receiving the precise time as the second moment, and the moment of receiving the difference moment as the third moment. The second local calibration time of the execution body without the second pulse signal interface is determined according to the relationship among the third moment, the second moment and the first moment to complete the software synchronization.

[0023] Preferably, controlling each actuator to synchronize multiple sensors in each actuator according to the local calibration time and the pulse per second signal to obtain sampling data includes:

[0024] If the current execution body is an execution body without a pulse-per-second signal interface, construct a pulse-per-second signal in the current execution body and send it to multiple sensors in the current execution body;

[0025] Determine whether each sensor has a pulse per second signal interface;

[0026] If it exists, the local calibration time and the pulse-per-second signal are sent to the sensor having the pulse-per-second signal interface to obtain the first sampling data;

[0027] If it does not exist, a corresponding synchronous pulse signal is constructed according to the sampling period of the sensor without the pulse-per-second signal interface, the pulse-per-second signal and the frequency multiplier, wherein the period of the synchronous pulse signal is the same as the sampling period of the sensor without the pulse-per-second signal interface;

[0028] triggering a sensor without a pulse per second signal interface according to the synchronization pulse signal to obtain second sampling data;

[0029] If the current execution body has a pulse-per-second signal interface, the pulse-per-second signal is sent to multiple sensors in the current execution body, and the process returns to the step of determining whether there is a pulse-per-second signal interface in the multiple sensors to determine the sampling data.

[0030] Preferably, triggering a sensor without a pulse per second signal interface according to the synchronization pulse signal to obtain second sampling data includes:

[0031] Get the data transmission time corresponding to the sensor that does not have a second pulse signal interface;

[0032] Determine the sampling time of the sensor without the pulse per second signal interface according to the relationship between the local time when the current execution body receives the second initial sampling data and the data transmission time to determine the corresponding sampling timestamp;

[0033] The sampling timestamp is added to the corresponding second initial sampling data of the sensor without the pulse per second signal interface to obtain the second sampling data.

[0034] Preferably, the sampled data is analyzed and processed to obtain the execution results of each execution body, including:

[0035] Receive sampling data corresponding to multiple sensors in the current execution body;

[0036] The sampling data are fused through a fusion algorithm to obtain an initial execution result;

[0037] Determine the timestamp of the initial execution result according to the data sampling time corresponding to each sampled data;

[0038] The timestamp is added to the initial execution result to obtain the execution result of the current execution body.

[0039] Preferably, the execution results of each execution body are predicted to the same time to complete the time synchronization of the vehicle, including:

[0040] Obtain the current execution result of each execution body and the timestamp of the current execution result according to the preset period;

[0041] Calculate each time difference based on the timestamp of each current execution result and the current time corresponding to the preset period;

[0042] Select the timestamp corresponding to the minimum time difference as the reference time;

[0043] Determine the corresponding difference time according to the relationship between the reference time and the timestamp corresponding to the current execution result of each execution body;

[0044] The reference time is taken as the same moment, and the execution results of each execution body are predicted to the same moment according to each difference time to obtain the corresponding current predicted execution result to complete the time synchronization of the vehicle.

[0045] Preferably, after the execution result prediction is performed to the same time, the method further includes:

[0046] Output the current prediction execution results in a collection form for subsequent processing.

[0047] In order to solve the above technical problems, the present invention further provides a vehicle time synchronization device, comprising:

[0048] A calibration module is used to obtain the standard time and pulse-per-second signal of the vehicle-mounted satellite navigation, and calibrate the accurate time according to the standard time and pulse-per-second signal;

[0049] The sensor synchronization module is used to synchronize the time of multiple sensors in each actuator according to the precise time and second pulse signal to obtain the sampling data of multiple sensors;

[0050] An analysis and processing module is used to analyze and process the sampled data to obtain the execution results of each execution body;

[0051] The execution body synchronization module is used to predict the execution results of each execution body to the same time to complete the time synchronization of the vehicle.

[0052] In order to solve the above technical problems, the present invention further provides a vehicle time synchronization device, comprising:

[0053] Memory for storing computer programs;

[0054] A processor is used to implement the steps of the above-mentioned vehicle time synchronization method when executing a computer program.

[0055] In order to solve the above technical problems, the present invention also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the vehicle time synchronization method as described above are implemented.

[0056] The present invention provides a vehicle time synchronization method, including obtaining the standard time and second pulse signal of the vehicle-mounted satellite navigation, and calibrating according to the standard time and second pulse signal to obtain the precise time; performing time synchronization on multiple sensors in each actuator according to the precise time and second pulse signal to obtain the sampling data of multiple sensors; analyzing and processing the sampling data to obtain the execution results of each actuator; and predicting the execution results of each actuator to the same time to complete the time synchronization of the vehicle. In addition to completing the time synchronization of multiple sensors inside the actuator, this method also realizes the time synchronization between actuators, so that after the sensor is time synchronized, the subsequent sampling data of the sensor is analyzed and processed by the actuator to obtain the execution results of each actuator, and then the software synchronization based on the execution results of the actuator is predicted to the same time, all based on the same time reference, thereby improving the accuracy of time synchronization between multiple actuators, and greatly improving the safety and effectiveness of the redundant multi-executor technology of autonomous driving.

