Simulation method and system for autonomous driving

Abstract

The automatic driving simulation method of the present invention belongs to the technical field of automatic driving simulation methods, and solves the technical problem that the existing method only uses its own ideal model and ignores the actual parameter changes after the vehicle is worn. It is suitable for updating vehicle simulation data. The vehicle is equipped with a simulation system and automatic driving software. The method includes: when the automatic driving software inputs a signal, the simulation system is controlled to start and the output data of the simulation system is obtained; after the vehicle is started, the state parameters of the vehicle and the real test data of its scene parameters are obtained in real time; the simulation data of the simulation system is updated according to the state parameters and the real test data of the scene parameters. The present invention is used to improve the accuracy of simulation.

Description

Technical Field

[0001] The present invention belongs to the technical field of self-driving simulation technology, and in particular relates to a simulation method and system for automatic driving. Background Art

[0002] In the autonomous driving industry, mass production is the ultimate goal of the industry. As an excellent method for testing and production of traditional vehicle OEMs, HIL (hardware in the loop) simulation system is still an irreplaceable tool method on the road to mass production of autonomous driving due to the high coupling between autonomous driving and traditional vehicles.

[0003] High-level autonomous driving systems require multi-dimensional simulation tests for control, perception, planning decisions and even hardware drivers. Traditional HIL systems only have a small amount of road, vehicle and obstacle information, lack many key simulation elements, or are unable to truly restore complex scenarios in reality. In the field of autonomous driving, there are also many self-developed simulation systems based on computer hosts to improve the realism of environmental simulation, but ignore the accuracy of vehicle models.

[0004] In view of this, the present invention is proposed. Summary of the invention

[0005] The purpose of the present invention is to provide a simulation method for autonomous driving, which solves the technical problem that the existing method only uses its own ideal model and ignores the actual parameter changes after vehicle wear. The technical solution of this case has many technical benefits, as described below:

[0006] A simulation method for autonomous driving is provided, which is applicable to updating vehicle simulation data, wherein the vehicle is equipped with a simulation system and autonomous driving software, and the method comprises:

[0007] When the automatic driving software inputs a signal, the simulation system is controlled to start and the output data of the simulation system is obtained;

[0008] After the vehicle is started, the vehicle status parameters and the real test data of its scenario parameters are obtained in real time;

[0009] The simulation data of the simulation system is updated based on the real test data of the state parameters and scene parameters.

[0010] In a preferred or optional embodiment, the method for updating simulation data of a simulation system according to the state parameters and scene parameters real test data includes:

[0011] The output data, state parameters and scene parameter real test data are fitted by the full least squares method to determine the fitting parameters;

[0012] The fitting parameters determine updated model parameters of the simulation system, and the updated model parameters are used to update the scene simulation model of the simulation system.

[0013] In a preferred or optional embodiment, the method for determining update model parameters of a simulation system by fitting parameters includes:

[0014] Get the simulation model parameters in the current simulation system;

[0015] The fitting parameters and the simulation model parameters are fused through a Kalman filter to determine the updated model parameters.

[0016] Secondly, an autonomous driving simulation system is provided, which is suitable for updating vehicle simulation data. The vehicle is equipped with a simulation system and autonomous driving software, and the system includes:

[0017] An acquisition unit, which inputs a signal to the autonomous driving software and controls the simulation system to start, acquires output data of the simulation system and acquires real test data of the vehicle's state parameters and scene parameters in real time;

[0018] The calculation unit is used to update the simulation data of the simulation system according to the real test data of the state parameters and the scene parameters.

[0019] In a preferred or optional embodiment, the acquisition unit is further used to acquire simulation model parameters in the current simulation system;

[0020] The calculation unit is used to determine the fitting parameters, and the fitting is performed by the full least square method according to the output data, the state parameters and the real test data of the scene parameters to determine the fitting parameters;

[0021] The fitting parameters determine updated model parameters of the simulation system, and the updated model parameters are used to update the scene simulation model of the simulation system.

[0022] In a preferred or optional implementation, the calculation unit is further configured to fuse the fitting parameters and the simulation model parameters through a Kalman filter to determine the updated model parameters.

[0023] In a preferred or optional embodiment, the simulation system includes a vehicle dynamics model simulator, which receives the updated model parameters to update the original scene data stored in the simulation system.

[0024] In a preferred or optional embodiment, the vehicle dynamics model simulator includes an operating mode selection, supports independent operating tests of multiple simulation scenario models, and / or includes a perception test mode that can combine multiple simulation scenario models for testing the stability and safety of the object under extreme scenario conditions.

[0025] In a preferred or optional embodiment, the vehicle is also equipped with an embedded platform for transmitting sensor data via TCP / UDP, and the updated model parameters are transmitted to the vehicle dynamics model simulator via the embedded platform.

