CN115983033A

CN115983033A - Automatic driving simulation test method and system and simulator equipment

Info

Publication number: CN115983033A
Application number: CN202310066108.XA
Authority: CN
Inventors: 张国星; 姚卫锋; 郭正东; 王成法
Original assignee: Beijing Baidu Netcom Science and Technology Co Ltd
Current assignee: Beijing Baidu Netcom Science and Technology Co Ltd
Priority date: 2023-01-12
Filing date: 2023-01-12
Publication date: 2023-04-18

Abstract

The invention provides an automatic driving simulation test method, an automatic driving simulation test system and analog machine equipment, and relates to the technical field of artificial intelligence, in particular to the technical fields of automatic driving, automatic driving tests, intelligent transportation and the like. The specific implementation scheme is as follows: receiving first driving instruction information sent by at least one interactive device; generating first vehicle state information obtained by the test vehicle responding to the first driving instruction information; determining whether the first vehicle state information matches first expected outcome information; and under the condition that the first vehicle state information is not matched with the first expected result information, generating a first test case, and realizing the automatic driving simulation test of the driver in the loop.

Description

Automatic driving simulation test method and system and simulator equipment

Technical Field

The present disclosure relates to the field of artificial intelligence technologies, and in particular, to the technical fields of automatic driving, automatic driving tests, intelligent transportation, and the like, and in particular, to an automatic driving simulation test method, system, and simulator device.

Background

With the development of artificial intelligence algorithm, the automatic driving technology is greatly improved. The autonomous driving simulation test may test the stability, reliability, etc. of an autonomous driving algorithm placed in an autonomous vehicle before the autonomous vehicle is on the road.

Disclosure of Invention

The disclosure provides an automatic driving simulation test method, an automatic driving simulation test system and analog machine equipment.

According to an aspect of the present disclosure, there is provided an automatic driving simulation test method, including:

receiving first driving instruction information sent by at least one interactive device;

generating first vehicle state information obtained by the test vehicle responding to the first driving instruction information;

determining whether the first vehicle state information matches first expected outcome information;

generating a first test case if the first vehicle status information does not match the first expected result information.

According to another aspect of the present disclosure, there is provided an automatic driving simulation test system, including: the system comprises an interactive terminal and a simulator device;

the interactive terminal is used for receiving first driving instruction information sent by at least one interactive device accessed to the interactive terminal and sending the first driving instruction information to the simulator device;

the simulator device is used for receiving first driving instruction information sent by the interactive terminal, generating first vehicle state information obtained by a test vehicle responding to the first driving instruction information, and generating a first test case based on the first vehicle state information.

According to another aspect of the present disclosure, there is provided a simulator apparatus including:

the analog machine equipment is used for receiving second driving instruction information sent by at least one interactive device connected with the analog machine equipment, generating second vehicle state information obtained by a test vehicle responding to the second driving instruction information, and generating a second test case based on the second vehicle state information.

According to another aspect of the present disclosure, there is provided a non-transitory computer readable storage medium having stored thereon computer instructions for causing the computer to perform the method of any one of the present disclosure.

According to another aspect of the present disclosure, a computer program product is provided, comprising a computer program which, when executed by a processor, implements the method of any one of the present disclosure.

The embodiment of the disclosure realizes the automatic driving simulation test of the driver in the ring.

It should be understood that the statements in this section do not necessarily identify key or critical features of the embodiments of the present disclosure, nor do they limit the scope of the present disclosure. Other features of the present disclosure will become apparent from the following description.

Drawings

The drawings are included to provide a better understanding of the present solution and are not to be construed as limiting the present disclosure. Wherein:

FIG. 1 is a schematic diagram of an automated driving simulation test method according to the present disclosure;

FIG. 2 is a schematic diagram of an autonomous driving system in a vehicle control gaming state with a driver during true driving according to the present disclosure;

FIG. 3 is a schematic diagram of the automated driving system after simulated access to the driver and simulated driver in a vehicle control gaming state according to the present disclosure;

FIG. 4 is a schematic diagram of an automated driving simulation test system according to the present disclosure;

FIG. 5 is a pictorial illustration of an accessible interaction device according to the present disclosure;

FIG. 6 is another schematic diagram of an automated driving simulation testing system according to the present disclosure;

FIG. 7 is yet another schematic diagram of an automated driving simulation testing system according to the present disclosure;

FIG. 8 is a schematic diagram of an autopilot simulation test case generation according to the present disclosure;

FIG. 9 is yet another schematic illustration of an automated driving simulation test system according to the present disclosure;

FIG. 10 is a block diagram of an electronic device used to implement the automated driving simulation test method of an embodiment of the present disclosure.

Detailed Description

Exemplary embodiments of the present disclosure are described below with reference to the accompanying drawings, in which various details of the embodiments of the disclosure are included to assist understanding, and which are to be considered as merely exemplary. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the present disclosure. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.

In the test of the automatic driving system, the drive test is an indispensable link. The automatic driving system is a product with highly integrated software and hardware, and under the condition that a driver participates in the automatic driving system test, a game relationship exists between the driver and the automatic driving system, namely, who takes over the control right of the vehicle. The automated driving simulation test is an important link for verifying the safety of the automated driving system before the automated driving vehicle loaded with the automated driving system goes on the road. Specifically, the autopilot simulation test may test the stability, reliability, etc. of an autopilot algorithm placed in an autopilot vehicle prior to the autopilot vehicle being on the road.

In The related art, the automatic driving simulation test mainly uses Software In The Loop (SIL) test, uses Hardware In The Loop (HIL) test as an auxiliary test, and uses few Vehicle In The Loop (VIL) tests, specifically, selects a test mode as required. However, the tested object of the software in-loop test is an automatic driving algorithm (namely software), the dependence on hardware is less, the test mode is single, users cannot be accessed, and then the state and the flow of the man-machine game on the road are difficult to reproduce; the hardware-in-loop test is a test aiming at the stability of the hardware, needs to be accessed into professional hardware equipment (such as various controllers on an automobile and the like), and has high test cost; the vehicle loop test needs to depend on whole vehicle hardware and take over at any time manually to carry out actual road side, and the human cost that consumes is big, test cycle length.

An automatic driving system for on-road testing is to deploy an automatic driving algorithm tested by software in a ring to a real vehicle to detect whether the automatic driving system on the real vehicle has problems, at the moment, the tested automatic driving system not only comprises the automatic driving algorithm tested by the software in the ring test, but also comprises hardware (such as a whole vehicle, a controller and the like) and a driver, under the condition, the automatic driving algorithm, the hardware and the driver are required to be matched with each other, and if the automatic driving system is designed imperfectly, faults or accidents are easy to occur. Moreover, due to the complexity of the automatic driving system, there may be more fault points, if an accident occurs in the road test, the technical trust crisis of the automatic driving system is easily caused, and the road test (i.e. the road test) also needs to occupy a certain amount of manpower and is limited by the manual working time, so that the test efficiency of the road test is low.

The test method of completely using software to test and then directly getting on the vehicle has the problems that the automatic driving system is in a man-machine game state when working on the vehicle, a driver interferes with a steering wheel, presses a button in an unexpected range and the like, and the operation of the automatic driving system can be influenced by the operation, so that the automatic driving system is not preferable to be completely closed or opened.

In order to realize a complete vehicle end simulation test of a driver in a loop, the embodiment of the disclosure provides an automatic driving simulation test method, which comprises the following steps: receiving first driving instruction information sent by at least one interactive device; generating first vehicle state information obtained by the test vehicle responding to the first driving instruction information; determining whether the first vehicle state information matches first expected outcome information; generating a first test case if the first vehicle status information does not match the first expected result information.