[0057] In addition, the present invention also provides a vehicle time synchronization device and medium, which have the same beneficial effects as the above-mentioned vehicle time synchronization method. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] In order to more clearly illustrate the embodiments of the present invention, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0059] Figure 1 A flow chart of a vehicle time synchronization method provided by an embodiment of the present invention;

[0060] Figure 2 A schematic diagram of an application of time synchronization of multiple in-vivo sensors provided by an embodiment of the present invention;

[0061] Figure 3 A structural diagram of a vehicle time synchronization device provided by an embodiment of the present invention;

[0062] Figure 4 A structural diagram of another vehicle time synchronization device provided by an embodiment of the present invention;

[0063] Figure 5 A structural diagram of a vehicle time synchronization device provided in another embodiment of the present invention. DETAILED DESCRIPTION

[0064] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0065] The core of the present invention is to provide a vehicle time synchronization method, device and medium to improve the accuracy of multi-executable time synchronization.

[0066] In order to enable those skilled in the art to better understand the solution of the present invention, the present invention is further described in detail below in conjunction with the accompanying drawings and specific implementation methods.

[0067] In order to improve the safety of autonomous driving, the implementation of high-level autonomous driving has a redundant design. Different redundancy schemes are used in the production of vehicles of different brands to achieve redundancy of sensors, sensor fusion, decision planning and execution control. The vehicle time synchronization method provided by the present invention is applicable to vehicles produced by different brands.

[0068] Figure 1 A flow chart of a vehicle time synchronization method provided by an embodiment of the present invention, such as Figure 1 As shown, the method includes:

[0069] S11: Obtain the standard time and pulse-per-second signal of the vehicle-mounted satellite navigation, and calibrate the standard time and pulse-per-second signal to obtain the precise time;

[0070] Specifically, vehicles with autonomous driving technology are equipped with a satellite navigation timing module, which sends National Marine Electronics Association (NEMA) data and Pulse Per Second (PPS) signals. NEMA data is standard time, including Universal Time Coordinated (UTC) time, latitude and longitude in degree and minute format, Global Positioning System (GPS) status, etc.

[0071] The PPS signal provides an accurate clock synchronization signal with a pulse width of 200-300ms. The rising edge is used as the timing point, and the rise time △T does not exceed 10ns. The satellite navigation timing module mainly outputs time scale information, including the PPS signal.

[0072] The local time of the vehicle time synchronization unit is calibrated according to the standard time and PPS signal to obtain the precise time. The vehicle's time synchronization unit is used to obtain and analyze the time information data of the vehicle navigation timing module, which is equivalent to the controller. The calibration method can be to convert the standard time into UTC time, and calibrate the local time of the controller through the second pulse signal and UTC time to obtain the precise time. Specifically, the rising edge of each second pulse signal is used as the starting time of the current second of UTC time, that is, when the controller receives the rising edge of each second pulse signal, it updates the whole second information of UTC time to the local time of the controller to obtain the precise time.

[0073] S12: performing time synchronization on multiple sensors in each actuator according to the precise time and the pulse per second signal to obtain sampling data of the multiple sensors;

[0074] The precise time and PPS signal obtained in the above step S11 are then used to synchronize the time of multiple sensors in each actuator to obtain the sampling data of multiple sensors. Specifically, the actuator controls the sensor to collect data and is responsible for the time synchronization of the sensor. The vehicle includes multiple actuators, and each actuator includes multiple sensors according to the actual processing and completed tasks.

[0075] The meaning of the interfaces of actuators and sensors is fixed during production. The time synchronization strategies for actuators and sensors without PPS signal interfaces are different from those for actuators and sensors with PPS signal interfaces. Actuators and sensors with PPS signal interfaces can achieve hardware synchronization or hard synchronization through precise time and PPS signals.

[0076] Actuators and sensors that do not have a PPS signal interface require software synchronization using precise time.

[0077] An actuator with a PPS signal interface may contain two types of sensors (one with a PPS signal interface and one without a PPS signal interface), and an actuator without a PPS signal interface may also contain two types of sensors (one with a PPS signal interface and one without a PPS signal interface), thus forming four situations. The present invention expands on the four situations to achieve time synchronization between different sensors in different actuators.

[0078] S13: Analyze and process the sampled data to obtain the execution results of each execution body;

[0079] After the sensor synchronization is achieved in step S12, the sampled data of the sensor is fused to obtain the execution result of the corresponding execution body. It should be noted that the analysis and processing can be based on a specific algorithm, such as a fusion algorithm, but there are many fusion algorithms, and the fusion algorithms in each execution body can be the same or different. The present invention does not make specific limitations and can be set according to specific actual conditions.

[0080] Multi-sensor fusion is an information processing process that uses computer technology to automatically analyze and synthesize information and data from multiple sensors or multiple sources according to certain criteria to complete the required decision-making and estimation. Various sensors are processed for multi-level and multi-space information complementation and optimal combination, and ultimately produce a consistent interpretation of the observed environment. In this process, it is necessary to make full use of multi-source data for reasonable control and use, and the ultimate goal of information fusion is to derive more useful information through multi-level and multi-faceted combinations of information based on the separated observation information obtained by each sensor. This not only takes advantage of the collaborative operation of multiple sensors, but also comprehensively processes data from other information sources to improve the intelligence of the entire sensor system.

[0081] Generally speaking, nonlinear mathematical methods can be used as fusion methods if they are fault-tolerant, adaptive, associative memory and parallel processing capable. They mainly include weighted average method, Kalman filter method, DS evidence reasoning method, production rules, fuzzy logic reasoning and artificial neural network, etc. There is no specific limitation, as long as a consistent description of the target can be obtained.

[0082] S14: Predicting the execution results of each execution body to the same time to complete the time synchronization of the vehicle.

[0083] The vehicle's time synchronization unit further aggregates the execution results of each execution body and predicts each execution result to the same time, all based on the same time reference, to achieve vehicle time synchronization.

