CN110209146B - Test method, device and equipment for automatic driving vehicle and readable storage medium - Google Patents
Test method, device and equipment for automatic driving vehicle and readable storage medium Download PDFInfo
- Publication number
- CN110209146B CN110209146B CN201910433322.8A CN201910433322A CN110209146B CN 110209146 B CN110209146 B CN 110209146B CN 201910433322 A CN201910433322 A CN 201910433322A CN 110209146 B CN110209146 B CN 110209146B
- Authority
- CN
- China
- Prior art keywords
- vehicle
- automatic driving
- environment
- information
- virtual
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B17/00—Systems involving the use of models or simulators of said systems
- G05B17/02—Systems involving the use of models or simulators of said systems electric
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B23/00—Testing or monitoring of control systems or parts thereof
- G05B23/02—Electric testing or monitoring
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
Abstract
The present disclosure provides a method, apparatus, device and readable storage medium for testing an autonomous vehicle, comprising: generating an autonomous vehicle in the simulation environment according to the received first generation instruction; constructing a traffic environment in the simulation environment according to the pre-recorded state information of the virtual vehicle so as to enable the automatic driving vehicle to run in the traffic environment; and acquiring environment perception information according to the position of the automatic driving vehicle in the running process of the automatic driving vehicle, and inputting the environment perception information into a control system of the automatic driving vehicle so that the automatic driving vehicle runs according to the environment perception information. According to the scheme provided by the disclosure, the control system of the automatic driving vehicle can acquire surrounding environment perception information, determine a driving strategy based on the information and further control the vehicle to run. Therefore, the scheme provided by the disclosure can determine whether the control system of the vehicle can control safe driving of the vehicle based on the environmental information around the vehicle through the running condition of the vehicle in the simulation system.
Description
Technical Field
The present disclosure relates to an automatic driving technology, and more particularly, to a method, an apparatus, a device, and a readable storage medium for testing an automatic driving vehicle.
Background
An automatic vehicle (Self-steering automatic vehicle) is also called an unmanned vehicle, a computer-driven vehicle or a wheeled mobile robot, and is an intelligent vehicle for realizing unmanned driving through a computer system. The automatic driving automobile can sense the surrounding environment, automatically plan and control the vehicle to run along a specified route on a road based on the surrounding environment and the route condition, or automatically plan a route to run after a destination is specified.
In order to ensure that the autonomous vehicle can safely travel, it is necessary to verify that the control software controlling the autonomous travel of the vehicle can normally control the autonomous vehicle. Therefore, it is necessary to test the autonomous vehicle before it actually takes the route.
In the prior art, the adopted test mode is to test the automatic driving vehicle on an actual road, but the mode has certain danger. In order to ensure the test safety, the test can be only carried out in a simple traffic environment, and the actual road condition is complex, so that the test mode method in the prior art cannot comprehensively test the vehicle, and the test mode in the prior art has the problem of inaccuracy.
Disclosure of Invention
The disclosure provides a test method, a test device, test equipment and a readable storage medium for an automatic driving vehicle, which are used for solving the problem that the test mode in the prior art is inaccurate because the test mode in the prior art cannot comprehensively test the vehicle.
A first aspect of the present disclosure is to provide a test method of an autonomous vehicle, including:
generating an autonomous vehicle in the simulation environment according to the received first generation instruction;
constructing a traffic environment in the simulation environment according to the pre-recorded state information of the virtual vehicle so that the automatic driving vehicle runs in the traffic environment;
and acquiring environment perception information according to the position of the automatic driving vehicle in the running process of the automatic driving vehicle, and inputting the environment perception information into a control system of the automatic driving vehicle so as to enable the automatic driving vehicle to run according to the environment perception information.
Another aspect of the present disclosure is to provide a test apparatus of an autonomous vehicle, including:
the generation module is used for generating the automatic driving vehicle in the simulation environment according to the received first generation instruction;
the construction module is used for constructing a traffic environment in the simulation environment according to the pre-recorded state information of the virtual vehicle so as to enable the automatic driving vehicle to run in the traffic environment;
and the control module is used for acquiring environment perception information according to the position of the automatic driving vehicle in the running process of the automatic driving vehicle and inputting the environment perception information into a control system of the automatic driving vehicle so as to enable the automatic driving vehicle to run according to the environment perception information.
It is yet another aspect of the present disclosure to provide a test apparatus of an autonomous vehicle, including:
a memory;
a processor; and
a computer program;
wherein the computer program is stored in the memory and configured to be executed by the processor to implement the method of testing an autonomous vehicle as described in the first aspect above.
It is a further aspect of the present disclosure to provide a computer readable storage medium having stored thereon a computer program for execution by a processor to implement the method of testing an autonomous vehicle as described in the first aspect above.
