CN115655748A - Multi-target motion event real-time measurement method and device, equipment and medium - Google Patents

Abstract

The application provides a method, a device, equipment and a medium for measuring a multi-target motion event in real time, which are applied to the technical field of automatic driving, wherein the method for measuring the multi-target motion event in real time comprises the following steps: acquiring logic data of a plurality of target vehicles in a measurement scene; and determining whether the motion event meets a trigger condition or not according to the logic data and measurement demand data of a preset motion event, and if so, outputting a motion event trigger signal to enable the multiple target vehicles to execute motion corresponding to the motion event trigger signal so as to form a real-time traffic flow in the measurement scene. By combining the logic data and the test case data in real time in the predefined test scenes for judgment, the required virtual dynamic traffic flow can be effectively provided for various test scenes of the vehicle through simple data processing, so that accurate real-time measurement is realized, the real-time measurement scheme is simple, and the implementation cost is low.

Description

Multi-target motion event real-time measurement method and device, equipment and medium

Technical Field

The application relates to the technical field of automatic driving, in particular to a method, a device, equipment and a medium for measuring a multi-target motion event in real time.

Background

The method is an essential means for acquiring the real driving condition of the target vehicle in the scenes of ADAS (Advanced Driver Assistance System), automatic driving test, verification, inspection and the like, and is also a common means for researching and analyzing the traffic accidents of the target vehicle. Therefore, in a dynamic traffic scene where the target vehicle is located, there is also a need for one or more background vehicles capable of being automatically controlled (or controlled), where the background vehicle used may be a real vehicle or a soft vehicle, and the background vehicle can strictly execute operations of various predefined elements (such as track, speed, acceleration, etc.) and trigger conditions (such as time, event, etc.), so as to provide a relatively real vehicle traffic flow for scenes such as ADAS test or automatic driving vehicle test, vehicle performance detection under regulation, verification, accident recurrence, etc. by placing the background vehicle in the dynamic traffic environment, that is, the dynamic traffic environment where the target vehicle is located can be relatively truly simulated, so as to verify the performance and function of the target vehicle in the ADAS test or automatic driving test.

Currently, in the application of the aforementioned scenario, almost all background vehicle event response controls are manually controlled. And manual control has the following defects:

on the one hand, manual control not only increases the cost of the test but also increases the uncertainty of the test, and manual control is absolutely not allowed for regulatory-type tests. On the other hand, this type of test also requires the addition of a large number of other measuring devices in the field, or the installation of complex sensors on background vehicles, such as high-effort autopilot controllers. On the other hand, facilities for testing the relative distance between the background vehicle and the host vehicle (i.e., the target vehicle) are necessary, and uncertainty of the traveling of the host vehicle and speed control error of the background vehicle cause great difficulty in measuring the relative distance.

In addition, if a dynamic traffic scene needing to be tested relates to more background vehicles, the dynamic traffic scene can hardly be realized by means of manual operation, and if the dynamic traffic scene needs to be tested is ensured by other measurement means, the whole test system is very complex and huge, so that the process of the whole system is uncontrollable, the field test of the automatic driving at present can only use a simple test case, the complex scene can only depend on simulation or public road experiments, the result obtained by the simulation possibly deviates from real data, a real test result cannot be obtained, and the public road test is also very difficult to develop due to the limitations of safety, cost, regulations and the like.

Therefore, in various current applications, such as performance detection and verification of an autonomous vehicle, vehicle accident recovery, etc., all of which are limited by the dynamic traffic flow provided by the existing schemes and are difficult to obtain the actual situation of the vehicle, a new scheme capable of generating the dynamic traffic flow based on a multi-target motion event and performing real-time measurement is needed.

Disclosure of Invention

In view of this, embodiments of the present disclosure provide a method, an apparatus, a device, and a medium for measuring a multi-target motion event in real time, which can provide an accurate dynamic traffic flow, reduce the difficulty of a scheme and the implementation cost, and improve the accuracy.

The embodiment of the specification provides the following technical scheme:

the embodiment of the specification provides a method for measuring a multi-target motion event in real time, which comprises the following steps:

acquiring logic data of a plurality of target vehicles in a measurement scene;

and determining whether the motion event meets a trigger condition or not according to the logic data and measurement demand data of a preset motion event, and if so, outputting a motion event trigger signal to enable the multiple target vehicles to execute motion corresponding to the motion event trigger signal so as to form a real-time traffic flow in the measurement scene.

An embodiment of the present specification further provides a device for measuring multiple target motion events in real time, including:

the logic data acquisition unit is used for acquiring logic data of a plurality of target vehicles in a measurement scene;

the motion event judging unit is used for determining whether the motion event meets the triggering condition or not according to the logic data and the measurement requirement data of the preset motion event;

and the triggering unit is used for outputting a motion event triggering signal when the motion event judging unit determines that the motion event meets the triggering condition, so that the target vehicles execute the motion corresponding to the motion event triggering signal to form a real-time traffic flow in the measuring scene.