[0084] The present invention does not make any specific limitation on the fusion prediction of the execution results of each execution body. It can be based on a reference time to predict the time corresponding to each execution result to the reference time, etc. It can also refer to the sensor fusion algorithm to achieve time synchronization between the execution bodies, etc.

[0085] A vehicle time synchronization method provided by an embodiment of the present invention includes obtaining the standard time and second pulse signal of the vehicle-mounted satellite navigation, and calibrating according to the standard time and second pulse signal to obtain the precise time; performing time synchronization on multiple sensors in each actuator according to the precise time and second pulse signal to obtain the sampling data of multiple sensors; analyzing and processing the sampling data to obtain the execution results of each actuator; and predicting the execution results of each actuator to the same time to complete the time synchronization of the vehicle. In addition to completing the time synchronization of multiple sensors within the actuator, this method also realizes the time synchronization between actuators, so that after the sensor is time synchronized, the subsequent sampling data of the sensor is analyzed and processed by the actuator to obtain the execution results of each actuator, and then the software synchronization based on the execution results of the actuator is predicted to the same time, all based on the same time reference, thereby improving the accuracy of time synchronization between multiple actuators, and greatly improving the safety and effectiveness of the redundant multi-executor technology of autonomous driving.

[0086] Based on the above embodiment, the step S11 of calibrating the standard time and the pulse per second signal to obtain the precise time includes:

[0087] Parse the standard time to get UTC time;

[0088] Calibrate based on the second pulse signal and UTC time to get accurate time.

[0089] Specifically, the standard time is parsed to obtain the UTC time. In the above embodiment, it is mentioned that the information of the standard time includes not only the time, but also the latitude and longitude information and the GPS status, etc. The present invention is mainly aimed at the synchronization of time, so the standard time is parsed to obtain the UTC time. The precise time obtained by calibrating the UTC time and the PPS signal is sent to each execution body to ensure the precise synchronization of the execution body time with the UTC time. The specific method can be to use the rising edge of each second pulse signal as the starting time of the current second of the UTC time, that is, when the controller receives the rising edge of each second pulse signal, the whole second information of the UTC time is updated to the local time of the controller, that is, the precise time.

[0090] The embodiment of the present invention provides a method for obtaining accurate time by calibrating according to standard time and pulse per second signal, which facilitates the subsequent completion of local calibration of the execution body.

[0091] Based on the above embodiment, the step S12 of performing time synchronization on multiple sensors in each execution body according to the precise time and the pulse per second signal to obtain sampling data of multiple sensors includes:

[0092] Calibrate the local time of each actuator according to the precise time and the second pulse signal to obtain the local calibration time;

[0093] Control each actuator to synchronize multiple sensors in each actuator according to the local calibration time and the pulse per second signal to obtain sampling data;

[0094] The local time of each execution body is calibrated according to the precise time and the second pulse signal to obtain the local calibration time, which specifically includes:

[0095] Send the precise time to each executor, and record the moment when the sending is completed as the first moment;

[0096] Determine whether each executive has a pulse per second signal interface;

[0097] If it does not exist, the difference time is sent to the execution body without the second pulse signal interface, wherein the difference time is the difference between the first time and the precise time;

[0098] Controlling the execution body with the pulse-per-second signal interface to calibrate with the precise time according to the pulse-per-second signal to obtain the first local calibration time of the execution body with the pulse-per-second signal interface to complete hardware synchronization;

[0099] The execution body without the second pulse signal interface is controlled to record the moment of receiving the precise time as the second moment, and the moment of receiving the difference moment as the third moment. The second local calibration time of the execution body without the second pulse signal interface is determined according to the relationship among the third moment, the second moment and the first moment to complete the software synchronization.

[0100] It should be noted that, when judging whether each executable body has a pulse-second signal interface, since the number of executable bodies is not fixed, the judgment step can be completed for all executable bodies, and hardware synchronization can be performed for the executable bodies with a pulse-second signal interface, and software synchronization can be performed for the executable bodies without a pulse-second signal interface; or it can be judged whether the current executable body has a pulse-second signal interface, if it exists, hardware synchronization is performed, if not, software synchronization is performed, and after the synchronization step is completed, it is judged again whether the next current executable body has a pulse-second signal interface, until the synchronization step of the last executable body is completed.

[0101] The time of the controller in the initial state is the precise time. The initial state of this embodiment is the state when the calibration between the controller and the executive body is not completed. At this time, the time of the executive body has not yet completed the calibration, so the local time of the controller is inconsistent with the local time of the executive body. For example, the controller sends the precise time t0 to the executive body, and the local time t1 of the controller corresponding to the completion time of the controller sending the precise time to the executive body is recorded as the first moment, and the local time t2 of the executive body corresponding to the receiving moment of the executive body receiving the precise time is recorded as the second moment.

[0102] The time synchronization process is different for different execution bodies. The execution body with a second pulse signal interface directly calibrates its own local time according to the PPS signal and the received precise time to obtain the corresponding first local calibration time. At this time, the completed time synchronization is hardware synchronization; the execution body without a second pulse signal interface needs to perform software synchronization. At this time, the controller sends a time message to the execution body again. The time information sent is the difference information of t1-t0. The local time t'1 of the controller corresponds to the completion moment when the controller sends the difference information to the execution body. The local time t3 of the execution body corresponds to the receiving moment when the execution body receives the difference information. It is recorded as the third moment. If the execution body calculates the specific value of t'1 at moment t3 and uses it to update the local time, the time synchronization can be completed. Therefore, t'1 is the second local calibration time of the execution body.