The technical effects of the test method, the test device, the test equipment and the readable storage medium for the automatic driving vehicle provided by the disclosure are as follows:
the test method, device, equipment and readable storage medium for the automatic driving vehicle provided by the disclosure comprise the following steps: generating an autonomous vehicle in the simulation environment according to the received first generation instruction; constructing a traffic environment in the simulation environment according to the pre-recorded state information of the virtual vehicle so as to enable the automatic driving vehicle to run in the traffic environment; the method comprises the steps of obtaining environment perception information according to the position of an automatic driving vehicle in the running process of the automatic driving vehicle, and inputting the environment perception information into a control system of the automatic driving vehicle so that the automatic driving vehicle runs according to the environment perception information. The method, the device, the equipment and the readable storage medium provided by the disclosure can construct a traffic environment, and enable the generated automatic driving vehicle to run in the traffic environment, so that different traffic environments can be constructed according to requirements, and environments for testing can be enriched. Meanwhile, the control system of the autonomous vehicle can acquire surrounding environment perception information, determine a driving strategy based on the information, and further control the vehicle to run. Therefore, the scheme provided by the disclosure can determine whether the control system of the vehicle can control safe driving of the vehicle based on the environmental information around the vehicle through the running condition of the vehicle in the simulation system.
Drawings
FIG. 1 is a flow chart illustrating a method of testing an autonomous vehicle in accordance with an exemplary embodiment of the present invention;
FIG. 2 is a flow chart illustrating a method of testing an autonomous vehicle in accordance with another exemplary embodiment of the present invention;
FIG. 3 is a block diagram illustrating a test setup for an autonomous vehicle in accordance with an exemplary embodiment of the present invention;
FIG. 4 is a block diagram illustrating a test setup for an autonomous vehicle in accordance with another exemplary embodiment of the present invention;
fig. 5 is a block diagram illustrating a test apparatus of an autonomous vehicle according to an exemplary embodiment of the present invention.
Detailed Description
When the driving performance of the automatic driving vehicle is tested, the vehicle can be directly driven on a road, and in the driving process, the vehicle can sense the surrounding environment and determine a driving strategy based on the surrounding environment. However, it is dangerous to place an autonomous vehicle with an unverified safety performance in a complex traffic environment, so that the autonomous vehicle can only be tested in a simple traffic environment and cannot be tested in various traffic environments in the prior art.
According to the scheme provided by the embodiment of the invention, the traffic environment can be constructed in the simulation environment, and the automatic driving vehicle can be placed in the preset traffic environment, so that the control system of the automatic driving vehicle can determine the driving strategy based on the traffic environment in the simulation environment. In the simulation environment, different traffic environments can be set according to requirements, so that the control system of the automatic driving vehicle can be tested according to different traffic environments, the test scenes are richer, and the test result is more comprehensive and accurate.
FIG. 1 is a flow chart illustrating a method for testing an autonomous vehicle in accordance with an exemplary embodiment of the present invention.
As shown in fig. 1, the test method for an autonomous vehicle according to the present embodiment includes:
The method provided by the embodiment can be applied to a simulation system, and the simulation system can be used for testing a control system of an automatic driving vehicle. In particular, autonomous vehicles may be generated in a simulation system and made to travel in a constructed traffic environment.
Optionally, the simulation environment may include a high-precision map, for example, a traffic light, a building, a lane line, and the like may be provided.
The simulation system can comprise a client and a background system of the client, the client and the background system can be arranged in the same electronic device or different electronic devices, and if the client and the background system are not arranged in the same electronic device, the client and the background system can be connected through a network.
The user can operate in the client to input the information of the automatic driving vehicle, such as the position of the vehicle, the initial state of the vehicle and the like. For example, the user may input the position information of the vehicle in the simulation environment, and the input manner may be various, such as directly inputting the position information, clicking the position by a mouse in the simulation environment, clicking the position by a finger in the simulation environment, and the like.
Specifically, other vehicles should not be present at the position of the autonomous vehicle, and therefore, the position information input by the user can also be judged, and if other vehicles in the traffic environment exist at the position, the user can be prompted that the position is illegal.
Further, the user may also input other information, such as the size of the vehicle, e.g. length, height, etc.
In practical application, the step can be executed by the client or the background system.
In one embodiment, the client may generate an autonomous vehicle based on information input by the user and based on content input by the user. The simulation environment may also be presented at the client and the resulting autonomous vehicle may be presented in the simulation environment where the user may make adjustments. The client may also send the generated autonomous vehicle information to a backend system.
In another embodiment, the client may take information input by the user and send the information to a back-office system, which generates the autonomous vehicle in a simulated environment. The background system can also feed back the automatically driven vehicle in the simulation environment to the client, so that the user can adjust the automatically driven vehicle in the client.
And 102, constructing a traffic environment in the simulation environment according to the pre-recorded state information of the virtual vehicle so as to enable the automatic driving vehicle to run in the traffic environment.
In the method provided by the embodiment, the state information of the virtual vehicles can be recorded in advance, and the state information is used for restoring the traffic environment formed by the virtual vehicles. The user can operate in the client to call the pre-recorded state information of the virtual vehicle.
Optionally, the state information of at least one set of virtual vehicles may be stored in the simulation system. The set of information may include the status of a plurality of vehicles over a period of time, such as the location of a vehicle within ten minutes. When a traffic environment is constructed, the position of the vehicle at each moment can be restored according to the state information of the virtual vehicle, and further a real traffic scene can be simulated.
