WO2021169588A1

WO2021169588A1 - Automatic driving simulation method and apparatus, and electronic device and storage medium

Info

Publication number: WO2021169588A1
Application number: PCT/CN2020/141757
Authority: WO
Inventors: 朱裕章; 邱聪
Original assignee: 上海商汤临港智能科技有限公司
Priority date: 2020-02-24
Filing date: 2020-12-30
Publication date: 2021-09-02
Also published as: KR20210114467A; CN111353221A; JP2022524584A

Abstract

Disclosed are an automatic driving simulation method and apparatus, and an electronic device and a storage medium. The method comprises: a message manager receives first vehicle state information sent by a vehicle simulator, the first vehicle state information comprising first chassis information and first positioning information; the message manager performs format conversion on the first chassis information and the first positioning information to obtain second chassis information and second positioning information, and sends the second chassis information and the second positioning information to an automatic driving system; the message manager receives a first control signal sent by the automatic driving system, and performs format conversion on the first control signal to obtain a second control signal, the second control signal being used for updating the vehicle state information by the vehicle simulator; and the message manager sends the second control signal to the vehicle simulator.

Description

Automatic driving simulation method and device, electronic equipment and storage medium

This disclosure requires that it be submitted to the Chinese Patent Office on February 24, 2020, the application number is 202010113305.9, and the title of the invention is "autonomous driving simulation method and device, electronic equipment and storage medium", the entire contents of which are incorporated into this disclosure by reference.

Technical field

The present disclosure relates to the field of simulator simulation technology, and in particular to an automatic driving simulation method and device, electronic equipment and storage medium.

Background technique

Autopilot systems need to be continuously tested during the research and development process, but the autopilot system has a relatively long period of road testing, and the test efficiency is relatively low. If it is tested in a more realistic autopilot simulation test device, not only can it be fully tested The performance of the autonomous driving system in rich scenarios can also provide timely feedback on problems and speed up the iteration of the system.

At present, there are many vehicle simulators for automatic driving system testing on the market. However, for specific autonomous driving projects, the supporting vehicle simulators are usually limited. The data or data interfaces that the vehicle simulator can provide when in use are not Cannot meet the data requirements of a specific automatic driving system, making the automatic driving system based on the vehicle simulator unable to match the test well.

Summary of the invention

The embodiments of the present disclosure provide an automatic driving simulation method and device, electronic equipment, and storage medium.

The first aspect of the embodiments of the present disclosure provides an automatic driving simulation method, including:

The message manager receives the first vehicle state information sent by the vehicle simulator, where the first vehicle state information includes first chassis information and first positioning information;

The message manager performs format conversion on the first chassis information and the first positioning information, obtains second chassis information and second positioning information, and sends the second chassis information and the second chassis information to the automatic driving system. Positioning information;

The message manager receives the first control signal sent by the automatic driving system, converts the format of the first control signal to obtain a second control signal, and the second control signal is used for the vehicle simulator to update the State the vehicle status information;

The message manager sends the second control signal to the vehicle simulator.

In an optional implementation manner, after the message manager sends the second control signal to the vehicle simulator, the method further includes:

The message manager receives the second vehicle state information sent by the vehicle simulator, where the second vehicle state information includes information obtained by the vehicle simulator after updating the vehicle state information according to the second control signal The third chassis information and the third positioning information.

In an optional implementation manner, the second control signal includes one or more of the following: positioning information to be processed, throttle data, brake data, gear position, and steering wheel angle;

and / or,

The first chassis information includes one or more of the following: speed, acceleration, and attitude information;

The attitude information includes one or more of the following: yaw angle, steering wheel angle.

In an optional implementation manner, the method further includes:

The message manager performs format conversion on the first chassis information and the first positioning information, obtains the information of the target vehicle, and sends the information of the target vehicle to the agent manager, where the target vehicle is the target vehicle. For the simulated vehicle in the vehicle simulator, the information of the target vehicle is used to: the agent manager updates the information of the agent in the vehicle simulation scene according to the information of the target vehicle when the vehicle simulation scene is loaded. State to obtain first perception information;

The message manager performs format conversion on the first perception information, obtains second perception information, and sends the second perception information to the automatic driving system, so that the automatic driving system is based on the second perception information Performing decision planning with the second vehicle state information to obtain the first control signal.

A second aspect of the embodiments of the present disclosure provides a message manager, including:

A transmission module for receiving first vehicle state information sent by a vehicle simulator, where the first vehicle state information includes first chassis information and first positioning information;

The conversion module is used for format conversion of the first chassis information and the first positioning information to obtain second chassis information and second positioning information; the transmission module is also used for sending the first chassis information to the automatic driving system 2. Chassis information and the second positioning information;

The transmission module is further configured to receive the first control signal sent by the automatic driving system; the conversion module is also configured to perform format conversion on the first control signal to obtain a second control signal, and the second control signal is The control signal is used by the vehicle simulator to update the vehicle state information;

The transmission module is further configured to send the second control signal to the vehicle simulator.

Optionally, the transmission module is further configured to, after sending the second control signal to the vehicle simulator, receive second vehicle status information sent by the vehicle simulator, wherein the second vehicle status information It includes third chassis information and third positioning information obtained after the vehicle simulator updates the vehicle state information according to the second control signal.

Optionally, the second control signal includes: positioning information to be processed, throttle data, braking data, gear position and/or steering wheel angle;

and / or,

The first chassis information includes speed, acceleration and/or attitude information, and the attitude information includes a yaw angle and/or a steering wheel angle.

Optionally, the conversion module is further configured to perform format conversion on the first chassis information and the first positioning information to obtain information about the target vehicle; the transmission module is also configured to send to the agent manager The information of the target vehicle, wherein the information of the target vehicle is used to update the information of the agent in the vehicle simulation scene according to the information of the target vehicle when the agent manager loads the vehicle simulation scene State to obtain first perception information;

The conversion module is further configured to convert the format of the first perception information to obtain second perception information; the transmission module is also configured to send the second perception information to the automatic driving system so that all The automatic driving system performs decision planning according to the second perception information and the second vehicle state information, and obtains the first control signal.

A third aspect of the embodiments of the present disclosure provides an automatic driving simulation test system, including:

An automatic driving system, a vehicle simulator, and the message manager described in the second aspect above.

Optionally, the automatic driving system includes a positioning module, a map module, a decision planning module, and a controller, where:

The map module is used to load a map and display at least one target vehicle on the map;

The positioning module is configured to obtain second chassis information and second position information from the message manager, and determine and update the target vehicle in the map according to the second chassis information and the second position information , The target vehicle is a simulated vehicle in the vehicle simulator;

The decision planning module is configured to determine the driving decision result of the target vehicle in the map according to the state of the target vehicle and second perception information from the message manager; the controller is configured to determine the driving decision result of the target vehicle in the map according to the target The driving decision result of the vehicle obtains a first control signal, and sends the first control signal to the message manager.

Optionally, the vehicle simulator stores a vehicle dynamics model, and the vehicle dynamics model is pre-established based on data collected by actual vehicle sensors during the driving process of the vehicle;

The vehicle simulator is used for:

Acquiring a second control signal sent by the message manager;

Updating vehicle state information based on the vehicle dynamics model and the second control signal to obtain second vehicle state information, where the second vehicle state information includes third chassis information and third positioning information;

Sending the second vehicle status information to the message manager.