[0103] For example, for an actuator without a PPS signal interface, the precise time t0 of the controller is 0ns. The controller sends the precise time t0 to the actuator, and the local time t1 (10ns) of the controller corresponding to the completion time of sending the precise time, and the local time t2 (100ns) of the actuator corresponding to the receiving time of the precise time. The controller sends a time message to the actuator again, and the time message sent is the difference information of t1-t0. The local time t'1 (12ns) of the controller corresponding to the completion time of sending the difference information to the actuator, and the receiving time of the difference information by the actuator corresponds to the local time t3 of the actuator. The present invention does not specifically limit the time interval between the moment (t'1) when the controller sends again and the moment (t1) when it sends for the first time, and it can be set according to actual conditions. Since the moment of completion of the sending of the controller and the receiving time of the actuator are only known to each other, that is, the actuator only knows its own receiving time, and the controller only knows its own sending completion time. The controller knows its sending time interval (t'1-t1) in its own local system, and the actuator knows its receiving time interval (t3-t2) in its own local system. The time intervals of the controller and the executive are the same, that is, (t'1-t1=t3-t2). In this embodiment, the time calibration of the executive without the PPS signal interface is intended to calibrate the t3 moment of the executive to the t'1 moment of the controller. According to the formula t'1-t1=t3-t2, it can be deduced that t'1=t3-t2+t1. For the executive, the unknown number t1 can be obtained by adding the contents of the two transmissions (that is, t0+(t1-t0)=t1), so the executive can successfully complete the calibration of the local time at t3.

[0104] It can be seen that the second local calibration time is obtained by subtracting the second time from the third time and adding the first time, that is, the second local calibration time = the third time - the second time + the first time.

[0105] Different local calibration times are obtained to complete the local time calibration of the execution body, and then the time synchronization of the sensors in each execution body is performed according to the different local calibration times and the second pulse signal, so that the sensor sampling data has the same time source, supporting the subsequent fusion algorithm processing. The present invention does not specifically limit the synchronization of sensors in each execution body. One point that needs to be explained is that sensors are also divided into those with PPS interfaces and those without PPS interfaces. In the process of sensor synchronization, it is also necessary to consider the software synchronization and hardware synchronization of different interfaces.

[0106] As a preferred embodiment, controlling each actuator to synchronize multiple sensors in each actuator according to the local calibration time and the pulse per second signal to obtain sampling data includes:

[0107] If the current execution body is an execution body without a pulse-per-second signal interface, construct a pulse-per-second signal in the current execution body and send it to multiple sensors in the current execution body;

[0108] Determine whether each sensor has a pulse per second signal interface;

[0109] If it exists, the local calibration time and the pulse-per-second signal are sent to the sensor having the pulse-per-second signal interface to obtain the first sampling data;

[0110] If it does not exist, a corresponding synchronous pulse signal is constructed according to the sampling period of the sensor without the pulse-per-second signal interface, the pulse-per-second signal and the frequency multiplier, wherein the period of the synchronous pulse signal is the same as the sampling period of the sensor without the pulse-per-second signal interface;

[0111] triggering a sensor without a pulse per second signal interface according to the synchronization pulse signal to obtain second sampling data;

[0112] If the current execution body has a pulse-per-second signal interface, the pulse-per-second signal is sent to multiple sensors in the current execution body, and the process returns to the step of determining whether there is a pulse-per-second signal interface in multiple sensors to determine the sampling data.

[0113] The method of triggering a sensor without a pulse per second signal interface according to the synchronization pulse signal to obtain second sampling data specifically includes:

[0114] Get the data transmission time corresponding to the sensor that does not have a second pulse signal interface;

[0115] Determine the sampling time of the sensor without the pulse per second signal interface according to the relationship between the local time when the current execution body receives the second initial sampling data and the data transmission time to determine the corresponding sampling timestamp;

[0116] Adding the sampling timestamp to the corresponding second initial sampling data of the sensor without the pulse per second signal interface to obtain the second sampling data;

[0117] Specifically, the current execution body is obtained, and it is determined whether the current execution body is an execution body with a second pulse signal interface. If the execution body does not have a second pulse signal interface, it is necessary to simulate and construct a second pulse signal by software. Specifically, a second pulse signal is constructed in the current execution body. The second pulse signal at this time is the same as the second pulse signal in step S11 and is sent to multiple sensors in the current execution body. Further, it is determined whether there is a PPS signal interface in multiple sensors. If so, the local calibration time and the constructed PPS signal are sent to the sensor with the second pulse signal interface to obtain the corresponding first sampling data.

[0118] It should be noted that, in determining whether each sensor has a pulse-second signal interface, since the number of sensors is uncertain, the determination step can be completed for all sensors. For sensors with pulse-second signal interfaces, the first sampling data can be obtained by locally calibrating the time and the pulse-second signal, and for sensors without pulse-second signal interfaces, a synchronous pulse signal can be constructed to obtain the second sampling data. Alternatively, it can be determined whether a pulse-second signal interface exists for the current sensor. If so, the first sampling data can be obtained by locally calibrating the time and the pulse-second signal. If not, the second sampling data can be obtained by constructing a synchronous pulse signal. After the sensor obtains the sampling data, it is determined again whether the next current sensor has a pulse-second signal interface, until the sampling data of the last sensor is obtained.

[0119] For sensors without PPS signal interface, it is necessary to construct corresponding synchronous pulse signals according to the sampling period of each sensor, the constructed second pulse signal and the frequency multiplier. The frequency of the output signal of the frequency multiplier is an integer multiple of the input signal frequency, that is, the signal spectrum can be moved to a higher frequency band by multiples. For this embodiment, multiple pulse signals can be formed within 1s. The synchronous pulse signal can be obtained according to the sampling period of each sensor, using the constructed second pulse signal and the frequency multiplier.