Compared with the prior art, the embodiment of the specification adopts at least one technical scheme which can achieve the beneficial effects that at least:

in a predefined test scene (such as a virtual scene based on a real-scene high-precision map), according to predefined motion events (such as test cases and data required by measurement thereof) and logic data information, which is acquired in real time, of all background vehicles and corresponding to the host vehicle in the measurement scene, the motions of the background vehicles and the host vehicle are controlled, so as to construct a real traffic flow (namely a dynamic traffic flow required by the test) required by the test cases, and thus, a full field Jing Yaosu of the whole traffic test scene can be obtained, and real-time measurement can be performed by using the full-scene elements. Therefore, the test control is carried out based on the motion event, a perception module which consumes computational power is not needed, only a very simple and efficient automatic driving path planning algorithm and a decision algorithm are used, namely all background vehicles which participate in the traffic can carry out path planning and decision control according to a preset mode, further based on logic data and measurement required data of all vehicles, when the motion event is determined to meet a trigger condition, a motion event trigger signal is output, so that a decision instruction corresponding to each vehicle can be formed by using the trigger signal, the background vehicle control is realized after the vehicle executes the instruction, the multi-vehicle cooperative driving control of the background vehicles can be realized, a closed-loop test can be formed, and a required virtual dynamic traffic scene can be provided for scenes such as ADAS test, automatic driving test, accident analysis, vehicle performance detection under regulation, verification and the like.

Moreover, since the virtual scene includes the full field Jing Yaosu of the test scene (such as static traffic elements and dynamic traffic elements), the aforementioned motion events of the background vehicles can be easily calculated by a simple program, so that the response capability of the background vehicles can be automatically realized very easily, and the response capability can be applied to any number of background vehicles.

Therefore, the real-time test is carried out based on the multi-target motion event, the automation of the simulation of the dynamic traffic scene can be realized, various complex dynamic traffic scenes can be truly reproduced, and the consistency and the authenticity of the test of the dynamic traffic scene are ensured. Meanwhile, the scheme can realize the cooperative control of background vehicles with unlimited quantity, thereby greatly reducing the cost of simulating the dynamic traffic scene and enhancing the simulation capability of the dynamic traffic scene.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings needed to be used in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.

FIG. 1 is a schematic diagram of a host vehicle and a background vehicle in vehicle performance detection;

FIG. 2 is a schematic illustration of a motion event measurement;

FIG. 3 is a schematic diagram of a real-time measurement of multiple target motion events;

FIG. 4 is a flow chart of real-time measurement of multiple target motion events;

FIG. 5 is a flow chart of parameter calculation in real-time measurement of multi-target motion events;

FIG. 6 is a schematic structural diagram of a real-time measurement device for multiple target motion events;

FIG. 7 is a schematic diagram of a system application architecture for real-time measurement of multiple target motion events;

FIG. 8 is a schematic diagram of a system application architecture for real-time measurement of multiple target motion events;

FIG. 9 is a flow diagram of virtual synchronization in real-time measurement of multi-object motion events;

FIG. 10 is a flow chart of multi-vehicle coordination in real-time measurement of multi-target motion events;

FIG. 11 is a flow chart of motion event triggering and execution in real-time measurement of multiple object motion events.

Detailed Description

The embodiments of the present application will be described in detail below with reference to the accompanying drawings.

The following description of the embodiments of the present application is provided by way of specific examples, and other advantages and effects of the present application will be readily apparent to those skilled in the art from the disclosure herein. It is to be understood that the embodiments described are only a few embodiments of the present application and not all embodiments. The present application is capable of other and different embodiments and its several details are capable of modifications and/or changes in various respects, all without departing from the spirit of the present application. It is to be noted that the features in the following embodiments and examples may be combined with each other without conflict. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.

It is noted that various aspects of the embodiments are described below within the scope of the appended claims. It should be apparent that the aspects described herein may be embodied in a wide variety of forms and that any specific structure and/or function described herein is merely illustrative. Based on the present application, one skilled in the art should appreciate that one aspect described herein may be implemented independently of any other aspects and that two or more of these aspects may be combined in various ways. For example, an apparatus may be implemented and/or a method practiced using any number and aspects set forth herein. Additionally, such an apparatus may be implemented and/or such a method may be practiced using other structure and/or functionality in addition to one or more of the aspects set forth herein.

It should be noted that the drawings provided in the following embodiments are only for illustrating the basic idea of the present application, and the drawings only show the components related to the present application rather than the number, shape and size of the components in actual implementation, and the type, amount and ratio of the components in actual implementation may be changed arbitrarily, and the layout of the components may be more complicated.

