CN113687600A - Simulation test method, simulation test device, electronic equipment and storage medium - Google Patents
Simulation test method, simulation test device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN113687600A CN113687600A CN202111224045.3A CN202111224045A CN113687600A CN 113687600 A CN113687600 A CN 113687600A CN 202111224045 A CN202111224045 A CN 202111224045A CN 113687600 A CN113687600 A CN 113687600A
- Authority
- CN
- China
- Prior art keywords
- simulation
- test
- simulation test
- data packet
- scene
- 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.)
- Pending
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
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention provides a simulation test method, a simulation test device, electronic equipment and a storage medium, wherein the method comprises the steps of firstly obtaining at least one data packet collected by a sensing source, wherein the data packet comprises environmental information of a sensing area, attribute information of each traffic participant and traffic behavior information, then determining target vehicles in the target data packet according to the attribute information and the traffic behavior information, respectively replacing each target vehicle in the target data packet with an automatic driving vehicle to obtain each simulation test scene corresponding to the target data packet, and generating a simulation test scene script corresponding to each simulation test scene, according to the traffic behavior information of the replaced target vehicle in each simulation test scene and the preset automatic driving algorithm, and carrying out simulation scene test on each simulation test scene script, outputting a test result, and finally evaluating the performance of the preset automatic driving algorithm according to the test result. The invention improves the authenticity and efficiency of constructing the simulation test environment and can meet the test requirement of the automatic driving algorithm.
Description
Technical Field
The invention relates to the technical field of automatic driving, in particular to a simulation test method, a simulation test device, electronic equipment and a storage medium.
Background
In an autopilot system, a simulation test scenario is typically constructed in which an autopilot algorithm is tested. When a simulation test scene is currently constructed, road information is mostly collected through a road side sensor, then a simulation environment is manually constructed, and then an automatic driving algorithm test is carried out in the environment. However, the simulation environment constructed in this way only considers road information, and has lower authenticity compared with a real environment, so that it is difficult to provide a high-quality simulation test scene for the automatic driving algorithm, and the accuracy of the algorithm test cannot be guaranteed. In addition, the simulation test scene is manually constructed, so that the test requirements are difficult to meet in efficiency and performance.
Therefore, the existing simulation test method has the technical problem that the test requirement of the automatic driving algorithm is difficult to meet, and needs to be improved.
Disclosure of Invention
The invention provides a simulation test method and a simulation test device, which are used for solving the technical problem that the test requirement of an automatic driving algorithm is difficult to meet in the existing simulation test method.
In order to solve the technical problems, the invention provides the following technical scheme:
the invention provides a simulation test method, which comprises the following steps:
acquiring at least one data packet acquired by a sensing source, wherein the data packet comprises environmental information of a sensing area, attribute information of each traffic participant and traffic behavior information;
determining a target vehicle in a target data packet according to the attribute information and the traffic behavior information;
respectively replacing each target vehicle in the target data packet with an automatic driving vehicle to obtain each simulation test scene corresponding to the target data packet and generate a simulation test scene script corresponding to each simulation test scene;
carrying out simulation scene testing on each simulation test scene script according to the traffic behavior information of the replaced target vehicle in each simulation test scene and a preset automatic driving algorithm, and outputting a test result;
and evaluating the performance of the preset automatic driving algorithm according to the test result.
The present invention also provides a simulation test apparatus, which includes:
the acquisition module is used for acquiring at least one data packet acquired by a sensing source, wherein the data packet comprises environmental information of a sensing area, attribute information of each traffic participant and traffic behavior information;
the determining module is used for determining a target vehicle in a target data packet according to the attribute information and the traffic behavior information;
the generation module is used for replacing each target vehicle in the target data packet with an automatic driving vehicle respectively to obtain each simulation test scene corresponding to the target data packet and generate a simulation test scene script corresponding to each simulation test scene;
the test module is used for carrying out simulation scene test on each simulation test scene script according to the traffic behavior information of the replaced target vehicle in each simulation test scene and a preset automatic driving algorithm and outputting a test result;
and the evaluation module is used for evaluating the performance of the preset automatic driving algorithm according to the test result.
The invention also provides an electronic device comprising a memory and a processor; the memory stores an application program, and the processor is used for running the application program in the memory to execute the operation in the simulation test method.
The present invention also provides a computer readable storage medium having stored thereon a computer program for execution by a processor to implement the simulation test method of any one of the above.
Has the advantages that: the invention provides a simulation test method, a simulation test device, electronic equipment and a storage medium, wherein the method comprises the steps of firstly obtaining at least one data packet collected by a sensing source, wherein the data packet comprises environmental information of a sensing area, attribute information of each traffic participant and traffic behavior information, then determining target vehicles in the target data packet according to the attribute information and the traffic behavior information, respectively replacing each target vehicle in the target data packet with an automatic driving vehicle to obtain each simulation test scene corresponding to the target data packet, and generating a simulation test scene script corresponding to each simulation test scene, according to the traffic behavior information of the replaced target vehicle in each simulation test scene and the preset automatic driving algorithm, and carrying out simulation scene test on each simulation test scene script, outputting a test result, and finally evaluating the performance of the preset automatic driving algorithm according to the test result. By the method, after the data packet is acquired through the sensing source, a plurality of simulation test scenes can be automatically established according to the real environment in the data packet and the data of real traffic participants, and the simulation test of the replaced automatic driving vehicle in each simulation test environment based on the preset automatic driving algorithm is automatically completed.
Drawings
The technical solution and other advantages of the present invention will become apparent from the following detailed description of specific embodiments of the present invention, which is to be read in connection with the accompanying drawings.
Fig. 1 is a schematic view of a scenario in which the simulation test method provided by the present invention is applicable.
Fig. 2 is a schematic flow chart of a simulation test method provided by the present invention.
FIG. 3 is a schematic diagram of a simulation test log according to the present invention.
FIG. 4 is a comparison diagram of the driving paths of all the traffic participants in the simulation test scenario of the present invention.
FIG. 5 is a schematic diagram of the comparison of the speed/acceleration of an autonomous vehicle and a replaced target vehicle in a simulation test scenario of the present invention.
Fig. 6 is a schematic diagram of an overall architecture of the simulation test method provided by the present invention.
Fig. 7 is a schematic structural diagram of a simulation test apparatus provided in the present invention.
Fig. 8 is a schematic structural diagram of an electronic device provided in the present invention.
Detailed Description
The technical solution of the present invention will be clearly and completely described below with reference to the accompanying drawings. It is to be understood that the described embodiments are merely exemplary of the invention, and not restrictive of the full scope of the invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The invention provides a simulation test method and a simulation test device, which are used for solving the technical problem that the test requirement of an automatic driving algorithm is difficult to meet in the existing simulation test method.