[0120] It should be noted that there are two sampling modes for sensors, triggered sampling and automatic sampling. In order to obtain accurate time, the executive body does not need the sensor to sample by itself, but needs to trigger sampling at a fixed time. At this time, the timing requires the executive body to send a message within a fixed time, and trigger the sensor to sample according to the sampling cycle and the constructed synchronization pulse signal. The period of the synchronization pulse signal is the same as the sampling period of the sensor. The present invention does not make a specific limitation on the multiplication number of the frequency multiplier, which can be set according to actual conditions.

[0121] The sensor is triggered according to the constructed synchronization pulse signal to obtain the corresponding second initial sampling data. At the same time, the data transmission time corresponding to the sensor is obtained, and the local time when the execution body receives the second initial sampling data is subtracted from the data transmission time to obtain the sampling time, and the sampling time is the sampling timestamp corresponding to the sensor, and the obtained sampling timestamp is added to the second initial sampling data to obtain the corresponding second sampling data.

[0122] If the current execution body is an execution body with a PPS signal interface, the PPS signal is sent to multiple sensors of the current execution body, and then the judgment step is the same as the above-mentioned sensor judgment step, and it is necessary to return to the step of judging whether there is a second pulse signal interface in multiple sensors.

[0123] Figure 2 A schematic diagram of an application of multi-execution in vivo sensor time synchronization provided by an embodiment of the present invention, such as Figure 2 As shown in the figure, the laser radar in the sensor itself has a PPS signal interface. The actuator sends the local calibration time and PPS signal to the laser radar, which performs time calibration based on this, and then collects data and sends it to the actuator. The camera and millimeter-wave radar do not have a PPS signal interface. The actuator uses the PPS signal and the frequency multiplier to construct a synchronous pulse signal with the same period as the sampling period according to the sampling period of the camera or millimeter-wave radar to trigger the camera or millimeter-wave radar to sample. After the collected data is sent to the actuator, the sampling time is obtained by subtracting the data transmission time from the local time of the actuator, and a sampling timestamp is added.

[0124] For the actuator 3 with a PPS interface, hardware synchronization is achieved through precise time and PPS signals; for the actuators 1 and 2 without a PPS interface, software synchronization is achieved through precise time.

[0125] Furthermore, the executive body on which the executive body proxy module relies may have a PPS interface, such as executive body 3, or may not have a PPS interface, such as executive bodies 1 and 2. The executive body proxy module may be a software program loaded by the controller inside the executive body to realize time synchronization, etc. The sensor inside the executive body module may be a separate camera, such as executive body 2, a combination of a camera and a millimeter-wave radar, such as executive body 1, or a combination of a camera, a millimeter-wave radar and a laser radar, such as executive body 3. The executive body uses a second pulse signal and different frequency multipliers to send corresponding synchronization pulse signals according to the sampling periods of the camera and the millimeter-wave radar to trigger the camera and the millimeter-wave radar to sample. After the collected data is sent to the executive body, the sampling time is obtained by subtracting the data transmission time from the local time of the executive body, and a sampling timestamp is added to complete the time synchronization of the sensors inside the executive body.

[0126] The embodiment of the present invention provides a method for performing time synchronization on multiple sensors in each execution body according to the precise time and the second pulse signal to obtain the sampling data of multiple sensors. For the determination of the local calibration time of the execution body synchronized by software, the local calibration of the execution body is first implemented before the sensor synchronization calibration is performed, thereby improving the accuracy of the time synchronization of the sensor. When the sensor is synchronized by software, a synchronous pulse signal with the same sampling period as the sensor is constructed according to the PPS signal and the frequency multiplier, so that the sensor sampling data has the same clock source, which is convenient for subsequent sampling data processing.

[0127] Based on the above embodiment, the step S13 of analyzing and processing the sampled data to obtain the execution results of each execution body includes:

[0128] Receive sampling data corresponding to the plurality of sensors in the current execution body;

[0129] The sampling data are fused through a fusion algorithm to obtain an initial execution result;

[0130] Determine the timestamp corresponding to the initial execution result according to the data sampling time corresponding to each sampled data;

[0131] The timestamp is added to the initial execution result to obtain the execution result of the current execution body.

[0132] Specifically, the current execution body receives various sampled data with the same time source, and then fuses the sampled data through a fusion algorithm to obtain an initial execution result. Since the current execution body does not mark the fusion execution result of the sensor fusion processing, it is necessary to determine its timestamp based on its data sampling time, and then add the timestamp to the initial execution result to complete the execution result of the current execution body.

[0133] The present invention does not specifically limit the fusion algorithm. It can be predicted to the same time based on the data sampling time of each sensor in the current execution body, and the same time is used as the timestamp.

[0134] The present invention provides the method of analyzing and processing the sampled data to obtain the execution results of each execution body, taking into account the time synchronization of the data processing process and the data transmission process, and then obtaining the execution result of the current execution body, thereby providing a guarantee for the time synchronization between subsequent multiple execution bodies.

[0135] Based on the above embodiment, the step S14 of predicting the execution results of each execution body to the same time to complete the time synchronization of the vehicle includes:

[0136] Obtain the current execution result of each execution body and the timestamp of the current execution result according to a preset period;

[0137] Calculate each time difference based on the timestamp of each current execution result and the current time corresponding to the preset period;

[0138] Select the timestamp corresponding to the minimum time difference as the reference time;

[0139] Determine the corresponding difference time according to the relationship between the reference time and the timestamp corresponding to the current execution result of each execution body;

[0140] The reference time is taken as the same moment, and the execution results of each execution body are predicted to the same moment according to each difference time to obtain the corresponding current predicted execution result to complete the time synchronization of the vehicle.