In addition, in the following description, specific details are provided to facilitate a thorough understanding of the examples. However, it will be understood by those skilled in the art that the invention may be practiced without these specific details.

As shown in fig. 1, in the performance detection of vehicles based on the "GB/T20608-2006 adaptive cruise control system performance requirement and detection method", a test vehicle 1 (which may also be referred to as a tested vehicle, a host vehicle, etc.) and background vehicles (such as a first background vehicle 2 and a second background vehicle 3 in the figure) are in the same dynamic traffic environment, where the two background vehicles run in the same direction at the same speed in front of the test vehicle, and the test vehicle and the first background vehicle 2 are in stable driving operation in the same lane (which may be driving operation in an automatic driving test or ADAS test).

In the actual test process, the background vehicle used can be a real vehicle or a soft vehicle, but the background vehicle must be capable of executing at least two types of control of trajectory tracking and event response, wherein the trajectory tracking refers to moving according to preset instructions such as trajectory, speed and acceleration, and is usually realized by the automatic driving function or the trajectory tracking function of the background vehicle; an incident response may refer to a background vehicle being able to maneuver according to corresponding instructions when a dynamic traffic scenario meets certain conditions.

Taking "slow front vehicle cut-in recognition and response of adjacent lane of straight road" in ADAS test as an example, as shown in fig. 2, the working process is briefly described as follows: the background vehicle 20 and the test host-vehicle 10 run in adjacent lanes, wherein the test host-vehicle 10 runs at a vehicle speed of 30km/h, the background vehicle 20 runs in front of the test host-vehicle 10 at a speed of 20km/h, the background vehicle 20 cuts into the host-vehicle lane when the distance between the background vehicle 20 and the test host-vehicle 10 is 8 meters, and the running at the speed of 20km/h is maintained. In this test scenario, the "event" is "when the distance between the background vehicle and the host vehicle is 8 meters", and the "maneuver" of the background vehicle 20 is "cutting into the host vehicle lane".

In the prior art, when an ADAS test or an automatic driving test is performed, event response control on all background vehicles is generally manually controlled, and manual control not only increases the test cost, but also increases the test uncertainty; also, a large number of other measuring devices, such as a facility capable of measuring the relative distance and the relative movement speed of the target vehicle, or an automatic driving range controller with high calculation power installed on the target vehicle, are required in the field, which not only requires high cost, but also causes great difficulty in measuring the relative distance due to uncertainty in traveling and speed control error of the target vehicle.

In view of the above, the inventor provides a multi-target motion event real-time measurement scheme by deeply researching, improving and exploring a dynamic traffic environment simulation scheme and various digital twin technologies: as shown in fig. 3, in the test scenario, the motion event measurement device (e.g. a remote server) may obtain, in real time, logical data corresponding to geographic location information of all moving objects participating in the test scenario, such as absolute location data of the moving objects (e.g. moving object 1 to moving object n in the figure), and the motion event measurement device may combine these logical data with measurement requirement data required by the moving objects in the test scenario, that is, with preset motion events and their response requirements, such as conditions (e.g. relative location, relative speed, etc.) for triggering occurrence of the motion events in the test case, automatically calculate in real time, and determine whether the motion events meet the trigger conditions in real time according to the calculation result, and once it is determined that the trigger conditions are met, the motion event measurement device outputs, in real time, a motion event trigger signal related to the motion events for each moving object in the scenario, so that each moving object performs motion corresponding to the motion event trigger signal, such as path planning, decision, and the like control, thereby implementing multi-vehicle cooperative measurement control of multiple background vehicles in the scene, thereby constructing a dynamic traffic flow data in real time, and forming a dynamic test scenario.

Therefore, based on the multi-target motion event, the motion data between the motion targets in the test scene can be calculated in real time according to the logic data of the information of the area in which the motion target is located in the scene, so that whether the motion event required by the test meets the trigger condition or not can be determined according to the data, and a trigger signal is sent to the motion target needing to execute the motion event when the motion event is triggered, so that the motion target executes the motion corresponding to the motion event, such as path planning, decision making and the like required by a vehicle in a dynamic traffic scene. Because the test scene is a service end (such as a server) which is constructed based on a high-precision map and contains all scene elements, the moving object can be a real vehicle and can also be a soft vehicle arranged in the service end, so that in the scheme, only a positioning device is required to be configured on each vehicle, positioning data is sent to the server, expensive sensing devices are not required to be configured on each vehicle, virtual sensors are not required to be configured on each virtual vehicle in the server, high-calculation sensing calculation with high calculation power is not required to be carried out by the server, automatic simulation of the dynamic traffic flow of the moving object in the test scene is very conveniently realized, various complex dynamic traffic scenes can be truly reproduced, the simulated dynamic traffic flow meets the requirements of various tests on the tested vehicles, and the consistency and the authenticity of the tests are improved.