Referring to fig. 1, fig. 1 is a schematic view of a scenario in which the simulation testing method provided by the present invention is applicable, where the scenario may include terminals and servers, and the terminals, the servers, and the terminals and the servers are connected and communicated through the internet formed by various gateways, and the like, where the application scenario includes a sensing source 11, a server 12, and a simulation platform 13; wherein:
the sensing source 11 may include roadside sensors and vehicle-mounted sensors on vehicles arranged on both sides of a lane in vehicle-road cooperation, the sensors may include cameras, laser radars, GPS and the like, and may realize accurate acquisition of relevant data of various lanes, environments, traffic participants and the like on the road;
the server 12 comprises a local server and/or a remote server and the like;
the simulation platform 13 is a platform for constructing a simulation test scene and performing an automatic driving algorithm test.
The sensing source 11, the server 12 and the simulation platform 13 are located in a wireless network or a wired network to realize data interaction among the three, wherein:
the multiple sensing sources 11 in a certain area collect environment information, attribute information of each traffic participant and traffic behavior information in respective sensing ranges, data collected by each sensing source 11 in each collection period form a data packet, and the data packets of the multiple sensing sources 11 are subjected to processing such as track filtering and merging and then fused to obtain a complete data packet and are uploaded to the server 12.
The sensing source 11 may collect and upload one or more data packets to the server 12, and after detecting that an unprocessed target data packet exists in the server 12, the simulation platform 13 determines a target vehicle in the target data packet according to attribute information and traffic behavior information of each traffic participant in the target data packet, where the target vehicle may be a vehicle driven by a person whose driving path is longer than a certain distance. For a target data packet, which usually includes more than one target vehicle, the simulation platform 13 replaces each target vehicle in the target data packet with an autonomous vehicle, the n target vehicles are replaced n times respectively, only one target vehicle is replaced each time, and the target vehicles replaced each time are different, so that n simulation test scenes corresponding to the target data packet are obtained, then simulation test scene scripts corresponding to each simulation test scene are generated and uploaded to the server 12, and the scripts describe environment information, attribute information of each traffic participant, traffic behavior information and the like through a script language.
After detecting that unprocessed simulation test scene scripts exist in the server 12, the simulation platform 13 performs simulation scene tests on the simulation test scene scripts according to the traffic behavior information of the replaced target vehicle in each simulation test scene and the preset automatic driving algorithm, so as to obtain the driving condition of the replaced automatic driving vehicle in the simulation test environment established on the basis of the real environment under the control of the preset automatic driving algorithm, output the test result, and finally evaluate the performance of the preset automatic driving algorithm according to the test result.
It should be noted that the system scenario diagram shown in fig. 1 is only an example, the server and the scenario described in the present invention are for more clearly illustrating the technical solution of the present invention, and do not constitute a limitation to the technical solution provided by the present invention, and it is known to those skilled in the art that as the system evolves and a new service scenario appears, the technical solution provided by the present invention is also applicable to similar technical problems. The following are detailed below. It should be noted that the following description of the embodiments is not intended to limit the preferred order of the embodiments.
Referring to fig. 2, fig. 2 is a schematic flow chart of a simulation testing method provided by the present invention, the method including:
s201: and acquiring at least one data packet acquired by a sensing source, wherein the data packet comprises environmental information of a sensing area, attribute information of each traffic participant and traffic behavior information.
In the invention, the sensing source comprises roadside sensors arranged on two sides of a lane in vehicle-road cooperation and vehicle-mounted sensors on vehicles, the sensors can comprise cameras, laser radars, GPS and the like, and the accurate acquisition of relevant data of various lanes, environments, traffic participants and the like on the road can be realized. In the vehicle-road cooperative system, one or more sensing sources are usually arranged in each real area, and each sensing source can periodically collect environmental information, attribute information of each traffic participant, traffic behavior information and the like in each sensing area and upload the information to a cloud end as a data packet. The environment information refers to information such as roads, obstacles, traffic signs, time, weather and the like in the sensing area, the traffic participants refer to pedestrians, vehicles and the like in the sensing area, the attribute information refers to quantity information and category information (pedestrians, vehicles, cars or buses, manned vehicles or automatic vehicles, old people or children and the like) of each traffic participant, and the traffic behavior information refers to related data of a series of traffic behaviors such as running tracks, running speeds, running accelerations, running times, running track lengths, straight running, turning around, turning, lane changing, stillness, walking, running and the like of each traffic participant.
In order to improve the diversity of subsequent simulation tests, a plurality of data packets in different time periods in the same region can be acquired, and data packets in different regions can also be acquired. When acquiring a data packet, data can be acquired only by one sensing source, for example, a camera arranged at a certain intersection acquires relevant data of all environments and traffic participants within a shooting range within five minutes to obtain one data packet, or data can be acquired respectively by two or more sensing sources with overlapped sensing ranges within one area to obtain a plurality of data packets, and then the data packets are fused to obtain a complete data packet, for example, a camera arranged on a certain running vehicle collects all the relevant video data of the environment and the traffic participants in the shooting range within five minutes, meanwhile, the laser radar arranged on the vehicle is used for collecting all the relevant point cloud data of the environment and the traffic participants within the shooting range within five minutes, and then fusing the video data packet and the point cloud data packet to obtain a complete data packet. The type of the data packet is not limited in the invention, and the data packet can be an independent data packet or a data packet obtained after fusion, and a person skilled in the art can select which type of data packet to obtain according to the test requirement.
After the data packets are uploaded to the cloud, the simulation platform starts to screen and optimize the cloud original data packets after detecting that unprocessed original data packets exist in the cloud. For each data packet, judging whether each acquired data packet is an effective data packet or not according to a preset effective condition; if so, optimizing the data in the effective data packet; and if not, discarding the invalid data packet. The step is mainly used for analyzing each data packet and extracting effective information from the data packet. Specifically, for each data packet, information such as a time length of the data packet, a position of each traffic participant, a number of each traffic participant, a speed, a length of a driving track, and the like is extracted, and then whether the data packet is valid is judged according to a preset valid condition, for example, whether the time length of the data packet satisfies a preset time length, whether the number of different types of traffic participants satisfies a preset number, whether the length of the track of each traffic participant, the speed, and the like satisfy preset values, and the like are judged to determine whether the data packet is a valid data packet. And for invalid data packets which do not meet the conditions, directly discarding the invalid data packets, and only keeping valid data packets to ensure the quality of the data packets.
Further optimization is needed for the screened effective data packets, and the optimization mainly comprises removal of noise data and combination of tracks. For example, a part of pedestrians walking on a sidewalk, or objects such as vehicles or pedestrians far away from the perception source have no influence on the subsequent scene simulation result, and the part of useless noise data can be removed to reduce the computation amount. For another example, due to the deficiency of the perception and tracking algorithm, the same traffic participant is recognized as three different objects, and then three different tracks appear on the traffic participant, and the three different tracks need to be optimized and connected into the same track. After optimization, the quality of the data packet is further improved.