Optionally, the state information of the virtual vehicle may also be set by the user. The user can add a virtual vehicle in the client and set the state information of the virtual vehicle, for example, the user can add a virtual vehicle and input the control information of the vehicle, for example, pressing an "up" key on a keyboard indicates that the virtual vehicle speeds up, and pressing a "down" key on the keyboard indicates that the virtual vehicle decelerates. The user can add a plurality of virtual vehicles, so that a more complex traffic environment can be formed according to the states of the plurality of virtual vehicles.
The state information of the virtual vehicle may include position information of the virtual vehicle at different times, for example, the state information may record 20 pieces of position information of one virtual vehicle in every 1 s. The position of each virtual vehicle at each moment can be determined according to the information, and the dynamic traffic environment can be restored by adjusting the positions of the vehicles.
Specifically, the autonomous vehicle may be placed in the constructed traffic environment, and a target location may be designated for the autonomous vehicle in the simulation environment, such that the autonomous vehicle is capable of traveling in the constructed traffic environment.
The timing of steps 101 and 102 may not be limiting. For example, a user may first select the state information of a set of virtual vehicles in the simulation system, construct a traffic environment, and then generate an autonomous vehicle therein. The user can also operate the client to generate an automatic driving vehicle in the simulation system, and then a set of state information of the virtual vehicle is selected to construct a traffic environment.
And 103, acquiring environment perception information according to the position of the automatic driving vehicle in the driving process of the automatic driving vehicle, and inputting the environment perception information into a control system of the automatic driving vehicle so that the automatic driving vehicle drives according to the environment perception information.
After the autonomous vehicle is generated and the traffic environment is constructed, the autonomous vehicle can travel in the current traffic environment. Meanwhile, the traffic environment comprises at least one virtual vehicle, and the position of the virtual vehicle can be updated according to the corresponding state information.
Further, the autonomous vehicle needs to determine a driving strategy depending on the sensed surrounding environment, and thus, environmental information around the autonomous vehicle, such as the distance, direction, and the like of the surrounding vehicle from the autonomous vehicle, may be acquired. The position of the autonomous vehicle can be determined, and then the environment perception information under the view angle of the autonomous vehicle can be obtained according to the position.
In practical application, the acquired environment perception information can be input into a control system of the automatic driving vehicle, so that the control system determines information such as the driving speed and direction of the vehicle, and further controls the automatic driving vehicle to drive.
The simulation system can also detect information such as relative positions between vehicles and further determine whether the vehicles collide with each other. The simulation picture, namely the dynamic picture of the automatic driving vehicle running in the current traffic environment, can be displayed in the client, so that a user can more intuitively determine whether the automatic driving vehicle can run safely.
Specifically, when the environment perception information is obtained, the environment perception information can be directly determined according to the state information of the virtual vehicle, so that the data processing amount in the simulation process is reduced, and the simulation speed is increased.
The method provided by the present embodiment is used for testing an autonomous vehicle, and is performed by a device provided with the method provided by the present embodiment, which is typically implemented in hardware and/or software.
The test method for the automatic driving vehicle provided by the embodiment comprises the following steps: generating an autonomous vehicle in the simulation environment according to the received first generation instruction; constructing a traffic environment in the simulation environment according to the pre-recorded state information of the virtual vehicle so as to enable the automatic driving vehicle to run in the traffic environment; the method comprises the steps of obtaining environment perception information according to the position of an automatic driving vehicle in the running process of the automatic driving vehicle, and inputting the environment perception information into a control system of the automatic driving vehicle so that the automatic driving vehicle runs according to the environment perception information. The method provided by the embodiment can be used for constructing the traffic environment and enabling the generated automatic driving vehicle to run in the traffic environment, so that different traffic environments can be constructed according to requirements, and the environment for testing can be enriched. Meanwhile, the control system of the autonomous vehicle can acquire surrounding environment perception information, determine a driving strategy based on the information, and further control the vehicle to run. Therefore, the present embodiment provides a scheme capable of determining whether the control system of the vehicle can control safe driving of the vehicle based on the environmental information around the vehicle, through the running condition of the vehicle in the simulation system.
Fig. 2 is a flowchart illustrating a test method of an autonomous vehicle according to another exemplary embodiment of the present invention.
As shown in fig. 2, the method for testing an autonomous vehicle according to the present embodiment includes:
According to the method provided by the embodiment, the user can operate the simulation system to record the state information of the virtual vehicle, and further, the state information can be directly acquired and the traffic environment can be constructed during simulation. Therefore, the state information can be reused, and the corresponding traffic environment does not need to be set every time during simulation.
Wherein the user may input information for generating the virtual vehicle in the client, for example, may click on a location in the simulation environment, indicating that a virtual vehicle is generated at the location.
Specifically, the method provided by this embodiment may be executed by the client, or may be executed by a background system of the simulation system.
For example, a user may select a function in a client that generates a virtual vehicle, the client may request a simulation environment from a simulation system, the client may display the simulation environment in an interface, and the user may determine an initial position of the virtual vehicle in the simulation environment by clicking. The client can generate a virtual vehicle in the simulation environment according to the position clicked by the user, and the client can also upload the information of the virtual vehicle to the background system.