It should be noted that, because each vehicle only needs to provide its own high-precision positioning data, and no other complex data (such as driving state, control behavior, etc.) of the vehicle is needed, the solution can implement multiple vehicle cooperation without limitation in quantity, not only can greatly reduce the cost of dynamic traffic scene simulation, but also can enhance the simulation capability of dynamic traffic scenes, such as simulation of any complex dynamic traffic scene, and enhance the test capability.

The technical solutions provided by the embodiments of the present application are described below with reference to the accompanying drawings.

As shown in fig. 4, an embodiment of the present specification provides a method for measuring multiple target motion events in real time, which may include:

and step S202, acquiring logic data of a plurality of target vehicles in a measuring scene. The logical data may refer to geographic information data of an area where a moving object (i.e., a target vehicle) in a scene map is located in a test scene, for example, positioning data of a real vehicle in the test scene running on a server, that is, coordinate data corresponding to the real vehicle reflected in a high-precision map in the server, and for example, coordinate data corresponding to a soft vehicle in the high-precision map in the server, and the like. It should be noted that the logic data may include position data and/or speed data, so as to quickly determine whether the current movement of the moving object may trigger a corresponding movement event according to the logic data of the moving object in combination with the data required for triggering the measurement of the preset movement event.

In the implementation, the logic data of the moving object is corresponding logic data in a high-precision map used by the moving object in a test scenario, and the data may be positioning data corresponding to absolute positioning data of a real vehicle in the test in an electronic map, or may be positioning data corresponding to a virtual soft vehicle in the test scenario in the electronic map by a server.

Step S204, determining whether the motion event meets a trigger condition according to the logic data and the measurement requirement data of the preset motion event, and executing step S206 if the motion event meets the trigger condition.

In implementation, the logic data of each moving target is combined with the measurement requirement data corresponding to the moving event required by the test, and whether the moving event meets the trigger condition or not can be quickly determined through simple calculation and comparison.

It should be noted that, in a test scenario, it is necessary to construct a dynamic traffic flow required by a test for a vehicle to be tested according to motions being performed by other moving targets and accordingly triggering related targets to perform corresponding actions, where a triggered event may be referred to as a motion event, and a corresponding trigger signal may be referred to as a motion event trigger signal.

And S206, outputting a motion event trigger signal to enable the plurality of target vehicles to execute the motion corresponding to the motion event trigger signal so as to form a real-time traffic flow in the measurement scene.

In implementation, by sending motion event trigger signals to the moving objects which need to execute the test-related actions, the moving objects will execute the related actions under the trigger of the motion event trigger signals. Thus, the triggered action may be a vehicle action related to a motion event, such as the aforementioned turning action of the background vehicle 20 cutting into the main lane of fig. 2.

Taking the foregoing example of fig. 2 as an example, the logic data may be: the test vehicle 10 is running at a speed of 30km/h in the test scene, the background vehicle 20 is running at a speed of 20km/h in the vicinity of the test vehicle 10 and in front of the test vehicle 10, and the position data of each vehicle is also logic data; the motion event may be: testing the cut-in recognition and response of the vehicle 10 to the low-speed front vehicle of the adjacent lane of the linear road; the measurement requirement data of the preset motion event may be: the background vehicle 20 and the test host vehicle 10 continue to run at various speeds, and the background vehicle 20 cuts into the host vehicle lane of the test host vehicle 10 and keeps running at a speed of 20 km/h; the trigger condition may be: the background vehicle 20 is not cut into the main lane, and is spaced from the test vehicle 10 by 8 meters back and forth. Thus, the logic data, motion events, and measurement requirement data are all related to the test requirements and are not limited herein.

Through the steps S202 to S206, the relevant logic data of the moving object is obtained in real time in the test scene, and then the logic data is simply compared with the data required for measuring the triggering motion event in the test in real time, and once it is determined that the motion event meets the triggering condition, a triggering signal is output, so that the relevant moving object executes the relevant motion under the triggering of the triggering signal, and thus a dynamic traffic flow required by the test is created for the test vehicle, and further the relevant test is performed based on the dynamic traffic flow, such as ADAS test, automatic driving test, accident recurrence and the like. Therefore, by providing a new background vehicle control technology, the event calculation can be automatically carried out at a remote server end through the collected vehicle high-precision positioning technology, the trigger signal required by the control instruction of the background vehicle is generated according to the set response requirement, the motion control of one or more background vehicles is automatically triggered, the automatic reappearance of the dynamic traffic scene is really realized, the test consistency is ensured, the manual deployment and implementation cost in the processes of ADAS test, automatic driving test and the like is greatly reduced, and the background vehicles which are not limited by the number are allowed to be used for constructing any complex dynamic traffic scene.