In one embodiment, after S201, the method further includes: decoupling traffic behavior information of each typical traffic participant in each data packet to obtain position information and speed information of each typical traffic participant at each moment; and constructing a behavior logic unit of each typical traffic participant according to the position information, the speed information and the attribute information of each typical traffic participant, and uploading the behavior logic unit to a typical object behavior library. For each optimized data packet which comprises the traffic behavior information and the attribute information of each traffic participant, typical traffic participants (including vehicles, pedestrians and the like) with typical behaviors and clear paths are found from the traffic participants, then the traffic behaviors of the typical traffic participants are decoupled, namely, a series of traffic behaviors of each typical traffic participant in the corresponding environment are represented by the position-time point and the speed-time point of each typical traffic participant in the driving process, and then the behavior logic unit of each typical traffic participant is constructed according to the attribute information of the typical traffic participant, when m typical traffic participants exist in a certain data packet, the m behavior logic units can be obtained, and all the constructed behavior logic units are uploaded to a typical object behavior library which is pre-established in the cloud end, so that various types of simulation test scenes can be constructed for later use.
For each data packet, a plurality of behavior logic units can be obtained, and when the number of the data packets is large enough, the number of the behavior logic units in the typical object behavior library can be considerable, so that a sufficient sample is provided for constructing various types of simulation test scenes. In addition, each behavior logic unit is derived from an object of a real environment, so that the reality of a simulation test scene established according to the behavior logic unit is higher, and the accuracy of the automatic driving algorithm test is improved.
S202: and determining the target vehicle in the target data packet according to the attribute information and the traffic behavior information.
And sequentially taking the data packets screened and optimized in the previous steps as target data packets, wherein each target data packet comprises a plurality of types of traffic participants, the traffic behaviors of the traffic participants are different, the traffic participants with the attributes of being manned vehicles are taken out from the target data packets, and the traffic behaviors are the traffic participants with the running track length larger than the preset length (for example, 10 meters) and taken as the target vehicles. In general, a plurality of traffic participants in a data packet can all satisfy the above conditions, and all the traffic participants are target vehicles.
S203: and respectively replacing each target vehicle in the target data packet with an automatic driving vehicle to obtain each simulation test scene corresponding to the target data packet and generate a simulation test scene script corresponding to each simulation test scene.
Assuming that N traffic participants exist in the target data packet, wherein N traffic participants are target vehicles, when N is 1, directly replacing the target vehicles with automatic driving vehicles, and then keeping the rest N-1 traffic participants and the environment unchanged to obtain a simulation test scene corresponding to the target data packet. When N is an integer larger than 1, one of the N target vehicles is replaced by the automatic driving vehicle, and the rest N-1 traffic participants and the environment are unchanged, so that one of the simulation test scenes corresponding to the target data packet is obtained. And then, taking another one of the N target vehicles to be replaced by the automatic driving vehicle, and obtaining another simulation test scene corresponding to the target data packet, wherein the rest N-1 traffic participants and the environment are not changed. And repeating the steps, executing n times of replacement operation, replacing one target vehicle each time, wherein the target vehicles replaced each time are different, and obtaining n simulation test scenes according to the target data packet.
For each simulation test scene, the simulation platform automatically generates a simulation test scene script corresponding to the scene, and the simulation test scene script describes the real relevant information of the environment and the traffic participants in the simulation test scene by using xml language and json language. As shown in Table 1, the scenario name epicode is used as an example, and the simulation test scenario script generally includes the following parts.
TABLE 1 simulation test scenarios script in each scenario description file and role
In each simulation test scenario, the driving starting point and the driving end point of the replaced target vehicle are used as the driving starting point and the driving end point of the replaced automatic driving vehicle, and because the replaced automatic driving vehicles in each simulation test scenario are different, the relevant description of the automatic driving vehicles in each simulation test scenario is also not completely the same. And after n simulation test scene scripts are sequentially generated, the n simulation test scene scripts are automatically uploaded to an automatic driving simulation test scene library at the cloud.
By the method, n simulation test scenario scripts can be obtained for one target data packet, so that the simulation test efficiency is improved.
S204: and carrying out simulation scene testing on each simulation test scene script according to the traffic behavior information of the replaced target vehicle in each simulation test scene and a preset automatic driving algorithm, and outputting a test result.
When detecting that an untested scene exists in the automatic driving simulation test scene library at the cloud end, the simulation platform automatically performs corresponding simulation scene test, simulates the driving condition of the replaced automatic driving vehicle under the control of a preset automatic driving algorithm when performing similar traffic behavior according to the traffic behavior information of the replaced target vehicle in a certain simulation test scene, and simultaneously ensures that other traffic participants and environments in the scene during test are performed according to the description in the simulation test scene script. And after the test is finished, outputting a test result in the form of a simulation test report.
In one embodiment, S204 specifically includes: determining a driving starting point and a driving end point of the replaced automatic driving vehicle according to the driving starting point and the driving end point of the replaced target vehicle in each simulation test scene; controlling each automatic driving vehicle to run in a simulation mode in a corresponding simulation test scene according to the running starting point and the running end point by using a preset automatic driving algorithm, and controlling other traffic participants to run in a simulation mode in the corresponding simulation test scene in the same mode as that in the target data packet; and outputting a test result according to the simulation driving data.
If the replaced target vehicle runs from the running starting point a to the running end point b in a certain simulation test scene, the running starting point of the replaced automatic driving vehicle in the current simulation test scene is also a, and the running end point is also b. And controlling other traffic participants in the scene to correspondingly drive according to the description in the script, wherein if a certain person drives the vehicle to drive from q1 point to q2 point at a constant speed v on a P lane in a time period from t1 to t2, the vehicle is also controlled to drive from q1 point to q2 point at a constant speed v on the P lane in a time period from t1 to t2 during the simulation test, namely the traffic behaviors of other traffic participants are simulated according to the traffic behaviors in the actually collected target data packet. In addition, the environment in the scene is simulated based on the real environment. In a simulation test environment with high authenticity, an automatic driving vehicle is controlled to drive from a point a to a point b by a preset automatic driving algorithm, simulation driving data of the automatic driving vehicle in the whole test period, such as simulation driving tracks, simulation driving speed, simulation driving time and the like, are obtained, and scene test results are output according to the simulation driving data.
In one embodiment, S204 specifically includes: carrying out simulation scene test on each simulation test scene script; and outputting a simulation test log according to a preset test index, and uploading the simulation test log to a simulation test log library. After simulation scene testing is carried out on each simulation test scene script, a scene test result is given according to preset test indexes, such as whether the automatic driving vehicle collides with other vehicles, whether the automatic driving vehicle successfully reaches a terminal, whether the driving speed, the driving acceleration and the driving time meet preset values or value ranges and the like, and the scene test result can be presented in a simulation test log mode and automatically uploaded to an automatic driving simulation test log library at the cloud end.
As shown in fig. 3, the simulation test log is obtained after the test of a certain scenario is finished. In fig. 3, Episode: test _1 refers to the first test of the simulation test scenario script with scenario name epicode, Result: FAILURE means that the test result is a FAILURE. Start Time and End Time are scene play Start Time and End Time, Duration: system Time and Simulation Time are the System Time and Simulation Time for which a scene lasts. The dynamic Model (T001) refers to an automatic driving vehicle Model named T001 in a scene, the Actor refers to a tested automatic driving vehicle Model, the Criterion refers to preset Test indexes including a colloid Test (the number of whole Collision), a drive Distance Test (a driving Distance), an Average Velocity Test (an Average speed), a Time Out (a scene playing completion Time) and the like, each index has an Expected Value and an Actual Value, and whether the Actual Value reaches the Result of the Expected Value or not. In addition, the simulation test log also shows a behavior tree of scene execution, in which each item in the behavior tree is bracketed to represent Running, i.e. an ongoing state, v represents Success, i.e. operation Success, and x represents Fail, i.e. operation failure. Through the simulation test log, the test state and the test result of each test in the simulation scene test can be clearly known.
In one embodiment, S204 specifically includes: carrying out simulation scene test on each simulation test scene script; and outputting a traffic behavior comparison graph of the automatic driving vehicle and the replaced target vehicle in each simulation test reference. When the simulation test log is generated, the driving path comparison graphs of all traffic participants in the scene are output in the form of pictures, the driving path comparison graphs comprise the driving path curves of the replaced target vehicle, the replaced automatic driving vehicle and other types of traffic participants, and the traffic behaviors of all the traffic participants are compared in the graphs to serve as a basis for judging the performance of the preset automatic driving algorithm. As shown in fig. 4, a1 is a map line in which the autonomous vehicle is located, a2 represents the travel paths of other traffic participants in the scene, A3 represents the simulated travel path of the autonomous vehicle, and a4 represents the actual travel path of the target vehicle of the replaced vehicle, so that the degree of overlap of the travel paths of the autonomous vehicle and the replaced target vehicle can be visually displayed in fig. 4.
As shown in fig. 5, a speed/acceleration comparison graph of the autonomous vehicle and the replaced target vehicle may be further outputted in the form of a picture, in fig. 5, the horizontal axis is a time axis, the vertical axis is a speed/acceleration numerical axis, B1 is a speed curve of the autonomous vehicle, B2 is an acceleration curve of the autonomous vehicle, and B3 is an actual speed curve of the replaced target vehicle. The difference in the travel speeds of the autonomous vehicle and the replaced target vehicle can be visually shown from fig. 5.
It should be noted that, in the above embodiments, each simulation scenario test script is used for performing a test once, but the present invention is not limited thereto, and in the process of automatically performing data packet analysis and simulation test, the number of times of testing the preset autopilot algorithm may be increased, and multiple tests may be performed in one script, so as to achieve the purpose of fully testing the preset autopilot algorithm, and repeatedly test for finding potential problems of the preset autopilot algorithm, thereby avoiding unnecessary hidden dangers.
S205: and evaluating the performance of the preset automatic driving algorithm according to the test result.
In the process, the simulation test reports can comprise simulation test logs and traffic behavior comparison graphs, the generated simulation test reports are automatically uploaded to a test result library at the cloud end, and the performance of the automatic driving algorithm can be evaluated according to the specific content of each simulation test report in the test result library. For example, the higher coincidence of the driving paths of the autonomous vehicle and the replaced target vehicle in the traffic behavior comparison map indicates that the performance of the autonomous driving algorithm is better, and the actual values of the preset test indexes in the simulation test log all reach the expected values and also indicate that the performance of the autonomous driving algorithm is better.
In one embodiment, S205 specifically includes: counting simulation test logs in a preset time period in a simulation test log library to obtain effective test data; generating an accumulated test report according to the effective test data; and evaluating the performance of the preset automatic driving algorithm according to the accumulated test report. Every time a simulation scene test is carried out, a corresponding simulation test log is obtained and uploaded to a simulation test log library at the cloud end, when the test is more at the moment, a plurality of simulation test logs exist in the simulation test log library, a preset time period is taken as one day, all simulation test logs obtained by all tests automatically carried out at the cloud end every day are counted, specifically, whether the scene test in each simulation test log passes or not is counted, the driving mileage of an automatically-driven vehicle, the driving speed, the driving time, the collision times and other information are counted, effective test data in the preset time period are obtained, the effective test data integrate test results of a plurality of simulation scenes, and therefore the test results can be more accurately and effectively reflected. Based on the valid test data, a cumulative test report is generated, as shown in table 2.
TABLE 2 cumulative test report for each index and description
When the passing rate of the simulation scene is high or the average collision frequency is low, the performance of the automatic driving algorithm is good, otherwise, the performance is poor. According to each effective test data in the accumulated test report in the table 2, the test results of a plurality of simulation scenes are integrated to evaluate the automatic driving algorithm, so that the accuracy of evaluating the automatic driving algorithm can be further improved.
According to the method, after the data packet is obtained through the sensing source, a plurality of simulation test scenes can be automatically established according to the real environment in the data packet and the data of real traffic participants, the simulation test of the replaced automatic driving vehicle in each simulation test environment based on the preset automatic driving algorithm is automatically completed, and due to the fact that all objects in the scenes are from the real environment and one data packet can obtain a plurality of simulation test scenes, the reality of the simulation test environment is improved, the efficiency of establishing the simulation test environment is improved, and the test requirements of the automatic driving algorithm are fully met.
Fig. 6 is a schematic diagram of an overall architecture of the simulation test method provided by the present invention. At least one data packet collected by the road side sensor and/or the vehicle-mounted sensor is uploaded to the cloud end, and when the simulation platform detects unprocessed data packets, the data packets are subjected to effectiveness screening, noise removal, track filtering, merging and the like to obtain processed data packets. The processed data packet has two purposes, on one hand, typical traffic participants with typical behaviors and clear paths are found from the traffic participants of the data packet, the traffic behaviors of the typical traffic participants are decoupled to obtain behavior logic units, the behavior logic units are uploaded to a typical object behavior library at the cloud end, and various types of simulation test scenes can be constructed for later use, and on the other hand, the processed data packet is used as a real data source for constructing the simulation test scenes and is used for testing the performance of the preset automatic driving algorithm. Specifically, a plurality of target vehicles of which the types are automobiles and the running path lengths are larger than the preset length are extracted from each data packet, the target vehicles in the same data packet are sequentially replaced by automatic driving vehicles, other traffic participants and the environment are kept unchanged, simulation scene conversion is carried out, a plurality of simulation test scenes corresponding to the data packet are obtained, then the simulation scenes are subjected to generalization processing, a plurality of simulation test scene scripts described by an xml language are obtained, and the simulation test scene scripts are uploaded to a scene library. And the simulation platform carries out simulation tests according to the simulation test scene scripts, tests the driving conditions of the automatic driving vehicles replaced in each simulation test scene under the preset automatic driving algorithm, generates simulation test logs under an evaluation system formed by preset test indexes and uploads the simulation test logs to a log library at the cloud end. The test results of the respective automatic driving vehicles in the corresponding scenes can be reflected through the simulation test logs, and the performance of the preset automatic driving algorithm can be evaluated.
When the automatic driving algorithm is subjected to simulation test at present, a large number of simulation scenes are required, the scenes are constructed only by manual operation, the actual situation is separated, and the efficiency and the performance cannot keep up with the requirements. The invention fully utilizes the data collected by the vehicle-road cooperative middle-road side sensor and/or the vehicle-mounted sensor to automatically generate the scene for the test of the automatic driving algorithm module, thereby not only improving the efficiency of constructing the simulation test scene (one data packet can be converted into n effective test scenes), but also improving the authenticity of the scene source (all environments in the scene and the traffic behaviors of traffic participants are all derived from real environments). Meanwhile, a typical object behavior library constructed by the behavior logic units of the traffic participants in the data packet can be provided for subsequent artificial construction of a simulation test scene, so that the performance test of the automatic driving algorithm module is performed in a virtual-real combined manner, and the data collected by the road side is better utilized.
Correspondingly, fig. 7 is a schematic structural diagram of a simulation testing apparatus provided by the present invention, please refer to fig. 7, the simulation testing apparatus includes:
the acquisition module 110 is configured to acquire at least one data packet acquired by a sensing source, where the data packet includes environment information of a sensing area, attribute information of each traffic participant, and traffic behavior information;
a determining module 120, configured to determine a target vehicle in the target data packet according to the attribute information and the traffic behavior information;
the generating module 130 is configured to replace each target vehicle in the target data packet with an automatic driving vehicle, obtain each simulation test scenario corresponding to the target data packet, and generate a simulation test scenario script corresponding to each simulation test scenario;
the test module 140 is configured to perform a simulation scenario test on each simulation test scenario script according to the traffic behavior information of the replaced target vehicle in each simulation test scenario and a preset automatic driving algorithm, and output a test result;
and the evaluation module 150 is used for evaluating the performance of the preset automatic driving algorithm according to the test result.
In one embodiment, the simulation testing device further comprises a judging module, wherein the judging module is used for judging whether each acquired data packet is an effective data packet according to a preset effective condition; if so, optimizing the data in the effective data packet; and if not, discarding the invalid data packet.
In one embodiment, the simulation testing device further comprises a construction module, wherein the construction module is used for decoupling traffic behavior information of each typical traffic participant in each data packet to obtain position information and speed information of each typical traffic participant at each moment; and constructing a behavior logic unit of each typical traffic participant according to the position information, the speed information and the attribute information of each typical traffic participant, and uploading the behavior logic unit to a typical object behavior library.
In one embodiment, the test module 140 is configured to determine a driving start point and a driving end point of the replaced autonomous vehicle according to the driving start point and the driving end point of the replaced target vehicle in each simulation test scenario; controlling each automatic driving vehicle to run in a simulation mode in a corresponding simulation test scene according to the running starting point and the running end point by using a preset automatic driving algorithm, and controlling other traffic participants to run in a simulation mode in the corresponding simulation test scene in the same mode as that in the target data packet; and outputting a test result according to the simulation driving data.
In one embodiment, the test module 140 is configured to perform a simulation scenario test on each simulation test scenario script; and outputting a traffic behavior comparison graph of the automatic driving vehicle and the replaced target vehicle in each simulation test reference.
In one embodiment, the test module 140 is configured to perform a simulation scenario test on each simulation test scenario script; and outputting a simulation test log according to a preset test index, and uploading the simulation test log to a simulation test log library.
In an embodiment, the evaluation module 150 is configured to count the simulation test logs in the simulation test log library within a preset time period to obtain valid test data; generating an accumulated test report according to the effective test data; and evaluating the performance of the preset automatic driving algorithm according to the accumulated test report.
Different from the prior art, the simulation test device provided by the invention firstly obtains at least one data packet collected by a sensing source, wherein the data packet comprises environment information of a sensing area, attribute information and traffic behavior information of each traffic participant, then determines a target vehicle in the target data packet according to the attribute information and the traffic behavior information, then respectively replaces each target vehicle in the target data packet with an automatic driving vehicle to obtain each simulation test scene corresponding to the target data packet, generates a simulation test scene script corresponding to each simulation test scene, performs simulation scene test on each simulation test scene script according to the traffic behavior information of the target vehicle replaced in each simulation test scene and a preset automatic driving algorithm, outputs a test result, and finally evaluates the performance of the preset automatic driving algorithm according to the test result. By the method, after the data packet is acquired through the sensing source, a plurality of simulation test scenes can be automatically established according to the real environment in the data packet and the data of real traffic participants, and the simulation test of the replaced automatic driving vehicle in each simulation test environment based on the preset automatic driving algorithm is automatically completed.
Accordingly, the present invention also provides an electronic device, as shown in fig. 8, which may include components such as a radio frequency circuit 801, a memory 802 including one or more computer-readable storage media, an input unit 803, a display unit 804, a sensor 805, an audio circuit 806, a WiFi module 807, a processor 808 including one or more processing cores, and a power supply 809. Those skilled in the art will appreciate that the electronic device configuration shown in fig. 8 does not constitute a limitation of the electronic device and may include more or fewer components than those shown, or some components may be combined, or a different arrangement of components. Wherein:
the radio frequency circuit 801 may be used for receiving and transmitting signals during information transmission and reception or during a call, and in particular, receives downlink information of a base station and then sends the received downlink information to one or more processors 808 for processing; in addition, data relating to uplink is transmitted to the base station. The memory 802 may be used to store software programs and modules, and the processor 808 may execute various functional applications and data processing by operating the software programs and modules stored in the memory 802. The input unit 803 may be used to receive input numeric or character information and generate keyboard, mouse, joystick, optical or trackball signal inputs related to user settings and function control.
The display unit 804 may be used to display information input by or provided to a user and various graphical user interfaces of the electronic device, which may be made up of graphics, text, icons, video, and any combination thereof.
The electronic device may also include at least one sensor 805, such as light sensors, motion sensors, and other sensors. The audio circuitry 806 includes speakers that can provide an audio interface between the user and the electronic device.
WiFi belongs to short-distance wireless transmission technology, and the electronic device can help the user send and receive e-mail, browse web pages, access streaming media, etc. through the WiFi module 807, which provides wireless broadband internet access for the user. Although fig. 8 shows the WiFi module 807, it is understood that it does not belong to the essential constitution of the electronic device, and may be omitted entirely as needed within the scope not changing the essence of the application.
The processor 808 is a control center of the electronic device, connects various parts of the entire mobile phone by using various interfaces and lines, and performs various functions of the electronic device and processes data by operating or executing software programs and/or modules stored in the memory 802 and calling data stored in the memory 802, thereby integrally monitoring the mobile phone.
The electronic device also includes a power supply 809 (e.g., a battery) for powering the various components, which may preferably be logically coupled to the processor 808 via a power management system to manage charging, discharging, and power consumption via the power management system.