In the embodiment of the disclosure, first driving instruction information sent by at least one interactive device is received, access of a user (driver) is realized, a man-machine game state is simulated, first vehicle state information obtained by a test vehicle responding to the first driving instruction information is generated, complete vehicle end test of the driver on a ring is realized, a first test case is generated under the condition that the first vehicle state information is determined not to be matched with first expected result information, and the generation of the test case under the condition that a test result is not matched with an expected result is realized, so that a real drive test case is supplemented or replaced, and the cost and the test risk of automatic drive test are reduced.

The automatic driving simulation test method, the automatic driving simulation test system and the simulator device provided by the embodiment of the disclosure can be applied to scenes that a driver or a passenger needs to be accessed to carry out automatic driving system test and the like during automatic driving simulation test.

The following describes in detail an automatic driving simulation test method provided by the embodiment of the present disclosure.

The automatic driving simulation test method provided by the embodiment of the disclosure can be applied to an automatic driving simulation test system or a simulator device and the like.

Referring to fig. 1, an automatic driving simulation test method provided by the embodiment of the present disclosure includes the following steps:

s101, receiving first driving instruction information sent by at least one interactive device.

In the embodiment of the disclosure, the automatic driving simulation test system or the simulator device can be simultaneously accessed to various interactive devices, so that flexible hardware device access is realized, and the hardware cost for testing the automatic driving system is reduced. Correspondingly, a driver or a user can send first driving instruction information to the automatic driving simulation test system or the simulator device through the interaction device, so that the simulated driver access test is realized.

In one example, the Virtual Reality cockpit refers to a device and an interface for restoring the cockpit in a laboratory through a Virtual Reality (VR) technology or a Mixed Reality (MR) technology, for verifying whether human-computer interaction is properly designed, or for training a driver. In the embodiment of the disclosure, the principle of a virtual reality cockpit is utilized, and the interactive device is accessed to the automatic driving simulation test system or the analog machine device, so that the first driving instruction information sent by a driver or a user through the interactive device is received, and the access of the simulated driver is realized.

The first driving instruction information may include at least one piece of first driving information, and a type and a function corresponding to each piece of first driving information. For example, the first driving information may include, for example, adjusting the steering wheel to the left by 10 degrees, adjusting the throttle to increase the fuel by 10%, and the like, the type corresponding to the first driving information may include, for example, a control type, a plan type, and the like, and the corresponding function of the first driving information may include, for example, adjusting the steering wheel direction, adjusting the throttle to increase the fuel, and adjusting the centrifugal force of the vehicle, and the like.

In one possible implementation, the interaction device may include at least one of: a consumer interaction device, a mechanical interaction device, a biological interaction device, and a physical interaction device; the consumer interaction device comprises: wearable equipment and wireless device, mechanical interaction equipment includes: steering wheel, driving lever, throttle, brake, mouse and keyboard, biological interaction equipment includes: helmet display and brain-computer interface, the physical interaction equipment includes: a physical sensor.

The physical sensor is a sensor for detecting a physical quantity, such as a piezoelectric sensor, a photoelectric sensor, a piezoresistive sensor, an electromagnetic sensor, and the like, and the physical sensor can detect and transmit a physical quantity, such as the magnitude of inertia of a test vehicle and the magnitude of centrifugal force of the vehicle.

Illustratively, the consumer interaction Device, the mechanical interaction Device, the biological interaction Device, the physical interaction Device, and the like may be wirelessly connected to the automatic driving simulation test system or the simulation Machine Device through a wireless connection or an Interface connection, so that a user may send first driving instruction information to the automatic driving simulation test system or the simulation Machine Device through an input Device such as a computer keyboard, a steering wheel, a user tablet Device (PAD) or a mobile Device, a Human Machine Interface (HMI), and the like, so as to simulate a simulation test of the automatic driving system in a Human-Machine game state.

In the embodiment of the disclosure, the automatic driving simulation test system or the simulator device can be simultaneously accessed to the human-computer interaction devices such as the consumer interaction device, the mechanical interaction device, the biological interaction device and the physical interaction device, thereby realizing flexible hardware device access, reducing the hardware cost for testing the automatic driving system, and compared with the human-computer game project with safety risk directly tested on the road, under the condition of highly restoring the test scene on the road, the human-computer interaction test can be realized without a large amount of hardware environment, namely professional devices, and simultaneously reducing the safety risk.

Referring to fig. 1, S102, first vehicle state information obtained by the test vehicle in response to the first driving instruction information is generated.

In one example, in the case of receiving the first driving instruction information, the vehicle model is used to simulate the test vehicle to respond to the first driving instruction information to generate first vehicle state information obtained by the test vehicle in response to the first driving instruction information, where the first vehicle state information may be, for example, information such as the vehicle speed, the position, and the like of the test vehicle.

In one possible embodiment, an autopilot algorithm, which may be an autopilot algorithm tested in a loop by software, is deployed in the autopilot simulation test system or simulator device.

Accordingly, the process of generating the first vehicle state information obtained by the test vehicle in response to the first driving instruction information may be: under the condition of receiving the first driving instruction information, simulating a man-machine game state, and combining a current instruction which is added on a test vehicle by an automatic driving algorithm deployed in an automatic driving simulation test system or a simulator device with the first driving instruction information to generate first vehicle state information which is obtained by the test vehicle responding to the first driving instruction information.

For example, the current instructions that an autopilot algorithm deployed in an autopilot simulation test system or simulator device applies to a test vehicle are: the oil supply amount of the throttle of the vehicle is adjusted and tested to be 30%, and the first driving instruction information is as follows: and adjusting the oil supply amount of the accelerator of the test vehicle to increase by 10%, and further generating a response instruction of the test vehicle: and adjusting the oil supply amount of the accelerator of the test vehicle to be 40% to obtain first vehicle state information of the test vehicle.

S103, determining whether the first vehicle state information is matched with the first expected result information.

And S104, generating a first test case under the condition that the first vehicle state information is not matched with the first expected result information.

The goal of the autopilot in-loop test is to test whether there is a potential problem with the autopilot algorithm, which may be case-based during the test. A case may be a collection of test results in different driving environments, such as including location information of road sign lines and location information of other obstacle vehicles and the like within a specified time period. The case can be generated from a log file of actual drive test or artificially and virtually constructed, and the software runs different automatic driving algorithms on the same case in a loop test to test whether the vehicle controlled by the automatic driving algorithms has collision or other types of traffic accidents and the like.

Wherein the first expected result information represents vehicle state information of the test vehicle during actual driving. Matching the first vehicle state information with the first expected result information, wherein if the first vehicle state information is matched with the first expected result information, the result of the automatic driving simulation test is matched with the drive test result in the real driving process, and the automatic driving system is relatively safe and stable; if the first vehicle state information is not matched with the first expected result information, the result of the automatic driving simulation test is not consistent with the drive test result in the real driving process, the process of the simulation test may have problems, and at this moment, a first test case is generated.

And under the condition that the first vehicle state information generated by the simulation test is not matched with the first expected result information, generating a first test case so as to adjust the automatic driving simulation algorithm subsequently, reproducing the case, reproducing the effect consistent with the real drive test result, and ensuring the stability and the safety of the automatic driving system.