In some embodiments, high-precision positioning data of a moving object under test can be incorporated into a high-precision electronic map, thereby providing more accurate logical data.

In an implementation, acquiring the logic data of the plurality of target vehicles in the measurement scenario may include: and acquiring absolute positioning data of the geographical positions of the target vehicles by a high-precision positioning unit.

Specifically, a high-precision positioning unit may be installed in a vehicle, where the high-precision positioning unit may be a vehicle positioning unit that combines satellite positioning technology and IMU (inertial measurement unit) technology, and may acquire a dynamic position of the vehicle in real time (e.g., a data refresh frequency greater than 50 Hz), where the positioning precision may be on the centimeter level (e.g., ± 5 cm), and the acquired vehicle positioning information may include: longitude, latitude, altitude, course angle, pitch angle, roll angle, etc.

It should be noted that an Inertial measurement unit (IMU for short) may be used to measure three-axis attitude angles and accelerations of a vehicle, may include a plurality of components such as a three-axis gyroscope, a three-axis accelerometer, and a three-axis magnetometer, and may provide information such as vehicle position and attitude for a test scene, for example, angular velocities of three axes are measured by the gyroscope, accelerations of three axes are measured by the accelerometer, and orientation information is obtained by the magnetometer.

In one example, the high-precision positioning unit may be connected to a wire-controlled bus network of a real vehicle (e.g., a background vehicle, a vehicle under test), so that the positioning data may be quickly transmitted to a remote server based on the bus network.

In one example, the acquired high-precision positioning information may be sent to a motion event measurement device (e.g., a server for remote cooperative driving) via a low-latency wireless communication network, for example, the logic data provided by the target vehicle may be acquired via a wireless communication network with an air interface transmission latency of less than 20 ms. Specifically, the air interface delay of the wireless communication network is less than 20ms, and may be in the form of a point-to-multipoint or full-duplex wireless communication network, that is, the wireless communication network may be a point-to-multipoint high-speed data transmission radio network, or may be a 4G or 5G communication network. Therefore, the data is transmitted through the low-delay network, and the data is only positioning information occupying a very small bandwidth, so that the requirement of real-time measurement is met.

By acquiring high-precision absolute positioning data, the precision of logic data can be ensured, and the test accuracy is improved.

In some embodiments, after the absolute positioning data is obtained, the absolute positioning data may be subjected to data processing based on the same coordinate system, so as to obtain reference logic data required by real-time measurement.

In an implementation, after the absolute positioning data is obtained, determining a multi-moving object event parameter according to the absolute positioning data, wherein the multi-moving object event parameter includes: the corresponding absolute position and absolute movement speed of each target vehicle in a new reference coordinate system, the relative position, relative distance and relative movement speed among a plurality of target vehicles and the movement event time.

As shown in fig. 5, after obtaining the absolute positioning data of the vehicles, after performing coordinate transformation in the same coordinate system, corresponding processing may be performed on the data in the same coordinate system to obtain relevant logic data required by the test, for example, absolute position calculation may be performed, absolute position data corresponding to each vehicle may be obtained, for example, relative position calculation may be performed to obtain relative position data between each vehicle, for example, relative distance calculation may be performed to obtain relative distance data between vehicles, for example, absolute movement parameter calculation may be performed to obtain absolute movement speed of the vehicles, for example, relative movement speed calculation may be performed to obtain relative movement speed between vehicles, for example, time recording may be performed to record the time when a movement event occurs, and the like.

After the logic data is obtained, the logic data and the motion event measurement requirement data can be combined to judge the motion event, and when the motion event meets the trigger condition, a motion event trigger signal is output.

In some embodiments, the multi-target motion event real-time measurement scheme provided by the invention can be used for providing an automatic background vehicle multi-vehicle cooperative control technology and facility for scenes such as ADAS (automatic vehicle analysis system) and automatic driving tests in a closed test yard, and is used for ensuring the test consistency and the test precision. Moreover, by using the scheme and related facilities, more complex multi-vehicle dynamic traffic scenes can be utilized in ADAS, automatic driving and other tests, the labor cost in the test process can be greatly reduced, and the test capability is enhanced.

Specifically, the target vehicle comprises a tested vehicle or a background vehicle, and the motion event comprises a test case for testing the traffic environment.

It should be noted that the target vehicle may be a real vehicle or a soft vehicle, and is not limited herein; the test case may be a test case constructed when the vehicle is tested, and is specifically determined by the test requirement, which is not limited herein.