Optionally, the second control signal includes to-be-processed positioning information, throttle data, braking data, gear position, and steering wheel angle;

The vehicle simulator is specifically used to obtain the accelerator data, brake data, and gear in the second control signal according to the preset mapping relationship between the accelerator data, brake data, gear position of the vehicle and the speed and acceleration of the vehicle Corresponding first speed and first acceleration;

Converting the steering wheel angle in the second control signal into the corresponding first front wheel angle according to the preset rotation ratio between the steering wheel angle of the vehicle and the front wheel angle of the vehicle;

Acquiring the first yaw angle of the target vehicle, and the distance from the center of the front wheel axle of the vehicle to the center of gravity of the vehicle and the distance from the center of the vehicle rear axle to the center of gravity of the vehicle;

Based on the positioning information, the first speed, the first acceleration, the first front wheel angle, the first yaw angle, the distance from the center of the front wheel axle of the vehicle to the center of gravity of the vehicle, and the vehicle The distance from the center of the rear wheel axle to the center of gravity of the vehicle to obtain the second vehicle state information.

Optionally, it also includes a vehicle dynamics model building module for:

Acquire the first data of the real vehicle traveling on the road collected by the sensor. The first data includes multiple sets of throttle data, brake data and speed, acceleration, wherein the throttle data, the brake data and the speed and the speed The acceleration has a corresponding relationship;

Constructing a mapping relationship between accelerator data, brake data, gear position and speed and acceleration of the vehicle based on the first data;

Acquiring second data of a real vehicle traveling on a road collected by a sensor, the second data including multiple sets of steering wheel angles and vehicle front wheel angles, and the steering wheel angle and the vehicle front wheel angle have a corresponding relationship;

Constructing a rotation proportional relationship between the steering wheel angle of the vehicle and the front wheel angle of the vehicle based on the second data;

A vehicle dynamics model is obtained based on the mapping relationship and the rotation ratio relationship.

Optionally, it also includes:

Agent manager for:

Load a vehicle simulation scene, the vehicle simulation scene includes an agent, and the agent includes at least one vehicle;

Receiving the information of the target vehicle from the message manager, and updating the state of the agent in the vehicle simulation scene according to the information of the target vehicle to obtain first perception information;

Sending the first perception information to the message manager.

Optionally, the agent manager is also used to:

Sending the information of the simulated vehicle in the vehicle simulation scene to other agents in the vehicle simulation scene, so that the other agents can update their own state according to the information of the simulated vehicle; and send the other agents The information of is sent to the simulated vehicle, so that the simulated vehicle updates its own state according to the information of the other agent.

Optionally, the intelligent body further includes one or more of the following: non-motor vehicles, animals, pedestrians, traffic cones, traffic lights, traffic signs, road signs, lane lines, and obstacles.

A fourth aspect of the embodiments of the present disclosure provides an electronic device, including a processor and a memory, the memory is used to store a computer program, the computer program is configured to be executed by the processor, and the processor is used to execute Part or all of the steps described in any method of the first aspect of the embodiments are disclosed.

The fifth aspect of the embodiments of the present disclosure provides another electronic device, including a processor and a memory, where the memory is used to store a computer program configured to be executed by the processor, and the processor is used to control The message manager in the second aspect of the embodiment of the present disclosure runs, or controls the operation of the automatic driving simulation test system as in the third aspect of the embodiment of the present disclosure.

A sixth aspect of the embodiments of the present disclosure provides a computer-readable storage medium for storing a computer program, wherein the computer program causes a computer to execute any method in the first aspect of the embodiments of the present disclosure Part or all of the steps described may enable the processor to control the operation of the message manager as described in the second aspect of the embodiment of the present disclosure, or enable the processor to control the operation of the message manager as described in the third aspect of the embodiment of the present disclosure. system running.

The seventh aspect of the embodiments of the present disclosure provides a computer program product containing instructions, which when run on a computer, causes the computer to execute the above-mentioned first aspect and any one of its possible implementation methods.

In the embodiment of the present disclosure, the first vehicle status information sent by the vehicle simulator is received through the message manager, and the first chassis information and the first positioning information included in the first vehicle status information are formatted to obtain the second chassis information and the second vehicle status information. Positioning information, and send the second chassis information and second positioning information to the automatic driving system. The message manager also receives the first control signal sent by the automatic driving system, converts the format of the first control signal, and obtains the second control signal. The manager sends a second control signal to the vehicle simulator, so that the vehicle simulator can update the vehicle status information according to the second control signal, thereby realizing the function of data format conversion and forwarding. The data format converted by the message manager is more conducive to forwarding objects Receiving and processing enables the automatic driving simulation test to be executed quickly and correctly, and improves the stability of data processing. For example, the message manager can convert the custom control signal of the autopilot system to be tested into a general control signal that can be recognized and processed by the vehicle simulator, so that the autopilot simulation task can be executed more accurately in the vehicle simulator. Since the control signal mainly includes the relatively simple parameters of the vehicle's chassis information and positioning information, and the analysis is simple, the message manager can quickly identify and convert. At the same time, the vehicle simulator and automatic driving system no longer need to be developed, that is, on the basis of not modifying the source code of the vehicle simulator or the source code of the automatic driving system, data exchange can be carried out and the automation can be accurately completed by replacing the intermediate message manager. The driving simulation test improves the compatibility of the automatic driving system and the versatility of the automatic driving simulation test system.

Description of the drawings

The drawings herein are incorporated into the specification and constitute a part of the specification. These drawings illustrate embodiments that conform to the present disclosure, and are used together with the specification to explain the technical solutions of the present disclosure.

FIG. 1 is a schematic flowchart of an automatic driving simulation method disclosed in an embodiment of the present disclosure;

Figure 2 is a schematic structural diagram of a message manager disclosed in an embodiment of the present disclosure;

FIG. 3 is a schematic diagram of the architecture of an automatic driving simulation test system disclosed in an embodiment of the present disclosure;

4 is a schematic structural diagram of another automatic driving simulation test system disclosed in an embodiment of the present disclosure;

Fig. 5 is a schematic structural diagram of an electronic device disclosed in an embodiment of the present disclosure.

Detailed ways

The technical solutions in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present disclosure. Obviously, the described embodiments are only a part of the embodiments of the present disclosure, rather than all the embodiments. Based on the embodiments in the present disclosure, all other embodiments obtained by those of ordinary skill in the art without creative work shall fall within the protection scope of the present disclosure.

The term "and/or" in the present disclosure is merely an association relationship describing associated objects, indicating that there can be three types of relationships, for example, A and/or B, which can mean: A alone exists, and A and B exist at the same time. There are three cases of B alone. In addition, the term "at least one" in this document means any one of a plurality of or any combination of at least two of the plurality, for example, including at least one of A, B, and C, may mean including A, Any one or more elements selected in the set formed by B and C. The terms “first”, “second”, etc. in the specification, claims, and drawings of the present disclosure are used to distinguish different objects, rather than to describe a specific sequence. In addition, the terms "including" and "having" and any variations of them are intended to cover non-exclusive inclusions. For example, a process, method, system, product, or device that includes a series of steps or units is not limited to the listed steps or units, but optionally includes unlisted steps or units, or optionally also includes Other steps or units inherent to these processes, methods, products or equipment.

