An evaluation system and test method for human-computer interaction of intelligent vehicles

Abstract

The present invention relates to the technical field of system evaluation, and discloses an evaluation system and test method for human-computer interaction of intelligent vehicles, including a collection subsystem, an operation subsystem, an auxiliary subsystem and a control subsystem; the collection subsystem includes an alarm collection sensor, and the alarm collection sensor is used to collect alarm information data of a DMS system; the operation subsystem includes a simulation robot; the auxiliary subsystem includes a co-pilot auxiliary pedal and a co-pilot auxiliary steering wheel both arranged on the co-pilot seat; the control subsystem includes a controller and a comparison module; the controller is used to output control instructions according to a preset strategy to control the action of the simulation robot; the comparison module is used to compare the control instructions with the alarm information data fed back by the DMS system, and evaluate the DMS system according to the comparison strategy. The present invention can accurately test and evaluate the operation effect of the DMS system, and in particular can accurately evaluate the operation effect of the DMS system under real driving conditions.

Description

Technical Field

[0001] The present invention relates to the technical field of system evaluation, and in particular to an evaluation system and a testing method for human-computer interaction of an intelligent vehicle. Background Art

[0002] With the development of automobile technology, especially the application of intelligent and networked technologies, the human-computer interaction system of smart cars is becoming more and more complex. The operation of the in-vehicle interactive system has a trend of larger screens and more and more operating tasks. The corresponding human-computer interaction of drivers is also becoming more and more frequent. For example, there are many interactive operations in music playback, map navigation, adaptive cruise system, automatic parking system, traffic congestion assistance system, etc. A good interactive system can bring convenient operation and good user experience, but a bad human-computer interaction system will make the driver's operation inefficient and the experience poor, which will make the driver abandon it over time; more seriously, a bad interactive design may affect the normal driving task of driving, causing the driver to be distracted and fatigued, bringing driving dangers.

[0003] Correspondingly, there is also a corresponding interactive system for reminding the above-mentioned driver distraction and fatigue driving status, namely the DMS system (Drive Monitoring System). At present, many vehicles are equipped with DMS systems, which can realize functions such as driver fatigue driving status monitoring, driver attention monitoring, and dangerous driving behavior monitoring, and can issue an alarm when risky behavior or risky driving status is identified, which helps to reduce the incidence of driving accidents. However, with the extensive use of such interactive systems, new problems have also emerged accordingly - there is currently no scientific and effective real-vehicle test and evaluation method that can effectively evaluate the interactive system itself, which makes it impossible to verify the accuracy of the DMS system itself; although the existing evaluation method for the DMS system can complete the evaluation of the DMS system, it has many defects.

[0004] There are two main ways to evaluate the DMS system: the first is to have real people simulate various distraction and fatigue actions to detect the DMS system's recognition accuracy of distraction and fatigue actions. However, this method cannot achieve standardization and consistency, resulting in large errors in the test results and poor horizontal comparability between different vehicles. At the same time, closing eyes, looking around and other real fatigue and distraction actions during real vehicle driving are very dangerous. The second method is to use a simulation robot to simulate distraction and fatigue actions. The standard of action control is improved, but because the simulation robot is installed in the driver's position, it will make it impossible to perform vehicle driving operations. If the DMS system evaluation requires real vehicle speed, GPS signal, map fence and other restrictions, it cannot be effectively evaluated. Summary of the invention

[0005] The present invention aims to provide an evaluation system and test method for human-computer interaction of intelligent vehicles, which can accurately test and evaluate the operation effect of the DMS system, especially can accurately evaluate the operation effect of the DMS system under real driving conditions.

[0006] To achieve the above object, the present invention provides the following solutions:

[0007] Solution 1:

[0008] An intelligent vehicle human-computer interaction evaluation system includes a collection subsystem, an operation subsystem, an auxiliary subsystem and a control subsystem;

[0009] The acquisition subsystem includes an alarm acquisition sensor, which establishes a communication connection with the DMS system and is used to collect alarm information data of the DMS system; the operation subsystem includes a simulation robot; the auxiliary subsystem includes a co-pilot auxiliary pedal and a co-pilot auxiliary steering wheel, both of which are arranged on the co-pilot seat; the co-pilot auxiliary pedal is connected to the main driver pedal and is used to control the main driver pedal; the co-pilot auxiliary steering wheel is connected to the main driver steering wheel and is used to control the main driver steering wheel;

[0010] The control subsystem includes a controller and a comparison module; the controller is used to output control instructions according to a preset strategy to control the action of the simulated robot; the comparison module is used to compare the control instructions with the alarm information data fed back by the DMS system, and evaluate the DMS system according to the comparison strategy.