Although not shown, the electronic device may further include a camera, a bluetooth module, and the like, which are not described in detail herein. Specifically, in this embodiment, the processor 808 in the electronic device loads an executable file corresponding to a process of one or more application programs into the memory 802 according to the following instructions, and the processor 808 runs the application programs stored in the memory 802, so as to implement the following functions:
acquiring at least one data packet acquired by a sensing source, wherein the data packet comprises environmental information of a sensing area, attribute information of each traffic participant and traffic behavior information; determining a target vehicle in the target data packet according to the attribute information and the traffic behavior information; respectively replacing each target vehicle in the target data packet with an automatic driving vehicle to obtain each simulation test scene corresponding to the target data packet and generate a simulation test scene script corresponding to each simulation test scene; carrying out simulation scene testing on each simulation test scene script according to the traffic behavior information of the replaced target vehicle in each simulation test scene and a preset automatic driving algorithm, and outputting a test result; and evaluating the performance of the preset automatic driving algorithm according to the test result.
In the foregoing embodiments, the descriptions of the respective embodiments have respective emphasis, and for parts that are not described in detail in a certain embodiment, reference may be made to related descriptions of other embodiments.
It will be understood by those skilled in the art that all or part of the steps of the methods of the above embodiments may be performed by instructions or by associated hardware controlled by the instructions, which may be stored in a computer readable storage medium and loaded and executed by a processor.
To this end, the present invention provides a computer readable storage medium having stored therein a plurality of instructions that are loadable by a processor to cause the following functions:
acquiring at least one data packet acquired by a sensing source, wherein the data packet comprises environmental information of a sensing area, attribute information of each traffic participant and traffic behavior information; determining a target vehicle in the target data packet according to the attribute information and the traffic behavior information; respectively replacing each target vehicle in the target data packet with an automatic driving vehicle to obtain each simulation test scene corresponding to the target data packet and generate a simulation test scene script corresponding to each simulation test scene; carrying out simulation scene testing on each simulation test scene script according to the traffic behavior information of the replaced target vehicle in each simulation test scene and a preset automatic driving algorithm, and outputting a test result; and evaluating the performance of the preset automatic driving algorithm according to the test result.
The above operations can be implemented in the foregoing embodiments, and are not described in detail herein.
Wherein the computer-readable storage medium may include: read Only Memory (ROM), Random Access Memory (RAM), magnetic or optical disks, and the like.
Since the instructions stored in the computer-readable storage medium can execute the steps of any method provided by the present invention, the beneficial effects that any method provided by the present invention can achieve can be achieved, for details, see the foregoing embodiments, and are not described herein again.
The simulation test method, the simulation test device, the electronic device and the storage medium provided by the invention are described in detail, specific examples are applied in the description to explain the principle and the implementation of the invention, and the description of the embodiments is only used for helping to understand the technical scheme and the core idea of the invention; those of ordinary skill in the art will understand that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (10)
1. A simulation test method is characterized by comprising the following steps:
acquiring at least one data packet acquired by a sensing source, wherein the data packet comprises environmental information of a sensing area, attribute information of each traffic participant and traffic behavior information;
determining a target vehicle in a target data packet according to the attribute information and the traffic behavior information;
respectively replacing each target vehicle in the target data packet with an automatic driving vehicle to obtain each simulation test scene corresponding to the target data packet and generate a simulation test scene script corresponding to each simulation test scene;
carrying out simulation scene testing on each simulation test scene script according to the traffic behavior information of the replaced target vehicle in each simulation test scene and a preset automatic driving algorithm, and outputting a test result;
and evaluating the performance of the preset automatic driving algorithm according to the test result.
2. The simulation test method of claim 1, further comprising, before the step of determining the target vehicle in the target data packet based on the attribute information and the traffic behavior information:
judging whether each acquired data packet is an effective data packet or not according to a preset effective condition;
if so, optimizing the data in the effective data packet; and if not, discarding the invalid data packet.
3. The simulation test method of claim 1, further comprising, after the step of obtaining at least one data packet collected by a perception source:
decoupling traffic behavior information of each typical traffic participant in each data packet to obtain position information and speed information of each typical traffic participant at each moment;
and constructing a behavior logic unit of each typical traffic participant according to the position information, the speed information and the attribute information of each typical traffic participant, and uploading the behavior logic unit to a typical object behavior library.
4. The simulation test method according to claim 1, wherein the step of performing the simulation scenario test on each simulation test scenario script according to the traffic behavior information of the target vehicle to be replaced in each simulation test scenario and the preset autopilot algorithm, and outputting the test result comprises:
determining a driving starting point and a driving end point of the replaced automatic driving vehicle according to the driving starting point and the driving end point of the replaced target vehicle in each simulation test scene;
controlling the respective automatic driving vehicles to perform simulation driving in the corresponding simulation test scenes by using a preset automatic driving algorithm according to the driving starting point and the driving end point, and controlling other traffic participants to perform simulation driving in the corresponding simulation test scenes in the same mode as that in the target data packet;
and outputting a test result according to the simulation driving data.
5. The simulation test method of claim 1, wherein the step of performing a simulation scenario test on each simulation test scenario script and outputting a test result comprises:
carrying out simulation scene test on each simulation test scene script;
and outputting a traffic behavior comparison graph of the automatic driving vehicle and the replaced target vehicle in each simulation test reference.
6. The simulation test method of claim 1, wherein the step of performing a simulation scenario test on each simulation test scenario script and outputting a test result comprises:
carrying out simulation scene test on each simulation test scene script;
and outputting a simulation test log according to a preset test index, and uploading the simulation test log to a simulation test log library.
7. The simulation test method of claim 6, wherein the step of evaluating the performance of the preset autopilot algorithm based on the test results comprises:
counting simulation test logs in a preset time period in a simulation test log library to obtain effective test data;
generating an accumulated test report according to the effective test data;
and evaluating the performance of the preset automatic driving algorithm according to the accumulated test report.
8. A simulation test apparatus, comprising:
the acquisition module is used for acquiring at least one data packet acquired by a sensing source, wherein the data packet comprises environmental information of a sensing area, attribute information of each traffic participant and traffic behavior information;
the determining module is used for determining a target vehicle in a target data packet according to the attribute information and the traffic behavior information;
the generation module is used for replacing each target vehicle in the target data packet with an automatic driving vehicle respectively to obtain each simulation test scene corresponding to the target data packet and generate a simulation test scene script corresponding to each simulation test scene;
the test module is used for carrying out simulation scene test on each simulation test scene script according to the traffic behavior information of the replaced target vehicle in each simulation test scene and a preset automatic driving algorithm and outputting a test result;
and the evaluation module is used for evaluating the performance of the preset automatic driving algorithm according to the test result.
9. An electronic device comprising a memory and a processor; the memory stores an application program, and the processor is configured to run the application program in the memory to perform the steps of the simulation testing method according to any one of claims 1 to 7.