Reference to "embodiments" herein means that a specific feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present disclosure. The appearance of the phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment mutually exclusive with other embodiments. Those skilled in the art clearly and implicitly understand that the embodiments described herein can be combined with other embodiments.

The embodiments of the present disclosure are described in detail below.

Please refer to FIG. 1. FIG. 1 is a schematic flowchart of an automatic driving simulation method disclosed in an embodiment of the present disclosure. As shown in FIG. 1, the automatic driving simulation method may be executed by a message manager, and may specifically include the following steps:

101. The message manager receives first vehicle state information sent by a vehicle simulator, where the first vehicle state information includes first chassis information and first positioning information.

The automatic driving system (Auto Driving System) involved in the embodiments of the present disclosure, also known as an automatic driving control system, is used to control a car or a robot to drive automatically under unmanned driving control.

The vehicle simulator can realize the vehicle simulation of the automatic driving system and test the performance of the automatic driving system. The message manager in the embodiment of the present disclosure can realize data conversion and forwarding between the automatic driving system and the vehicle simulator.

The foregoing message manager may be a hardware device, and the automatic driving simulation method may be implemented by a processor in the message manager calling computer-readable instructions stored in a memory. In an implementation manner, the product form of the message manager may also be software, or an electronic device integrating software and hardware, and so on. For example, through platform development on the software side, a software message manager can be obtained on the software side, or a software program developed and designed can be deployed on an electronic device to execute the method executable by the message manager in the embodiment of FIG. 1.

In the embodiments of the present disclosure, by setting the message manager as an intermediate station, data processing and forwarding can be performed, and as a data exchange bridge between the vehicle simulator and the automatic driving system, it can solve that the data or data interface provided by the general vehicle simulator does not meet specific requirements. The data requirements of the autonomous driving system project caused the problem of data exchange between the two.

Specifically, the message manager may receive the first vehicle state information sent by the vehicle simulator, where the first vehicle state information includes first chassis information and first positioning information.

The first chassis information may include one or more of the following: speed, acceleration, and attitude information; the attitude information may include one or more of the following: yaw angle, steering wheel angle. The first positioning information is positioning information of the target vehicle, and specifically may be coordinate information or latitude and longitude information.

Taking the target vehicle as the simulation object of this automatic driving system and vehicle simulator as an example, the vehicle simulator can perform vehicle simulation processing on the target vehicle according to the control signal sent by the automatic driving system and converted and forwarded by the message manager to obtain The vehicle status information of the target vehicle, where the control signal output by the automatic driving system may include one or more of the following: the target vehicle’s pending positioning information, throttle data, brake data, gear position, steering wheel angle, these data can be controlled by the automatic The automatic driving algorithm of the driving system is obtained and updated periodically.

After receiving the first vehicle state information sent by the vehicle simulator, step 102 may be executed.

In an optional implementation manner, an agent manager can be set for the automated driving simulation task, and the method further includes:

The message manager performs format conversion on the first chassis information and the first positioning information, obtains the information of the target vehicle, and sends the information of the target vehicle to the agent manager, where the target vehicle is a simulation in the vehicle simulator. A vehicle, the information of the target vehicle is used to: when the agent manager loads the vehicle simulation scene, update the state of the agent in the vehicle simulation scene according to the information of the target vehicle to obtain the first perception information;

The message manager performs format conversion on the first perception information, obtains the second perception information, and sends the second perception information to the automatic driving system, so that the automatic driving system performs processing according to the second perception information and the second vehicle status information. Make decisions and plans and get the first control signal.

Specifically, the agent manager may load a vehicle simulation scene, the vehicle simulation scene includes an agent, and the agent may include at least one vehicle. Optionally, the agent also includes one or more of the following: non-motorized vehicles, animals, pedestrians, traffic cones, traffic lights, traffic signs, road signs, lane lines, obstacles, and there is no restriction here.

The target vehicle is a simulated vehicle in the vehicle simulator, and the message manager may also convert the first chassis information and the first positioning information sent by the vehicle simulator into the target vehicle information, and send the information to the agent manager The information of the target vehicle, so that the agent manager can update the state of the agent in the vehicle simulation scene according to the information of the target vehicle when the vehicle simulation scene is loaded, and obtain the above-mentioned first perception information. It can be understood that the agent manager can control the agent in the vehicle simulation scene according to the information of the target vehicle sent by the vehicle simulator that is converted and forwarded by the message manager. The information is sent to other agents in the vehicle simulation scene, so that other agents can update their own state according to the information of the simulated vehicle.

After converting the first perception information into the second perception information, the message manager may send the second perception information to the aforementioned automatic driving system. The automatic driving system can comprehensively make decision planning based on the second perception information and the obtained second vehicle state information, so as to control the target vehicle to consider the state of the surrounding agents when driving, and obtain the above-mentioned first control signal.

102. The message manager performs format conversion on the first chassis information and the first positioning information, obtains the second chassis information and the second positioning information, and sends the second chassis information and the second positioning information to the automatic driving system.

The message manager can realize the information format conversion between the vehicle simulator and the automatic driving system. Specifically, the message manager can pre-set the format mapping relationship between the vehicle simulator and the automatic driving system of data of different message types, as well as different The forwarding and mapping relationship of message type data between data interfaces; when receiving data sent by one of the parties, the data can be identified first to determine the message type of the data. For example, if the first chassis information belongs to chassis information, you can The format mapping relationship between the vehicle simulator and the automatic driving system is determined, the conversion format corresponding to the first chassis information is determined, and the format conversion is performed to obtain the corresponding second chassis information; and, according to the forwarding mapping relationship between the chassis information in the data interface, It may be determined that the forwarding object corresponding to the first chassis information is the data interface of the automatic driving system, so as to send the second chassis information to the automatic driving system after obtaining the second chassis information.

Similarly, the message manager can convert the format of the first positioning information to obtain the second positioning information and send it to the automatic driving system.

103. The message manager receives the first control signal sent by the automatic driving system, performs format conversion on the first control signal, and obtains a second control signal, which is used by the vehicle simulator to update the vehicle state information .

Similar to the method described in step 102, the message manager may receive the first control signal sent by the autopilot system, and the first control signal may include one or more of the following: positioning information to be processed, throttle data, brake data , Gears, steering wheel angle.

Also take the target vehicle as the vehicle simulated by the autopilot system and the vehicle simulator as an example. The autopilot system can process the vehicle status information of the target vehicle sent by the vehicle simulator and converted and forwarded by the message manager to obtain The control signal of the target vehicle is forwarded to the vehicle simulator through the conversion of the message manager. Specifically, when the message manager receives the first control signal sent by the automatic driving system, it also performs format conversion on the first control signal to obtain the second control signal, and step 104 may be executed.

104. The message manager sends the second control signal to the vehicle simulator.

After the message manager obtains the second control signal by converting the data format of the first control signal of the automatic driving system into a data format suitable for processing by the vehicle manager, the message manager sends the second control signal to the vehicle simulator to enable the vehicle simulator The vehicle state information of the target vehicle can be updated according to the second control signal.

In an embodiment, after step 104, the method further includes:

The message manager receives the second vehicle status information sent by the vehicle simulator, where the second vehicle status information includes the third chassis information and third chassis information obtained after the vehicle simulator updates the vehicle status information according to the second control signal. Positioning information.