[0011] The working principle and advantages of this solution are: during the evaluation, the simulation robot is placed on the driving seat of the vehicle, and the controller outputs control instructions to control the simulation robot to perform different actions. Here, the simulation robot simulates the action, and the standardization and consistency of the action can be reliably guaranteed, which helps to reduce the test error. The DMS system in the vehicle monitors and feedbacks the action of the simulation robot. At the same time, the alarm collection sensor instantly collects the alarm information fed back by the DMS system, and the comparison module evaluates the DMS system by comparing the control instructions and the DMS system feedback data according to the comparison strategy. In addition, the tester can sit in the co-pilot seat of the vehicle and drive and control the car through the auxiliary subsystem, thereby constructing an evaluation environment under real driving conditions, and can evaluate the DMS system evaluation results under different restrictions, and can evaluate the DMS system in a real application environment.

[0012] This solution solves the problems existing in the existing DMS system evaluation methods through a simple system structure setting. Compared with the real-person evaluation solution, this solution uses a simulated robot to perform the test action, uses a comparison module to complete the evaluation analysis, standardizes the test action, and digitizes the evaluation analysis, which can ensure a high evaluation accuracy. Compared with the evaluation solution that only uses a simulated robot, this solution uses the setting of an auxiliary subsystem to enable the car to drive safely and synchronously during the evaluation process, and then can evaluate the DMS system under real driving conditions. It can meet the sensor trigger restriction conditions for action perception in some DMS systems (such as vehicle speed conditions, movement conditions, etc.), ensuring the comprehensiveness and reliability of the evaluation.

[0013] Furthermore, the passenger auxiliary pedal includes a passenger auxiliary accelerator pedal and a passenger auxiliary brake pedal; the passenger auxiliary accelerator pedal and the main driver accelerator pedal, and the passenger brake pedal and the main driver brake pedal are all connected by steel wires.

[0014] Beneficial effect: The auxiliary pedal of the co-pilot controls the accelerator and brake of the main driver, and can accurately control the movement of the vehicle.

[0015] Furthermore, the controller is provided with a manual control module; the manual control module is used to manually select output control instructions.

[0016] Beneficial effects: The controller can provide a manual control mode, allowing testers to independently select output control instructions, which is more applicable.

[0017] Furthermore, the control instructions include blinking instructions, eye movement instructions, yawning instructions, head turning instructions, head raising instructions, head lowering instructions and hand raising instructions.

[0018] Beneficial effects: There are a variety of control instructions, which can control the simulation robot to simulate different distraction and fatigue operations for the DMS system to identify and process.

[0019] Furthermore, the acquisition subsystem also includes a voice recognition sensor and an image recognition sensor; the voice recognition sensor and the image recognition sensor are used to acquire voice and image data of the DMS system respectively.

[0020] Beneficial effects: In addition to collecting the alarm information of the DMS system itself, this solution also collects the voice and image data of the DMS system, which can provide more diverse data references for evaluating the DMS system.

[0021] Furthermore, the preset strategy includes randomly calling a number of different control instructions to form a control group and executing them; the preset strategy also includes executing various types of control instructions in sequence and each type of control instruction is executed a preset number of times.

[0022] Beneficial effects: The preset strategy contains two types of operating logic. Through the output of random combination and sequential repetition of control instructions, different test methods can be simulated, which can better evaluate the DMS system's response ability to distraction and fatigue operations.

[0023] Furthermore, the comparison strategy includes comparing the control instruction output time point with the DMS system feedback time point, and determining the feedback timeliness of the DMS system according to the difference between the output time point and the feedback time point; comparing the control instruction output times with the DMS system feedback times, and determining the feedback accuracy of the DMS system according to the difference between the output times and the feedback times.

[0024] Beneficial effects: The feedback timeliness and accuracy of the DMS system can be evaluated according to the comparison strategy, and the evaluation effect is good.

[0025] Option 2:

[0026] A method for testing human-computer interaction of an intelligent vehicle, using an evaluation system for human-computer interaction of an intelligent vehicle as described in Scheme 1; comprising the following steps:

[0027] Step 1: Install a simulation robot on the main driving seat of the vehicle to be tested; control the operation of the vehicle to be tested through the auxiliary subsystem;

[0028] Step 2: The controller outputs control instructions according to the preset strategy to control the movement of the simulated robot; the DMS system of the vehicle under test monitors the movement of the simulated robot in real time;

[0029] Step 3: The comparison module compares the control instructions and the DMS system feedback data, and evaluates the DMS system according to the comparison strategy.

[0030] The effects and advantages of this solution are: the controller and the simulation robot output the test action, the auxiliary subsystem completes the vehicle operation control, and the comparison module completes the evaluation and analysis. The evaluation method provided by this solution has a simple process and is easy to operate. It can accurately test and evaluate the operation effect of the DMS system, especially the operation effect of the DMS system under real driving conditions.

[0031] Furthermore, the testing environment of the vehicle to be tested includes indoor drum, closed test field and public road.

[0032] Beneficial effects: The test environment of the vehicle to be tested is diverse and includes a real road environment, which can effectively test the operation status of the DMS system under restrictions such as real vehicle speed, GPS signal, map fence, etc. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] Figure 1 This is a schematic diagram of the structure of an evaluation system of Embodiment 1 of an evaluation system and a test method for human-computer interaction of an intelligent vehicle according to the present invention;

[0034] Figure 2 This is a schematic diagram of the auxiliary subsystem structure of Embodiment 1 of an evaluation system and a test method for human-computer interaction of an intelligent vehicle according to the present invention;

[0035] Figure 3 A schematic diagram of a steering wheel connection structure of a first embodiment of an evaluation system and a test method for human-computer interaction of an intelligent vehicle according to the present invention;

[0036] Figure 4 This is a real-life diagram of the auxiliary subsystem structure of Embodiment 1 of an evaluation system and test method for human-computer interaction of an intelligent vehicle according to the present invention. DETAILED DESCRIPTION

[0037] The following is a further detailed description through specific implementation methods:

[0038] Embodiment 1:

[0039] The embodiment is basically as shown in the attached Figure 1 Shown: An intelligent vehicle human-computer interaction evaluation system includes an acquisition subsystem, an operation subsystem, an auxiliary subsystem and a control subsystem.

[0040] The acquisition subsystem includes an alarm acquisition sensor, which establishes a communication connection with the DMS system, and the alarm acquisition sensor is used to collect alarm information data of the DMS system. Among them, the DMS system (Drive Monitoring System) refers to the driver monitoring system. The DMS system referred to in this embodiment is a conventional driver monitoring system configured in an intelligent vehicle, which realizes the recognition and monitoring of the driver's action behavior through the cooperation of a camera and other body sensors, and sends out an alarm message when the monitoring determines that the driver is in an abnormal driving state, forming alarm information data.

[0041] The operation subsystem includes a simulation robot; the simulation robot includes a simulation head and a simulation torso; the size of the simulation human complies with the provisions of the basic human body values ​​in the standard "GB / T 10000-1988 Chinese Adult Human Body Size" to ensure that the simulation robot meets the human body standards for the driver's position. In this embodiment, a conventional simulation robot with action simulation function can be used.

[0042] The auxiliary subsystem includes a passenger auxiliary pedal and a passenger auxiliary steering wheel, both of which are arranged on the passenger seat; the passenger auxiliary pedal is connected to the main driver pedal and is used to control the main driver pedal; the passenger auxiliary steering wheel is connected to the main driver steering wheel and is used to control the main driver steering wheel. Figure 2 and Figure 4As shown, the passenger auxiliary pedal includes a passenger auxiliary accelerator pedal and a passenger auxiliary brake pedal; the passenger auxiliary accelerator pedal and the main driver accelerator pedal, as well as the passenger brake pedal and the main driver brake pedal are all connected by steel wires, and the passenger auxiliary accelerator pedal and the main driver accelerator pedal maintain consistent movements, and the passenger brake pedal and the main driver brake pedal maintain consistent movements.

[0043] Specifically, the size of the auxiliary steering wheel for the co-driver is the same as that of the main driver's steering wheel, as shown in the attached figure. Figure 3 As shown, the auxiliary steering wheel for the co-driver is connected to the steering wheel for the main driver through a steering wheel connecting rod, which includes a rigid connecting rod, a ball head and a ball sleeve. The rigid connecting rod is welded with a ball head and a ball sleeve at both ends, which can be well matched with the inner surface of the steering wheel, and the connection structure is simple and the connection is effective.

[0044] The control subsystem includes a controller and a comparison module; the controller is used to output control instructions according to a preset strategy to control the action of the simulated robot; the comparison module is used to compare the control instructions with the alarm information data fed back by the DMS system, and evaluate the DMS system according to the comparison strategy.

[0045] The control instructions include blinking instructions, eyeball rotation instructions, yawning instructions, head turning instructions, head raising instructions, head lowering instructions, and hand raising instructions. In this embodiment, the hand raising instructions include instructions involving hand movements such as making and receiving phone calls and smoking instructions. Specifically, corresponding to the above control instructions, the complete behavioral actions executed by the simulation robot are shown in Appendix 1:

[0046] Appendix 1 Definition table of a single complete trial of behavioral actions

[0047]

[0048] The preset strategy includes randomly calling several different control instructions to form a control group and executing them; for example: randomly selecting 3-5 control instructions from the above control instructions to form a control group. The preset strategy also includes executing various control instructions in sequence and executing each type of control instruction a preset number of times. In this embodiment, the preset number of times can be set to 20 times, 40 times or 60 times, and certain external test conditions can be added accordingly. In this way, the execution times of various control instructions are quantitatively controlled, which can more fairly analyze and evaluate the sensitivity and accuracy of the DMS system for different actions.

[0049] Specifically, in this embodiment, the preset number of times can be set according to Appendix 2.

[0050] Schedule 2 Preset Times

[0051]

[0052] The comparison strategy includes comparing the control instruction output time point with the DMS system feedback time point, and determining the feedback timeliness of the DMS system according to the difference between the output time point and the feedback time point; comparing the control instruction output times with the DMS system feedback times, and determining the feedback accuracy of the DMS system according to the difference between the output times and the feedback times.

[0053] Specifically, in this embodiment, the control instruction output time point specifically refers to the time point when the control instruction is transmitted to the simulation robot, and may also correspond to the time point when the simulation robot receives the control instruction and starts to act. The DMS system feedback time point specifically refers to the time point when the DMS system produces alarm information after monitoring and identifying the action information, and also corresponds to the time point when the alarm collection sensor receives the alarm information data of the DMS system. In this embodiment, when the difference between the output time point and the feedback time point is 0-4s, it is determined that the feedback timeliness of the DMS system is high; when the difference between the output time point and the feedback time point is 5-8s, it is determined that the feedback timeliness of the DMS system is medium; when the difference between the output time point and the feedback time point is greater than 9s, it is determined that the feedback timeliness of the DMS system is low. This scheme is set up in this way, and the judgment criteria for different feedback timeliness are set based on the action duration corresponding to a single control instruction, and the evaluation benchmark is reliable.

[0054] The control instruction output times are the total number of control instruction outputs; the DMS system feedback times are the total number of feedback alarm information data of the DMS system, which also corresponds to the total number of alarm information data received by the alarm collection sensor from the DMS system. In this embodiment, when the difference between the output times and the feedback times is 0-2 times, the feedback accuracy of the DMS system is determined to be high; when the difference between the output times and the feedback times is 3-5 times, the feedback accuracy of the DMS system is determined to be medium; when the difference between the output times and the feedback times is greater than 6 times, the feedback accuracy of the DMS system is determined to be low. This scheme is set up in this way, and the feedback accuracy level is confirmed based on the difference between the output times and the feedback times. The difference determination range of each level is strictly set, and the evaluation reliability is high.

[0055] This embodiment also provides a method for testing human-computer interaction of an intelligent vehicle, which uses the above-mentioned evaluation system for human-computer interaction of an intelligent vehicle; the method comprises the following steps:

[0056] Step 1: Install a simulation robot on the main driving seat of the vehicle to be tested; the tester controls the operation of the vehicle to be tested through the auxiliary subsystem. Specifically, the test environment of the vehicle to be tested includes indoor drums, closed test sites and public roads.

[0057] It is understandable that the test environment of the vehicle to be tested in this solution can be a static scene (i.e., a scene where the vehicle is stationary and not moving). When the vehicle is stationary, the auxiliary subsystem does not participate in the operation. When the vehicle to be tested is tested in a test environment such as an indoor drum, a closed test field, or an open road, the tester can operate the co-pilot auxiliary pedal and the co-pilot auxiliary steering wheel in the auxiliary subsystem to control the movement of the vehicle, forming an evaluation environment under actual driving conditions.