In some embodiments, according to a predefined test case, all background vehicles participating in the test scene are triggered to perform movements such as path planning, decision control and the like. Therefore, when a plurality of target vehicles perform the motion corresponding to the motion event trigger signal, at least one of the following actions may be performed according to the actually occurring motion event: braking, steering, accelerating, starting and stopping.

In some embodiments, a final decision result (e.g., vehicle actuator command) of the vehicle may be formed in the real-time motion event measurement device according to the trigger signal, and then sent to the background vehicle through the low-latency wireless communication network for controlling the actual motion of the background vehicle.

Based on the same inventive concept, the specification also provides a multi-target motion event real-time measuring device corresponding to the method. As shown in fig. 6, the multi-target motion event real-time measuring apparatus 600 includes: a logic data acquisition unit 601, a motion event judgment unit 602, and a trigger unit 603. The logic data acquisition unit 601 is used for acquiring logic data of a plurality of target vehicles in a measurement scene; a motion event determining unit 602, configured to determine whether the motion event meets a trigger condition according to the logic data and measurement requirement data of a preset motion event; and the triggering unit 603 is configured to output a motion event trigger signal when the motion event determining unit determines that the motion event meets the trigger condition, so that the multiple target vehicles execute motions corresponding to the motion event trigger signal, so as to form a real-time traffic flow in the measurement scene.

It should be noted that the foregoing multi-target motion event real-time measurement apparatus is an exemplary functional division, and in practical applications, related functional units may be set as needed, and a related motion event real-time measurement action is performed in the related functional units.

Optionally, the multi-object motion event real-time measuring apparatus 600 further includes a coordinate conversion unit 604, wherein the coordinate conversion unit is configured to convert the absolute positioning data into multi-object motion event parameters after the logic data obtaining unit 601 obtains the absolute positioning data of the geographic position of the target vehicle in the measurement scene, where the multi-object motion event parameters include: the corresponding absolute position and absolute movement speed of each target vehicle in a new reference coordinate system, the relative position, relative distance and relative movement speed among a plurality of target vehicles and the movement event time.

Based on the same inventive concept, the specification also provides an application system example corresponding to the method.

As shown in fig. 7 to 11, the real-time measurement of the multi-target motion event may be provided in a remote assisted driving server, wherein the remote driving server may be a test scenario server of a full scenario element constructed based on a high-precision electronic map. In implementation, a test case module, a dynamic model, a synchronization module, a multi-vehicle cooperative driving module, and the like are arranged in a server, on one hand, a real vehicle can be mapped to a virtual vehicle in a test scene in the server, and a virtual vehicle (such as a background vehicle) can also be added in the test scene, so that the server can be operated with the vehicle mapping module to construct a corresponding virtual vehicle (such as a virtual host vehicle, a virtual background vehicle, and the like), and on the other hand, virtual vehicle synchronization and multi-vehicle cooperative driving can be performed based on a motion event after the logical data of each vehicle is combined with the test case.

As shown in fig. 7, the motion event real-time measurement system of the present invention works according to the following principle: the real vehicles A1 to An transmit the self-movement positioning data to the remote assistant driving server C1 through the communication network B1 in real time, so that the remote assistant driving server C1 can combine the test cases based on the positioning data, and then generate a trigger signal to the relevant moving vehicle according to the trigger condition of the actual movement event to enable the vehicle to execute corresponding movement, thereby completing the cooperative control of real-time measurement and real-time measurement.

Specifically, as shown in fig. 8, the real-time motion event measurement system of the present invention may include the following components: the system comprises a high-precision positioning unit 101 installed on a host vehicle 100, an on-board unit 202 installed on a background vehicle 200 and connected with a wire control bus network of the background vehicle, a low-delay wireless communication network 300 which can be a 5G network or a point-to-multipoint high-speed data transmission station, and a remote cooperative driving server 400.

The high-precision positioning unit 101 is installed on the main vehicle, can be a vehicle positioning unit fusing satellite positioning and IMU (inertial measurement unit), is used for acquiring vehicle positioning data, and can acquire the dynamic position of the vehicle in real time (the data refresh frequency is more than 50 Hz), and the positioning precision is centimeter level (+ -5 cm). And the acquired high-precision positioning information is sent to a remote cooperative driving server through a low-delay wireless communication network.

The on-board unit 202 is installed on a background vehicle (the number of the background vehicles may be one or more, only one is shown in the schematic diagram for simplicity), and is connected to a control bus network of the background vehicle through a vehicle bus, and can directly control actuators (a brake, a direction, an accelerator, a start-stop switch, and the like) of the background vehicle through a program, and the remote driving server sends a control instruction to the background vehicle through a low-latency wireless communication network.

