Hardware test method, device and equipment of autonomous vehicle and storage medium

Abstract

The application relates to the field of automatic driving control, and discloses a hardware test method, device and equipment of an automatic driving vehicle and a storage medium. The method comprises the following steps: when it is detected that a current driving environment is a hardware-in-the-loop test environment, isolating real positioning information of the automatic driving vehicle; based on a preset virtual test environment, constructing virtual coordinate information of the hardware-in-the-loop test environment where the automatic driving vehicle is located; based on the virtual coordinate information, starting an automatic driving mode of the automatic driving vehicle, and performing a hardware-in-the-loop test on the automatic driving vehicle in the automatic driving mode. The application realizes quick starting of an automatic driving system of the automatic driving vehicle in the hardware-in-the-loop test, and improves the test range of the hardware load condition of the automatic driving vehicle.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of automatic driving control, and in particular to a hardware testing method and device for an automatic driving vehicle, an equipment and a storage medium. BACKGROUND

[0002] When testing an automatic driving vehicle in some extreme driving environments, or after iteration of an automatic driving system, if actual driving scene testing is directly performed on a road surface, dangerous accidents are likely to occur, which may pose a risk to automatic driving users or others. Therefore, generally, hardware-in-the-loop (HIL) testing can be performed on an automatic driving vehicle indoors to avoid the risks brought by actual driving scene testing and to complete simulation testing of the automatic driving vehicle. The HIL testing includes a vehicle controller (VCU), a battery management system (BMS), an ADAS controller, or a computing platform of an automatic driving system.

[0003] When starting to perform HIL testing, an automatic driving vehicle needs to meet certain conditions to start the automatic driving system for testing. For example, a positioning module needs to transmit coordinate information meeting the starting condition to a perception module. If a virtual GPS coordinate is directly constructed by a GPS sensor and input to the perception module through the positioning module, the positioning module will not only accept the GPS coordinate, but also fuse the GPS coordinate with a high-definition map and a laser point cloud. If the GPS coordinate is randomly input and the automatic driving system cannot be started, the GPS signal is weak indoors and the positioning is indoors, which cannot match the high-definition map of the scene to be tested, and the automatic driving system cannot be started. That is, the existing HIL testing process has the problem that it is difficult to start the automatic driving system. SUMMARY

[0004] The main purpose of the present application is to solve the technical problem that it is difficult to start the automatic driving system in the existing HIL testing process.

[0005] The first aspect of the present application provides a hardware testing method for an automatic driving vehicle, comprising: when it is detected that a current driving environment is a hardware-in-the-loop (HIL) testing environment, isolating real positioning information of the automatic driving vehicle; based on a preset virtual testing environment, constructing virtual coordinate information of a HIL testing environment in which the automatic driving vehicle is located; based on the virtual coordinate information, starting an automatic driving mode of the automatic driving vehicle, and performing HIL testing on the automatic driving vehicle in the automatic driving mode.

[0006] Optionally, in the first implementation manner of the first aspect, the constructing, based on the preset virtual test environment, the virtual coordinate information of the hardware-in-loop test environment in which the autonomous vehicle is located comprises: identifying, based on the preset virtual test environment, high-definition map information and point cloud map information of the hardware-in-loop test environment in which the autonomous vehicle is located; and matching, according to the high-definition map information and the point cloud map information, a position of the autonomous vehicle in the hardware-in-loop test environment to obtain the virtual coordinate information.

[0007] Optionally, in the second implementation manner of the first aspect, the isolating, when it is detected that the current driving environment is the hardware-in-loop test environment, the real positioning information in which the autonomous vehicle is located comprises: detecting, when it is detected that the current driving environment is the hardware-in-loop test environment, whether a navigation component on the autonomous vehicle publishes real coordinate information to a positioning component; and intercepting, when it is detected that the navigation component publishes the real coordinate information, the real coordinate information by using an isolation layer in the navigation component.

[0008] Optionally, in the third implementation manner of the first aspect, the isolating, when it is detected that the current driving environment is the hardware-in-loop test environment, the real positioning information in which the autonomous vehicle is located comprises: detecting, when it is detected that the current driving environment is the hardware-in-loop test environment, whether a positioning component on the autonomous vehicle receives real coordinate information published by a navigation component; and discarding, when it is detected that the positioning component receives the real coordinate information published by the navigation component, the received real coordinate information by using a discarding unit on the positioning component.

[0009] Optionally, in the fourth implementation manner of the first aspect, the starting, based on the virtual coordinate information, the autonomous driving mode of the autonomous vehicle comprises: generating a positioning activation instruction based on the virtual coordinate information, and sending the positioning activation instruction to a perception control component on the autonomous vehicle; starting, according to the positioning activation instruction, a deep perception model deployed on the perception control component, and generating a perception activation instruction, and sending the perception activation instruction to a planning component on the autonomous vehicle; and generating, according to the perception activation instruction, an autonomous driving activation instruction by the planning component, and publishing the autonomous driving activation instruction to start the autonomous driving mode of the autonomous vehicle.

[0010] The second aspect of the present application provides a hardware testing device of an autonomous vehicle, comprising: an information isolation module configured to isolate real positioning information of the autonomous vehicle when it is detected that a current driving environment is a hardware-in-the-loop testing environment; a coordinate construction module configured to construct virtual coordinate information of the hardware-in-the-loop testing environment based on a preset virtual testing environment; and a starting module configured to start an autonomous driving mode of the autonomous vehicle based on the virtual coordinate information, and perform hardware-in-the-loop testing on the autonomous vehicle in the autonomous driving mode.

[0011] Optionally, in the first implementation manner of the second aspect of the present application, the coordinate construction module comprises: an identification unit configured to identify high-definition map information and point cloud map information of the hardware-in-the-loop testing environment based on the preset virtual testing environment; and a matching unit configured to match a position of the autonomous vehicle in the hardware-in-the-loop testing environment based on the high-definition map information and the point cloud map information to obtain the virtual coordinate information.

[0012] Optionally, in the second implementation manner of the second aspect of the present application, the information isolation module comprises: a release detection unit configured to detect whether a navigation component of the autonomous vehicle releases real coordinate information to a positioning component when it is detected that the current driving environment is the hardware-in-the-loop testing environment; and an interception unit configured to intercept the real coordinate information released by the navigation component to the positioning component when it is detected that the navigation component releases the real coordinate information to the positioning component.

[0013] Optionally, in the third implementation manner of the second aspect of the present application, the information isolation module further comprises: a reception detection unit configured to detect whether the positioning component of the autonomous vehicle receives the real coordinate information released by the navigation component when it is detected that the current driving environment is the hardware-in-the-loop testing environment; and a rejection unit configured to reject the received real coordinate information by using a rejection unit on the positioning component when it is detected that the positioning component receives the real coordinate information released by the navigation component.

[0014] Optionally, in a fourth implementation manner of the second aspect of the present application, the starting module comprises: a positioning activation unit, configured to generate a positioning activation instruction based on the virtual coordinate information, and send the positioning activation instruction to a perception control component on the autonomous vehicle; a perception activation unit, configured to start a deep perception model deployed on the perception control component according to the positioning activation instruction, and generate a perception activation instruction, and send the perception activation instruction to a planning component on the autonomous vehicle; and a starting unit, configured to generate an autonomous driving activation instruction by the planning component according to the perception activation instruction, and publish the autonomous driving activation instruction to start the autonomous driving mode of the autonomous vehicle.

[0015] The third aspect of the present application provides a hardware testing device of an autonomous vehicle, comprising: a memory and at least one processor, the memory storing instructions; and the at least one processor invoking the instructions in the memory to enable the hardware testing device of the autonomous vehicle to perform the hardware testing method of the autonomous vehicle.

[0016] The fourth aspect of the present application provides a computer readable storage medium storing instructions, which, when executed on a computer, enable the computer to perform the hardware testing method of the autonomous vehicle.

[0017] In the technical solution provided by the present application, when it is detected that the current driving environment is a hardware-in-the-loop test environment, the real positioning information published by the navigation module to the positioning module in the autonomous vehicle is isolated, then the virtual coordinate information of the autonomous vehicle is constructed by the positioning module according to the virtual test environment required by the hardware-in-the-loop test, so that it can be fused with the high-precision map and the point cloud map of the hardware-in-the-loop test environment, and on the basis of the virtual coordinate information, the starting condition of the autonomous driving system is met, the autonomous driving mode of the autonomous vehicle can be started, and the hardware-in-the-loop test of the autonomous vehicle can be performed in the autonomous driving mode. Therefore, the autonomous driving system can be quickly started in the hardware-in-the-loop test process, the hardware performance quality of the autonomous vehicle under the participation of the hardware can be tested, the actual load effect test of the hardware-in-the-loop is increased, and the load situation of the entire hardware under the actual autonomous driving environment can be tested. BRIEF DESCRIPTION OF DRAWINGS

[0018] Figure 1 FIG. 1 is a schematic diagram of a first embodiment of the hardware testing method of the autonomous vehicle in the embodiments of the present application;

[0019] Figure 2 FIG. 2 is a schematic diagram of a second embodiment of the hardware testing method of the autonomous vehicle in the embodiments of the present application;

[0020] Figure 3An embodiment schematic diagram of a hardware testing device of an autonomous vehicle in the embodiment of the present application;

[0021] Figure 4 Another embodiment schematic diagram of a hardware testing device of an autonomous vehicle in the embodiment of the present application;

[0022] Figure 5 An embodiment schematic diagram of a hardware testing device of an autonomous vehicle in the embodiment of the present application. DETAILED DESCRIPTION

[0023] The embodiment of the present application provides a hardware testing method, device and equipment of an autonomous vehicle and a storage medium. When it is detected that a current driving environment is a hardware-in-the-loop test environment, real positioning information of the autonomous vehicle is isolated. Virtual coordinate information of the hardware-in-the-loop test environment of the autonomous vehicle is constructed based on a preset virtual test environment. An autonomous driving mode of the autonomous vehicle is started based on the virtual coordinate information, and the hardware-in-the-loop test is performed on the autonomous vehicle in the autonomous driving mode. The present application realizes quick starting of the autonomous driving system of the autonomous vehicle in the hardware-in-the-loop test, and improves the test range of the hardware load condition of the autonomous vehicle.

[0024] The terms "first", "second", "third", "fourth" and the like in the specification and claims of the present application and the above-described drawings (if any) are used to distinguish similar objects, and do not necessarily have to be used to describe a specific order or sequence. It should be understood that the data thus used can be interchanged under appropriate circumstances, so that the embodiments described herein can be implemented in an order other than that illustrated or described herein. In addition, the terms "include" or "have" and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, system, product or device including a series of steps or units does not have to be limited to only those steps or units clearly listed, but can include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0025] For the sake of understanding, the specific flow of the embodiment of the present application is described below. Please refer to Figure 1 The first embodiment of the hardware testing method of the autonomous vehicle in the embodiment of the present application includes:

[0026] 101. When it is detected that the current driving environment is a hardware-in-the-loop test environment, the real positioning information of the autonomous vehicle is isolated.

[0027] It can be understood that the execution subject of the present application can be a hardware testing device of an autonomous vehicle, and can also be a terminal or a server, and the specific place is not limited. The embodiment of the present application takes the server as the execution subject for example.

[0028] In this embodiment, the hardware test of the autonomous vehicle is a hardware-in-the-loop test performed indoors, which can also be a software-in-the-loop test. When the autonomous vehicle performs the hardware-in-the-loop test indoors, the indoor GPS signal is weak, and the GPS positioning does not change correspondingly with the project of the hardware-in-the-loop test. Therefore, the real positioning information collected by the GPS module cannot be matched with the high-precision map and the point cloud map of the driving environment of the hardware-in-the-loop test. Thus, the real positioning information of the autonomous vehicle is isolated, and the real positioning information is not used to perform the subsequent hardware-in-the-loop test.

[0029] In this embodiment, when the autonomous vehicle starts, the bottom driving module of the autonomous driving system is started, including a laser radar, a millimeter wave radar, a camera, a GPS, etc. Then, a driving start instruction is sent to the positioning module of the autonomous driving system. The positioning module is also started based on the driving start instruction, and first detects whether the current driving environment is a hardware-in-the-loop test environment.

[0030] Specifically, for example, an identification string of the hardware-in-the-loop test environment can be set in advance, and the positioning module detects whether the identification string is input to determine whether the current driving environment is a hardware-in-the-loop test environment. The hardware-in-the-loop test conditions can also be set in advance, such as receiving real positioning information of the GPS module, and then matching and fusing with the hardware-in-the-loop test conditions. According to the matching and fusion result, it is determined whether the current driving environment is a hardware-in-the-loop test environment. Wherein, the matching and fusion success indicates that it is a hardware-in-the-loop test environment, and the matching and fusion failure indicates that it is not a hardware-in-the-loop test environment.