[0058] Step 2: The controller outputs control instructions according to a preset strategy to control the movements of the simulated robot; the DMS system of the vehicle under test monitors the movements of the simulated robot in real time.

[0059] Step 3: The comparison module compares the control instructions and the DMS system feedback data, and evaluates the DMS system according to the comparison strategy.

[0060] The present embodiment provides an evaluation system and test method for human-computer interaction of intelligent vehicles, which can accurately test and evaluate the operation effect of the DMS system, especially can accurately evaluate the operation effect of the DMS system under real driving conditions. In conventional evaluation schemes for DMS systems, the operation effect of the DMS system is more simply result-oriented, and only the missed detection rate is comprehensively evaluated, but the timeliness of the operation of the DMS system is not evaluated. However, in fact, the timeliness of the DMS system's response to distraction / fatigue actions is very important for real driving behavior. In real driving scenarios, the driver's distraction of a few tenths of a second may cause a major safety accident. Even if the DMS system can detect distraction / fatigue behavior without missing it, if the DMS system does not detect and remind in time, the DMS system is still unreliable. This solution discovers the above problems and sets up corresponding comparison strategies to evaluate the feedback timeliness and feedback accuracy of the DMS system in multiple dimensions, which can evaluate and analyze the DMS system more comprehensively.

[0061] In addition, this solution uses a simulation robot to perform test actions. In conventional test solutions, real testers are often preferred to perform the test because real actions can better ensure the authenticity of distraction and fatigue actions, and real testers can control the vehicle autonomously, which is more in line with the real application environment and can trigger some special operating conditions of the DMS system; however, real-person testing also has problems such as uncontrollable behavior and non-standard simulation of distraction / fatigue actions, which makes the test results less reliable. This solution uses a simulation robot for testing, which can ensure that the action behavior is always controllable and the action simulation remains accurate. Although some of the action authenticity is lost, in fact, for DMS system testing, the authenticity of the action is not a standard that must be achieved. The standardization of the action and the authenticity of the overall test environment are more important, because this is directly aligned with the DMS system function execution trigger standard.

[0062] In this solution, the former (i.e., the standardization of actions) is ensured by using simulation robots, while the latter (i.e., the authenticity of the overall test environment) is ensured by setting up auxiliary subsystems. Even if there are a few conventional test solutions that use simulation robots for testing, they cannot guarantee the latter, because the simulation robot itself cannot drive the car and occupies the driving seat, and the DMS system cannot operate during the actual driving process. Some DMS system functions that require special vehicle speed conditions and geographical location conditions to be triggered cannot be triggered by conventional solutions, resulting in an incomplete evaluation of the DMS system and poor reliability. This solution solves this problem better by transferring the control function of the car's movement from the main driver's seat through the auxiliary subsystem, making it easier for testers to intervene and operate the car's movement, allowing the DMS system to operate during the actual driving process, and being able to control the special vehicle operating conditions required by the DMS system. Compared with real-person test solutions, the test is more standardized and safer.

[0063] Embodiment 2:

[0064] A smart car human-computer interaction evaluation system is disclosed. Based on the first embodiment, the acquisition subsystem and the control subsystem are adjusted.

[0065] Specifically, the controller is provided with a manual control module; the manual control module is used to manually select output control instructions. The acquisition subsystem also includes a voice recognition sensor and an image recognition sensor; the voice recognition sensor and the image recognition sensor are used to collect voice and image data of the DMS system respectively.

[0066] Specifically, the voice recognition sensor and image recognition sensor described in this embodiment can be the voice recognition sensor and image recognition sensor used by the DMS system, and the comparison module receives the data information collected by the voice recognition sensor and image recognition sensor. In this embodiment, when the comparison module determines the feedback timeliness of the DMS system according to the difference between the output time point and the feedback time point, it also calls the voice and image data of the DMS system to further verify whether the DMS system detects the action of the simulated robot.

[0067] This embodiment also provides a testing method for human-computer interaction of an intelligent vehicle, which is the same as the method described in the first embodiment and will not be described in detail here.

[0068] Compared with the first embodiment, the present embodiment provides an intelligent automobile human-computer interaction evaluation system and test method, which also collects the voice and image data of the DMS system, can provide more diverse data references for evaluating the DMS system, and is more convenient for comparison and analysis of comparison modules. In addition, the manual control module allows testers to independently select output control instructions, which is more applicable.

[0069] The above is only an embodiment of the present invention. The common sense such as the known specific structure and characteristics in the scheme is not described in detail here. The ordinary technicians in the relevant field know all the common technical knowledge in the technical field of the invention before the application date or priority date, can obtain all the existing technologies in the field, and have the ability to apply the conventional experimental means before that date. The ordinary technicians in the relevant field can improve and implement this scheme in combination with their own abilities under the enlightenment given by this application. Some typical known structures or known methods should not become obstacles for ordinary technicians in the relevant field to implement this application. It should be pointed out that for those skilled in the art, without departing from the structure of the present invention, several deformations and improvements can be made, which should also be regarded as the protection scope of the present invention, which will not affect the effect of the implementation of the present invention and the practicality of the patent. The protection scope required by this application shall be based on the content of its claims, and the specific implementation methods and other records in the specification can be used to interpret the content of the claims.

Claims

1. An intelligent car human-computer interaction evaluation system, characterized in that: It includes acquisition subsystem, operation subsystem, auxiliary subsystem and control subsystem; The acquisition subsystem includes an alarm acquisition sensor, which establishes a communication connection with the DMS system and is used to collect alarm information data of the DMS system; the operation subsystem includes a simulation robot; the auxiliary subsystem includes a co-pilot auxiliary pedal and a co-pilot auxiliary steering wheel both of which are arranged on the co-pilot seat; The co-pilot auxiliary pedal is connected to the main driver pedal and is used to control the main driver pedal; the co-pilot auxiliary steering wheel is connected to the main driver steering wheel and is used to control the main driver steering wheel; The control subsystem includes a controller and a comparison module; the controller is used to output control instructions according to a preset strategy to control the action of the simulation robot; the comparison module is used to compare the control instructions with the alarm information data fed back by the DMS system, and evaluate the DMS system according to the comparison strategy; The comparison strategy includes comparing the control instruction output time point with the DMS system feedback time point, and determining the feedback timeliness of the DMS system according to the difference between the output time point and the feedback time point; comparing the control instruction output times with the DMS system feedback times, and determining the feedback accuracy of the DMS system according to the difference between the output times and the feedback times.

2. The intelligent vehicle human-computer interaction evaluation system according to claim 1, characterized in that: The passenger auxiliary pedal includes a passenger auxiliary accelerator pedal and a passenger auxiliary brake pedal; The co-pilot auxiliary accelerator pedal and the main driver accelerator pedal, and the co-pilot brake pedal and the main driver brake pedal are all connected by steel wires.

3. The intelligent vehicle human-computer interaction evaluation system according to claim 2, characterized in that: The controller is provided with a manual control module; the manual control module is used to manually select output control instructions.

4. The intelligent vehicle human-computer interaction evaluation system according to claim 1, characterized in that: The control instructions include blinking instructions, eyeball rotation instructions, yawning instructions, head turning instructions, head raising instructions, head lowering instructions and hand raising instructions.

5. The intelligent vehicle human-computer interaction evaluation system according to claim 2, characterized in that: The acquisition subsystem also includes a voice recognition sensor and an image recognition sensor; the voice recognition sensor and the image recognition sensor are used to acquire voice and image data of the DMS system respectively.

6. The intelligent vehicle human-computer interaction evaluation system according to claim 1, characterized in that: The preset strategy includes randomly calling a number of different control instructions to form a control group and executing them; the preset strategy also includes executing various types of control instructions in sequence and each type of control instruction is executed a preset number of times.

7. A test method for human-computer interaction of an intelligent vehicle, characterized in that: The method comprises applying an intelligent vehicle human-computer interaction evaluation system as described in any one of claims 1 to 6, comprising the following steps: Step 1: Install a simulation robot on the main driving seat of the vehicle to be tested; control the operation of the vehicle to be tested through the auxiliary subsystem; Step 2: The controller outputs control instructions according to the preset strategy to control the action of the simulated robot; the DMS system of the vehicle under test monitors the action of the simulated robot in real time; at the same time, the alarm collection sensor synchronously collects the alarm information data fed back by the DMS system; Step 3: The comparison module compares the control instructions and the alarm information data fed back by the DMS system, and evaluates the DMS system according to the comparison strategy.

8. The method for testing human-computer interaction of an intelligent vehicle according to claim 7, characterized in that: The test environment for the vehicle to be tested includes indoor drums, closed test sites and public roads.

Images