10. A computer-readable storage medium, having stored thereon a computer program for execution by a processor to perform the steps of the simulation testing method of any of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111224045.3A CN113687600A (en) | 2021-10-21 | 2021-10-21 | Simulation test method, simulation test device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111224045.3A CN113687600A (en) | 2021-10-21 | 2021-10-21 | Simulation test method, simulation test device, electronic equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113687600A true CN113687600A (en) | 2021-11-23 |
Family
ID=78587687
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111224045.3A Pending CN113687600A (en) | 2021-10-21 | 2021-10-21 | Simulation test method, simulation test device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113687600A (en) |
Cited By (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113868778A (en) * | 2021-12-02 | 2021-12-31 | 中智行科技有限公司 | Simulation scene management method and device |
| CN114070471A (en) * | 2021-11-29 | 2022-02-18 | 广州文远知行科技有限公司 | Test data packet transmission method, device, system, equipment and medium |
| CN114065549A (en) * | 2021-11-30 | 2022-02-18 | 广州文远知行科技有限公司 | Automatic driving level evaluation method, device, equipment and storage medium |
| CN114238050A (en) * | 2021-11-29 | 2022-03-25 | 广州文远知行科技有限公司 | Method, device and equipment for detecting uncertainty in simulation task and storage medium |
| CN114355793A (en) * | 2021-12-24 | 2022-04-15 | 阿波罗智能技术(北京)有限公司 | Training method and device of automatic driving planning model for vehicle simulation evaluation |
| CN114384820A (en) * | 2021-11-30 | 2022-04-22 | 重庆长安汽车股份有限公司 | Automatic driving algorithm simulation test system and method based on cloud rack |
| CN114398250A (en) * | 2021-11-30 | 2022-04-26 | 际络科技(上海)有限公司 | Vehicle test evaluation method and device based on functional scene |
| CN114398254A (en) * | 2021-11-30 | 2022-04-26 | 际络科技(上海)有限公司 | Automatic driving simulation test method and system based on element correlation |
| CN114936515A (en) * | 2022-04-25 | 2022-08-23 | 北京宾理信息科技有限公司 | Method and system for generating simulated traffic scene file |
| CN114973656A (en) * | 2022-05-10 | 2022-08-30 | 清华大学 | Method, device, equipment, medium and product for evaluating traffic interaction performance |
| CN115326422A (en) * | 2022-07-29 | 2022-11-11 | 重庆长安汽车股份有限公司 | Test method and device of automatic driving system, electronic equipment and storage medium |
| CN115440028A (en) * | 2022-07-22 | 2022-12-06 | 中智行(苏州)科技有限公司 | Traffic road scene classification method based on labeling |
| CN115452408A (en) * | 2022-08-26 | 2022-12-09 | 交控科技股份有限公司 | Method and device for testing vehicle-mounted sensing equipment |
| CN115542774A (en) * | 2022-09-30 | 2022-12-30 | 重庆长安汽车股份有限公司 | Automatic driving simulation test system and method |
| CN115798295A (en) * | 2022-11-30 | 2023-03-14 | 深圳市声扬科技有限公司 | Driving test simulation method and device, electronic equipment and storage medium |
| CN115858398A (en) * | 2023-02-07 | 2023-03-28 | 中汽智联技术有限公司 | Method and device for generating automatic driving test scene and storage medium |
| CN116167252A (en) * | 2023-04-25 | 2023-05-26 | 小米汽车科技有限公司 | Method, device, equipment and storage medium for determining radar configuration information |
| CN116206441A (en) * | 2022-12-30 | 2023-06-02 | 云控智行科技有限公司 | Optimization method, device, equipment and medium of automatic driving planning model |
| CN116663329A (en) * | 2023-07-26 | 2023-08-29 | 西安深信科创信息技术有限公司 | Automatic driving simulation test scene generation method, device, equipment and storage medium |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109684514A (en) * | 2018-12-11 | 2019-04-26 | 武汉文都创新教育研究院（有限合伙） | Students ' behavior positioning system and method based on track data |
| CN110263381A (en) * | 2019-05-27 | 2019-09-20 | 南京航空航天大学 | A kind of automatic driving vehicle test emulation scene generating method |
| CN111123920A (en) * | 2019-12-10 | 2020-05-08 | 武汉光庭信息技术股份有限公司 | Method and device for generating automatic driving simulation test scene |
| CN111249733A (en) * | 2020-01-09 | 2020-06-09 | 完美世界(北京)软件科技发展有限公司 | Method and device for creating virtual object |
| CN111580493A (en) * | 2020-04-14 | 2020-08-25 | 吉利汽车研究院（宁波）有限公司 | Automatic driving simulation method, system and medium |
| CN111781855A (en) * | 2020-07-15 | 2020-10-16 | 北京领骏科技有限公司 | Traffic on-loop automatic driving simulation system |
| CN112567374A (en) * | 2020-10-21 | 2021-03-26 | 华为技术有限公司 | Simulated traffic scene file generation method and device |
| CN112789619A (en) * | 2020-12-31 | 2021-05-11 | 华为技术有限公司 | Simulation scene construction method, simulation method and device |
| CN112948270A (en) * | 2021-04-06 | 2021-06-11 | 东风小康汽车有限公司重庆分公司 | Method, device, equipment and medium for road test simulation analysis of automatic driving vehicle |
| CN113342704A (en) * | 2021-08-06 | 2021-09-03 | 腾讯科技（深圳）有限公司 | Data processing method, data processing equipment and computer readable storage medium |
| CN113408141A (en) * | 2021-07-02 | 2021-09-17 | 阿波罗智联(北京)科技有限公司 | Automatic driving test method and device and electronic equipment |
-
2021
- 2021-10-21 CN CN202111224045.3A patent/CN113687600A/en active Pending
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109684514A (en) * | 2018-12-11 | 2019-04-26 | 武汉文都创新教育研究院（有限合伙） | Students ' behavior positioning system and method based on track data |
| CN110263381A (en) * | 2019-05-27 | 2019-09-20 | 南京航空航天大学 | A kind of automatic driving vehicle test emulation scene generating method |
| CN111123920A (en) * | 2019-12-10 | 2020-05-08 | 武汉光庭信息技术股份有限公司 | Method and device for generating automatic driving simulation test scene |
| CN111249733A (en) * | 2020-01-09 | 2020-06-09 | 完美世界(北京)软件科技发展有限公司 | Method and device for creating virtual object |
| CN111580493A (en) * | 2020-04-14 | 2020-08-25 | 吉利汽车研究院（宁波）有限公司 | Automatic driving simulation method, system and medium |
| CN111781855A (en) * | 2020-07-15 | 2020-10-16 | 北京领骏科技有限公司 | Traffic on-loop automatic driving simulation system |
| CN112567374A (en) * | 2020-10-21 | 2021-03-26 | 华为技术有限公司 | Simulated traffic scene file generation method and device |
| CN112789619A (en) * | 2020-12-31 | 2021-05-11 | 华为技术有限公司 | Simulation scene construction method, simulation method and device |
| CN112948270A (en) * | 2021-04-06 | 2021-06-11 | 东风小康汽车有限公司重庆分公司 | Method, device, equipment and medium for road test simulation analysis of automatic driving vehicle |
| CN113408141A (en) * | 2021-07-02 | 2021-09-17 | 阿波罗智联(北京)科技有限公司 | Automatic driving test method and device and electronic equipment |
| CN113342704A (en) * | 2021-08-06 | 2021-09-03 | 腾讯科技（深圳）有限公司 | Data processing method, data processing equipment and computer readable storage medium |