[0031] In this embodiment, the real positioning information of the autonomous vehicle is collected by the GPS module, and then transmitted to the positioning module for starting the autonomous driving system. At this time, the isolation of the real positioning information is the isolation of the transmission of the real positioning information between the GPS module and the positioning module. Specifically, the real positioning information can be isolated in two aspects, including sending from the GPS module and receiving from the positioning module.

[0032] 102、Based on the preset virtual test environment, virtual coordinate information of the hardware-in-the-loop test environment of the autonomous vehicle is constructed;

[0033] In this embodiment, the virtual test environment for hardware-in-the-loop testing is set in advance, so that after the automatic driving system is started, the automatic driving vehicle can perform corresponding automatic driving operation according to the virtual test environment. Before that, it is necessary to detect whether the hardware-in-the-loop device of the automatic driving vehicle has the condition of starting automatic driving, so as to start the automatic driving system and make the automatic driving vehicle in the automatic driving mode. The detection of whether the hardware-in-the-loop device of the automatic driving vehicle has the condition of starting automatic driving is to detect whether the position coordinates of the automatic driving vehicle conform to the virtual test environment of automatic driving, so that the position coordinates of the automatic driving vehicle can be matched and fused with the high-precision map and the point cloud map of the virtual test environment. Therefore, the virtual coordinate information of the automatic driving vehicle in the virtual test environment needs to be constructed.

[0034] Specifically, the virtual test environment simulates the driving scene environment for hardware-in-the-loop testing of the automatic driving vehicle, including the pose information, type information, speed information, natural environment information, road information, host vehicle information, etc. of each obstacle in the driving scene environment. Through modeling of the virtual test environment in the room, the automatic driving system is made to believe that it is in a real driving scene. Then the virtual test environment is correspondingly configured with a high-precision map and a point cloud map in the driving scene. At this time, according to the real-time position information of the automatic driving vehicle in the high-precision map and the point cloud map, the virtual coordinate information is constructed, and the real-time position information of the automatic driving vehicle is converted from the high-precision map coordinate system and the point cloud coordinate system to the GPS coordinate system to obtain the virtual coordinate information.

[0035] 103、Based on the virtual coordinate information, the automatic driving mode of the automatic driving vehicle is started, and the hardware-in-the-loop testing of the automatic driving vehicle is performed in the automatic driving mode.

[0036] In this embodiment, after the virtual coordinate information of the automatic driving vehicle is constructed, if the perception module on the automatic driving system perceives that the virtual coordinate information of the automatic driving vehicle conforms to the automatic driving environment, it is determined that the hardware-in-the-loop device of the automatic driving vehicle has the condition of starting automatic driving, and then the automatic driving system is started and generates an automatic driving instruction to send to the planning module of the automatic driving system to start the planning module, and finally sends an automatic driving mode starting instruction to the whole system.

[0037] In this embodiment, after the automatic driving vehicle starts the automatic driving mode, the virtual coordinate information is continuously constructed according to the environment required for hardware-in-the-loop testing, so as to test the performance of the automatic driving vehicle in the hardware-in-the-loop testing environment, such as the influence of software, hardware changes or iteration on the whole automatic driving system, the load condition of each hardware of the automatic driving vehicle in the hardware-in-the-loop testing environment, etc.

[0038] In the embodiment of the present application, when it is detected that the current driving environment is a hardware-in-the-loop test environment, the real positioning information published by the navigation module in the autonomous vehicle to the positioning module is isolated, and then virtual coordinate information of the autonomous vehicle is constructed by the positioning module according to the virtual test environment required by the hardware-in-the-loop test, so that it can be fused with the high-precision map and the point cloud map of the hardware-in-the-loop test environment. On the basis of the virtual coordinate information, the starting condition of the autonomous driving system is met, the autonomous driving mode of the autonomous vehicle can be started, and the hardware-in-the-loop test of the autonomous vehicle is performed in the autonomous driving mode. Therefore, the autonomous driving system can be quickly started during the hardware-in-the-loop test, the hardware performance quality of the autonomous vehicle under the participation of hardware can be tested, the actual load effect test of the hardware-in-the-loop is increased, and the load situation of the entire hardware under the actual autonomous driving environment can be tested.