[0141] Specifically, first find the timestamp corresponding to the execution result of the execution body in the storage unit with the smallest difference with the current time as the reference time, then calculate the difference between this reference time and the timestamp of the execution result of other execution bodies in the storage unit, and finally predict each execution result according to the difference to obtain the execution result of the reference time, complete the software synchronization, and send out the synchronized execution result set. It should be noted that there is no specific limitation on the prediction method for predicting to the same time, and it can be through a prediction model or a filtering method. As an embodiment, the execution results of each execution body provided in this embodiment can be predicted to the same time through the Kalman filtering method to complete the time synchronization of the vehicle.

[0142] For example, the preset period is 50ms, that is, the execution result in the memory is obtained every 50ms. If the system obtains the execution result at the 100th ms, this time corresponds to the current time (this time is the local time of the vehicle time synchronization unit, that is, the precise time after calibration), and the execution results of the obtained execution bodies A, B, and C correspond to timestamps of 80ms, 90ms, and 95ms, respectively. Then, according to the difference between the current time and each timestamp, the timestamp corresponding to the minimum time difference is found, that is, 95ms, and the timestamp is selected as the reference time. It is further determined that the difference between the execution body A and the reference time is 15ms, and the difference between the execution body B and the reference time is 5ms. Then, the execution results of the execution bodies A and B are predicted to this reference time according to the time difference to complete software synchronization.

[0143] The execution result of each execution body is stored in the corresponding storage unit, and each time the execution result sent by the execution body is received, it will be overwritten and updated to the corresponding storage unit. The current execution result of each execution body is obtained according to the preset period, and the nearest timestamp in the current time corresponding to the preset period is obtained in the current execution result as the reference time.

[0144] The embodiment of the present invention provides a method for predicting the execution results of each actuator to the same time to complete the time synchronization of the vehicle. Based on the same time reference (same time), the accuracy of time synchronization between multiple actuators is improved, so that the safety and effectiveness of the automatic driving redundant multi-executor technology are greatly improved.

[0145] Based on the above embodiment, after the execution results in step S14 are predicted to the same time, the following further includes:

[0146] Output the current prediction execution results in a collection form for subsequent processing.

[0147] Specifically, the current prediction execution results collected within each preset period are sent out in the form of a collection to facilitate subsequent data processing by the staff.

[0148] The embodiment of the present invention provides outputting the current prediction execution result in a set form for subsequent processing. After completing the time synchronization of the redundant multi-executors of the autonomous driving, it is also convenient for the subsequent data processing of the execution result to improve safety.

[0149] The above describes in detail various embodiments corresponding to the vehicle time synchronization method. On this basis, the present invention also discloses a vehicle time synchronization device corresponding to the above method. Figure 3 FIG. 1 is a structural diagram of a vehicle time synchronization device provided by an embodiment of the present invention. Figure 3 As shown, the time synchronization device of the vehicle includes:

[0150] The calibration module 11 is used to obtain the standard time and pulse-per-second signal of the vehicle-mounted satellite navigation, and calibrate the standard time and pulse-per-second signal to obtain the precise time;

[0151] A sensor synchronization module 12 is used to synchronize the time of multiple sensors in each execution body according to the precise time and the second pulse signal to obtain the sampling data of the multiple sensors;

[0152] The analysis and processing module 13 is used to analyze and process the sampled data to obtain the execution results of each execution body;

[0153] The execution body synchronization module 14 is used to predict the execution results of each execution body to the same time to complete the time synchronization of the vehicle.

[0154] Since the embodiments of the device part correspond to the above embodiments, please refer to the description of the embodiments of the method part for the embodiments of the device part, and will not be repeated here.

[0155] The embodiment of the present invention provides a time synchronization device for a vehicle, including obtaining the standard time and second pulse signal of the vehicle-mounted satellite navigation, and calibrating according to the standard time and second pulse signal to obtain the precise time; performing time synchronization on multiple sensors in each actuator according to the precise time and second pulse signal to obtain the sampling data of multiple sensors; analyzing and processing the sampling data to obtain the execution results of each actuator; and predicting the execution results of each actuator to the same time to complete the time synchronization of the vehicle. In addition to completing the time synchronization of multiple sensors inside the actuator, the device also realizes the time synchronization between actuators, so that after the clock synchronization of the sensor, the subsequent sampling data of the sensor is obtained by analyzing and processing the execution results of each actuator, and then the software synchronization prediction based on the execution results of the actuator is predicted to the same time, all based on the same time reference, thereby improving the accuracy of time synchronization between multiple actuators, and greatly improving the safety and effectiveness of the redundant multi-executor technology of autonomous driving.

[0156] Figure 4 A structural diagram of another vehicle time synchronization device provided by an embodiment of the present invention, such as Figure 4 As shown, the device comprises:

[0157] A memory 21, used for storing computer programs;

[0158] The processor 22 is used to implement the steps of the vehicle time synchronization method when executing the computer program.

[0159] The vehicle time synchronization device provided in this embodiment may include but is not limited to a smart phone, a tablet computer, a laptop computer, or a desktop computer.

[0160] Among them, the processor 22 may include one or more processing cores, such as a 4-core processor, an 8-core processor, etc. The processor 22 can be implemented in at least one hardware form of a digital signal processor (DSP), a field-programmable gate array (FPGA), and a programmable logic array (PLA). The processor 22 may also include a main processor and a coprocessor. The main processor is a processor for processing data in the awake state, also known as a central processing unit (CPU); the coprocessor is a low-power processor for processing data in the standby state. In some embodiments, the processor 22 may be integrated with a graphics processing unit (GPU), which is responsible for rendering and drawing the content to be displayed on the display screen. In some embodiments, the processor 22 may also include an artificial intelligence (AI) processor, which is used to process computing operations related to machine learning.

[0161] The memory 21 may include one or more computer-readable storage media, which may be non-transitory. The memory 21 may also include a high-speed random access memory, and a non-volatile memory, such as one or more disk storage devices, flash memory storage devices. In this embodiment, the memory 21 is at least used to store the following computer program 211, wherein, after the computer program is loaded and executed by the processor 22, it can implement the relevant steps of the vehicle time synchronization method disclosed in any of the aforementioned embodiments. In addition, the resources stored in the memory 21 may also include an operating system 212 and data 213, etc., and the storage method may be temporary storage or permanent storage. Among them, the operating system 212 may include Windows, Unix, Linux, etc. The data 213 may include, but is not limited to, data involved in the vehicle time synchronization method, etc.

[0162] In some embodiments, the time synchronization device of the vehicle may further include a display screen 23 , an input / output interface 24 , a communication interface 25 , a power supply 26 , and a communication bus 27 .

[0163] Those skilled in the art can understand that Figure 4 The structure shown in the figure does not constitute a limitation on the time synchronization device of the vehicle, and may include more or less components than those shown in the figure.

[0164] The processor 22 implements the vehicle time synchronization method provided by any of the above embodiments by calling the instructions stored in the memory 21 .

[0165] For an introduction to the structural diagram of a vehicle time synchronization device provided by the present invention, please refer to the above method embodiment, and the present invention will not be repeated here. It has the same beneficial effects as the above vehicle time synchronization method.

[0166] Furthermore, the present invention also provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by the processor 22, the steps of the vehicle time synchronization method as described above are implemented.

[0167] It is understandable that if the method in the above embodiment is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk and other media that can store program code.

[0168] For an introduction to a computer-readable storage medium provided by the present invention, please refer to the above method embodiment, which will not be described in detail herein. It has the same beneficial effects as the above vehicle time synchronization method.

[0169] As an example, Figure 5 A structural diagram of a vehicle time synchronization device provided by another embodiment of the present invention, such as Figure 5 As shown, the device includes a vehicle-mounted satellite navigation timing module 31, a time synchronization module 32 and an executive agent module 33;

[0170] The vehicle-mounted satellite navigation timing module 31 is connected to the other modules to provide time information data and second pulse signals, which can be a GPS timing module or a Beidou timing module;

[0171] The time synchronization module 32 is equivalent to the controller of the present invention, that is, Figure 2The controller is connected to the execution body proxy module 33, and the time information data of the vehicle-mounted satellite navigation timing module 31 is obtained and analyzed, so as to calibrate the time of each execution body according to the analyzed time, and make predictions according to the execution results fed back by the execution body proxy module 33, so as to realize software synchronization; wherein, for the execution body with the hardware interface of the second pulse signal, the time synchronization module 32 realizes hardware synchronization by analyzing the time and the second pulse signal; for the execution body without the hardware interface of the second pulse signal, the time synchronization module 32 realizes software synchronization by analyzing the time;

[0172] The execution body proxy module 33 is deployed inside the execution body, and is used to obtain the analysis time sent by the time synchronization module 32 and the second pulse signal sent by the vehicle-mounted satellite navigation timing module 31, complete the time calibration of the execution body and the time synchronization of multiple sensors inside the execution body, and add the sampling timestamp to the execution result of the execution body and send it to the time synchronization module 32 to facilitate subsequent synchronization.

[0173] For an introduction to a structural diagram of a vehicle time synchronization device provided by another embodiment of the present invention and a flowchart of a vehicle time synchronization method provided by another embodiment of the present invention, please refer to the above method embodiment. The present invention will not be repeated here, and it has the same beneficial effects as the above vehicle time synchronization method.

[0174] The above is a detailed introduction to a vehicle time synchronization method, device and medium provided by the present invention. The various embodiments in the specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same and similar parts between the various embodiments can be referenced to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part description. It should be pointed out that for ordinary technicians in this technical field, without departing from the principle of the present invention, several improvements and modifications can be made to the present invention, and these improvements and modifications also fall within the scope of protection of the claims of the present invention.

[0175] It should also be noted that, in this specification, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "comprises", "comprising" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "comprising a ..." does not exclude the presence of other identical elements in the process, method, article or device including the element.

Claims

1. A vehicle time synchronization method, characterized in that: include: Obtaining the standard time and pulse-second signal of the vehicle-mounted satellite navigation, and calibrating according to the standard time and the pulse-second signal to obtain the precise time; Performing time synchronization on multiple sensors in each actuator according to the precise time and the second pulse signal to obtain sampling data of multiple sensors; Analyzing and processing the sampled data to obtain execution results of each of the execution bodies; Predicting the execution results of each of the execution bodies to the same time to complete the time synchronization of the vehicle; Correspondingly, analyzing and processing the sampled data to obtain the execution results of each of the execution bodies includes: Receiving the sampling data corresponding to the plurality of sensors in the current execution body; The sampling data are fused by a fusion algorithm to obtain an initial execution result; Determine the timestamp of the initial execution result according to the data sampling time corresponding to each of the sampled data; The timestamp is added to the initial execution result to obtain the execution result of the current execution body.