Cited By (28)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114238050A (en) * | 2021-11-29 | 2022-03-25 | 广州文远知行科技有限公司 | Method, device and equipment for detecting uncertainty in simulation task and storage medium |
| CN114070471A (en) * | 2021-11-29 | 2022-02-18 | 广州文远知行科技有限公司 | Test data packet transmission method, device, system, equipment and medium |
| CN114070471B (en) * | 2021-11-29 | 2023-11-21 | 广州禹迹科技有限公司 | Test data packet transmission method, device, system, equipment and medium |
| CN114398250A (en) * | 2021-11-30 | 2022-04-26 | 际络科技(上海)有限公司 | Vehicle test evaluation method and device based on functional scene |
| CN114384820A (en) * | 2021-11-30 | 2022-04-22 | 重庆长安汽车股份有限公司 | Automatic driving algorithm simulation test system and method based on cloud rack |
| CN114398254A (en) * | 2021-11-30 | 2022-04-26 | 际络科技(上海)有限公司 | Automatic driving simulation test method and system based on element correlation |
| CN114384820B (en) * | 2021-11-30 | 2023-12-22 | 重庆长安汽车股份有限公司 | Cloud platform based automatic driving algorithm simulation test system and method |
| CN114065549A (en) * | 2021-11-30 | 2022-02-18 | 广州文远知行科技有限公司 | Automatic driving level evaluation method, device, equipment and storage medium |
| CN113868778A (en) * | 2021-12-02 | 2021-12-31 | 中智行科技有限公司 | Simulation scene management method and device |
| CN113868778B (en) * | 2021-12-02 | 2022-03-11 | 中智行科技有限公司 | Simulation scene management method and device |
| CN114355793A (en) * | 2021-12-24 | 2022-04-15 | 阿波罗智能技术(北京)有限公司 | Training method and device of automatic driving planning model for vehicle simulation evaluation |
| CN114355793B (en) * | 2021-12-24 | 2023-12-29 | 阿波罗智能技术(北京)有限公司 | Training method and device for automatic driving planning model for vehicle simulation evaluation |
| CN114936515B (en) * | 2022-04-25 | 2023-09-19 | 北京宾理信息科技有限公司 | Method and system for generating simulated traffic scene file |
| CN114936515A (en) * | 2022-04-25 | 2022-08-23 | 北京宾理信息科技有限公司 | Method and system for generating simulated traffic scene file |
| CN114973656A (en) * | 2022-05-10 | 2022-08-30 | 清华大学 | Method, device, equipment, medium and product for evaluating traffic interaction performance |
| CN114973656B (en) * | 2022-05-10 | 2024-08-09 | 清华大学 | Traffic interaction performance evaluation method, device, equipment, medium and product |
| CN115440028A (en) * | 2022-07-22 | 2022-12-06 | 中智行(苏州)科技有限公司 | Traffic road scene classification method based on labeling |
| CN115440028B (en) * | 2022-07-22 | 2024-01-30 | 中智行(苏州)科技有限公司 | Traffic road scene classification method based on labeling |
| CN115326422A (en) * | 2022-07-29 | 2022-11-11 | 重庆长安汽车股份有限公司 | Test method and device of automatic driving system, electronic equipment and storage medium |
| CN115452408A (en) * | 2022-08-26 | 2022-12-09 | 交控科技股份有限公司 | Method and device for testing vehicle-mounted sensing equipment |
| CN115542774A (en) * | 2022-09-30 | 2022-12-30 | 重庆长安汽车股份有限公司 | Automatic driving simulation test system and method |
| CN115798295A (en) * | 2022-11-30 | 2023-03-14 | 深圳市声扬科技有限公司 | Driving test simulation method and device, electronic equipment and storage medium |
| CN116206441A (en) * | 2022-12-30 | 2023-06-02 | 云控智行科技有限公司 | Optimization method, device, equipment and medium of automatic driving planning model |
| CN115858398A (en) * | 2023-02-07 | 2023-03-28 | 中汽智联技术有限公司 | Method and device for generating automatic driving test scene and storage medium |
| CN116167252A (en) * | 2023-04-25 | 2023-05-26 | 小米汽车科技有限公司 | Method, device, equipment and storage medium for determining radar configuration information |
| CN116167252B (en) * | 2023-04-25 | 2024-01-30 | 小米汽车科技有限公司 | Method, device, equipment and storage medium for determining radar configuration information |
| CN116663329A (en) * | 2023-07-26 | 2023-08-29 | 西安深信科创信息技术有限公司 | Automatic driving simulation test scene generation method, device, equipment and storage medium |
| CN116663329B (en) * | 2023-07-26 | 2024-03-29 | 安徽深信科创信息技术有限公司 | Automatic driving simulation test scene generation method, device, equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113687600A (en) | Simulation test method, simulation test device, electronic equipment and storage medium | |
| CN115049057B (en) | Model deployment method and device, electronic equipment and storage medium | |
| CN113342704B (en) | Data processing method, data processing equipment and computer readable storage medium | |
| CN113596158B (en) | Scene-based algorithm configuration method and device | |
| CN112148493A (en) | Streaming media task management method and device and data server | |
| CN105575155A (en) | Method and equipment for determining vehicle driving information | |
| CN114926766A (en) | Identification method and device, equipment and computer readable storage medium | |
| CN113033463A (en) | Deceleration strip detection method and device, electronic equipment and storage medium | |
| CN113516102A (en) | Deep learning parabolic behavior detection method based on video | |
| CN111695627A (en) | Road condition detection method and device, electronic equipment and readable storage medium | |
| CN115546693A (en) | Target detection model training method, device, equipment and storage medium | |
| CN112233428A (en) | Traffic flow prediction method, traffic flow prediction device, storage medium and equipment | |
| CN111696368A (en) | Overspeed illegal data generation method and illegal server | |
| CN108320497A (en) | Pedestrian running red light behavioral value method, apparatus and computer readable storage medium | |
| Ding et al. | Edge-to-cloud intelligent vehicle-infrastructure based on 5G time-sensitive network integration | |
| CN112201047B (en) | Suspected vehicle foothold analysis method and device based on Flink framework | |
| CN112509321A (en) | Unmanned aerial vehicle-based driving control method and system for urban complex traffic situation and readable storage medium | |
| CN113299058A (en) | Method, device, medium, and electronic device for identifying responsibility of traffic accident | |
| CN111553497A (en) | Equipment working state detection method and device of multimedia terminal | |
| CN115544737A (en) | Simulation traffic scene construction method and system based on digital twins and related equipment | |
| CN115909126A (en) | Target detection method, apparatus and storage medium | |
| CN106601009B (en) | A kind of parking information generation method and device | |
| KR102377233B1 (en) | System for acquiring mobility data under real driving circumstance and for simulating them | |
| CN113963310A (en) | People flow detection method and device for bus station and electronic equipment | |
| CN110705493A (en) | Method and system for detecting vehicle running environment, electronic device and storage medium |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20211123 |