For another example, the user may select a function of generating a virtual vehicle in the client, the client may request the simulation environment from the simulation system, the client may display the simulation environment in the interface, the user may determine an initial position of the virtual vehicle in the simulation environment by clicking, and the client may send the position information to the background system, so that the background system generates a virtual vehicle in the simulation environment according to the received position and feeds the virtual vehicle back to the client, so that the client displays the generated virtual vehicle in the simulation environment.
And step 202, determining the running state information of the virtual vehicle according to the received control command.
Further, after initializing the virtual vehicle, the user may also operate the virtual vehicle so that the virtual vehicle may simulate the driving manner of the real vehicle, such as fuel filling, braking, turning, and the like. The user may input control information that in turn sends control instructions to the simulation system for controlling the virtual vehicle.
During actual application, the client can obtain a control instruction submitted by a user, determine the running state of the virtual vehicle based on the control instruction, send a control signal to the background system according to the control instruction, and determine the running state of the virtual vehicle by the control system.
The user can respectively control the operations of oiling, braking, left turning and right turning of the vehicle by operating the upper key, the lower key, the left key and the right key on the keyboard. The client can also be provided with controls with control functions of oiling, braking, left turning, right turning and the like, and a user can send control instructions by operating the controls.
Specifically, the state information of the vehicle at each time may be determined according to a control instruction generated by a user operation. Along with the operation of the user, the information such as the position and the speed of the virtual vehicle is also changed, and the states of the virtual vehicle at different moments can be recorded.
Furthermore, in order to construct a more complex traffic environment, a plurality of virtual vehicles can be added, and meanwhile, the running state information of each virtual vehicle can be determined. The plurality of virtual vehicles may each have state information corresponding to each time.
In practical applications, the traffic environment may be restored according to the driving state information of the virtual vehicles, for example, the positions of the virtual vehicles at time 0, time 1, time 2, and the like are determined according to the driving state information, and the positions of the virtual vehicles are adjusted according to the positions, so as to restore the traffic environment.
During the running process of the existing virtual vehicle, a new virtual vehicle can be added into the existing virtual vehicle, for example, at the 20 th moment, a user can add the new virtual vehicle into the simulation environment, and the running state of the newly added virtual vehicle can be controlled. The simulation system may generate a new virtual vehicle and determine the driving status information of the vehicle according to steps 201, 202. At this time, since the virtual vehicle is joined at the 20 th time, the running state information of the newly joined virtual vehicle includes the state of the virtual vehicle at the 20 th time and thereafter.
When the running state of the virtual vehicle is determined (including the initially generated virtual vehicle and the newly added virtual vehicle), the client can generate a control signal of the virtual vehicle according to the control instruction, then the client sends the control signal to the background system, and the background system predicts the state of the virtual vehicle at each moment and further determines the running state information.
Alternatively, a vehicle dynamics simulation module may be provided in the background system, which may determine the position information of the virtual vehicle at different times, so that the driving state information including the position information may be determined. A traffic scene running time length, such as ten minutes, can also be set, and then the corresponding position information of the virtual vehicle within a ten-minute time length can be determined.
In one embodiment, the running state information of all the virtual vehicles may be used, and in another embodiment, the running state information may be used as the state of the virtual vehicle in a certain period of time.
Optionally, the driving state information includes at least one of the following information corresponding to a plurality of times:
vehicle position, vehicle speed, vehicle heading.
Optionally, when the virtual vehicles are generated and controlled to run in the simulation environment, it may be further determined whether a collision occurs between the virtual vehicles, and if the collision occurs, the user may be prompted, or the user may reset the virtual vehicles if the relevant information of the virtual vehicles is considered to be illegal.
And step 203, determining a target time according to the received recording instruction, and recording the state information of the virtual vehicle from the target time.
The traffic scene can be displayed in the client, a dynamic picture can be generated according to the running state information of each virtual vehicle, and the position of each virtual vehicle changes along with the change of time in the picture. The user can select the starting time of the state information of the virtual vehicle according to the time condition of the traffic environment. For example, when the client displays, the user may click a recording button in the client, so that the client starts recording the status information of the virtual vehicle.
Specifically, the recorded status information may include only the position of the virtual vehicle, or may include information such as the speed and direction of the vehicle. For example, if the user clicks the record button at the 10 th time of the traffic scene operation, the client may record the position information of each virtual vehicle after the 10 th time of the traffic scene operation.
Furthermore, the user can also operate a key for stopping recording, so that the client stops recording.
And step 204, generating the automatic driving vehicle in the simulation environment according to the received first generation instruction.
The specific principle and implementation of step 204 are similar to those of step 101, and are not described herein again.
Optionally, according to actual requirements, the stationary state may be used as the initial state of the vehicle, and a certain driving speed may also be used as the initial state of the vehicle.
After the operation simulation system generates the automatic driving vehicle, the user can operate in the client side to further determine the initial state of the automatic driving vehicle.
Specifically, for example, the user may input an initial speed, a traveling direction, and the like of the vehicle in the client, thereby sending an initialization instruction to the simulation system. The client can determine the initialization state according to the operation of the user, and the client can also send the content input by the user to the background system, and the background system determines the initialization state.
Further, the state of the autonomous vehicle may be controlled according to the initial state when the autonomous vehicle is traveling in a traffic environment.