[0039] Please refer to Figure 2 The second embodiment of the hardware test method of the autonomous vehicle in the embodiment of the present application comprises:

[0040] 201. When it is detected that the current driving environment is a hardware-in-the-loop test environment, it is detected whether the navigation component on the autonomous vehicle publishes real coordinate information to the positioning component;

[0041] 202. When it is detected that the navigation component publishes real coordinate information, the real coordinate information is intercepted by using the isolation layer in the navigation component;

[0042] In this embodiment, when the real coordinate information of the autonomous vehicle is intercepted, since the real coordinate information is unidirectionally transmitted from the navigation component (such as a GPS module) to the positioning component in the autonomous driving system, the real coordinate information can be intercepted from the publication process of the navigation component. The navigation component senses the real coordinate information of the autonomous vehicle in real time according to a preset period, and then publishes the sensed real coordinate information according to a preset period. A data isolation layer is arranged in the navigation component to isolate the real coordinate information to be published.

[0043] In addition, the real coordinate information can also be intercepted from the receiving and forwarding process of the positioning component, as follows:

[0044] 1) When it is detected that the current driving environment is a hardware-in-the-loop test environment, it is detected whether the positioning component on the autonomous vehicle receives the real coordinate information published by the navigation component;

[0045] 2) When it is detected that the positioning component receives the real coordinate information published by the navigation component, the received real coordinate information is removed by using the removal unit on the positioning component.

[0046] In this embodiment, the positioning component passively receives the real coordinate information issued by the navigation component. Here, a rejection unit can be set in the positioning component to reject the real coordinate information received from the navigation component, so that the real coordinate information is intercepted and will not be sent to the perception module of the next logical calculation module. The virtual coordinate information is constructed by the positioning component instead of the real coordinate information and is sent to the perception module.

[0047] 203、based on the preset virtual test environment, identify the high-precision map information and the point cloud map information of the hardware-in-the-loop test environment where the autonomous vehicle is located;

[0048] 204、according to the high-precision map information and the point cloud map information, match the position of the autonomous vehicle in the hardware-in-the-loop test environment, and obtain virtual coordinate information;

[0049] In this embodiment, the high-precision map information corresponding to the virtual driving environment is identified, which can be specifically represented in a two-dimensional high-precision map coordinate system such as WGS84 coordinate system, Beijing 54 coordinate system, Xi'an 80 coordinate system, and GCJ2000 coordinate system. The point cloud map information corresponding to the virtual driving environment is identified, which can be specifically represented in a three-dimensional point cloud coordinate system.

[0050] In this embodiment, the real-time position coordinates of the autonomous vehicle in each preset period in the virtual test environment are found in the high-precision map coordinate system to generate virtual coordinate information. The real-time position coordinates of the autonomous vehicle in each preset period in the virtual test environment are found in the point cloud coordinate system, and after conversion of one or more items such as geocentric coordinate system, environmental horizontal coordinate system, inertial navigation coordinate system, and scanner coordinate system, virtual coordinate information is generated. Finally, the virtual coordinate information generated by the high-precision map coordinate system and the point cloud coordinate system is fused and transmitted to the perception module in real time according to the preset period.

[0051] 205、based on the virtual coordinate information, generate a positioning activation instruction, and send the positioning activation instruction to the perception control component on the autonomous vehicle;

[0052] 206、according to the positioning activation instruction, start the deep perception model deployed on the perception control component, and generate a perception activation instruction, and send the perception activation instruction to the planning component on the autonomous vehicle;

[0053] 207、according to the perception activation instruction, generate an autonomous driving activation instruction through the planning component, and issue the autonomous driving activation instruction to start the autonomous driving mode of the autonomous vehicle, and perform hardware-in-the-loop testing on the autonomous vehicle in the autonomous driving mode.

[0054] In this embodiment, when starting the automatic driving system of the automatic driving vehicle, first start the bottom driving module, including laser radar, millimeter wave radar, camera, GPS and other driving modules, after successful startup, generate the ready notification of the driving activation instruction, and then send it to the positioning component by the GPS module. After receiving the ready notification sent by the GPS module, the positioning component starts and automatically detects whether the current environment is a HIL environment, that is, a hardware-in-the-loop test environment (distinguished by pre-set environment variables of normal driving environment and hardware-in-the-loop test environment). If it is a HIL environment, a map coordinate conforming to the automatic driving environment is autonomously fabricated according to the pre-set virtual test environment, and a positioning activation instruction is generated to determine that the positioning component can execute automatic driving. Then the generated virtual coordinate information is sent to the perception control component together with the ready notification of the generated positioning activation instruction. After receiving the ready notification of the positioning activation instruction, the perception control component starts the deep learning perception model to execute subsequent environment perception of automatic driving, and generates a ready notification of the perception activation instruction after successful startup to determine that the perception control component can execute automatic driving and send it to the last planning component in the automatic driving system. After receiving the ready notification, the planning component starts the planning algorithm to execute subsequent route planning of automatic driving, and sends the string of autonomous ready after successful startup to issue the automatic driving activation instruction to the entire automatic driving system to determine that the automatic driving module of the entire automatic driving system is started and can execute the hardware-in-the-loop test of the automatic driving vehicle according to the subsequent continuous input of virtual positioning information.

[0055] The hardware test method of the automatic driving vehicle in the embodiment of the application is described above, and the hardware test device of the automatic driving vehicle in the embodiment of the application is described below. Please refer to Figure 3 An embodiment of the hardware test device of the automatic driving vehicle in the embodiment of the application includes:

[0056] The information isolation module 301 is configured to isolate the real positioning information of the automatic driving vehicle when it is detected that the current driving environment is a hardware-in-the-loop test environment.

[0057] The coordinate construction module 302 is configured to construct virtual coordinate information of the hardware-in-the-loop test environment of the automatic driving vehicle based on a pre-set virtual test environment.

[0058] The starting module 303 is configured to start the automatic driving mode of the automatic driving vehicle based on the virtual coordinate information, and execute the hardware-in-the-loop test of the automatic driving vehicle in the automatic driving mode.

[0059] In the embodiment of the present application, when it is detected that the current driving environment is a hardware-in-the-loop test environment, the real positioning information published by the navigation module in the autonomous vehicle to the positioning module is isolated, and then virtual coordinate information of the autonomous vehicle is constructed by the positioning module according to the virtual test environment required by the hardware-in-the-loop test, so that it can be fused with the high-precision map and the point cloud map of the hardware-in-the-loop test environment. On the basis of the virtual coordinate information, the starting condition of the autonomous driving system is met, the autonomous driving mode of the autonomous vehicle can be started, and the hardware-in-the-loop test of the autonomous vehicle is performed in the autonomous driving mode. Therefore, the autonomous driving system can be quickly started during the hardware-in-the-loop test, the hardware performance quality of the autonomous vehicle under the participation of hardware can be tested, the actual load effect test of the hardware-in-the-loop is increased, and the load condition of the entire hardware under the actual autonomous driving environment can be tested.

[0060] Please refer to Figure 4 Another embodiment of the hardware test device of the autonomous vehicle in the embodiment of the present application includes:

[0061] The information isolation module 301 is configured to isolate real positioning information of the autonomous vehicle when it is detected that the current driving environment is a hardware-in-the-loop test environment.

[0062] The coordinate construction module 302 is configured to construct virtual coordinate information of the hardware-in-the-loop test environment of the autonomous vehicle based on a preset virtual test environment.

[0063] The starting module 303 is configured to start the autonomous driving mode of the autonomous vehicle based on the virtual coordinate information, and perform the hardware-in-the-loop test of the autonomous vehicle in the autonomous driving mode.

[0064] Specifically, the coordinate construction module 302 includes:

[0065] The identification unit 3021 is configured to identify high-precision map information and point cloud map information of the hardware-in-the-loop test environment of the autonomous vehicle based on a preset virtual test environment.

[0066] The matching unit 3022 is configured to match the position of the autonomous vehicle in the hardware-in-the-loop test environment according to the high-precision map information and the point cloud map information, and obtain virtual coordinate information.

[0067] Specifically, the information isolation module 301 includes:

[0068] The publication detection unit 3011 is configured to detect whether the navigation component on the autonomous vehicle publishes real coordinate information to the positioning component when it is detected that the current driving environment is a hardware-in-the-loop test environment.

[0069] The interception unit 3012 is configured to intercept real coordinate information published by the navigation component to the positioning component by using an isolation layer in the navigation component when it is detected that the navigation component publishes the real coordinate information to the positioning component.

[0070] Specifically, the information isolation module 301 further includes:

[0071] The receiving detection unit 3013 is configured to detect whether the positioning component on the automatic driving vehicle receives real coordinate information published by the navigation component when it is detected that the current driving environment is a hardware-in-the-loop test environment.

[0072] The culling unit 3014 is configured to cull the received real coordinate information by using a culling unit on the positioning component when it is detected that the positioning component receives the real coordinate information published by the navigation component.

[0073] Specifically, the starting module 303 includes:

[0074] The positioning activation unit 3031 is configured to generate a positioning activation instruction based on the virtual coordinate information, and send the positioning activation instruction to a perception control component on the automatic driving vehicle.

[0075] The perception activation unit 3032 is configured to start a deep perception model deployed on the perception control component according to the positioning activation instruction, and generate a perception activation instruction, and send the perception activation instruction to a planning component on the automatic driving vehicle.

[0076] The starting unit 3033 is configured to generate an automatic driving activation instruction by the planning component according to the perception activation instruction, and publish the automatic driving activation instruction to start an automatic driving mode of the automatic driving vehicle.

[0077] The above Figure 3 and Figure 4 The hardware test device of the automatic driving vehicle in the embodiment of the application is described in detail from the perspective of a modular functional entity, and the hardware test device of the automatic driving vehicle in the embodiment of the application is described in detail from the perspective of hardware processing.

[0078] Figure 5is a structural schematic diagram of a hardware testing device of an autonomous vehicle provided by an embodiment of the present application. The hardware testing device 500 of the autonomous vehicle can have a large difference due to different configurations or performances, and can include one or more processors (central processing units, CPUs) 510 (for example, one or more processors) and a memory 520, one or more storage media 530 (for example, one or more mass storage devices) for storing application programs 533 or data 532. The memory 520 and the storage media 530 can be temporary storage or persistent storage. The programs stored in the storage media 530 can include one or more modules (not shown in the figure), and each module can include a series of instruction operations on the hardware testing device 500 of the autonomous vehicle. Furthermore, the processor 510 can be configured to communicate with the storage media 530 and execute the series of instruction operations in the storage media 530 on the hardware testing device 500 of the autonomous vehicle.

[0079] The hardware testing device 500 of the autonomous vehicle can also include one or more power supplies 540, one or more wired or wireless network interfaces 550, one or more input / output interfaces 560, and / or one or more operating systems 531, such as Windows Server, Mac OS X, Unix, Linux, FreeBSD, and the like. Those skilled in the art can understand that the hardware testing device of the autonomous vehicle can include more or fewer components than those shown in the figure, or some components can be combined, or different components can be arranged. Figure 5 The hardware testing device structure of the autonomous vehicle shown in the figure does not constitute a limitation on the hardware testing device of the autonomous vehicle, and can include more or fewer components than those shown in the figure, or some components can be combined, or different components can be arranged.

[0080] The present application also provides a hardware testing device of an autonomous vehicle, which includes a memory and a processor, the memory stores computer readable instructions, and the computer readable instructions are executed by the processor to make the processor execute the steps of the hardware testing method of the autonomous vehicle in each of the embodiments.

[0081] The present application also provides a computer readable storage medium, which can be a non-volatile computer readable storage medium or a volatile computer readable storage medium, and the computer readable storage medium stores instructions, and the instructions make a computer execute the steps of the hardware testing method of the autonomous vehicle when the instructions are run on the computer.

[0082] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described system, device and unit can refer to the corresponding processes in the foregoing method embodiments, which will not be described herein.

[0083] The integrated unit, if implemented in the form of a software function unit and sold or used as an independent product, can be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the present application or the entire or part of the technical solutions that essentially contribute to the prior art can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in various embodiments of the present application. The aforementioned storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and various media that can store program codes.

[0084] The above-described embodiments are only used to illustrate the technical solutions of the present application, rather than limit them; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacements for some technical features; and these modifications or replacements do not make the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A hardware testing method for an autonomous vehicle, characterized in that, The hardware testing method includes: When the current driving environment is detected to be a hardware-in-the-loop test environment, the transmission of real positioning information between the GPS module and the positioning module in the autonomous vehicle is isolated. Based on a preset virtual test environment, virtual coordinate information of the hardware-in-the-loop test environment of the autonomous vehicle is constructed; Based on the virtual coordinate information, the autonomous driving mode of the autonomous vehicle is activated, and a hardware-in-the-loop test is performed on the autonomous vehicle in the autonomous driving mode. The step of activating the autonomous driving mode of the autonomous vehicle based on the virtual coordinate information includes: generating a positioning activation command based on the virtual coordinate information and sending the positioning activation command to the perception control component on the autonomous vehicle; activating the depth perception model deployed on the perception control component and generating a perception activation command according to the positioning activation command, and sending the perception activation command to the planning component on the autonomous vehicle; generating an autonomous driving activation command through the planning component according to the perception activation command, and issuing the autonomous driving activation command to activate the autonomous driving mode of the autonomous vehicle.

2. The hardware testing method for autonomous vehicles according to claim 1, characterized in that, The virtual coordinate information for constructing the hardware-in-the-loop test environment of the autonomous vehicle based on a preset virtual test environment includes: Based on a preset virtual test environment, the high-precision map information and point cloud map information of the hardware-in-the-loop test environment where the autonomous vehicle is located are identified. Based on the high-precision map information and the point cloud map information, the position of the autonomous vehicle in the hardware-in-the-loop test environment is matched to obtain virtual coordinate information.

3. The hardware testing method for autonomous vehicles according to claim 1, characterized in that, The step of isolating the transmission of real positioning information between the GPS module and the positioning module in the autonomous vehicle when the current driving environment is detected as a hardware-in-the-loop test environment includes: When the current driving environment is detected to be a hardware-in-the-loop test environment, it is detected whether the navigation component on the autonomous vehicle publishes real coordinate information to the positioning component. When the real coordinate information published by the navigation component is detected, the real coordinate information is intercepted using the isolation layer in the navigation component.

4. The hardware testing method for autonomous vehicles according to claim 1, characterized in that, The step of isolating the transmission of real positioning information between the GPS module and the positioning module in the autonomous vehicle when the current driving environment is detected as a hardware-in-the-loop test environment includes: When the current driving environment is detected to be a hardware-in-the-loop test environment, it is detected whether the positioning component on the autonomous vehicle receives the real coordinate information published by the navigation component. When the positioning component detects that it has received real coordinate information published by the navigation component, it uses the elimination unit on the positioning component to eliminate the received real coordinate information.

5. A hardware testing device for an autonomous vehicle, characterized in that, The hardware testing equipment for the autonomous vehicle includes: The information isolation module is used to isolate the transmission of real positioning information between the GPS module and the positioning module in the autonomous vehicle when the current driving environment is detected to be a hardware-in-the-loop test environment. The coordinate construction module is used to construct virtual coordinate information of the hardware-in-the-loop test environment where the autonomous vehicle is located, based on a preset virtual test environment. The startup module is used to start the autonomous driving mode of the autonomous vehicle based on the virtual coordinate information, and to perform hardware-in-the-loop testing on the autonomous vehicle in the autonomous driving mode. The step of activating the autonomous driving mode of the autonomous vehicle based on the virtual coordinate information includes: generating a positioning activation command based on the virtual coordinate information and sending the positioning activation command to the perception control component on the autonomous vehicle; activating the depth perception model deployed on the perception control component and generating a perception activation command according to the positioning activation command, and sending the perception activation command to the planning component on the autonomous vehicle; generating an autonomous driving activation command through the planning component according to the perception activation command, and issuing the autonomous driving activation command to activate the autonomous driving mode of the autonomous vehicle.

6. The hardware testing apparatus for autonomous vehicles according to claim 5, characterized in that, The coordinate construction module includes: The identification unit is used to identify the high-precision map information and point cloud map information of the hardware-in-the-loop test environment where the autonomous vehicle is located, based on a preset virtual test environment. The matching unit is used to match the position of the autonomous vehicle in the hardware-in-the-loop test environment based on the high-precision map information and the point cloud map information to obtain virtual coordinate information.

7. The hardware testing apparatus for autonomous vehicles according to claim 6, characterized in that, The information isolation module includes: The detection unit is used to detect whether the navigation component on the autonomous vehicle publishes real coordinate information to the positioning component when the current driving environment is detected to be a hardware-in-the-loop test environment. An interception unit is used to intercept real coordinate information published by the navigation component to the positioning component when the real coordinate information is detected by the navigation component.

8. A hardware testing device for autonomous vehicles, characterized in that, The hardware testing equipment for the autonomous vehicle includes: a memory and at least one processor, wherein the memory stores instructions; The at least one processor invokes the instructions in the memory to cause the hardware testing equipment of the autonomous vehicle to perform the steps of the hardware testing method for the autonomous vehicle as described in any one of claims 1-4.

9. A computer-readable storage medium storing instructions thereon, characterized in that, When the instructions are executed by the processor, they implement the steps of the hardware testing method for the autonomous vehicle as described in any one of claims 1-4.

Images