The on-board unit 202 may also have a high-precision positioning function, and may obtain the dynamic position of the background vehicle in real time (with a data refresh frequency greater than 50 Hz), where the positioning precision is in the centimeter level (± 5 cm), and the obtained background vehicle positioning information includes longitude, latitude, altitude, heading angle, pitch angle, and roll angle. Correspondingly, the acquired high-precision positioning information is sent to a remote cooperative driving server through a low-delay wireless communication network

The air interface delay of the low-latency wireless communication network 300 is less than 20ms, and may be a point-to-multipoint or full-duplex wireless communication network, specifically, a point-to-multipoint high-speed data transmission radio network, or a 4G or 5G communication network.

The remote cooperative driving server 400 is composed of the main functional modules operating thereon: the system comprises a test case 401, a real-scene high-precision map 402, a vehicle dynamics model 403, vehicle virtual operation 404 of a plurality of virtual vehicles (such as a main vehicle is mapped into a first virtual vehicle, and a background vehicle is mapped into a second virtual vehicle), a virtual vehicle synchronization module 405 and a multi-vehicle cooperative driving module 406.

Specifically, the remote cooperative driving server 400 may be a high-performance computer installed with the following software modules, and may have a network communication interface that can communicate with the host vehicle and the background vehicle through a low-latency wireless communication network:

a test case 401 integrated with various types of case data required for testing;

a live-action high-precision map 402, which is a live-action three-dimensional high-precision map of a real test site, has the precision of centimeter level, contains all static traffic elements of the test site, and comprises semantic data of a road network;

a vehicle dynamics model 403, which may form a virtual host vehicle, a background vehicle, such as a high-precision three-dimensional model of the host vehicle, a high-precision three-dimensional model of the background vehicle;

virtual operation 404 of the vehicle, virtual movement of a high-precision three-dimensional model of the host vehicle, a high-precision three-dimensional model of the background vehicle and the like in a test scene;

the virtual vehicle synchronization module 405 reads the high-precision positioning data of the host vehicle and the background vehicle in real time (more than 50 Hz), positions the virtual host vehicle and the virtual background vehicle to the corresponding positions of the real-scene high-precision map according to the high-precision positioning data, and keeps the postures (the course angle, the pitch angle and the posture angle) consistent with the host vehicle and the background vehicle;

the multi-vehicle cooperative driving module 406 completes path planning and decision control of all virtual background vehicles participating in the test according to a predefined test case, and sends a final decision result (vehicle actuator command) to a real background vehicle through a low-delay wireless communication network for controlling actual motion of the background vehicle.

As shown in fig. 9 to 11, the system operation process is schematically as follows:

the high-precision positioning data of the respective vehicles are used as motion state information by the main vehicle high-precision positioning unit and the vehicle-mounted unit on the background vehicle, and are sent to the remote cooperative driving server through the low-delay wireless communication network;

in the remote cooperative driving server, mapping out corresponding virtual vehicles (a virtual background vehicle and a virtual host vehicle) based on a real-scene high-precision map, a vehicle three-dimensional model and the like, and synchronizing the virtual running vehicle with a real background vehicle and the host vehicle in the real-scene high-precision map by a virtual vehicle synchronization module so as to acquire logic data (such as position and posture) of the background vehicle and the host vehicle in the real-scene high-precision map in real time;

the multi-vehicle cooperative driving module calculates the path planning and decision control instruction of the virtual background vehicle in real time according to the real-scene high-precision map information, the motion state of the virtual vehicle, the dynamic model of the real vehicle and the test requirement (namely a test case) to form a vehicle control instruction;

the decision control instruction is sent to a vehicle-mounted unit of a related background vehicle for receiving through a low-delay wireless communication network;

the background vehicle moves according to the instruction of the remote cooperative driving server, and triggers the actuator to execute relevant actions (such as braking, direction change, throttle control, gear adjustment and the like) so that the vehicle finishes the motion required by real-time measurement.

In addition, the main vehicle high-precision positioning unit and the vehicle-mounted unit on the background vehicle can also send the motion states of the respective vehicles to the remote cooperative driving server through the low-delay wireless communication network to form a closed loop, which is not further described.

The information of all background vehicles and the host vehicle is acquired in real time in a virtual scene (namely a real-scene high-precision map) which is defined in advance, and the movement of the corresponding virtual background vehicles and the host vehicle is controlled according to the information, so that the full-scene element of the whole traffic test scene is obtained. Therefore, a sensing module which consumes calculation power is not needed, only a very simple and efficient automatic driving path planning algorithm and a decision algorithm are used, path planning and decision control can be carried out on all virtual background vehicles which participate in traffic in a preset mode, and real background vehicles are directly controlled by using the decision instructions, so that a closed loop is formed.

Also, since the virtual scene contains the full field Jing Yaosu (static traffic element and dynamic traffic element) of the test scene, the aforementioned events of the background vehicles can be easily obtained by simple calculation of the program, so that the response capability of the background vehicles can be automatically realized very easily, and the response capability can be applied to any number of background vehicles.

Therefore, automation of dynamic traffic scene simulation can be realized, and test consistency is guaranteed. Meanwhile, cooperative control of background vehicles with unlimited quantity can be realized, the cost of simulating the dynamic traffic scene is greatly reduced, and the simulation capability of the dynamic traffic scene is enhanced.

Based on the same inventive concept, the embodiment of the present specification provides an electronic device corresponding to the multi-target motion event real-time measurement method in any one of the foregoing embodiments, where the electronic device includes at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to: the method for measuring the multi-target motion event in real time according to any one embodiment of the specification.

Based on the same inventive concept, the embodiments of the present specification provide a computer storage medium for real-time measurement of multiple target motion events, the computer storage medium storing computer-executable instructions, which when executed by a processor, perform the steps of the real-time measurement method of multiple target motion events as provided in any one of the embodiments of the present specification.

It should be noted that the computer storage medium may include, but is not limited to: a portable disk, a hard disk, random access memory, read only memory, erasable programmable read only memory, optical storage device, magnetic storage device, or any suitable combination of the foregoing.

In a possible implementation manner, the present application may also provide that the data processing is implemented in the form of a program product, which includes program code for causing a terminal device to perform several steps of the method according to any one of the foregoing embodiments when the program product is run on the terminal device.

Where program code for executing the present application is written in any combination of one or more programming languages, the program code may execute entirely on the user device, partly on the user device, as a stand-alone software package, partly on the user device and partly on a remote device or entirely on the remote device.

The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments can be referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the product embodiments described later, since they correspond to the method, the description is simple, and the relevant points can be referred to the partial description of the system embodiments.

The above description is only for the specific embodiments of the present application, but the scope of the present application is not limited thereto, and any changes or substitutions that can be easily conceived by those skilled in the art within the technical scope of the present application should be covered within the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.

Claims (10)

1. A multi-target motion event real-time measurement method is characterized by comprising the following steps:

acquiring logic data of a plurality of target vehicles in a measurement scene;

and determining whether the motion event meets a trigger condition according to the logic data and measurement demand data of a preset motion event, and if so, outputting a motion event trigger signal to enable the plurality of target vehicles to execute motion corresponding to the motion event trigger signal so as to form a real-time traffic flow in the measurement scene.

2. The method of claim 1, wherein obtaining the logistic data for a plurality of target vehicles in a survey scenario comprises: and acquiring absolute positioning data of the geographical positions of the target vehicles.

3. The method of claim 2, wherein after acquiring the absolute positioning data, determining a multiple moving object event parameter from the absolute positioning data, wherein the multiple moving object event parameter comprises: the corresponding absolute position and absolute movement speed of each target vehicle in a new reference coordinate system, the relative position, relative distance and relative movement speed among a plurality of target vehicles and the movement event time.

4. The method of claim 1, wherein the target vehicle comprises a vehicle under test or a background vehicle, and the motion event comprises a test case for testing a traffic environment.

5. The method of claim 2, wherein the logic data provided by the target vehicle is obtained over a wireless communication network with an air interface transmission delay of less than 20 ms.

6. The method of claim 1, wherein the plurality of target vehicles performing the motion corresponding to the motion event trigger signal comprises at least one of: braking, steering, accelerating, starting and stopping.

7. A multi-target motion event real-time measurement device, comprising:

the logic data acquisition unit is used for acquiring logic data of a plurality of target vehicles in a measurement scene;

the motion event judging unit is used for determining whether the motion event meets the triggering condition or not according to the logic data and the measurement requirement data of the preset motion event;

and the triggering unit outputs a motion event triggering signal when the motion event judging unit determines that the motion event meets the triggering condition, so that the target vehicles execute the motion corresponding to the motion event triggering signal to form a real-time traffic flow in the measurement scene.

8. The apparatus of claim 7, further comprising a coordinate transformation unit configured to transform absolute positioning data of the geographic location of the target vehicle in the measurement scenario into a multiple-moving object event parameter after the absolute positioning data is acquired by the logic data acquisition unit, wherein the multiple-moving object event parameter comprises: the corresponding absolute position and absolute movement speed of each target vehicle in a new reference coordinate system, the relative position, relative distance and relative movement speed among a plurality of target vehicles and the movement event moment.

9. An electronic device, comprising:

at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to: the method for real-time measurement of multiple target motion events of any one of claims 1-6.

10. A computer storage medium storing computer-executable instructions that, when executed by a processor, perform the method of real-time measurement of multiple target motion events of any one of claims 1-6.

Images