2. The vehicle time synchronization method according to claim 1, characterized in that: The calibrating according to the standard time and the second pulse signal to obtain the precise time comprises: Parse the standard time to obtain UTC time; Calibration is performed based on the pulse-per-second signal and the UTC time to obtain the precise time.

3. The vehicle time synchronization method according to claim 2, characterized in that: The step of performing time synchronization on multiple sensors in each execution body according to the precise time and the second pulse signal to obtain sampling data of multiple sensors includes: Calibrate the local time of each of the execution bodies according to the precise time and the second pulse signal to obtain the local calibration time; Each of the execution bodies is controlled to perform time synchronization on a plurality of the sensors in the respective execution bodies according to the local calibration time and the second pulse signal to obtain the sampling data.

4. The vehicle time synchronization method according to claim 3, characterized in that: The step of calibrating the local time of each of the execution bodies according to the precise time and the second pulse signal to obtain the local calibration time specifically includes: Sending the precise time to each of the executors, and recording the moment when the sending is completed as the first moment; Determine whether each of the execution bodies has a pulse per second signal interface; If it does not exist, sending the difference time to the execution body without the second pulse signal interface, wherein the difference time is the difference between the first time and the precise time; Controlling the execution body having the pulse-per-second signal interface to calibrate with the precise time according to the pulse-per-second signal to obtain a first local calibration time of the execution body having the pulse-per-second signal interface to complete hardware synchronization; The execution body without the second pulse signal interface is controlled to record the moment of receiving the precise time as the second moment, and the moment of receiving the difference moment as the third moment. The second local calibration time of the execution body without the second pulse signal interface is determined according to the relationship between the third moment, the second moment and the first moment to complete software synchronization.

5. The vehicle time synchronization method according to claim 4, characterized in that: The controlling each of the execution bodies to synchronize the time of the multiple sensors in the respective execution bodies according to the local calibration time and the second pulse signal to obtain the sampling data comprises: If the current execution body is an execution body without the pulse-per-second signal interface, constructing the pulse-per-second signal in the current execution body and sending it to multiple sensors in the current execution body; Determine whether each of the sensors has the pulse per second signal interface; If it exists, sending the local calibration time and the pulse-per-second signal to a sensor having the pulse-per-second signal interface to obtain first sampling data; If it does not exist, construct a corresponding synchronization pulse signal according to the sampling period of the sensor without the second pulse signal interface, the second pulse signal and the frequency multiplier, wherein the period of the synchronization pulse signal is the same as the sampling period of the sensor without the second pulse signal interface; triggering a sensor without the pulse per second signal interface according to the synchronization pulse signal to obtain second sampling data; If the current execution body is an execution body having the pulse-per-second signal interface, the pulse-per-second signal is sent to multiple sensors in the current execution body, and the process returns to the step of determining whether the pulse-per-second signal interface exists in the multiple sensors to determine the sampling data.

6. The vehicle time synchronization method according to claim 5, characterized in that: The step of triggering a sensor without the pulse per second signal interface according to the synchronization pulse signal to obtain second sampling data includes: Acquire the data transmission time corresponding to the sensor that does not have the pulse per second signal interface; Determine the sampling time of the sensor without the pulse per second signal interface according to the relationship between the local time when the current execution body receives the second initial sampling data and the data transmission time to determine the corresponding sampling timestamp; The sampling timestamp is added to the second initial sampling data of the corresponding sensor without the pulse per second signal interface to obtain the second sampling data.

7. The vehicle time synchronization method according to any one of claims 1 to 6, characterized in that: The step of predicting the execution results of each of the actuators to the same time to complete the time synchronization of the vehicle includes: Acquire the current execution result of each of the execution bodies and the timestamp of the current execution result according to a preset period; Calculate each time difference according to the timestamp of each current execution result and the current time corresponding to the preset period; Select the timestamp corresponding to the minimum time difference as the reference time; Determine the corresponding difference time according to the relationship between the reference time and the timestamp corresponding to the current execution result of each of the execution bodies; The reference time is taken as the same moment, and the execution results of each of the execution bodies are predicted to the same moment according to each of the difference times to obtain the corresponding current predicted execution results to complete the time synchronization of the vehicle.

8. The vehicle time synchronization method according to claim 7, characterized in that: After the execution result is predicted to the same time, the method further includes: The current prediction execution result is output in a set form for subsequent processing.

9. A time synchronization device for a vehicle, characterized in that: include: A calibration module, used to obtain the standard time and pulse-per-second signal of the vehicle-mounted satellite navigation, and calibrate according to the standard time and the pulse-per-second signal to obtain the precise time; A sensor synchronization module, used for performing time synchronization on a plurality of sensors in each execution body according to the precise time and the second pulse signal to obtain sampling data of a plurality of the sensors; An analysis and processing module, used for analyzing and processing the sampled data to obtain the execution results of each of the execution bodies; An execution body synchronization module, used for predicting the execution results of each execution body to the same time to complete the time synchronization of the vehicle; Correspondingly, analyzing and processing the sampled data to obtain the execution results of each of the execution bodies includes: Receiving the sampling data corresponding to the plurality of sensors in the current execution body; The sampling data are fused by a fusion algorithm to obtain an initial execution result; Determine the timestamp of the initial execution result according to the data sampling time corresponding to each of the sampled data; The timestamp is added to the initial execution result to obtain the execution result of the current execution body.

10. A time synchronization device for a vehicle, characterized in that: include: Memory for storing computer programs; A processor, configured to implement the steps of the vehicle time synchronization method as claimed in any one of claims 1 to 8 when executing the computer program.

11. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the vehicle time synchronization method according to any one of claims 1 to 8 are implemented.

Images