And step 205, generating a virtual vehicle in the simulation environment according to the pre-recorded state information of the virtual vehicle, and adjusting the state of the virtual vehicle in real time according to the running state information.
In practical application, a user can select a set of state information of the existing virtual vehicle, so that the pre-recorded state information of the virtual vehicle is obtained according to a selection instruction of the user, and the virtual vehicle is generated in a simulation environment.
The simulation system may store the state information of the virtual vehicle recorded by the user operation, and may also store default state information of the virtual vehicle. The user can select among them to determine a set of state information that currently needs to be applied.
Specifically, the virtual vehicles may be generated in the simulation environment based on initial position information of each virtual vehicle in the state information. The state information includes the position information of each virtual vehicle at each time, including the position of the vehicle at the initial time, and therefore, each virtual vehicle can be generated first.
Optionally, if the status information includes a virtual vehicle to join later, for example, it may be considered that the time sequence in the status information starts from time 0, and if an initial vehicle of a virtual vehicle joins at time 10, the virtual vehicle may be generated at time 10 when the traffic environment is constructed.
Further, the state information also comprises the position information of the vehicle at different moments, so that the position of the virtual vehicle can be adjusted in real time in the simulation scene, and the dynamic process of vehicle running is simulated.
Step 2061 may be performed after step 205, and step 2062 may also be performed.
Step 2061, determining the environment perception information of the automatic driving vehicle according to the state information of the virtual vehicle and the position of the automatic driving vehicle which are recorded in advance.
In practical applications, the control system of the autonomous vehicle is a driving strategy made depending on the surrounding environment information. Thus, the environmental awareness information of the autonomous vehicle can be determined with the known traffic environment.
In one embodiment, since the state information of each virtual vehicle in the traffic environment is known, the environmental information of the surroundings of the autonomous vehicle can be determined from these known states. Generally, an autonomous vehicle can sense vehicles within a certain range around the autonomous vehicle, so that the position of the autonomous vehicle can be determined, an area range can be determined according to the sensing range of the vehicle, the states of the virtual vehicles within the area range are acquired from the state information of the virtual vehicles recorded in advance according to the running time of the traffic environment in the simulation scene, and the environment sensing information of the autonomous vehicle is determined according to the states of the vehicles.
Specifically, a perception system of the automatic driving vehicle can be obtained in advance, and then the environment perception information conforming to the perception system is determined according to the virtual vehicle state around the vehicle. For example, the environmental awareness information may be determined based on a current orientation of the virtual vehicle and the autonomous vehicle, and a radar location disposed in the autonomous vehicle.
In another embodiment, in order to avoid the inconsistency between the perception data determined by the perception system of the vehicle and the data inferred by the virtual vehicle state, the perception system of the autonomous vehicle may be provided in the simulation system.
When the automatic driving vehicle is generated, a sensing system of the vehicle can be selected, for example, the sensing system can be determined by inputting the vehicle model, or a set of sensing systems can be directly selected. In such an embodiment, environmental data of the surroundings of the autonomous vehicle may be determined from the position of the autonomous vehicle, based on the state information of the virtual vehicle at each time. For example, virtual vehicles and their states within the perception range of the autonomous vehicle at time 1 may be determined and environmental data may be determined based on this information, e.g., point cloud data generated by these virtual vehicles may be scanned in the simulated environment from the perspective of the autonomous vehicle. The determined environmental data can be input into a perception system of the automatic driving vehicle, and the perception system performs calculation to obtain environmental perception information of the automatic driving vehicle.
After step 2061 or step 2062, step 207 may be performed.
Step 207 is similar to the specific principle and implementation of inputting the sensing information into the control system in step 103, and is not described herein again.
Fig. 3 is a block diagram illustrating a test apparatus of an autonomous vehicle according to an exemplary embodiment of the present invention.
As shown in fig. 3, the test apparatus for an autonomous vehicle according to the present embodiment includes:
a generation module 31 for generating an autonomous vehicle in the simulated environment according to the received first generation instruction;
a building module 32, configured to build a traffic environment in the simulation environment according to the pre-recorded state information of the virtual vehicle, so that the autonomous vehicle runs in the traffic environment;
the control module 33 is configured to obtain environment sensing information according to a position of the autonomous vehicle during a running process of the autonomous vehicle, and input the environment sensing information into a control system of the autonomous vehicle, so that the autonomous vehicle runs according to the environment sensing information.
The test device of the automatic driving vehicle provided by the embodiment comprises: the generation module is used for generating the automatic driving vehicle in the simulation environment according to the received first generation instruction; the construction module is used for constructing a traffic environment in the simulation environment according to the pre-recorded state information of the virtual vehicle so as to enable the automatic driving vehicle to run in the traffic environment; and the control module is used for acquiring the environment perception information according to the position of the automatic driving vehicle in the running process of the automatic driving vehicle and inputting the environment perception information into a control system of the automatic driving vehicle so as to enable the automatic driving vehicle to run according to the environment perception information. The device that this embodiment provided can construct traffic environment to make the autopilot that generates can travel in this traffic environment, thereby can construct different traffic environment according to the demand, can enrich the environment of testing. Meanwhile, the control system of the autonomous vehicle can acquire surrounding environment perception information, determine a driving strategy based on the information, and further control the vehicle to run. Therefore, the present embodiment provides a scheme capable of determining whether the control system of the vehicle can control safe driving of the vehicle based on the environmental information around the vehicle, through the running condition of the vehicle in the simulation system.