Specifically, after receiving the second control signal, the vehicle simulator can update the vehicle state information according to the second control signal, obtain the second vehicle state information, including the third chassis information and the third positioning information, and send it to the message manager , The message manager then processes the second vehicle status information, which is specifically described in step 101, which will not be repeated here. It can be seen that this step can be executed periodically until the automatic driving simulation task ends.

The interface of the autopilot system can be set and changed in the message manager to be able to adapt to different autopilot systems for simulation testing. At the same time, the interface of the vehicle simulator can be set and changed, so that different vehicle simulators can be used for application. Generally, the existing automatic driving system data interface needs to be adapted to the vehicle simulator for development. If other types of vehicle simulators are replaced in the test system, the automatic driving system needs to be re-developed for the new vehicle simulator, otherwise it cannot be adapted to use , The development cost is very high. In the present disclosure, a message manager is added to the test system, and the message manager is used to convert and forward the data exchanged between the autopilot system and the vehicle simulator. When the vehicle simulator needs to be replaced, the message manager and vehicle simulator are modified. The communication interface between the autopilot devices without the need to redesign the autopilot system, thereby improving the compatibility of the autopilot system; and/or, when the autopilot system to be tested needs to be replaced, the message manager and the autopilot system need to be modified. There is no need to replace the vehicle simulator with a vehicle simulator that is compatible with the new automatic driving system. Optionally, if the test system is also equipped with an agent manager, based on the foregoing, the agent management needs to be replaced The communication interface between the message manager and the agent manager is modified without the need to redesign the automatic driving system and the vehicle simulator, thereby reducing the cost and improving the versatility of the automatic driving simulation test device.

The embodiment of the present disclosure receives the first vehicle state information sent by the vehicle simulator through the message manager, the first vehicle state information includes the first chassis information and the first positioning information, and then the first chassis information and the first positioning information The format conversion is performed to obtain the second chassis information and the second positioning information, and the second chassis information and the second positioning information are sent to the automatic driving system. The message manager also receives the first control signal sent by the automatic driving system, performs format conversion on the first control signal, and obtains a second control signal, which is used by the vehicle simulator to update the vehicle state information. The message manager sends the second control signal to the vehicle simulator, which can realize the function of data format conversion and forwarding. The data format converted by the message manager is used for the forwarding object to receive and process, so that the automatic driving simulation test can be Fast and correct execution improves the stability of data processing. For example, the message manager can convert the custom control signal of the autopilot system to be tested into a general control signal that can be recognized and processed by the vehicle simulator, so that the autopilot simulation task can be executed more accurately in the vehicle simulator. Since the control signal mainly includes the relatively simple parameters of the vehicle's chassis information and positioning information, and the analysis is simple, the message manager can quickly identify and convert. At the same time, the vehicle simulator and the automatic driving system no longer need to be developed, that is, on the basis of not modifying the source code of the vehicle simulator or the source code of the automatic driving system, only the middle message manager can be replaced to exchange data and complete the automatic operation accurately. The driving simulation test improves the compatibility of the automatic driving system and the versatility of the automatic driving simulation test system.

Those skilled in the art can understand that in the method of specific implementation, the writing order of each step does not mean a strict execution order but constitutes any limitation on the implementation process. The specific execution order of each step should be based on its function and possible inherent Logic is determined.

The foregoing mainly introduces the solutions of the embodiments of the present disclosure from the perspective of the execution process on the method side. It can be understood that, in order to realize the aforementioned functions, the message manager and/or the automated driving simulation test system includes hardware structures and/or software modules corresponding to each function. Those skilled in the art should be aware that, in combination with the units and algorithm steps of the examples described in the embodiments disclosed herein, the present disclosure can be implemented in the form of hardware or a combination of hardware and computer software. Whether a certain function is executed by hardware or computer software-driven hardware depends on the specific application and design constraint conditions of the technical solution. Professionals and technicians can use different methods for specific applications to implement the described functions, but such implementation should not be considered as going beyond the scope of the present disclosure.

The embodiments of the present disclosure can divide the message manager into functional units (modules) according to the method examples described above. For example, each functional unit can be divided corresponding to each function, or two or more functions can be integrated into one. Processing unit. The integrated unit can be implemented in the form of hardware or software functional unit. It should be noted that the division of units in the embodiments of the present disclosure is illustrative, and is only a logical function division, and there may be other division methods in actual implementation.

Please refer to FIG. 2. FIG. 2 is a schematic structural diagram of a message manager provided by an embodiment of the present disclosure. As shown in FIG. 2, the message manager 200 includes:

The transmission module 210 is configured to receive first vehicle state information sent by a vehicle simulator, where the first vehicle state information includes first chassis information and first positioning information;

The conversion module 220 is used for format conversion of the first chassis information and the first positioning information to obtain second chassis information and second positioning information; the transmission module 210 is also used for sending the second chassis to the automatic driving system Information and the second positioning information;

The transmission module 210 is also used to receive the first control signal sent by the automatic driving system; the conversion module 220 is also used to format the first control signal to obtain a second control signal, and the second control signal is used Update the vehicle status information in the vehicle simulator;

The transmission module 210 is also used to send the second control signal to the vehicle simulator.

Optionally, the transmission module 210 is further configured to, after sending the second control signal to the vehicle simulator, receive second vehicle status information sent by the vehicle simulator, where the second vehicle status information includes The third chassis information and third positioning information obtained after the simulator updates the vehicle state information according to the second control signal.

And/or, the first chassis information includes speed, acceleration, and/or attitude information, and the attitude information includes yaw angle and/or steering wheel angle.

Optionally, the conversion module 220 is further configured to perform format conversion on the first chassis information and the first positioning information to obtain information about the target vehicle; the transmission module 210 is also configured to send the target vehicle to the agent manager Vehicle information, where the target vehicle information is used to: when the agent manager loads the vehicle simulation scene, update the state of the agent in the vehicle simulation scene according to the target vehicle information to obtain the first perception information ；

The conversion module 220 is also used for format conversion of the first perception information to obtain second perception information; the transmission module 210 is also used for sending the second perception information to the automatic driving system, so that the automatic driving system A decision plan is made according to the second perception information and the second vehicle state information, and the first control signal is obtained.

Refer to FIG. 3, which is a schematic structural diagram of an automatic driving simulation test system provided by an embodiment of the present disclosure. As shown in Fig. 3, the automated driving simulation test system 300 includes:

The automatic driving system 330, the vehicle simulator 320, and the message manager 200 as shown in FIG. 2. Optionally, the automated driving simulation test system may further include the agent manager 340 mentioned in the embodiment shown in FIG. 1.

In order to further clearly describe the automatic driving simulation method and the automatic driving simulation test system in the embodiments of the present application, please refer to FIG. 4, which is a schematic structural diagram of another automatic driving simulation test system disclosed in an embodiment of the present disclosure. As shown in FIG. 4, the automatic driving simulation test system includes a vehicle simulator 410, a message manager 420, an agent manager 430, and an automatic driving system 440, where the automatic driving system 440 is a system to be tested.