In the embodiment of the disclosure, the first driving instruction information sent by at least one interactive device is received, the access of a user (driver) is realized, the man-machine game state is simulated, the first vehicle state information obtained by a test vehicle responding to the first driving instruction information is generated, the complete vehicle-end test of the driver on a ring is realized, the first test case is generated under the condition that the first vehicle state information is determined to be unmatched with the first expected result information, the generation of the test case under the condition that the test result is not consistent with the expected result is realized, so that the real road test case is supplemented or replaced, the cost and the test risk of the automatic driving test are reduced, the subsequent reappearance and regression of the test case are facilitated, the problems existing in the case are solved, and the stability and the safety of the automatic driving system are guaranteed.

In a possible implementation manner, the first driving instruction information includes at least one first driving information, and a type and a function corresponding to each first driving information; the above method may further comprise:

acquiring first control information for a test vehicle;

for each piece of first driving information, in the case that the type of the first driving information hits the control type and the function hits any function item corresponding to the control type, the generating of the first vehicle state information obtained by the test vehicle in response to the first driving instruction information includes: generating first vehicle state information obtained by the test vehicle responding to the first control information and the first driving information; wherein, the function items corresponding to the control types at least comprise: adjusting the steering wheel direction, adjusting the oil supply amount of the accelerator and adjusting the size of the brake.

The first control information is information for controlling the driving of the test vehicle, and may be, for example, steering wheel steering information (for example, 15 degrees left or 20 degrees right), accelerator fuel supply amount adjustment information, brake adjustment information, and the like. The first control information may be generated initially at the start of the test, or generated by an automatic driving algorithm deployed in an automatic driving simulation test system or a simulator device during the test.

Under the condition that the first driving instruction information is received, the automatic driving simulation test system or the simulator device traverses each piece of first driving information in the first driving instruction information, and under the condition that the type of the first driving information is determined to be in the control type and the function of the first driving information is determined to be in any function item corresponding to the control type, first vehicle state information obtained by the test vehicle responding to the first control information and the first driving information is generated. The control type represents a type for controlling the test vehicle, and any function item corresponding to the control type represents information for controlling a certain function of the test vehicle.

Illustratively, the first control information is: adjust the steering wheel 20 degrees to the right, the first driving information is: adjusting the steering wheel to 5 degrees left, the type to be the control type and the function to adjust the steering wheel direction, and generating first control information (adjusting the steering wheel to 20 degrees right) and first driving information (adjusting the steering wheel to 5 degrees left) of the response of the test vehicle at the moment to obtain first vehicle state information after adjusting the steering wheel to 15 degrees right. The first driving information containing the steering wheel direction is sent by a user through a steering wheel of the mechanical interaction equipment; the first driving information containing the amount of the oil fed by the accelerator is sent by a user through the accelerator of the mechanical interaction equipment; the first driving information containing the adjusted brake size is sent by the user through the brake of the mechanical interaction device, and the like.

In the embodiment of the disclosure, the automatic driving simulation test system or the simulator device can perform unified management on the first driving instruction information, determine the type and the function of the first driving information contained in the first driving instruction information under the condition that the first driving instruction information is received, and then combine the acquired first control information for the test vehicle with the first driving information under the condition that the type hits any one of the function items corresponding to the control type and the function hits any one of the function items corresponding to the control type to generate the first vehicle state information of the corresponding test vehicle, so as to simulate the process of generating the first vehicle state information of the test vehicle under the man-machine game state, and further verify the stability and the safety of the automatic driving system.

In a possible implementation, the method may further include:

for each piece of first driving information, under the condition that the type of the first driving information hits a simulation type and a function hits any function item corresponding to the simulation type, simulating and generating first object state information of objects except the test vehicle based on the first vehicle state information and the first driving information; the function items corresponding to the simulation types at least comprise: the moving speed of the target object, the moving direction of the target object, and the moving probability of the target object.

In the process of the automatic driving simulation test, two vehicles are involved, one is a test vehicle (namely, an automatic driving vehicle to be tested, or called a main vehicle), and the other is a vehicle except the test vehicle (namely, a non-automatic driving vehicle, which can be a vehicle operated by a virtual driver simulated by a computer and also can be called an obstacle vehicle). The state of the vehicle other than the test vehicle has a certain influence on the test of the test vehicle, for example, the speed of the test vehicle is influenced by the position, speed and the like of the vehicle other than the test vehicle.

And under the condition that the first driving instruction information is received, the automatic driving simulation test system or the simulator equipment traverses each piece of first driving information in the first driving instruction information, and under the condition that the type of the first driving information is determined to hit the simulation type and the function of the first driving information hits any function item corresponding to the simulation type, simulating and generating first object state information of objects except the test vehicle on the basis of the first vehicle state information of the test vehicle and the first driving information.

The simulation type represents a type for simulating the state of the object except the test vehicle, and any function item corresponding to the simulation type represents information for simulating a certain attribute or function of the object except the test vehicle. The first object state information may contain information of the position, speed, direction, and the like of the object other than the test vehicle, which may be an obstacle car, a guardrail in the middle of a road, a roadside building, and the like, in a static state or in a dynamic state. The target object may be any object other than the test vehicle.

For example, the first vehicle state information includes a vehicle speed, a position, and a direction of the test vehicle, the first driving information is a moving speed of the obstacle vehicle, the type is a simulation type, and the moving speed of the function as the target object, and at this time, first object state information of an object (including the obstacle vehicle) other than the test vehicle is simulation-generated in conjunction with the moving speed of the obstacle vehicle based on the vehicle speed, the position, and the direction of the test vehicle, wherein the first object state information of the obstacle vehicle generated by the simulation is information including the moving speed, the position, and the direction of the obstacle vehicle generated in conjunction with the vehicle speed, the position, the direction, and the moving speed of the obstacle vehicle of the test vehicle.

Illustratively, the first vehicle state information includes a vehicle speed, a position and a direction of the test vehicle, the first driving information is a movement probability of an obstacle vehicle, the type is a simulation type, and the movement probability of the function is a target object, and at this time, first object state information of an object (including the obstacle vehicle) other than the test vehicle is simulation-generated based on the vehicle speed, the position and the direction of the test vehicle in combination with the movement probability of the obstacle vehicle, wherein the first object state information of the obstacle vehicle generated by the simulation is information including the movement speed, the position, the direction and the movement probability of the obstacle vehicle, generated in combination with the vehicle speed, the position, the direction and the movement probability of the test vehicle. The first driving information including the moving speed of the target object, the moving direction of the target object, or the moving probability of the target object may be sent by the user through a keyboard of the mechanical interaction device, or sent by the user through a wearable device or a wireless device of the consumer interaction device.

In the embodiment of the disclosure, the automatic driving simulation test system or the simulator device can uniformly manage the first driving instruction information, determine the type and the function of the first driving information contained in the first driving instruction information when the first driving instruction information is received, and then combine the first vehicle state information of the generated test vehicle with the first driving information to generate the first object state information of the object except the test vehicle in a simulation manner when the type and the function hit any function item corresponding to the simulation type, so that the automatic driving algorithm can generate the control information for the test vehicle based on the first object state information to realize the closed-loop test of the automatic driving simulation.

In a possible embodiment, the method may further include:

for each piece of first driving information, under the condition that the type of the first driving information hits a planning type and any function item corresponding to the planning type is hit by a function, generating first control information for the test vehicle based on first object state information and the first driving information; the function items corresponding to the planning types at least comprise: heart rate information, magnitude of inertia, and magnitude of centrifugal force of the vehicle.

And under the condition that the first driving instruction information is received, traversing each piece of first driving information in the first driving instruction information by the automatic driving simulation test system or the simulator equipment, and under the condition that the type of the first driving information is determined to hit the planning type and the function of the first driving information is determined to hit any function item corresponding to the planning type, generating first control information aiming at the test vehicle according to the first object state information generated by the simulation and the first driving information.

The planning type represents a type used for planning a path and a driving of the test vehicle, and any function item corresponding to the planning type represents information used for planning the path or the driving of the test vehicle.

For example, the first object state information includes a moving speed, a position, and a direction of the obstacle vehicle, the first driving information is a heart rate of the user, the type is a plan type, and the function is heart rate information, at this time, a user state corresponding to the heart rate of the user may be determined according to a preset correspondence table between the heart rate and the user state, for example, the heart rate of the user is high, the user state is determined to be anxiety, further, according to the moving speed, the position, and the direction of the obstacle vehicle and the anxiety state of the user, first control information for the test vehicle may be intelligently generated (the generation process may be completed by using a pre-trained target model or a preset target information generation algorithm), and the first control information is generated by calculating, according to the moving speed, the position, and the direction of the obstacle vehicle, and in combination with the anxiety state of the user, the control information including a vehicle speed, the position, and the direction of the test vehicle.

Illustratively, the first object state information includes a moving speed, a position and a direction of the obstacle vehicle, the first driving information is a centrifugal force magnitude, a type of the test vehicle is a planning type, and a function of the centrifugal force magnitude of the test vehicle, at this time, a lane bending degree corresponding to the centrifugal force magnitude of the test vehicle may be determined according to a preset correspondence table between the centrifugal force magnitude of the vehicle and the lane bending degree, for example, the centrifugal force magnitude is determined, and the lane bending degree is determined to be large, and further, according to the moving speed, the position, the direction and the lane bending degree of the obstacle vehicle, first control information for the test vehicle (the generation process may also be completed by using a pre-trained target model or a pre-set target information generation algorithm) is intelligently generated, and the first control information includes a vehicle speed, a position, a direction and the like of the test vehicle according to the moving speed, the position and the direction of the obstacle vehicle and is calculated by combining the lane bending degree. The first driving information containing the heart rate information may be sent by the user through a helmet display or a brain-computer interface of the bio-interaction device, the first driving information containing the inertia magnitude and the centrifugal force magnitude of the vehicle, the first driving information containing the heart rate information may be sent by the user through a physical sensor of the physical interaction device, and the like.

In the embodiment of the disclosure, the automatic driving simulation test system or the simulator device can uniformly manage the first driving instruction information, determine the type and the function of the first driving information contained in the first driving instruction information under the condition that the first driving instruction information is received, and then combine the generated first object state information with the first driving information under the condition that the type hits any one of the function items corresponding to the planning type and the function hits the planning type, and intelligently generate the first control information for the test vehicle, so that the first vehicle state information of the test vehicle is further generated based on the first control information, and the closed-loop test of the automatic driving simulation is realized.

Illustratively, the automatic driving simulation test method provided by the embodiment of the present disclosure includes:

the method comprises the steps that firstly, an automatic driving simulation test system or a simulator device receives first driving instruction information sent by at least one interaction device, wherein the first driving instruction information can comprise at least one piece of first driving information and types and functions corresponding to the first driving information.

And step two, acquiring first control information aiming at the test vehicle.

Step three, aiming at each piece of first driving information, under the condition that the type of the first driving information hits the control type and the function hits any function item corresponding to the control type, generating first vehicle state information obtained by the test vehicle responding to the first control information and the first driving information; wherein, the function items corresponding to the control types at least comprise: adjusting the steering wheel direction, adjusting the oil supply amount of the accelerator and adjusting the size of the brake.

Step four, for each piece of first driving information, under the condition that the type of the first driving information hits a simulation type and a function hits any function item corresponding to the simulation type, simulating and generating first object state information of objects except the test vehicle based on the first vehicle state information and the first driving information; the function items corresponding to the simulation types at least comprise: the moving speed of the target object, the moving direction of the target object, and the moving probability of the target object.

Step five, aiming at each piece of first driving information, under the condition that the type of the first driving information hits the planning type and the function hits any function item corresponding to the planning type, generating first control information aiming at the test vehicle based on the first object state information and the first driving information; the function items corresponding to the planning types at least comprise: heart rate information, magnitude of inertia, and magnitude of centrifugal force of the vehicle.

The first driving instruction information sent by at least one interactive device is received in the first step, the access of a driver is realized, the second step to the fifth step realize a closed-loop test, and the automatic driving simulation test of the driver in the loop is realized by combining the first step.

Corresponding to the automatic driving simulation test method, the disclosure also provides an automatic driving simulation test system.

Fig. 2 is a schematic diagram of an automatic driving system and a human driver in a vehicle control right game state in a real driving process, the automatic driving system is represented in a dotted line box in fig. 2, a sensing module of the automatic driving system senses position information of a barrier car, a traffic light and other surrounding scenes around a driving vehicle according to sensor data of the driving vehicle, and the sensed position information is respectively sent to a prediction module and a planning module. The positioning module of the automatic driving system positions vehicle state information (such as vehicle speed, accelerator oil supply amount and the like) of a driving vehicle according to sensor data of the driving vehicle and sends the vehicle state information to the planning module. The prediction module predicts the information such as the speed and the direction of the driving vehicle according to the received position information of the barrier vehicle/traffic light and the like to obtain prediction information, and sends the prediction information to the planning module. The planning module plans the route of the driving vehicle according to the prediction information and the vehicle state information to obtain planning information (such as specific information of speed, direction and the like), and sends the planning information to the control module. The control module generates corresponding control information based on the planning information to control the driving vehicle to run according to the control information, and under the condition that the driver is accessed, the driver can also send the control information to the driving vehicle to compete for the control right of the driving vehicle, namely under the condition that the driver is accessed, the driver and the automatic driving system are in a game state, and the control information can be simultaneously sent to the driving vehicle to take over the control right of the driving vehicle.

Referring to fig. 3, fig. 3 is a schematic diagram illustrating an automatic driving system after a simulation is connected to a driver and a simulation that the driver is in a vehicle Control game state, and a Planning and Control (PNC) in fig. 3 corresponds to software modules of the automatic driving system, which may include a sensing module, a positioning module, a prediction module, a Planning module, and a Control module shown in fig. 2. The simulated driver can simulate the reaction of the driver according to the sensor data of the simulated vehicle to give corresponding control information so as to compete for the control right of taking over the vehicle with the game of the automatic driving system.

Referring to fig. 4, an automatic driving simulation test system 400 provided by the embodiment of the present disclosure includes: an interactive terminal 401 and a simulator device 402. The interactive terminal 401 may be any device capable of connecting an interactive device, and the simulator device 402 may be a device which is deployed with an automatic driving algorithm, a vehicle model, and the like and capable of performing an automatic driving simulation test.

The interactive terminal 401 is configured to receive first driving instruction information sent by at least one interactive device accessing the interactive terminal 401, and send the first driving instruction information to the analog device 402;

the simulator device 402 is configured to receive the first driving instruction information sent by the interactive terminal 401, generate first vehicle state information obtained by the test vehicle in response to the first driving instruction information, and generate a first test case based on the first vehicle state information.

In the embodiment of the present disclosure, the interactive terminal 401 may be an independent access hardware device, and may access multiple interactive devices simultaneously, so as to implement flexible hardware device access and reduce hardware cost for testing the autopilot system. A driver or a user can send first driver instruction information to the interactive terminal 401 through the interactive device to achieve simulated driver access testing, and the interactive terminal 401 sends the first driver instruction information to the simulator device 402. The first driving instruction information may include at least one piece of first driving information, and a type and a function corresponding to each piece of first driving information.

In one example, the simulator device 402, upon receiving the first driving instruction information, simulates the test vehicle in response to the first driving instruction information by using the vehicle model to generate first vehicle state information obtained by the test vehicle in response to the first driving instruction information, where the first vehicle state information may be, for example, information of a vehicle speed, a position, and the like of the test vehicle. Or under the condition that the first driving instruction information is received, simulating a man-machine game state, combining a current instruction which is filled on the test vehicle by an automatic driving algorithm deployed in the simulator equipment with the first driving instruction information, and generating first vehicle state information which is obtained by the test vehicle responding to the first driving instruction information.

Further, the simulator device 402 determines whether the first vehicle state information generated by the simulation test meets expectations (i.e., the vehicle state information of the test vehicle in the real driving process), and generates a first test case if the first vehicle state information does not meet expectations, so that the automatic driving simulation algorithm is adjusted subsequently, and the case is reproduced, so that the effect consistent with the real driving test result is reproduced, and the stability and the safety of the automatic driving system are ensured.

In the embodiment of the disclosure, the interactive terminal can be accessed to at least one interactive device, flexible hardware device access is realized, the first driving instruction information sent by the at least one interactive device accessed to the interactive terminal can be received, user (driver) access is realized, the simulation machine device simulates a man-machine game state, the first vehicle state information obtained by the test vehicle responding to the first driving instruction information is generated, complete vehicle-end test of the driver on a loop is realized, the first test case can be further generated based on the generated first vehicle state information, and the generation of the test case is realized, so that a real road test case is supplemented or replaced, the cost and the risk of automatic driving test are reduced, the test case can be conveniently reproduced and regressed subsequently, the problems existing in the test case are solved, and the stability and the safety of the automatic driving system are guaranteed.

In a possible implementation, the above-mentioned interaction device comprises at least one of: a consumer interaction device, a mechanical interaction device, a biological interaction device, and a physical interaction device; the consumer interaction device comprises: wearable equipment and wireless device, mechanical interaction equipment includes: steering wheel, driving lever, throttle, brake, mouse and keyboard, biological interaction equipment includes: helmet display and brain-computer interface, the physical interaction equipment includes: a physical sensor.

Illustratively, as shown in fig. 5, the consumer interaction device, the mechanical interaction device, the biological interaction device, the physical interaction device, and the like may access the interaction terminal 401 in a wireless manner or in an interface manner, so that the user may send the first driving instruction information to the interaction terminal 401 through the interaction device, and further send the first driving instruction information to the simulator device 402 through the interaction terminal 401.

In the embodiment of the disclosure, the interactive terminal can be accessed to the human-computer interaction devices such as the consumer interaction device, the mechanical interaction device, the biological interaction device and the physical interaction device, so that flexible hardware device access is realized, the cost of accessing the interactive device to the automatic driving simulation test is reduced, the problems of data transmission delay, non-uniform hardware interfaces and the like are reduced, and compared with a human-computer game project which is directly tested on the road and has a safety risk, under the condition that the road test scene can be highly restored, a large amount of hardware environments do not need to be arranged, namely, the human-computer interaction test can be realized without professional devices, and meanwhile, the safety risk is reduced.

In one possible implementation, referring to fig. 6, the simulator device 402 includes: a first path planning module 4023, a first agent simulation module 4022, and a first vehicle status update module 4021.

The interactive terminal 401 is specifically configured to receive first driving instruction information sent by at least one interactive device accessing the interactive terminal 401, where the first driving instruction information includes at least one piece of first driving information and a type and a function corresponding to each piece of first driving information; for each piece of first driving information, according to the type and function corresponding to the first driving information and a preset correspondence table between the type and function and the receiving module, the receiving module corresponding to the first driving information is determined in the first path planning module 4023, the first agent simulation module 4022 and the first vehicle state updating module 4021, and the first driving information is sent to the determined receiving module.

In one example, the first driving instruction information sent by the user (or the driver) through the interactive device may be sent to any module of the simulator device 402 through the interactive terminal 401. The interactive terminal 401 is preset with a correspondence table between types and functions and receiving modules, and can perform unified management on the received first driving instruction information. Under the condition that the first driving instruction information is received, a corresponding relation table between preset types and functions and receiving modules is inquired according to the types and the functions corresponding to the first driving information in the first driving instruction information, the receiving modules corresponding to the first driving information are determined in the first path planning module 4023, the first agent simulation module 4022 and the first vehicle state updating module 4021, and after the receiving modules are determined, the first driving information is sent to the corresponding receiving modules.

For example, the first agent simulation module 4022 may be a proxy server, and the first vehicle status update module 4021 may be a vehicle model or the like. The user (or driver) can send the first driving instruction information to any module of the simulator device 402 through the interactive terminal 401 at any stage and any time of the automatic driving simulation test through the interactive device.

In the embodiment of the disclosure, the interactive terminal can be accessed to at least one interactive device, so that flexible hardware device access is realized, the first driving instruction information sent by at least one interactive device accessed to the interactive terminal can be received, access of a user (driver) is realized, a corresponding relation table between types and functions and a receiving module is preset, and the received first driving instruction information can be uniformly managed.

In a possible embodiment, the interactive terminal 401 is specifically configured to query, for each piece of first driving information, a preset type and a correspondence table between functions and receiving modules, determine that the receiving module corresponding to the first driving information is the first vehicle state updating module 4021 when the type of the first driving information hits the control type and the function hits any one of the function items corresponding to the control type, and send the first driving information to the first vehicle state updating module 4021; the function items corresponding to the control types at least comprise: adjusting the steering wheel direction, adjusting the oil supply amount of an accelerator and adjusting the size of a brake;

correspondingly, the first vehicle state updating module 4021 is configured to receive the first control information sent by the first path planning module 4023 and the first driving information sent by the interactive terminal 401, generate first vehicle state information obtained by the test vehicle in response to the first control information and the first driving information, and send the first vehicle state information to the first agent simulation module 4022.

In the embodiment of the present disclosure, the automatic driving simulation test is a driver in-loop test, the automatic driving simulation test can run in a closed loop in the test process, and the test may be started by the first vehicle state updating module 4021 generating first vehicle state information (such as a position, a vehicle speed, an accelerator oil supply amount, and the like) of the test vehicle, and sending the first vehicle state information to the first agent simulation module 4022. After receiving the first vehicle state information of the test vehicle, the first agent simulation module 4022 generates first object state information of objects except the test vehicle in a simulation manner, sends the first object state information to the first path planning module 4023, the first path planning module 4023 generates first control information for the test vehicle according to the first object state information of the objects except the test vehicle, sends the first control information to the first vehicle state update module 4021, the first vehicle state update module 4021 receives the first control information sent by the first path planning module 4023, generates the test vehicle to obtain new first vehicle state information in response to the first control information, and sends the new first vehicle state information to the first agent simulation module 4022, so that the automatic driving simulation test can operate in a closed loop.

In the process of the automatic driving simulation test, the interactive terminal 401 receives first driving instruction information, traverses each piece of first driving information, queries a preset type and a corresponding relation table between functions and receiving modules, determines a receiving module corresponding to each piece of first driving information, determines that the receiving module of the first driving information is the first vehicle state updating module 4021 when the type of the first driving information hits the control type and the function hits any function item corresponding to the control type, and sends the first driving information to the first vehicle state updating module 4021. Therefore, the first vehicle state updating module 4021 can generate the first vehicle state information obtained by the test vehicle in response to the first control information and the first driving information, by combining the first driving information and the first control information sent by the first path planning module 4023.

The control type represents a type for controlling the test vehicle, and any function item corresponding to the control type represents information for controlling a certain function of the test vehicle. The first vehicle state updating module 4021 generates the first control information responded by the test vehicle and the first vehicle state information obtained by the first driving information by combining the first driving information and the first control information, where the first vehicle state updating module 4021 may fuse the first driving information and the first control information, and the fusion may be, for example, superposition, merging, and the like of the information, and then generates the first vehicle state information obtained by the test vehicle responding to the first control information and the first driving information according to the fused information.

In the embodiment of the disclosure, the interactive terminal can perform unified management on the first driving instruction information, and when the first driving instruction information is received, determine a receiving module corresponding to each piece of first driving information included in the first driving instruction information, and when the receiving module is a first vehicle state updating module, the first vehicle state updating module generates corresponding first vehicle state information of the test vehicle by combining the received first control information sent by the first path planning module and the first driving information sent by the interactive terminal, so as to simulate a process of generating the first vehicle state information of the test vehicle in a man-machine game state, and further verify the stability and the safety of the automatic driving system.

In a possible implementation manner, the interactive terminal 401 is specifically configured to query, for each piece of first driving information, a preset type and a correspondence table between a function and a receiving module, determine that the receiving module corresponding to the first driving information is the first agent simulation module 4022 when the type of the first driving information hits the simulation type and the function hits any one of the function items corresponding to the simulation type, and send the first driving information to the first agent simulation module 4022; the function items corresponding to the simulation types at least comprise: the moving speed of the target object, the moving direction of the target object and the moving probability of the target object;

correspondingly, the first agent simulation module 4022 is configured to receive the first vehicle state information sent by the first vehicle state update module 4021 and the first driving information sent by the interactive terminal 401, generate the first object state information of the object other than the test vehicle based on the first vehicle state information and the first driving information in a simulation manner, and send the first object state information to the first path planning module 4023.

In the process of the automatic driving simulation test, the interactive terminal 401 receives first driving instruction information, traverses each piece of first driving information, queries a preset type and a corresponding relation table between functions and receiving modules, determines a receiving module corresponding to each piece of first driving information, determines that the receiving module of the first driving information is the first agent simulation module 4022 when the type of the first driving information hits a simulation type and the function hits any function item corresponding to the simulation type, and sends the first driving information to the first agent simulation module 4022. So that the first agent simulation module 4022 can generate the first object state information of the object other than the test vehicle by simulation in combination with the first driving information and the first vehicle state information of the test vehicle.

The first agent simulation module 4022 generates the first object state information of the object except the test vehicle by simulation in combination with the first driving information and the first vehicle state information, where the first agent simulation module 4022 may fuse the first driving information and the first vehicle state information, for example, superposition, merging, and the like of the information, and then generate the first object state information of the object except the test vehicle by simulation according to the fused information.

In the embodiment of the disclosure, the interactive terminal can uniformly manage the first driving instruction information, determines a receiving module corresponding to the first driving information contained in the first driving instruction information under the condition that the first driving instruction information is received, and when the receiving module is a first intelligent agent simulation module, the first intelligent agent simulation module simulates and generates first object state information of objects except for a test vehicle by combining the received first driving information and the first vehicle state information, so that an automatic driving algorithm can generate control information for the test vehicle based on the first object state information, and a closed-loop test of automatic driving simulation is realized.

In a possible implementation manner, the interactive terminal 401 is specifically configured to query, for each piece of first driving information, a preset type and a correspondence table between a function and a receiving module, determine that the receiving module corresponding to the first driving information is the first path planning module 4023 when the type of the first driving information hits the planning type and the function hits any one of the function items corresponding to the planning type, and send the first driving information to the first path planning module 4023; the function items corresponding to the planning types at least comprise: heart rate information, inertia and vehicle centrifugal force;

correspondingly, the first path planning module 4023 is configured to receive the first object status information sent by the first agent simulation module 4022 and the first driving information sent by the interactive terminal 401, generate first control information for the test vehicle based on the first object status information and the first driving information, and send the first control information to the first vehicle status update module 4021.

In the process of the automatic driving simulation test, the interactive terminal 401 receives first driving instruction information, traverses each piece of first driving information, queries a preset type and a corresponding relation table between functions and receiving modules, determines a receiving module corresponding to each piece of first driving information, determines that the receiving module of the first driving information is a first path planning module 4023 under the condition that the type of the first driving information hits a planning type and the function hits any one of function items corresponding to the planning type, and sends the first driving information to the first path planning module 4023. So that the first path planning module 4023 can generate first control information for the test vehicle in combination with the first driving information and the first object state information generated by the simulation.

The first path planning module 4023 may combine the first driving information and the first object state information generated by the simulation to generate first control information for the test vehicle, where the first path planning module 4023 may fuse the first driving information and the first object state information, for example, superposition, merging, and the like of information, and generate the first control information for the test vehicle according to the fused information.

In the embodiment of the disclosure, the interactive terminal can perform unified management on the first driving instruction information, determine a receiving module corresponding to the first driving information included in the first driving instruction information when the first driving instruction information is received, and when the receiving module is a first path planning module, the first path planning module combines the received first driving information and the first object state information to intelligently generate first control information for the test vehicle, so that the first vehicle state information of the test vehicle is further generated based on the first control information, and a closed-loop test of automatic driving simulation is realized.

In the embodiment of the present disclosure, the interactive terminal 401 may support a user to send driving instruction information to any module in the automatic driving simulation test system in a self-defined manner through any interactive device accessing the interactive terminal 401.

As shown in fig. 7, in an exemplary embodiment, the first path planning module 4023 includes: a planning submodule, a prediction submodule and a control submodule; correspondingly, the first driving information sent by the interactive terminal 401 to the first path planning module 4023 may also be sent to a planning submodule, a prediction submodule, or a control submodule in a refined manner.

As shown in fig. 7, in the process of the automatic driving simulation test, a user may send target driving information to any link of the test through an interactive device accessing an interactive terminal. For example, the first control information is sent to a first vehicle state updating module, so that the first vehicle state updating module generates first vehicle state information obtained by the test vehicle responding to the first control information and the target driving information; or, sending the first object state information to a first intelligent agent simulation module so that the first intelligent agent simulation module generates first object state information (state information corresponding to the barrier vehicles/traffic lights in fig. 7) of the object except the test vehicle based on the first vehicle state information and the target driving information; or, the information is sent to a prediction submodule, so that the prediction submodule predicts information such as a path of the test vehicle based on the first object state information of the object except the test vehicle and the target driving information, and obtains prediction information (for example, the information such as the path of the test vehicle and the vehicle speed can be predicted); or sending the information to a planning submodule so that the planning submodule generates planning information for the test vehicle (such as information for planning a path, a vehicle speed, a direction and the like of the test vehicle) based on the first object state information, the prediction information and the target driving information of the objects except the test vehicle; or, the first control information is sent to the control sub-module, so that the control sub-module generates the first control information for the test vehicle based on the planning information and the target driving information.

In a possible implementation, the automatic driving simulation test system may further include: a first simulation verification module.

The first simulation verification module is used for determining whether the first vehicle state information is matched with the first expected result information or not, and generating a first test case under the condition that the first vehicle state information is not matched with the first expected result information.

For example, as shown in fig. 8, a real driving test and an automatic driving simulation test method according to the embodiment of the present disclosure are respectively used to test an automatic driving algorithm, a first simulation verification module matches first vehicle state information (simulated traffic accident) obtained in a simulation test process with first expected result information (real traffic accident) obtained by the real driving test, detects whether the first vehicle state information obtained by the simulation test is consistent with a real driving test result (first expected result information), if so, it indicates that the simulation test can replace the real driving test, and if not, an algorithm failure case can be generated and stored in a failure case set, so that an engineer can adjust the automatic driving algorithm, or the automatic driving simulation test is used to reproduce the real driving test, so as to recover a result consistent with the real driving test.

In the embodiment of the disclosure, under the condition that the first vehicle state information generated by the simulation test is not matched with the first expected result information, the first test case is generated so as to be convenient for subsequently adjusting the automatic driving simulation algorithm and reproducing the case, so that the effect consistent with the real drive test result is reproduced, and the stability and the safety of the automatic driving system are ensured.

Illustratively, the automatic driving simulation test system provided by the embodiment of the disclosure can perform full-flow simulation tests on an application program, such as automatic travel orders, vehicle arrival, passenger unlocking and boarding, starting to go to a destination, passenger alighting and the like, so as to realize a low-risk test automatic driving system.

The disclosed embodiment also provides a simulator device, which is used for receiving second driving instruction information sent by at least one interactive device accessed to the simulator device, generating second vehicle state information obtained by a test vehicle responding to the second driving instruction information, and generating a second test case based on the second vehicle state information.

In one example, a user may access at least one interactive device through a local machine port of the analog machine device, through which driver access is achieved.

In the embodiment of the disclosure, the simulator device can be connected to at least one interactive device, flexible hardware device connection is realized, second driving instruction information sent by at least one interactive device connected to the simulator device can be received, user (driver) connection is realized, a man-machine game state is simulated, second vehicle state information obtained by a test vehicle responding to the second driving instruction information is generated, complete vehicle-end test of the driver on a loop is realized, a second test case can be further generated based on the generated second vehicle state information, and generation of the test case is realized, so that a real road test case is supplemented or replaced, the cost and the risk of automatic driving test are reduced, the test case is conveniently reproduced and regressed subsequently, problems existing in the case are solved, and the stability and the safety of the automatic driving system are guaranteed.

In one possible embodiment, as shown in fig. 9, a simulator device 900 includes: a driving module 901, a second path planning module 904, a second agent simulation module 903, and a second vehicle status update module 902;

the driving module 901 is configured to receive second driving instruction information sent by at least one interactive device accessing the driving module 901, where the second driving instruction information includes at least one piece of second driving information and types and functions corresponding to the second driving information; for each piece of second driving information, according to the type and function corresponding to the second driving information and a preset correspondence table between the type and function and the receiving module, the receiving module corresponding to the second driving information is determined in the second path planning module 904, the second agent simulation module 903, and the second vehicle state updating module 902, and the second driving information is sent to the determined receiving module.

In one example, the driving module 901 can access the at least one interactive device in a wireless manner or an interface connection manner, so as to realize driver access.

In a possible implementation manner, the driving module is specifically configured to query, for each piece of second driving information, a preset type and a correspondence table between functions and receiving modules, determine, when the type of the second driving information hits the control type and the function hits any one of function items corresponding to the control type, that the receiving module corresponding to the second driving information is a second vehicle state updating module, and send the second driving information to the second vehicle state updating module; the function items corresponding to the control types at least comprise: adjusting the steering wheel direction, adjusting the oil supply amount of an accelerator and adjusting the size of a brake;

and the second vehicle state updating module is used for receiving the second control information sent by the second path planning module and the second driving information sent by the driving module, generating second vehicle state information obtained by the test vehicle in response to the second control information and the second driving information, and sending the second vehicle state information to the second intelligent agent simulation module.

In a possible implementation manner, the driving module is specifically configured to query, for each piece of second driving information, a preset type and a correspondence table between a function and a receiving module, determine, when the type of the second driving information hits the simulation type and the function hits any one of function items corresponding to the simulation type, that the receiving module corresponding to the second driving information is a second agent simulation module, and send the second driving information to the second agent simulation module; the function items corresponding to the simulation types at least comprise: the moving speed of the target object, the moving direction of the target object and the moving probability of the target object;

and the second intelligent agent simulation module is used for receiving second vehicle state information sent by the second vehicle state updating module and second driving information sent by the driving module, simulating and generating second object state information of objects except the test vehicle based on the second vehicle state information and the second driving information, and sending the second object state information to the second path planning module.

In a possible implementation manner, the driving module is specifically configured to query, for each piece of second driving information, a preset type and a correspondence table between a function and a receiving module, determine, when the type of the second driving information hits the planning type and the function hits any one of function items corresponding to the planning type, that the receiving module corresponding to the second driving information is the second path planning module, and send the second driving information to the second path planning module; the function items corresponding to the planning types at least comprise: heart rate information, inertia and vehicle centrifugal force;

and the second path planning module is used for receiving second object state information sent by the second intelligent agent simulation module and second driving information sent by the driving module, generating second control information aiming at the test vehicle based on the second object state information and the second driving information, and sending the second control information to the second vehicle state updating module.

In a possible implementation, the simulator apparatus further includes: a second simulation verification module;

and the second simulation verification module is used for determining whether the second vehicle state information is matched with the second expected result information or not, and generating a second test case under the condition that the second vehicle state information is not matched with the second expected result information.

In the technical scheme of the disclosure, the processes of collecting, storing, using, processing, transmitting, providing, disclosing and the like of the personal information of the related user all accord with the regulations of related laws and regulations, and do not violate the common customs of public order. It should be noted that the head model in this embodiment is not a head model for a specific user, and cannot reflect personal information of a specific user. It should be noted that the two-dimensional face image in the present embodiment is from a public data set.

The present disclosure also provides an electronic device, a readable storage medium, and a computer program product according to embodiments of the present disclosure.

The present disclosure provides an electronic device including:

at least one processor; and

a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,

the memory stores instructions executable by the at least one processor to cause the at least one processor to perform the method of any one of the present disclosure.

A non-transitory computer readable storage medium is provided that stores computer instructions for causing a computer to perform the method of any one of the present disclosure.

FIG. 10 illustrates a schematic block diagram of an example electronic device 1000 that can be used to implement embodiments of the present disclosure. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be examples only, and are not meant to limit implementations of the disclosure described and/or claimed herein.

As shown in fig. 10, the apparatus 1000 includes a computing unit 1001 that can perform various appropriate actions and processes according to a computer program stored in a Read Only Memory (ROM) 1002 or a computer program loaded from a storage unit 1008 into a Random Access Memory (RAM) 1003. In the RAM1003, various programs and data necessary for the operation of the device 1000 can also be stored. The calculation unit 1001, the ROM1002, and the RAM1003 are connected to each other by a bus 1004. An input/output (I/O) interface 1005 is also connected to bus 1004.

A number of components in device 1000 are connected to I/O interface 1005, including: an input unit 1006 such as a keyboard, a mouse, and the like; an output unit 1007 such as various types of displays, speakers, and the like; a storage unit 1008 such as a magnetic disk, an optical disk, or the like; and a communication unit 1009 such as a network card, a modem, a wireless communication transceiver, or the like. The communication unit 1009 allows the device 1000 to exchange information/data with other devices through a computer network such as the internet and/or various telecommunication networks.

Computing unit 1001 may be a variety of general and/or special purpose processing components with processing and computing capabilities. Some examples of the computing unit 1001 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various dedicated Artificial Intelligence (AI) computing chips, various computing units running machine learning model algorithms, a Digital Signal Processor (DSP), and any suitable processor, controller, microcontroller, and so forth. The calculation unit 1001 executes the respective methods and processes described above, such as the automated driving simulation test method. For example, in some embodiments, the autopilot simulation test method may be implemented as a computer software program tangibly embodied in a machine-readable medium, such as the storage unit 1008. In some embodiments, part or all of the computer program may be loaded and/or installed onto device 1000 via ROM1002 and/or communications unit 1009. When the computer program is loaded into RAM1003 and executed by computing unit 1001, one or more steps of the automated driving simulation testing method described above may be performed. Alternatively, in other embodiments, the computing unit 1001 may be configured to perform the automated driving simulation test method in any other suitable manner (e.g., by means of firmware).

Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuitry, field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standard Products (ASSPs), system on a chip (SOCs), complex Programmable Logic Devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs that are executable and/or interpretable on a programmable system including at least one programmable processor, which may be special or general purpose, receiving data and instructions from, and transmitting data and instructions to, a storage system, at least one input device, and at least one output device.

Program code for implementing the methods of the present disclosure may be written in any combination of one or more programming languages. These program code may be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the program code, when executed by the processor or controller, causes the functions/acts specified in the flowchart and/or block diagram to be performed. The program code may execute entirely on the machine, partly on the machine, as a stand-alone software package partly on the machine and partly on a remote machine or entirely on the remote machine or server.

In the context of this disclosure, a machine-readable medium may be a tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which a user can provide input to the computer. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic, speech, or tactile input.

The systems and techniques described here can be implemented in a computing system that includes a back-end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back-end, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), wide Area Networks (WANs), and the Internet.

The computer system may include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server may be a cloud server, a server of a distributed system, or a server combining a blockchain.

It should be understood that various forms of the flows shown above may be used, with steps reordered, added, or deleted. For example, the steps described in the present disclosure may be executed in parallel or sequentially or in different orders, and are not limited herein as long as the desired results of the technical solutions disclosed in the present disclosure can be achieved.

The above detailed description should not be construed as limiting the scope of the disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may be made in accordance with design requirements and other factors. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present disclosure should be included in the scope of protection of the present disclosure.

Claims

1. An automated driving simulation test method, comprising:

2. The method of claim 1, wherein the interactive device comprises at least one of: a consumer interaction device, a mechanical interaction device, a biological interaction device, and a physical interaction device; the consumer interaction device comprises: wearable equipment and wireless device, mechanical interaction equipment includes: steering wheel, driving lever, throttle, brake, mouse and keyboard, biological interaction equipment includes: helmet display and brain-computer interface, the physical interaction device includes: a physical sensor.

3. The method of claim 1, wherein the first driving instruction information includes at least one first driving information, and a type and a function corresponding to each first driving information; the method further comprises the following steps:

acquiring first control information for the test vehicle;

for each piece of first driving information, under the condition that the type of the first driving information hits a control type and the function hits any function item corresponding to the control type, the generating of the first vehicle state information obtained by the test vehicle responding to the first driving instruction information comprises: generating first vehicle state information obtained by the test vehicle responding to the first control information and the first driving information; wherein, the function items corresponding to the control types at least comprise: adjusting the steering wheel direction, adjusting the oil supply amount of the accelerator and adjusting the size of the brake.

4. The method of claim 3, further comprising:

5. The method of claim 4, further comprising:

for each piece of first driving information, generating first control information for the test vehicle based on the first object state information and the first driving information when the type of the first driving information hits a planning type and a function hits any function item corresponding to the planning type; the function items corresponding to the planning types at least comprise: heart rate information, magnitude of inertia, and magnitude of centrifugal force of the vehicle.

6. An automated driving simulation test system, comprising: the system comprises an interactive terminal and a simulator device;

7. The automated driving simulation testing system of claim 6, wherein the interactive device comprises at least one of: a consumer interaction device, a mechanical interaction device, a biological interaction device, and a physical interaction device; the consumer interaction device comprises: wearable equipment and wireless device, mechanical interaction device includes: steering wheel, driving lever, throttle, brake, mouse and keyboard, biological interaction equipment includes: helmet display and brain-computer interface, the physical interaction device includes: a physical sensor.

8. The automated driving simulation test system of claim 6, wherein the simulator device comprises: the system comprises a first path planning module, a first intelligent agent simulation module and a first vehicle state updating module;

the interactive terminal is specifically used for receiving first driving instruction information sent by at least one interactive device accessed to the interactive terminal, wherein the first driving instruction information comprises at least one piece of first driving information and types and functions corresponding to the first driving information; and aiming at each piece of first driving information, determining a receiving module corresponding to the first driving information in the first path planning module, the first intelligent agent simulation module and the first vehicle state updating module according to the type and the function corresponding to the first driving information and a preset corresponding relation table between the type and the function and the receiving module, and sending the first driving information to the determined receiving module.

9. The automated driving simulation test system of claim 8,

the interactive terminal is specifically configured to query a preset type and a corresponding relation table between functions and receiving modules for each piece of first driving information, determine that the receiving module corresponding to the first driving information is the first vehicle state updating module when the type of the first driving information hits the control type and the function hits any one of the function items corresponding to the control type, and send the first driving information to the first vehicle state updating module; the function items corresponding to the control types at least comprise: adjusting the steering wheel direction, adjusting the oil supply amount of an accelerator and adjusting the size of a brake;

the first vehicle state updating module is configured to receive first control information sent by the first path planning module and first driving information sent by the interactive terminal, generate first vehicle state information obtained by a test vehicle in response to the first control information and the first driving information, and send the first vehicle state information to the first intelligent agent simulation module.

10. The automated driving simulation test system of claim 9,

the interactive terminal is specifically configured to query a preset type and a correspondence table between functions and receiving modules for each piece of first driving information, determine that the receiving module corresponding to the first driving information is the first agent simulation module when the type of the first driving information hits a simulation type and the function hits any one of function items corresponding to the simulation type, and send the first driving information to the first agent simulation module; the function items corresponding to the simulation types at least comprise: the moving speed of the target object, the moving direction of the target object and the moving probability of the target object;

the first agent simulation module is configured to receive the first vehicle state information sent by the first vehicle state updating module and the first driving information sent by the interactive terminal, generate first object state information of an object other than the test vehicle based on the first vehicle state information and the first driving information in a simulation manner, and send the first object state information to the first path planning module.

11. The automated driving simulation test system of claim 8,

the interactive terminal is specifically configured to query a preset type and a correspondence table between functions and receiving modules for each piece of first driving information, determine that the receiving module corresponding to the first driving information is the first path planning module when the type of the first driving information hits a planning type and the function hits any one of function items corresponding to the planning type, and send the first driving information to the first path planning module; the function items corresponding to the planning types at least comprise: heart rate information, inertia and vehicle centrifugal force;

the first path planning module is used for receiving the first object state information sent by the first agent simulation module and the first driving information sent by the interactive terminal, generating first control information for the test vehicle based on the first object state information and the first driving information, and sending the first control information to the first vehicle state updating module.

12. The automated driving simulation test system of any of claims 6-11, the simulator device comprising: a first simulation verification module;

the first simulation verification module is used for determining whether the first vehicle state information is matched with first expected result information or not, and generating a first test case under the condition that the first vehicle state information is not matched with the first expected result information.

13. A simulator apparatus comprising:

14. A non-transitory computer readable storage medium having stored thereon computer instructions for causing the computer to perform the method of any one of claims 1-5.

15. A computer program product comprising a computer program which, when executed by a processor, implements the method according to any one of claims 1-5.