The specific principle and implementation of the testing device for the autonomous driving vehicle provided by the embodiment are similar to those of the embodiment shown in fig. 1, and are not described herein again.
Fig. 4 is a block diagram illustrating a test apparatus of an autonomous vehicle according to another exemplary embodiment of the present invention.
As shown in fig. 4, on the basis of the foregoing embodiment, the testing apparatus for an autonomous vehicle provided in this embodiment optionally further includes a setting module 34, configured to, before the generating module 31 generates the autonomous vehicle in the simulation environment according to the received first generation instruction:
generating a virtual vehicle according to the received second generation instruction;
determining the running state information of the virtual vehicle according to the received control instruction;
and determining a target time according to the received recording instruction, and recording the state information of the virtual vehicle from the target time.
Optionally, the setting module 34 includes a prediction unit 341, configured to:
and generating a control signal according to the control instruction, and predicting the running state information of the virtual vehicle according to the control signal.
Optionally, the driving state information includes at least one of the following information corresponding to a plurality of times:
vehicle position, vehicle speed, vehicle heading.
Optionally, the building module 32 is specifically configured to:
and generating the virtual vehicle in the simulation environment according to the pre-recorded state information of the virtual vehicle, and adjusting the state of the virtual vehicle in real time according to the running state information.
Optionally, the control module 33 includes a first control unit 331, configured to:
and determining the environment perception information of the automatic driving vehicle according to the pre-recorded state information of the virtual vehicle and the position of the automatic driving vehicle.
Optionally, the control module 33 includes a second control unit 332, configured to:
the method comprises the steps of obtaining environmental data around an automatic driving vehicle according to the position of the automatic driving vehicle, and inputting the environmental data into a sensing system of the automatic driving vehicle so that the sensing system processes the environmental data to obtain environmental sensing information.
Optionally, the apparatus further comprises an initialization module 35 configured to, after the generation module 31 generates the autonomous vehicle in the simulation environment according to the received first generation instruction:
determining an initial state of the autonomous vehicle according to the received initialization instruction to enable the autonomous vehicle to travel in the traffic environment according to the initial state.
The specific principle and implementation of the apparatus provided in this embodiment are similar to those of the embodiment shown in fig. 2, and are not described here again.
Fig. 5 is a block diagram illustrating a test apparatus of an autonomous vehicle according to an exemplary embodiment of the present invention.
As shown in fig. 5, the present embodiment provides a test apparatus for an autonomous vehicle, including:
a memory 51;
a processor 52; and
a computer program;
wherein the computer program is stored in the memory 51 and configured to be executed by the processor 52 to implement any of the automated vehicle testing methods described above.
The present embodiments also provide a computer-readable storage medium, having stored thereon a computer program,
the computer program is executed by a processor to implement any of the automated vehicle testing methods described above.
Those of ordinary skill in the art will understand that: all or a portion of the steps of implementing the above-described method embodiments may be performed by hardware associated with program instructions. The program may be stored in a computer-readable storage medium. When executed, the program performs steps comprising the method embodiments described above; and the aforementioned storage medium includes: various media that can store program codes, such as ROM, RAM, magnetic or optical disks.
Finally, it should be noted that: the above embodiments are only used to illustrate the technical solution of the present invention, and not to limit the same; while the invention has been described in detail and with reference to the foregoing embodiments, it will be understood by those skilled in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; and the modifications or the substitutions do not make the essence of the corresponding technical solutions depart from the scope of the technical solutions of the embodiments of the present invention.
Claims (7)
1. A method of testing an autonomous vehicle, comprising:
generating an autonomous vehicle in the simulation environment according to the received first generation instruction;
constructing a traffic environment in the simulation environment according to the pre-recorded state information of the virtual vehicle so that the automatic driving vehicle runs in the traffic environment;
acquiring environment perception information according to the position of the automatic driving vehicle in the running process of the automatic driving vehicle, and inputting the environment perception information into a control system of the automatic driving vehicle so as to enable the automatic driving vehicle to run according to the environment perception information;
wherein the obtaining of the environmental awareness information according to the location of the autonomous vehicle during the driving of the autonomous vehicle comprises: determining the environmental perception information of the autonomous vehicle according to the pre-recorded state information of the virtual vehicle and the position of the autonomous vehicle;
acquiring environment perception information in the driving process of the automatic driving vehicle, wherein the environment perception information comprises the following steps: acquiring environmental data around the automatic driving vehicle according to the position of the automatic driving vehicle, and inputting the environmental data into a perception system of the automatic driving vehicle so that the perception system processes the environmental data to obtain the environmental perception information, wherein the environmental data around the automatic driving vehicle is as follows: point cloud data generated by scanning virtual vehicles within a perception range of the autonomous vehicle from the autonomous vehicle perspective;
before generating the autonomous vehicle in the simulation environment according to the received first generation instruction, the method further comprises:
generating a virtual vehicle according to the received second generation instruction;
determining the running state information of the virtual vehicle according to the received control instruction;
determining a target time according to the received recording instruction, and recording the state information of the virtual vehicle from the target time;
the constructing of the traffic environment in the simulation environment according to the pre-recorded state information of the virtual vehicle comprises:
and generating the virtual vehicle in the simulation environment according to the pre-recorded state information of the virtual vehicle, and adjusting the state of the virtual vehicle in real time according to the running state information.