For example, based on the specific description in the embodiment shown in FIG. 1 and the architecture of the automated driving simulation test system shown in FIG. 4, the automated driving simulation process may specifically include:

(1) The vehicle simulator 410 can obtain general control signals from the message manager 420 to update its own position, and at the same time send general first chassis information and first positioning information to the message manager 420;

(2) The message manager 420 may convert the first chassis information and the first positioning information into target vehicle information, send it to the agent manager 430, and convert the first chassis information and the first positioning information into second chassis information And the second positioning information, sent to the automatic driving system 440;

(3) The agent manager 430 obtains the target vehicle information through the message manager 420 for processing, controls the managed agent to respond to the target vehicle, updates the agent's own state, obtains the first perception information, and sends it to the message manager 420;

(4) The message manager 420 may also convert the first perception information into second perception information, and send it to the automatic driving system 440;

(5) The automatic driving system 440 may perform automatic driving control of the target vehicle according to the second chassis information, the second positioning information, and the second perception information, output the first control signal, and send it to the message manager 420;

(6) The message manager 420 may convert the first control signal into a second control signal and send it to the vehicle simulator 410. The vehicle simulator 410 may execute the processing steps described in (1) in response to the second control signal, that is, the above steps (1)-(6) may be executed periodically until the automatic driving simulation test ends.

In an alternative embodiment, the automatic driving system 440 includes a positioning module 441, a map module 442, a decision planning module 443, and a controller 444, wherein:

The map module 442 is used to load the map and display at least one target vehicle on the map;

The positioning module 441 is used to obtain the second chassis information and second location information from the message manager, and determine and update the state of the target vehicle in the map according to the second chassis information and the second location information. The target vehicle is The simulated vehicle in the vehicle simulator;

The decision planning module 443 is configured to determine the driving decision result of the target vehicle in the map according to the state of the target vehicle and the second perception information from the message manager; the controller 44 is configured to determine the driving decision result of the target vehicle according to the target vehicle. As a result, the first control signal is obtained, and the first control signal is sent to the message manager.

Specifically, the map module 442 in the automatic driving system 440 is used to load the map and display at least one target vehicle on the map;

The positioning module 441 can obtain the second chassis information and the second location information from the message manager 420, determine and update the status of the target vehicle on the map according to the second chassis information and the second location information, and then the decision-making and planning module 443 then according to the target The state of the vehicle and the second perception information from the message manager 420 are used to make decisions on the subsequent driving path, direction, speed, etc. of the vehicle to determine the driving decision result of the target vehicle on the map; the controller 444 can then make a decision based on the driving decision. As a result, the first control signal is obtained, and the automatic driving system 440 may send the first control signal to the message manager 420.

The simulation result can be output by relying on the visualization function of the autopilot system 400 under test, that is, the autopilot simulation test system 400 can display data such as simulation videos and images.

In an optional implementation manner, the vehicle simulator 410 stores a vehicle dynamics model, which is pre-established based on data collected by actual vehicle sensors during the driving process of the vehicle;

The vehicle simulator 410 is used for:

Acquiring the second control signal sent by the message manager;

Update vehicle state information based on the vehicle dynamics model and the second control signal to obtain second vehicle state information, where the second vehicle state information includes third chassis information and third positioning information;

Send the second vehicle status information to the message manager.

The vehicle simulator 410 in the embodiment of the present disclosure may use a preset vehicle dynamics model to describe the movement mode of the simulated vehicle. Collect data during the driving process of the vehicle through actual vehicle sensors, establish a more realistic vehicle dynamics model in advance, and apply it in the vehicle simulator 410, so that the vehicle simulator 410 can be based on the vehicle dynamics model and the received second vehicle dynamics model. The control signal updates the vehicle state information, thereby obtaining the second vehicle state information.

Among them, the second control information generated by the automatic driving system 440, converted and forwarded by the message manager 420, in which the throttle data, brake data, steering wheel angle, etc. are not sufficiently visualized in the calculation process, and can be converted first, and then simulated in the vehicle. The operation is performed in the device 410. Therefore, the vehicle's accelerator data, brake data, the mapping relationship between gear and speed, acceleration, and the rotation ratio between the steering wheel angle of the vehicle and the front wheel angle of the vehicle can be preset in the vehicle dynamics model.

More specifically, the establishment process of the vehicle dynamics model includes:

Acquire first data of a real vehicle traveling on the road collected by a sensor. The first data includes multiple sets of throttle data, brake data, speed, and acceleration, where the throttle data, the brake data, and the speed, and the acceleration have a corresponding relationship ；

Based on the first data, a mapping relationship between accelerator data, brake data, gear position and speed and acceleration of the vehicle is constructed;

Based on the second data, construct a rotation proportional relationship between the steering wheel angle of the vehicle and the front wheel angle of the vehicle;

The parameters and performance of the simulated vehicle in the general vehicle simulator are not consistent with the actual vehicle parameters and performance. In the simulation test, it is necessary to obtain the parameters of the bottom of the vehicle, such as the torsion torque of the vehicle, vehicle power, tire friction coefficient, etc. These parameters are generally difficult to obtain, so the simulation of the vehicle is difficult to match the actual road test vehicle well.

In the embodiment of the present disclosure, the preset mapping relationship between the accelerator data, brake data, gear position of the vehicle and the speed and acceleration of the vehicle, and the preset rotation ratio relationship between the steering wheel angle of the vehicle and the front wheel angle of the vehicle can be collected by The real vehicle data statistics are obtained.

Specifically, in order to simulate the automatic driving of real test vehicles as much as possible, in the embodiments of the present disclosure, sensors and real vehicles can be first used to randomly and massively collect multiple sets of throttle data, brake data and data by driving real vehicles on the road. Speed, acceleration, where the throttle data, the braking data and the speed, the acceleration have a corresponding relationship, and can measure multiple sets of steering wheel angles and vehicle front wheel angles of multiple vehicles, the steering wheel angle and the vehicle front wheel angle have a correspondence Relations, and then through interpolation fitting method to construct the preset vehicle throttle data, brake data, gears and vehicle speed, acceleration mapping relationship, and the preset vehicle steering wheel angle and vehicle front wheel angle of rotation ratio The relationship, as the longitudinal mathematical expression of the vehicle dynamics model, can realize the control of the simulated vehicle. Only the parameters such as accelerator, brake, gear position and steering wheel angle can be calculated and output vehicle status messages. This avoids the difficulty of vehicles. Provides the dilemma of the underlying performance parameters, which can more realistically simulate actual road test vehicles.

Specifically, the second control signal includes to-be-processed positioning information, throttle data, braking data, gear position and steering wheel angle;

The vehicle simulator 410 is specifically used for:

Obtain the first speed and first acceleration corresponding to the throttle data, brake data and the gear in the second control signal according to the preset mapping relationship between the accelerator data, brake data, gear position and the speed and acceleration of the vehicle;

Obtain the first yaw angle of the target vehicle, and the distance from the center of the front wheel axle of the vehicle to the center of gravity of the vehicle and the distance from the center of the rear wheel axle of the vehicle to the center of gravity of the vehicle;

Based on the positioning information, the first speed, the first acceleration, the first front wheel angle, the first yaw angle, the distance from the center of the front wheel axle of the vehicle to the center of gravity of the vehicle, and the distance from the center of the rear wheel axle of the vehicle to the center of gravity of the vehicle, the second vehicle is obtained status information.

In the vehicle simulator 410, for the received control signal, according to the preset vehicle's accelerator data, brake data, the mapping relationship between the gear and the vehicle's speed and acceleration, and the preset vehicle's steering wheel angle and the front wheel of the vehicle The rotation ratio relationship of the rotation angle can obtain the corresponding first speed, first acceleration and first front wheel rotation angle, so that the calculation of the vehicle state can be performed. Specifically, the distance from the center of the front wheel axle of the target vehicle to the center of gravity of the vehicle and the distance from the center of the rear wheel axle of the vehicle to the center of gravity of the vehicle can be obtained. It is set and sent to the vehicle simulator 410 through the message manager 420. Based on the positioning information obtained by the vehicle simulator 410, the first speed, the first acceleration, the first front wheel angle, the first yaw angle, the distance from the center of the front wheel axle of the vehicle to the center of gravity of the vehicle, and the distance from the center of the rear wheel axle of the vehicle to the center of gravity of the vehicle The distance to obtain the second vehicle state information may specifically include any one or more of the following: second positioning information, second speed, second acceleration, and second yaw angle. The positioning information of the vehicle in the embodiment of the present disclosure may be represented by the position coordinate of the vehicle.

In the embodiments of the present disclosure, the suspension system, tire model, and environment model of the vehicle are simplified. In one embodiment, the obtained vehicle dynamics model includes the obtained mapping relationship and the rotation ratio relationship, where the mapping relationship and the rotation ratio relationship are Based on the calculation formula. The calculation formula provided can be as follows:

x _t+1 = x _t +v _t cos(Ψ _t +β)*dt;

y _t+1 =y _t +v _t sin(Ψ _t +β)*dt;

Ψ _t+1 =Ψ _t +v _t l _r sin(β)*dt;

v _t+1 =v _t +a*dt;

Among them, (x, y) represents the position coordinates of the vehicle, v and a are the speed and acceleration of the vehicle respectively, Ψ _t is the yaw angle of the vehicle, which represents the direction of the vehicle body, and l _f and l _r are the vehicle's center of gravity to the front wheel axle respectively The distance between the midpoint and the midpoint of the rear wheel axle, δ _f is the front wheel angle of the vehicle, which can be limited to negative counterclockwise, or it can be set as required. Since the rear wheels of most vehicles are not rotatable, the vehicle dynamics model of the embodiments of the present disclosure may not consider the rotation angle of the rear wheels, which can reduce the amount of data processing to a certain extent.

The vehicle dynamics model is obtained by using the actual real vehicle parameters and the calibration relationship, which is closer to the real road test vehicle, and makes the simulation test scene more abundant, more comprehensive and accurate.

Through the preset vehicle dynamics model, the control of the simulated vehicle only needs throttle data, brake data, gear position and steering wheel angle, as well as the positioning information to be processed and the fixed vehicle parameters (l _f and l _r ) as a reference. Carry out conversion operation and calculation processing, specifically including the conversion of input data based on the mapping relationship and the rotation ratio relationship, and then perform calculation processing according to the formula, and finally output vehicle status information, including vehicle position update (second positioning information), speed, acceleration And attitude information (including the second yaw angle and steering wheel angle, etc.), data processing in the automatic driving simulation test can be realized simply and accurately.

In an optional implementation manner, the automated driving simulation test system 400 further includes: an agent manager 430 for:

Receiving the information of the target vehicle from the message manager 420, and updating the state of the agent in the vehicle simulation scene according to the information of the target vehicle to obtain the first perception information;

The first perception information is sent to the message manager 420.

Specifically, the agent manager 430 can be used to combine with the vehicle simulator 410 to simulate a simulation scene. The agent in the simulation scene is an element that can interact with the target vehicle. Optionally, the agent also includes one or more of the following : Non-motorized vehicles, animals, pedestrians, traffic cones, traffic lights, traffic signs, road signs, lane lines, obstacles. It should be noted that, in addition to the target vehicle concerned in the set simulation test, other vehicles can be traffic flow vehicles simulated in the scene.

In the agent manager 430, which agents can interact with the simulated vehicle can be set and changed, and interaction rules can be set. The agent manager 430 may obtain the information of the target vehicle through the message manager 420, control the managed agent to respond to the target vehicle according to the corresponding interaction rules, update its own state to obtain perception information, and then feed back to the message manager 420. For the traffic flow vehicles in the smart manager 430, a preset automatic driving algorithm can be used to complete the simulated driving and can interact with the target vehicle.

The message manager 420 can send the first perception information of the agent in the simulation scene where the target vehicle is located to the automatic driving system 440, where the message manager 420 can also perform format conversion, and the obtained second perception information is satisfactory for the automatic driving system 440 Data in a custom format can specifically include the location information, speed, etc. of the agent in the agent manager. For example, when the target vehicle hits a traffic cone, the traffic cone changes its state in response to the situation (dumping or flying out, moving to a certain position, etc.), or the traffic flow vehicle is under the influence of the target vehicle. Changing its own driving route, etc., is not limited in the embodiment of the present disclosure.

The general purpose and customization involved in the embodiments of the present disclosure refer to the data format. The general purpose format of the general format is relatively strong, but the general automatic driving system will define its own data format according to its own needs.

Optionally, the agent manager 430 is further used to: send the information of the simulated vehicle in the vehicle simulation scene to other agents in the vehicle simulation scene, so that the other agents can update their own state according to the information of the simulated vehicle; and The information of other agents is sent to the simulated vehicle, so that the simulated vehicle updates its own state according to the information of other agents.

Generally, vehicle simulation using traffic flow is a scenario in the form of a script, which is mainly for traffic flow playback. There is no interaction between the simulated scene and the simulated vehicle, which is different from the real situation. However, in the embodiments of the present disclosure, the simulated vehicle can be managed uniformly with other agents in the simulation scene through the agent manager, and all objects can use the same state update interface, which can realize the interaction of objects in the simulation scene and the simulation scene. The interaction between the object and the simulated vehicle itself.

Optionally, at least two simulated vehicles may be set in the automatic driving simulation test system 400 for simulation testing, and at least two simulated vehicles may independently perform automatic driving simulation processing. The multi-vehicle simulation can be the same as the data processing method of the aforementioned one target vehicle as a simulated vehicle. The information of the at least two simulated vehicles can be processed separately in the same automatic driving system 400, and different control signals can be generated and provided to the same vehicle simulator. 410 for processing.

In the scenario of multi-vehicle simulation, the simulated vehicle and other agents in the agent manager 430 belong to the same concept, so they can be managed in a unified manner to achieve simultaneous multi-vehicle simulation. In the agent manager 430, compared to one of the simulated vehicles, the other simulated vehicle can be regarded as other agents. Therefore, the agent manager 430 can also support the information interaction between multiple simulated vehicles to generate corresponding The perception information is provided to the automatic driving system 400 through the message manager 420.

Through the above steps, under the premise of rapid and accurate realization of the automated driving simulation test, the interaction between the simulated vehicle and the simulated simulation scene can also be realized. At the same time, the interaction between the traffic flow vehicles can form complex agent behaviors, providing more abundant Test scenario.

The vehicle simulator 410, the agent manager 430 and the automatic driving system 440 can all be replaced as needed. For the changed modules, the interface communication part can be set and changed in the message manager 420, so that the modules can be smooth and accurate. Data interaction.