[0026] Compared with the prior art, the technical solution provided by the present invention has the following beneficial effects:

[0027] The method provided in this case takes into account the real test data of the scenario parameters and combines them with the vehicle's state parameters to update the data in the simulation system in real time and improve the accuracy of the vehicle model. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0029] Figure 1 It is a schematic diagram of the process of the present invention; DETAILED DESCRIPTION

[0030] The following describes the embodiments of the present invention through specific examples, and those skilled in the art can easily understand other advantages and effects of the present invention from the contents disclosed in this specification. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all of the embodiments. The present invention can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present invention. It should be noted that the following embodiments and features in the embodiments can be combined with each other without conflict. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work belong to the scope of protection of the present invention.

[0031] It should be noted that various aspects of the embodiments within the scope of the appended claims are described below. It should be apparent that the aspects described herein can be embodied in a wide variety of forms, and any specific structure and / or function described herein is merely illustrative. Based on the present invention, it should be understood by those skilled in the art that an aspect described herein can be implemented independently of any other aspect, and two or more of these aspects can be combined in various ways. For example, any number of aspects described herein can be used to implement the device and / or practice the method. In addition, other structures and / or functionalities other than one or more of the aspects described herein can be used to implement this device and / or practice this method.

[0032] It should also be noted that the illustrations provided in the following embodiments are only schematic illustrations of the basic concept of the present invention. The drawings only show components related to the present invention rather than being drawn according to the number, shape and size of components in actual implementation. In actual implementation, the type, quantity and proportion of each component may be changed arbitrarily, and the component layout may also be more complicated.

[0033] In addition, in the following description, specific details are provided to facilitate a thorough understanding of the examples. However, those skilled in the art will understand that aspects can be practiced without these specific details. In order to enable those skilled in the art to better understand the scheme of the present invention, the present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. The terms "first" and "second" are used for descriptive purposes only and are not to be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the present invention, unless otherwise stated, "multiple" means two or more.

[0034] In the current industry, the HIL simulation software of vehicle OEMs tends to focus on high-precision vehicle dynamics simulation. Internet industry simulation tends to focus on the verification and development of upper-level software algorithms, ignoring the safety and importance of vehicle dynamics simulation. The patent of this invention takes into account both high-precision vehicle dynamics models and highly realistic environment simulators. The patent of this invention evaluates the growth of the tested system object based on the historical statistics of simulation data, which helps developers to better discover and solve problems to a certain extent.

[0035] like Figure 1 The autonomous driving simulation method is suitable for updating vehicle simulation data, where the vehicle is equipped with a simulation system and autonomous driving software, and the method includes:

[0036] S101: When the automatic driving software inputs a signal, the control simulation system is started, and the output data of the simulation system is obtained. The simulation system stores multiple scene simulation models, and input is performed according to the model determined by the driving;

[0037] S102: After the vehicle is started, the vehicle status parameters and the real test data of the scene parameters are obtained in real time, where:

[0038] The state parameters of the vehicle, including vehicle speed, acceleration, and the working parameters of its corresponding components, can be determined based on the vehicle simulation model in the prior art, such as the vehicle body dynamics model, engine model, motor model, tire model, brake and transmission system model, etc., to output real-time data. The real test data of the scene parameters is the detection function of the camera, laser radar, millimeter wave radar, and ultrasonic radar installed on the vehicle, generating the raw sensor data as the real scene data.

[0039] It should be pointed out that in the current industry, the HIL simulation software of vehicle OEMs tends to be highly accurate in vehicle dynamics simulation. Internet industry simulation tends to be focused on the verification and development of upper-level software algorithms, ignoring the safety of vehicle dynamics simulation. Only using its own ideal model, it ignores the technical issues of vehicle wear and tear and scene changes. This case aims to update the data of the simulation system by acquiring real-time real scene data.

[0040] S103: updating the simulation data of the simulation system according to the real test data of the state parameters and the scene parameters, specifically:

[0041] The output data, state parameters and scene parameter real test data are fitted by the full least squares method to determine the fitting parameters. The fitting parameters determine the updated model parameters of the simulation system. The updated model parameters are used to update the scene simulation model of the simulation system. Specifically: the simulation data for updating the simulation system cannot be used directly in the simulator. Therefore, it is necessary to match them through fusion, such as obtaining the simulation model parameters in the current simulation system. The fitting parameters and the simulation model parameters are fused through the Kalman filter to determine the updated model parameters. The updated model parameters are transmitted to the vehicle dynamics model simulator to complete the update of the original scene model data to ensure the safety of the vehicle dynamics simulation.

[0042] Secondly, an autonomous driving simulation system is provided, which is suitable for updating vehicle simulation data. The vehicle is equipped with a simulation system and autonomous driving software, and the system includes:

[0043] An acquisition unit, which inputs a signal to the autonomous driving software and starts the control simulation system, acquires the output data of the simulation system and acquires the real test data of the vehicle's state parameters and scene parameters in real time;

[0044] The computing unit is used to update the simulation data of the simulation system according to the real test data of the state parameters and the scene parameters.

[0045] As a specific implementation method provided in this case, the acquisition unit is also used to acquire simulation model parameters in the current simulation system;

[0046] A calculation unit, used for determining fitting parameters, and determining the fitting parameters by fitting the output data, the state parameters and the real test data of the scene parameters through the full least square method;

[0047] The fitting parameters determine the updated model parameters of the simulation system, and the updated model parameters are used to update the scene simulation model of the simulation system, such as by fusing through a Kalman filter to determine the updated model parameters.

[0048] As a specific implementation method provided in this case, the simulation system includes a vehicle dynamics model simulator, which receives updated model parameters to update the original scene data stored in the simulation system.

[0049] As a specific implementation method provided in this case, the vehicle dynamics model simulator includes an operation mode selection, supports independent operation tests of multiple simulation scenario models, and / or includes a perception test mode that can combine multiple simulation scenario models for testing the stability and safety of the object under extreme scenario conditions.

[0050] Responsible for the simulation mode of ADHIL. On the one hand, it is the operation mode selection of the simulator, which supports independent operation test of each module, that is, the operation frequency of each module can be different; it also supports the same frequency operation of each module to ensure the synchronization of the operation frequency of each module; the second aspect refers to the difference in test modules. According to the test requirements, only the control test mode, planning test mode or perception test mode can be turned on, or the turned-on modules can be combined to increase the upper limit of the test, which is used to test the stability and safety of the test object under extreme scenario conditions.

[0051] As a specific implementation method provided in this case, the vehicle is also equipped with an embedded platform for transmitting sensor data via TCP / UDP, and the updated model parameters are transmitted to the vehicle dynamic model simulator through the embedded platform.

[0052] The embedded platform is an automotive-grade domain controller platform for autonomous driving systems. It integrates AP (adaptive platform) and CP (classic platform) communication architectures that comply with the AUTOSAR (AUTomotive Open System Architecture) specifications. The processor is responsible for running autonomous driving software such as control planning and perception, and evaluating the computing power and memory required for each module.

[0053] The above is a detailed introduction to the product provided by the present invention. Specific examples are used in this article to illustrate the principle and implementation method of the present invention. The description of the above embodiments is only used to help understand the core idea of ​​the present invention. It should be pointed out that for ordinary technicians in this technical field, without departing from the principle of invention, several improvements and modifications can be made to the invention, and these improvements and modifications also fall within the scope of protection of the invention claims.

Claims

1. A simulation method for autonomous driving, applicable to updating vehicle simulation data, wherein the vehicle is equipped with a simulation system and autonomous driving software, characterized in that: The method comprises: When the automatic driving software inputs a signal, the simulation system is controlled to start and the output data of the simulation system is obtained; After the vehicle is started, the vehicle status parameters and the real test data of its scenario parameters are obtained in real time; According to the state parameters and the real test data of the scene parameters, the simulation data of the simulation system is updated, including the output data, the state parameters and the real test data of the scene parameters are fitted by the least square method to determine the fitting parameters; the fitting parameters determine the update model parameters of the simulation system, and the update model parameters are used to update the scene simulation model of the simulation system, wherein the method of determining the update model parameters of the simulation system by the fitting parameters includes: The simulation model parameters in the current simulation system are obtained, and the fitting parameters and the simulation model parameters are fused through a Kalman filter to determine the updated model parameters.

2. An autonomous driving simulation system, suitable for updating vehicle simulation data, wherein the vehicle is equipped with a simulation system and autonomous driving software, characterized in that: The system comprises: An acquisition unit, which inputs a signal to the autonomous driving software and controls the simulation system to start, acquires output data of the simulation system and acquires real test data of the vehicle's state parameters and scene parameters in real time; A calculation unit is used to update the simulation data of the simulation system according to the state parameter and the real test data of the scene parameter, including fitting the output data, the state parameter and the real test data of the scene parameter by the least square method to determine the fitting parameters; the fitting parameters determine the update model parameters of the simulation system, and the update model parameters are used to update the scene simulation model of the simulation system, wherein the method of determining the update model parameters of the simulation system by the fitting parameters includes: The simulation model parameters in the current simulation system are obtained, and the fitting parameters and the simulation model parameters are fused through a Kalman filter to determine the updated model parameters.

3. The simulation system according to claim 2, characterized in that: The simulation system includes a vehicle dynamics model simulator, which receives the updated model parameters to update the stored original scene data in the simulation system.

4. The simulation system according to claim 3, characterized in that: The vehicle dynamics model simulator includes an operating mode selection, supports independent operating tests of multiple simulation scenario models, and / or includes a perception test mode that can combine multiple simulation scenario models to test the stability and safety of the object under extreme scenario conditions.

5. The simulation system according to claim 4, characterized in that: The vehicle is also equipped with an embedded platform for transmitting sensor data via TCP / UDP, and the updated model parameters are transmitted to the vehicle dynamics model simulator via the embedded platform.

Images