2. The method of claim 1, wherein determining the driving state information of the virtual vehicle according to the received control command comprises:
and generating a control signal according to the control instruction, and predicting the running state information of the virtual vehicle according to the control signal.
3. The method according to claim 1 or 2, characterized in that the driving state information includes at least one of the following information for a plurality of times:
vehicle position, vehicle speed, vehicle heading.
4. The method of claim 1, after generating the autonomous vehicle in the simulated environment according to the received first generation instruction, further comprising:
determining an initial state of the autonomous vehicle according to the received initialization instruction to enable the autonomous vehicle to travel in the traffic environment according to the initial state.
5. A test apparatus for an autonomous vehicle, comprising:
the generation module is used for generating the automatic driving vehicle in the simulation environment according to the received first generation instruction;
the construction module is used for constructing a traffic environment in the simulation environment according to the pre-recorded state information of the virtual vehicle so as to enable the automatic driving vehicle to run in the traffic environment;
the control module is used for acquiring environment perception information according to the position of the automatic driving vehicle in the running process of the automatic driving vehicle and inputting the environment perception information into a control system of the automatic driving vehicle so as to enable the automatic driving vehicle to run according to the environment perception information;
wherein the control module comprises a first control unit for: determining the environmental perception information of the automatic driving vehicle according to the pre-recorded state information of the virtual vehicle and the position of the automatic driving vehicle;
the control module further comprises a second control unit for: acquiring environmental data around an automatic driving vehicle according to the position of the automatic driving vehicle, and inputting the environmental data into a perception system of the automatic driving vehicle so as to enable the perception system to process the environmental data to obtain environmental perception information, wherein the environmental data around the automatic driving vehicle is as follows: point cloud data generated by scanning virtual vehicles within a perception range of the autonomous vehicle from the autonomous vehicle perspective;
a setup module to, prior to the generation module generating an autonomous vehicle in a simulated environment according to the received first generation instruction:
generating a virtual vehicle according to the received second generation instruction;
determining the running state information of the virtual vehicle according to the received control instruction;
determining a target time according to the received recording instruction, and recording the state information of the virtual vehicle from the target time;
the building module is specifically configured to: and generating the virtual vehicle in the simulation environment according to the pre-recorded state information of the virtual vehicle, and adjusting the state of the virtual vehicle in real time according to the running state information.
6. A test apparatus for an autonomous vehicle, comprising:
a memory;
a processor; and
a computer program;
wherein the computer program is stored in the memory and configured to be executed by the processor to implement the method of any of claims 1-4.
7. A computer-readable storage medium, having stored thereon a computer program,
the computer program is executed by a processor to implement the method according to any one of claims 1-4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910433322.8A CN110209146B (en) | 2019-05-23 | 2019-05-23 | Test method, device and equipment for automatic driving vehicle and readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910433322.8A CN110209146B (en) | 2019-05-23 | 2019-05-23 | Test method, device and equipment for automatic driving vehicle and readable storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110209146A CN110209146A (en) | 2019-09-06 |
| CN110209146B true CN110209146B (en) | 2020-12-01 |
Family
ID=67788336
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910433322.8A Active CN110209146B (en) | 2019-05-23 | 2019-05-23 | Test method, device and equipment for automatic driving vehicle and readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110209146B (en) |
Families Citing this family (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110795818B (en) * | 2019-09-12 | 2022-05-17 | 腾讯科技（深圳）有限公司 | Method and device for determining virtual test scene, electronic equipment and storage medium |
| CN110793784B (en) * | 2019-09-16 | 2021-10-26 | 腾讯科技（深圳）有限公司 | Test method and device for automatic driving vehicle, storage medium and electronic device |
| WO2021056556A1 (en) * | 2019-09-29 | 2021-04-01 | 驭势科技（北京）有限公司 | Vehicle-mounted autonomous driving test system and test method |
| CN110673636B (en) * | 2019-09-30 | 2023-01-31 | 上海商汤临港智能科技有限公司 | Unmanned simulation test system and method, and storage medium |
| CN111223354A (en) * | 2019-12-31 | 2020-06-02 | 塔普翊海（上海）智能科技有限公司 | Unmanned trolley, and AR and AI technology-based unmanned trolley practical training platform and method |