In an alternative embodiment, the automatic driving simulation test system 400 may be a software system deployed on an electronic device, and the message manager 420, the vehicle simulator 410, the agent manager 430, and the automatic driving system may be software modules. , The automatic driving simulation test system 400 can be deployed on a terminal device to perform simulation test tasks; in another embodiment, the automatic driving simulation test system 400 includes a vehicle simulator 410, an agent manager 430, and a message manager Both the 420 and the automatic driving system 400 may be physical devices.

Generally, the existing automatic driving system data interface needs to be adapted to the vehicle simulator for development. If other types of vehicle simulators are replaced in the test system, the automatic driving system needs to be re-developed for the new vehicle simulator, otherwise it cannot be adapted to use , The development cost is very high. In the present disclosure, by adding a message manager to the test system, the message manager is used to convert and forward the data exchanged between the autopilot system and the vehicle simulator. When the vehicle simulator needs to be replaced, the message manager and the vehicle simulator can be modified. The communication interface between the vehicle simulators eliminates the need to redesign the automatic driving system, thereby improving the compatibility of the automatic driving system; and/or, when the automatic driving system to be tested needs to be replaced, the message manager and the The communication interface between the automatic driving systems, so that there is no need to replace the vehicle simulator with a vehicle simulator that is compatible with the new automatic driving system; optionally, if the test system is also equipped with an agent manager, on the basis of the foregoing, When the agent manager needs to be replaced, the communication interface between the message manager and the agent manager can be modified, so that there is no need to redesign the automatic driving system and the vehicle simulator, thereby reducing costs and improving the generality of the automatic driving simulation test system sex.

Please refer to FIG. 5. FIG. 5 is a schematic structural diagram of an electronic device disclosed in an embodiment of the present disclosure. As shown in FIG. 5, the electronic device 500 includes a processor 501 and a memory 502. The electronic device 500 may also include a bus 503. The processor 501 and the memory 502 may be connected to each other through the bus 503, and the bus 503 may be an interconnection of peripheral components. Connect standard (Peripheral Component Interconnect, PCI) bus or extended industry standard architecture (Extended Industry Standard Architecture, EISA) bus, etc. The bus 503 can be divided into an address bus, a data bus, a control bus, and so on. For ease of presentation, only one thick line is used to represent in FIG. 5, but it does not mean that there is only one bus or one type of bus. The electronic device 500 may also include an input/output device 504, and the input/output device 504 may include a display screen, such as a liquid crystal display screen. The memory 502 is used to store a computer program; the processor 501 is used to call the computer program stored in the memory 502 to execute some or all of the method steps mentioned in the embodiment of FIG. 1. Implementing the electronic device 500 shown in FIG. 5, the electronic device 500 can set and change the interface with the automatic driving system, so as to be able to adapt to different automatic driving systems for simulation testing, which will not be repeated here.

Alternatively, the processor 501 is configured to call a computer program stored in the memory 502 to execute part or all of the method steps executed by the automatic driving simulation test system 400 in the embodiment described in FIG. 4.

The embodiments of the present disclosure also provide a computer storage medium, wherein the computer storage medium is used to store a computer program, and the computer program causes the computer to execute any of the automatic driving simulation methods or automatic driving simulation methods recorded in the method embodiments described above. Part or all of the steps of the method executed by the driving simulation test system.

It should be noted that for the foregoing method embodiments, for the sake of simple description, they are all expressed as a series of action combinations, but those skilled in the art should know that the present disclosure is not limited by the described sequence of actions. Because according to the present disclosure, certain steps can be performed in other order or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the involved actions and modules are not necessarily required by the present disclosure.

In the foregoing embodiments, the description of each embodiment has its own focus. For parts that are not described in detail in an embodiment, reference may be made to related descriptions of other embodiments.

In the several embodiments provided in the present disclosure, it should be understood that the disclosed device may be implemented in other ways. For example, the device embodiments described above are merely illustrative, for example, the division of the units is only a logical function division, and there may be other divisions in actual implementation, for example, multiple units or components may be combined or may be Integrate into another system, or some features can be ignored or not implemented. In addition, the displayed or discussed mutual coupling or direct coupling or communication connection may be indirect coupling or communication connection through some interfaces, devices or units, and may be in electrical or other forms.

The units (modules) described as separate components may or may not be physically separate, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed to multiple networks. Unit. Some or all of the units may be selected according to actual needs to achieve the objectives of the solutions of the embodiments.

In addition, the functional units in the various embodiments of the present disclosure may be integrated into one processing unit, or each unit may exist alone physically, or two or more units may be integrated into one unit. The integrated unit can be implemented in the form of hardware or software functional unit.

If the integrated unit 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 memory. Based on this understanding, the technical solution of the present disclosure 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 memory, A number of instructions are included to enable a computer device (which may be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in the various embodiments of the present disclosure. The aforementioned memory includes: U disk, read-only memory (Read-Only Memory, ROM), random access memory (Random Access Memory, RAM), mobile hard disk, magnetic disk or optical disk and other media that can store program codes.

Those of ordinary skill in the art can understand that all or part of the steps in the various methods of the foregoing embodiments can be completed by a program instructing relevant hardware. The program can be stored in a computer-readable memory, and the memory can include : Flash disk, read-only memory, random access device, magnetic disk or CD, etc.

The embodiments of the present disclosure are described in detail above, and specific examples are used in this article to illustrate the principles and implementation of the present disclosure. The descriptions of the above embodiments are only used to help understand the methods and core ideas of the present disclosure; at the same time, for Those of ordinary skill in the art, based on the ideas of the present disclosure, will have changes in the specific implementation and the scope of application. In summary, the content of this specification should not be construed as limiting the present disclosure.

Claims

An automatic driving simulation method, characterized in that it includes:

The message manager receives the first vehicle state information sent by the vehicle simulator, where the first vehicle state information includes first chassis information and first positioning information;

The message manager performs format conversion on the first chassis information and the first positioning information, obtains second chassis information and second positioning information, and sends the second chassis information and the second chassis information to the automatic driving system. Positioning information;

The message manager receives the first control signal sent by the automatic driving system, converts the format of the first control signal to obtain a second control signal, and the second control signal is used for the vehicle simulator to update the State the vehicle status information;

The message manager sends the second control signal to the vehicle simulator.
The method of claim 1, wherein:

After the message manager sends the second control signal to the vehicle simulator, the method further includes:

The message manager receives the second vehicle state information sent by the vehicle simulator, where the second vehicle state information includes information obtained by the vehicle simulator after updating the vehicle state information according to the second control signal The third chassis information and the third positioning information.
The method according to claim 1 or 2, wherein the second control signal includes one or more of the following: positioning information to be processed, throttle data, braking data, gear position, steering wheel angle;

and / or,

The first chassis information includes one or more of the following: speed, acceleration, and attitude information; the attitude information includes one or more of the following: yaw angle, steering wheel angle.
The method according to any one of claims 1-3, wherein the method further comprises:

The message manager performs format conversion on the first chassis information and the first positioning information, obtains the information of the target vehicle, and sends the information of the target vehicle to the agent manager, where the target vehicle is the target vehicle. For the simulated vehicle in the vehicle simulator, the information of the target vehicle is used to: the agent manager updates the information of the agent in the vehicle simulation scene according to the information of the target vehicle when the vehicle simulation scene is loaded. State to obtain first perception information;

The message manager performs format conversion on the first perception information, obtains second perception information, and sends the second perception information to the automatic driving system, so that the automatic driving system is based on the second perception information Performing decision planning with the second vehicle state information to obtain the first control signal.
A message manager, characterized in that it comprises:

A transmission module for receiving first vehicle state information sent by a vehicle simulator, where the first vehicle state information includes first chassis information and first positioning information;

The conversion module is used for format conversion of the first chassis information and the first positioning information to obtain second chassis information and second positioning information; the transmission module is also used for sending the first chassis information to the automatic driving system 2. Chassis information and the second positioning information;

The transmission module is further configured to receive the first control signal sent by the automatic driving system; the conversion module is also configured to perform format conversion on the first control signal to obtain a second control signal, and the second control signal is The control signal is used by the vehicle simulator to update the vehicle state information;

The transmission module is further configured to send the second control signal to the vehicle simulator.
The message manager according to claim 5, wherein:

The transmission module is further configured to receive second vehicle status information sent by the vehicle simulator after sending the second control signal to the vehicle simulator, wherein the second vehicle status information includes The third chassis information and third positioning information obtained after the vehicle simulator updates the vehicle state information according to the second control signal.
The message manager according to claim 5 or 6, wherein the second control signal comprises: positioning information to be processed, throttle data, brake data, gear position and/or steering wheel angle;

and / or,

The first chassis information includes speed, acceleration and/or attitude information, and the attitude information includes a yaw angle and/or a steering wheel angle.
The message manager according to any one of claims 5-7, wherein:

The conversion module is also used for format conversion of the first chassis information and the first positioning information to obtain information of the target vehicle; the transmission module is also used for sending the target vehicle to the agent manager The information of the target vehicle is used to: the agent manager updates the state of the agent in the vehicle simulation scene according to the information of the target vehicle when the vehicle simulation scene is loaded to obtain the first A perception information;

The conversion module is further configured to convert the format of the first perception information to obtain second perception information; the transmission module is also configured to send the second perception information to the automatic driving system so that all The automatic driving system performs decision planning according to the second perception information and the second vehicle state information, and obtains the first control signal.
An automatic driving simulation test system, which is characterized in that it comprises:

An automatic driving system, a vehicle simulator, and a message manager according to any one of claims 5-8.
The system according to claim 9, wherein the automatic driving system comprises a positioning module, a map module, a decision planning module and a controller, wherein:

The map module is used to load a map and display at least one target vehicle on the map;

The positioning module is configured to obtain second chassis information and second position information from the message manager, and determine and update the target vehicle in the map according to the second chassis information and the second position information , The target vehicle is a simulated vehicle in the vehicle simulator;

The decision planning module is configured to determine the driving decision result of the target vehicle in the map according to the state of the target vehicle and the second perception information from the message manager;

The controller is configured to obtain a first control signal according to the driving decision result of the target vehicle, and send the first control signal to the message manager.
The system according to claim 9 or 10, wherein the vehicle simulator stores a vehicle dynamics model, and the vehicle dynamics model is pre-established based on data collected by actual vehicle sensors during the driving process of the vehicle;

The vehicle simulator is used for:

Acquiring a second control signal sent by the message manager;

Updating vehicle state information based on the vehicle dynamics model and the second control signal to obtain second vehicle state information, where the second vehicle state information includes third chassis information and third positioning information;

Sending the second vehicle status information to the message manager.
The system according to claim 11, wherein the second control signal includes positioning information to be processed, throttle data, braking data, gear position, and steering wheel angle;

The vehicle simulator is specifically used to obtain the accelerator data, brake data, and gear in the second control signal according to the preset mapping relationship between the accelerator data, brake data, gear position of the vehicle and the speed and acceleration of the vehicle Corresponding first speed and first acceleration;

Converting the steering wheel angle in the second control signal into the corresponding first front wheel angle according to the preset rotation ratio between the steering wheel angle of the vehicle and the front wheel angle of the vehicle;

Acquiring the first yaw angle of the target vehicle, and the distance from the center of the front wheel axle of the vehicle to the center of gravity of the vehicle and the distance from the center of the vehicle rear axle to the center of gravity of the vehicle;

Based on the positioning information, the first speed, the first acceleration, the first front wheel angle, the first yaw angle, the distance from the center of the front wheel axle of the vehicle to the center of gravity of the vehicle, and the vehicle The distance from the center of the rear wheel axle to the center of gravity of the vehicle to obtain the second vehicle state information.
The system according to claim 11 or 12, further comprising a vehicle dynamics model establishment module for:

Acquire the first data of the real vehicle traveling on the road collected by the sensor. The first data includes multiple sets of throttle data, brake data and speed, acceleration, wherein the throttle data, the brake data and the speed and the speed The acceleration has a corresponding relationship;

Constructing a mapping relationship between accelerator data, brake data, gear position and speed and acceleration of the vehicle based on the first data;

Acquiring second data of a real vehicle traveling on a road collected by a sensor, the second data including multiple sets of steering wheel angles and vehicle front wheel angles, and the steering wheel angle and the vehicle front wheel angle have a corresponding relationship;

Constructing a rotation proportional relationship between the steering wheel angle of the vehicle and the front wheel angle of the vehicle based on the second data;

A vehicle dynamics model is obtained based on the mapping relationship and the rotation ratio relationship.
The system according to any one of claims 9-13, further comprising:

Agent manager for:

Load a vehicle simulation scene, the vehicle simulation scene includes an agent, and the agent includes at least one vehicle;

Receiving the information of the target vehicle from the message manager, and updating the state of the agent in the vehicle simulation scene according to the information of the target vehicle to obtain first perception information;

Sending the first perception information to the message manager.
The system according to claim 14, wherein the agent manager is further used for:

Sending the information of the simulated vehicle in the vehicle simulation scene to other agents in the vehicle simulation scene, so that the other agents can update their own state according to the information of the simulated vehicle; and send the other agents The information of is sent to the simulated vehicle, so that the simulated vehicle updates its own state according to the information of the other agent;

The intelligent body also includes one or more of the following: non-motor vehicles, animals, pedestrians, traffic cones, traffic lights, traffic signs, road signs, lane lines, and obstacles.
An electronic device, comprising a processor and a memory, the memory is used to store a computer program, the computer program is configured to be executed by the processor, and the processor is used to execute claims 1-4 The method according to any one, or, the processor is used to control the operation of the message manager according to any one of claims 5-8, or to control the automatic driving according to any one of claims 9-15 The simulation test system is running.
A computer-readable storage medium, wherein the computer-readable storage medium is used to store a computer program, wherein, when the computer program is called by a processor, the processor executes any of claims 1-4 The method according to one item, or, makes the processor control the operation of the message manager according to any one of claims 5-8, or makes the processor control the operation according to any one of claims 9-15 The described automatic driving simulation test system is running.
A computer program product, the computer program product comprising a computer program or instruction, in the case that the computer program or instruction runs on a computer, the computer is caused to execute the method according to any one of claims 1 to 4, Alternatively, the computer is made to control the operation of the message manager according to any one of claims 5-8, or the computer is made to control the operation of the automatic driving simulation test system according to any one of claims 9-15.