| CN111353221A (en) * | 2020-02-24 | 2020-06-30 | 上海商汤临港智能科技有限公司 | Automatic driving simulation method and device, electronic equipment and storage medium |
| CN111338232B (en) * | 2020-02-26 | 2023-09-05 | 杭州飞步科技有限公司 | Automatic driving simulation method and device |
| CN111368409A (en) * | 2020-02-27 | 2020-07-03 | 杭州飞步科技有限公司 | Vehicle flow simulation processing method, device, equipment and storage medium |
| CN111366374B (en) * | 2020-03-04 | 2024-02-02 | 腾讯科技（深圳）有限公司 | Vehicle testing method and device, electronic equipment and storage medium |
| CN112230632A (en) * | 2020-10-28 | 2021-01-15 | 北京航迹科技有限公司 | Method, apparatus, device and storage medium for automatic driving |
| CN114970112B (en) * | 2022-04-29 | 2023-05-09 | 阿波罗智能技术(北京)有限公司 | Method, device, electronic equipment and storage medium for automatic driving simulation |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2001142445A (en) * | 1999-11-17 | 2001-05-25 | Nec Corp | On-screen display device |
| CN109213126A (en) * | 2018-09-17 | 2019-01-15 | 安徽江淮汽车集团股份有限公司 | Autonomous driving vehicle test macro and method |
| CN208433001U (en) * | 2018-05-24 | 2019-01-25 | 北京汽车集团有限公司 | Driving simulation test device and system |
Family Cites Families (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105956268B (en) * | 2016-04-29 | 2018-01-02 | 百度在线网络技术（北京）有限公司 | Test scene construction method and device applied to pilotless automobile |
| CN115686005A (en) * | 2016-06-28 | 2023-02-03 | 柯尼亚塔有限公司 | System and computer-implemented method for training virtual models of an autopilot system |
| CN108241354B (en) * | 2016-12-26 | 2022-11-22 | 法法汽车(中国)有限公司 | Test method for automatic driving simulation system |
| JP6824137B2 (en) * | 2017-10-13 | 2021-02-03 | キャッツ株式会社 | Operation simulator of autonomous driving vehicle, operation confirmation method of autonomous driving vehicle, control device of autonomous driving vehicle and control method of autonomous driving vehicle |
| CN107727411B (en) * | 2017-10-30 | 2019-09-27 | 青岛慧拓智能机器有限公司 | A kind of automatic driving vehicle assessment scene generation system and method |
| CN108919779A (en) * | 2018-07-02 | 2018-11-30 | 北京小马智行科技有限公司 | A kind of interactive mode unmanned vehicle emulation mode and emulation platform |
| CN109657355B (en) * | 2018-12-20 | 2021-05-11 | 安徽江淮汽车集团股份有限公司 | Simulation method and system for vehicle road virtual scene |
| CN109782737A (en) * | 2019-01-28 | 2019-05-21 | 平安科技（深圳）有限公司 | Unmanned vehicle analog detection method and system |
-
2019
- 2019-05-23 CN CN201910433322.8A patent/CN110209146B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2001142445A (en) * | 1999-11-17 | 2001-05-25 | Nec Corp | On-screen display device |
| CN208433001U (en) * | 2018-05-24 | 2019-01-25 | 北京汽车集团有限公司 | Driving simulation test device and system |
| CN109213126A (en) * | 2018-09-17 | 2019-01-15 | 安徽江淮汽车集团股份有限公司 | Autonomous driving vehicle test macro and method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110209146A (en) | 2019-09-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110209146B (en) | Test method, device and equipment for automatic driving vehicle and readable storage medium | |
| CN111897305B (en) | Data processing method, device, equipment and medium based on automatic driving | |
| CN110333730B (en) | Verification method, platform and storage medium for safety of expected function of automatic driving algorithm | |
| CN109884916B (en) | Automatic driving simulation evaluation method and device | |
| CN111006879B (en) | Port environment-oriented man-machine hybrid driving automatic driving test method and test platform thereof | |
| CN108428357B (en) | Parallel remote control driving system for intelligent internet vehicle | |
| CN111505965A (en) | Method and device for simulation test of automatic driving vehicle, computer equipment and storage medium | |
| CN107221222B (en) | Multi-mode driving simulation system for work efficiency evaluation and evaluation method thereof | |
| CN111795832B (en) | Intelligent driving vehicle testing method, device and equipment | |
| CN111580493B (en) | Automatic driving simulation method, system and medium | |
| JP2022524168A (en) | Methods and systems for determining the driver's intentions in steering a semi-automatic vehicle | |
| CN111881519A (en) | Automatic driving test method and device, computer equipment and storage medium | |
| CN113848855B (en) | Vehicle control system test method, device, equipment, medium and program product | |
| CN111752258A (en) | Operation test of autonomous vehicle | |
| US20220289253A1 (en) | Method for evaluating autonomous driving system, apparatus and storage medium | |
| CN112286206A (en) | Automatic driving simulation method, system, equipment, readable storage medium and platform | |
| EP4150463A1 (en) | Generating simulation environments for testing av behaviour | |
| CN112671487B (en) | Vehicle testing method, server and testing vehicle | |
| US11897503B2 (en) | Method and apparatus for detecting unexpected control state in autonomous driving system | |
| CN114212108A (en) | Automatic driving method, device, vehicle, storage medium and product | |
| CN115309085A (en) | Unmanned dual-communication redundancy control method, system, electronic equipment and medium | |
| CN112965917A (en) | Test method, device, equipment and storage medium for automatic driving | |
| CN114217613B (en) | Remote control method and device and remote driving system | |
| US20240038073A1 (en) | Method and apparatus for providing flight vehicle operation information | |
| US11679757B2 (en) | Control assistant system to align driving and riding experience between gasoline and electric vehicles |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |