WO2022160900A1 - Procédé et dispositif de construction d'environnement de test - Google Patents

Procédé et dispositif de construction d'environnement de test Download PDF

Info

Publication number
WO2022160900A1
WO2022160900A1 PCT/CN2021/132797 CN2021132797W WO2022160900A1 WO 2022160900 A1 WO2022160900 A1 WO 2022160900A1 CN 2021132797 W CN2021132797 W CN 2021132797W WO 2022160900 A1 WO2022160900 A1 WO 2022160900A1
Authority
WO
WIPO (PCT)
Prior art keywords
behavior
behavior data
data
traffic
scene
Prior art date
Application number
PCT/CN2021/132797
Other languages
English (en)
Chinese (zh)
Inventor
宿建烽
朱杰
Original Assignee
华为技术有限公司
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by 华为技术有限公司 filed Critical 华为技术有限公司
Publication of WO2022160900A1 publication Critical patent/WO2022160900A1/fr

Links

Images

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
    • G01M17/00—Testing of vehicles
    • G01M17/007—Wheeled or endless-tracked vehicles
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/23—Clustering techniques
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/23—Clustering techniques
    • G06F18/232—Non-hierarchical techniques
    • 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
    • G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model

Definitions

  • the present application relates to the field of unmanned driving technology, and in particular, to a test scene construction method and device.
  • test scene data includes, for example, the overtaking scene, the traffic light scene, the curve driving scene, and so on.
  • test scene data is basically obtained by manual means.
  • the staff can play back the data collected by the collection vehicle, and identify and select the required scene data with the naked eye. After the required scene data is selected, the scene data can be automatically converted into a data set required for testing by software tools. It can be seen that the method of obtaining test scene data in the related art relies too much on manual processing, which is time-consuming, labor-intensive, and inefficient, and the accuracy also depends on the ability of the staff.
  • an embodiment of the present application provides a method for constructing a test scenario, including:
  • the motion behavior being composed of at least one behavior element
  • the behavior data set includes a plurality of behavior data whose similarity is higher than a preset threshold, and the behavior data is set to be extracted from real road condition data ;
  • the test scene construction method provided by the embodiment of the present application can use the behavior data extracted from the real road condition data as the material for constructing the motion behavior of the traffic moving object in the process of constructing the preset traffic test scene.
  • using the real road condition data as the data base can not only reduce the difference between the test scene and the real scene, but also improve the richness of the data.
  • the cost of acquiring test data can be greatly reduced by using an automated way of acquiring behavior data sets. Based on this, the constructed traffic test scene not only has high realism, but also can obtain abundant test data at low cost, which provides better technical support for testing the performance of intelligent vehicles.
  • the behavior data set is set to be constructed in the following manner:
  • At least one behavior data of at least one traffic moving object is extracted from the real road condition data, and the one behavior data includes at least one motion parameter information;
  • cluster analysis is performed on at least one behavior data of the traffic moving objects, and a behavior data set corresponding to at least one behavior element is generated.
  • the embodiment of the present application provides a method for acquiring a behavior data set, in which, at least one behavior data of at least one traffic moving object is acquired from real road condition data. Then, cluster analysis is performed on the at least one behavior data to generate a behavior data set corresponding to at least one behavior element.
  • Using automatically acquired behavior data in test scenarios can not only enhance the authenticity of test scenarios, but also improve the efficiency of acquiring test data.
  • cluster analysis is performed on at least one behavior data of the traffic moving objects to generate a behavior data set corresponding to at least one behavior element, include:
  • For different traffic moving objects select at least one target behavior data that conforms to the characteristics of preset behavior elements from at least one behavior data of the traffic moving objects;
  • the target behavior data required in the test scenario can be selected from a large amount of real behavior data, and the characteristics of the behavior elements can be specifically defined in advance, and the target behavior data can be selected by using the characteristics.
  • the combination of the behavior data in different sets of behavior data into at least one movement behavior of the traffic moving object includes:
  • the selected behavior data is connected into a motion behavior.
  • the embodiments of the present application provide a method for automatically combining multiple behavior data into motion behaviors.
  • the connecting the selected behavior data into a motion behavior includes:
  • the selected behavior data is smoothly connected according to the changes of the motion parameters contained in the adjacent behavior data.
  • the continuity and smoothness between different behavior data can be enhanced.
  • the method further includes:
  • scene data of the preset traffic test scene includes at least one of road information, traffic facility control information, environmental information, and initial positions of traffic moving objects;
  • the at least one movement behavior is respectively set in the preset traffic test scene, the test object is tested, and the test result is obtained.
  • the motion behavior is set in a preset traffic test scene, and the test object is tested.
  • the test object is tested.
  • the at least one motion behavior is respectively set in the preset traffic test scene, the test object is tested, and the test result is obtained, including:
  • the motion behavior When it is determined that the motion behavior conforms to the scene characteristics, the motion behavior is set in the preset traffic test scene, the test object is tested, and a test result is obtained.
  • the rationality of the motion behavior set in the preset traffic test scene can be guaranteed.
  • the behavior data set further includes a plurality of first behavior data whose similarity with the plurality of behavior data is less than a first preset threshold, and the plurality of The ratio of the number of behavior data to the plurality of first behavior data is not less than a preset ratio threshold.
  • the behavior data set includes a certain proportion of unconventional behavior data, which satisfies the richness of the behavior data set to a certain extent and enhances the robustness of the test scene.
  • the behavior data includes at least one of the following motion parameter information: speed in the direction of travel, lateral speed of travel, acceleration of travel, lateral acceleration of travel, travel distance, turning radius, travel Duration, walking speed, walking acceleration, walking duration.
  • the traffic moving objects include at least one of the following: cars, trucks, buses, trams, trains, motorcycles, electric vehicles, bicycles, pedestrians, and animals.
  • the motion behavior includes at least one of the following: overtaking, going straight at the intersection, turning at the intersection, merging into the traffic flow, and pedestrians passing the sidewalk.
  • the behavior elements include at least one of the following: driving in a straight line, switching lanes to the left, switching lanes to the right, turning left at a right angle, turning at a right angle, and parking.
  • the method before the determining of the motion behavior of the traffic moving object required for constructing the preset traffic test scene, the method further includes:
  • the preset traffic test scene selected by the user and the configured scene data of the preset traffic test scene are acquired.
  • the embodiment of the present application provides a way for the user terminal to select a traffic simulation scene and configure scene data.
  • embodiments of the present application provide a method for constructing a simulation scene, including:
  • At least one behavior data of at least one traffic moving object is extracted from the real road condition data, and the one behavior data includes at least one motion parameter information;
  • a traffic simulation scene is constructed using the at least one behavior data of the at least one traffic moving object.
  • the one behavior data includes at least one motion parameter information, and further includes:
  • cluster analysis is performed on at least one behavior data of the traffic moving objects, and a behavior data set corresponding to at least one behavior element is generated.
  • the constructing a traffic simulation scene by using the at least one behavior data of the at least one traffic moving object includes:
  • an embodiment of the present application provides an apparatus for constructing a test scenario, including:
  • a motion behavior determination module configured to determine the motion behavior of the traffic moving object required for constructing a preset traffic test scene, and the motion behavior is composed of at least one behavior element;
  • a data set obtaining module configured to obtain a behavior data set corresponding to the at least one behavior element, wherein the behavior data set includes a plurality of behavior data whose similarity is higher than a preset threshold, and the behavior data is set as Extracted from real road condition data;
  • a behavior data combination module configured to combine the behavior data in different sets of behavior data into at least one motion behavior of the traffic moving object.
  • the behavior data set is set to be constructed according to the following modules:
  • the road condition data determination module is used to determine the real road condition data
  • a behavior data extraction module configured to extract at least one behavior data of at least one traffic moving object from the real road condition data, where the one behavior data includes at least one motion parameter information;
  • the behavior data clustering module is configured to perform cluster analysis on at least one behavior data of the traffic moving objects for different traffic moving objects, and generate a behavior data set corresponding to at least one behavior element.
  • the behavior data clustering module is specifically used for:
  • For different traffic moving objects select at least one target behavior data that conforms to the characteristics of preset behavior elements from at least one behavior data of the traffic moving objects;
  • the behavior data combination module is specifically used for:
  • the selected behavior data is connected into a motion behavior.
  • the behavior data combination module is further used for:
  • the selected behavior data is smoothly connected according to the changes of the motion parameters contained in the adjacent behavior data.
  • the apparatus further includes:
  • a scene data acquisition module configured to acquire scene data of the preset traffic test scene, where the scene data includes at least one of road information, traffic facility control information, environmental information, and initial positions of traffic moving objects;
  • test scene construction module configured to construct the preset traffic test scene according to the scene data
  • a test result acquisition module configured to respectively set the at least one motion behavior in the preset traffic test scene, test the test object, and acquire the test result.
  • test result acquisition module is specifically used for:
  • the motion behavior When it is determined that the motion behavior conforms to the scene characteristics, the motion behavior is set in the preset traffic test scene, the test object is tested, and a test result is obtained.
  • the behavior data set further includes a plurality of first behavior data whose similarity with the plurality of behavior data is less than a first preset threshold, and the plurality of first behavior data are The ratio of the number of behavior data to the plurality of first behavior data is not less than a preset ratio threshold.
  • the behavior data includes at least one of the following motion parameter information: speed in the direction of travel, lateral speed of travel, acceleration of travel, lateral acceleration of travel, travel distance, turning radius, travel Duration, walking speed, walking acceleration, walking duration.
  • the traffic moving objects include at least one of the following: cars, trucks, buses, trams, trains, motorcycles, electric vehicles, bicycles, pedestrians, and animals.
  • the motion behavior includes at least one of the following: overtaking, going straight at the intersection, turning at the intersection, merging into the traffic flow, and pedestrians passing the sidewalk.
  • the behavior element includes at least one of the following: driving in a straight line, switching lanes to the left, switching lanes to the right, turning left at a right angle, turning at a right angle, and parking.
  • the apparatus further includes:
  • the test scene acquisition module is configured to acquire the preset traffic test scene selected by the user and the configured scene data of the preset traffic test scene.
  • an apparatus for constructing a simulation scene including:
  • the road condition data acquisition module is used to acquire real road condition data
  • a behavior data extraction module configured to extract at least one behavior data of at least one traffic moving object from the real road condition data, where the one behavior data includes at least one motion parameter information;
  • a scene construction module configured to construct a traffic simulation scene by using the at least one behavior data of the at least one traffic moving object.
  • the method further includes:
  • the behavior data clustering module is configured to perform cluster analysis on at least one behavior data of the traffic moving objects for different traffic moving objects, and generate a behavior data set corresponding to at least one behavior element.
  • the scene construction module is specifically used for:
  • the device for constructing a simulation scene is provided in a vehicle or a cloud.
  • an embodiment of the present application provides a device, characterized in that it includes:
  • memory for storing processor-executable instructions
  • the processor is configured to implement one or more methods of the first aspect or multiple possible implementation manners of the first aspect when executing the instructions.
  • embodiments of the present application provide a non-volatile computer-readable storage medium on which computer program instructions are stored, characterized in that, when the computer program instructions are executed by a processor, the above-mentioned first aspect is implemented Or one or more of the various possible implementation manners of the first aspect.
  • embodiments of the present application provide a computer program product, which is characterized by comprising computer-readable codes, or a non-volatile computer-readable storage medium carrying computer-readable codes, when the computer can
  • the processor in the electronic device executes the method for implementing the first aspect or one or more of various possible implementation manners of the first aspect.
  • an embodiment of the present application provides a chip, which is characterized in that it includes at least one processor, and the processor is configured to run a computer program or computer instruction stored in a memory to execute the first aspect or the first A method of one or more of the various possible implementations of an aspect.
  • FIG. 1 shows a schematic structural diagram of a traffic test system provided by an embodiment of the present application.
  • FIG. 2 shows a schematic diagram of a collection device 101 provided by an embodiment of the present application.
  • FIG. 3A shows a schematic structural diagram of an intelligent vehicle 200 provided by an embodiment of the present application.
  • FIG. 3B shows a module block diagram of an intelligent vehicle 200 provided by an embodiment of the present application.
  • FIG. 4 shows a schematic flowchart of a test scenario construction method provided by an embodiment of the present application.
  • FIG. 5 shows a schematic diagram of an application scenario provided by an embodiment of the present application.
  • FIG. 6 shows a schematic diagram of an application scenario provided by an embodiment of the present application.
  • FIG. 7 shows a schematic diagram of an application scenario provided by an embodiment of the present application.
  • FIG. 8 shows a schematic diagram of an application scenario provided by an embodiment of the present application.
  • FIG. 9 shows a schematic diagram of an application scenario provided by an embodiment of the present application.
  • FIG. 10 shows a schematic diagram of an application scenario provided by an embodiment of the present application.
  • FIG. 11 shows a schematic flowchart of a simulation scene construction method provided by an embodiment of the present application.
  • FIG. 12 shows a schematic block diagram of the acquisition apparatus 101 and the test scene construction apparatus 103 provided by the embodiment of the present application.
  • FIG. 13 shows a schematic structural diagram of a terminal device according to an embodiment of the present application.
  • FIG. 14 shows a structural block diagram of a computer program product according to an embodiment of the present application.
  • “/” may indicate that the objects associated before and after are an “or” relationship, for example, A/B may indicate A or B; “and/or” may be used to describe that there are three types of associated objects A relationship, for example, A and/or B, can mean that A exists alone, A and B exist at the same time, and B exists alone, where A and B can be singular or plural.
  • words such as “first” and “second” may be used to distinguish technical features with the same or similar functions. The words “first”, “second” and the like do not limit the quantity and execution order, and the words “first”, “second” and the like do not limit the difference.
  • words such as “exemplary” or “for example” are used to represent examples, illustrations or illustrations, and any embodiment or design solution described as “exemplary” or “for example” should not be construed are preferred or advantageous over other embodiments or designs.
  • the use of words such as “exemplary” or “such as” is intended to present the relevant concepts in a specific manner to facilitate understanding.
  • the technical features in the technical feature are distinguished by “first”, “second”, etc., and the technical features described by the “first” and “second” There is no order of precedence or size.
  • FIG. 1 is a schematic structural diagram of a traffic test system provided by an embodiment of the present application.
  • the system includes a collection device 101 and a test scene construction device 103, wherein the collection device 101 and the test scene construction device 103 can pass the network communication, so as to send the collected data for constructing the test scene to the test scene construction apparatus 103, and the test scene construction apparatus 103 completes the construction of the test scene.
  • the collection device 101 may be an electronic device with data collection capability and data transceiver capability.
  • the acquisition device 101 may be an acquisition vehicle equipped with one or more sensors such as lidar, camera, Global Navigation Satellite System (GNSS), Inertial Measurement Unit (IMU), etc.
  • the collecting vehicle can collect road condition data, and extract at least one behavior data of at least one traffic moving object from the road condition data, and the at least one behavior data can be used as a real material for constructing a test scene.
  • GNSS Global Navigation Satellite System
  • IMU Inertial Measurement Unit
  • lidar is mainly used to collect point cloud data, because lidar can accurately reflect position information, so the position and motion parameters of traffic moving objects, road information, traffic facility information and some other information can be obtained through lidar; camera It is mainly used to collect the types of traffic objects (motor vehicles, non-motor vehicles, pedestrians, etc.), road signs, lane lines, etc.; GNSS is mainly used to record the coordinates of the current collection point; IMU is mainly used to record the angle and Acceleration information is used to correct the position and angle of the acquisition vehicle.
  • the collecting device 101 may also be a roadside unit installed at an intersection, and the roadside unit may monitor multiple traffic moving objects in the coverage area and collect behavior data of each traffic moving object.
  • the behavior data of the traffic moving objects may be collected by one roadside unit, or the behavior data of the traffic moving objects may be collected by the cooperation of multiple roadside units, which is not limited in this application.
  • the roadside unit may be composed of a high-gain directional beam control read-write antenna and a radio frequency controller.
  • the high-gain directional beam control read-write antenna is a microwave transceiver module, responsible for signal and data transmission/reception, modulation/demodulation, encoding/decoding, encryption/decryption; the radio frequency controller is used to control the transmission and reception of data and the processing of the upper computer.
  • the behavior data of various traffic moving objects can be collected by the collecting device 101 .
  • the traffic moving objects may include objects moving on the road, including: cars, trucks, buses, trams, trains, motorcycles, electric vehicles, bicycles, pedestrians, and the like.
  • the behavior data of the traffic object may include driving straight, switching lanes left, switching lanes right, right-angle turn left, right-angle turn, and parking.
  • each behavior data may include at least one motion parameter and its parameter value, the motion parameters may include speed in the direction of travel, transverse speed of travel, acceleration of travel, transverse acceleration of travel, travel distance, turning radius, travel time, travel speed, travel speed Acceleration, walking time, etc.
  • motion parameters such as acceleration, speed, and distance may be included.
  • the collection device 101 may include a behavior data identification module, which can perform an analysis on the road condition data based on the preset behavior definition rules and according to the motion information, environmental data, map data, etc. of the collection device 101 . Analyze and mine to identify the above-mentioned various behavior data of multiple traffic moving objects in the road condition data.
  • the collecting device 101 may further include a labeling module, which is used to label the behavior data in the original road condition data, so as to facilitate the extraction of the behavior data. For example, the start and end time of the behavior data in the original road condition data, as well as the type of the corresponding traffic moving object, the parameter value of the motion parameter, and the like can be marked.
  • the test scene construction apparatus 103 may be an electronic device with data processing capability and data transceiving capability, may be a physical device such as a host, rack server, blade server, etc., or may be a virtual device such as a virtual machine, a container, and the like.
  • the test scene construction device 103 can, after acquiring the plurality of behavior data of the plurality of traffic moving objects sent by the collecting device 101, can perform clustering processing on the plurality of behavior data according to different traffic moving objects to generate a plurality of behavior data. Behavior data sets, that is, the similarity of behavior data in each behavior data set is higher than a preset threshold. Based on the above behavior data set, a traffic test scene can be constructed. In the traffic test scene, the motion behavior of the traffic moving object needs to be constructed.
  • the motion behavior is composed of at least one behavior element, and the motion behavior includes the following At least one of: overtaking, going straight at intersection, turning at intersection, merging into traffic flow, pedestrian crossing sidewalk, etc.
  • the overtaking motion behavior needs to be arranged in the test scene.
  • behavior elements such as left lane change, straight acceleration, right lane change, and lane keeping can be included.
  • the behavior data set corresponding to each behavior element can be obtained respectively. In this way, the behavior data in the different sets of behavior data can be combined into at least one movement behavior of the traffic moving object.
  • an embodiment of the present application provides an intelligent vehicle 200 , and the intelligent vehicle 200 may include a collection device 101 and a test scene construction device 103 .
  • the acquisition device 101 may include one or more sensors in the intelligent vehicle 200 such as a lidar, a camera, a Global Navigation Satellite System (GNSS), an inertial measurement unit (Inertial Measurement Unit, IMU).
  • the test scenario construction device 103 may be provided in the processor and memory in the intelligent vehicle 200 .
  • the test scene constructed by the test scene construction device 103 can not only be used for performance testing of the intelligent vehicle 200, but also can be used to simulate a traffic scene, and the simulated traffic scene may include a test that passes the performance test Scenes.
  • users can select the traffic scenarios that need to be simulated through the on-board computer 248 of the smart vehicle 200 , such as simulating overtaking, going straight at intersections, and merging. Incoming traffic flow and other traffic scenarios.
  • the intelligent vehicle 200 can display the test scene constructed by the test scene construction device 103 to the user, so that the user can experience the driving state of the intelligent vehicle 200 in the traffic scene.
  • FIG. 3B is a functional block diagram of an intelligent vehicle 200 provided by an embodiment of the present application.
  • the smart vehicle 200 can be used as an embodiment of the acquisition device 101 in the test scene construction system architecture, and can also be used as an embodiment of the smart vehicle 200 in FIG. 3A .
  • the intelligent vehicle 200 may be configured in a fully or partially autonomous driving mode.
  • the intelligent vehicle 200 can control itself while in an autonomous driving mode, and can determine the current state of the vehicle and its surroundings through human manipulation, determine the possible behavior of at least one other vehicle in the surrounding environment, and determine the other
  • the intelligent vehicle 200 is controlled based on the determined information with a confidence level corresponding to the likelihood that the vehicle will perform the possible behavior.
  • the intelligent vehicle 200 may be set to operate without human interaction.
  • Intelligent vehicle 200 may include various subsystems, such as travel system 202 , sensor system 204 , control system 206 , one or more peripherals 208 and power supply 210 , computer system 212 and user interface 216 .
  • intelligent vehicle 200 may include more or fewer subsystems, and each subsystem may include multiple elements. Additionally, each of the subsystems and elements of the intelligent vehicle 200 may be wired or wirelessly interconnected.
  • the travel system 202 may include components that provide powered motion for the intelligent vehicle 200 .
  • travel system 202 may include engine 218 , energy source 219 , transmission 220 , and wheels/tires 221 .
  • Engine 218 may be an internal combustion engine, an electric motor, an air compression engine, or other types of engine combinations, such as a gasoline engine and electric motor hybrid engine, an internal combustion engine and air compression engine hybrid engine.
  • Engine 218 converts energy source 219 into mechanical energy.
  • Examples of energy sources 219 include gasoline, diesel, other petroleum-based fuels, propane, other compressed gas-based fuels, ethanol, solar panels, batteries, and other sources of electricity. Energy source 219 may also provide energy to other systems of intelligent vehicle 200 .
  • Transmission 220 may transmit mechanical power from engine 218 to wheels 221 .
  • Transmission 220 may include a gearbox, a differential, and a driveshaft.
  • transmission 220 may also include other devices, such as clutches.
  • the drive shafts may include one or more axles that may be coupled to one or more wheels 221 .
  • Sensor system 204 may include several sensors that sense information about the environment surrounding intelligent vehicle 200 .
  • the sensor system 204 may include a global positioning system 222 (the positioning system may be a GPS system, a Beidou system or other positioning systems), an inertial measurement unit (IMU) 224, a radar 226, a laser rangefinder 228 and camera 230.
  • the sensor system 204 may also include sensors that monitor the internal systems of the smart vehicle 200 (eg, an in-vehicle air quality monitor, a fuel gauge, an oil temperature gauge, etc.). Sensor data from one or more of these sensors can be used to detect objects and their corresponding characteristics (position, shape, orientation, velocity, etc.). This detection and identification is a critical function for the safe operation of autonomous intelligent vehicle 200 .
  • the positioning system 222 may be used to estimate the geographic location of the intelligent vehicle 200 .
  • the IMU 224 is used to sense position and orientation changes of the intelligent vehicle 200 based on inertial acceleration.
  • IMU 224 may be a combination of an accelerometer and a gyroscope.
  • the IMU 224 may be used to measure the curvature of the intelligent vehicle 200 .
  • Radar 226 may utilize radio signals to sense objects within the surrounding environment of intelligent vehicle 200 .
  • radar 226 may be used to sense the speed and/or heading of objects.
  • the laser rangefinder 228 may utilize laser light to sense objects in the environment in which the intelligent vehicle 200 is located.
  • the laser rangefinder 228 may include one or more laser sources, laser scanners, and one or more detectors, among other system components.
  • Camera 230 may be used to capture multiple images of the surrounding environment of intelligent vehicle 200 .
  • Camera 230 may be a still camera or a video camera.
  • Control system 206 controls the operation of the intelligent vehicle 200 and its components.
  • Control system 206 may include various elements including steering system 232 , throttle 234 , braking unit 236 , sensor fusion algorithms 238 , computer vision system 240 , route control system 242 , and obstacle avoidance system 244 .
  • Steering system 232 is operable to adjust the heading of intelligent vehicle 200 .
  • it may be a steering wheel system.
  • the throttle 234 is used to control the operating speed of the engine 218 and thus the speed of the intelligent vehicle 200 .
  • the braking unit 236 is used to control the deceleration of the intelligent vehicle 200 .
  • the braking unit 236 may use friction to slow the wheels 221 .
  • the braking unit 236 may convert the kinetic energy of the wheels 221 into electrical current.
  • the braking unit 236 may also take other forms to slow down the wheels 221 to control the speed of the smart vehicle 200 .
  • Computer vision system 240 is operable to process and analyze images captured by camera 230 in order to identify objects and/or features in the environment surrounding intelligent vehicle 200 .
  • the objects and/or features may include traffic signals, road boundaries and obstacles.
  • Computer vision system 240 may use object recognition algorithms, Structure from Motion (SFM) algorithms, video tracking, and other computer vision techniques.
  • SFM Structure from Motion
  • computer vision system 240 may be used to map the environment, track objects, estimate the speed of objects, and the like.
  • the route control system 242 is used to determine the travel route of the intelligent vehicle 200 .
  • route control system 242 may combine data from sensors 238, GPS 222, and one or more predetermined maps to determine a driving route for intelligent vehicle 200.
  • Obstacle avoidance system 244 is used to identify, evaluate, and avoid or otherwise traverse potential obstacles in the environment of intelligent vehicle 200 .
  • control system 206 may additionally or alternatively include components other than those shown and described. Alternatively, some of the components shown above may be reduced.
  • the intelligent vehicle 200 interacts with external sensors, other vehicles, other computer systems, or users through peripheral devices 208 .
  • Peripherals 208 may include a wireless communication system 246 , an onboard computer 248 , a microphone 250 and/or a speaker 252 .
  • peripherals 208 provide a means for a user of intelligent vehicle 200 to interact with user interface 216 .
  • the onboard computer 248 may provide information to the user of the smart vehicle 200 .
  • User interface 216 may also operate on-board computer 248 to receive user input.
  • the onboard computer 248 can be operated via a touch screen.
  • the test scene constructed by the test scene construction module 103 is used to simulate a traffic scene, the user can select the traffic scene to be simulated or configure scene data through the on-board computer 248, and the on-board computer 248 can also display intelligent The driving state of the vehicle 200 in the test scene, so that the driver can simulate driving in the vehicle, thereby increasing the driving experience.
  • peripheral devices 208 may provide a means for intelligent vehicle 200 to communicate with other devices located within the vehicle.
  • microphone 250 may receive audio (eg, voice commands or other audio input) from a user of intelligent vehicle 200 .
  • speaker 252 may output audio to a user of intelligent vehicle 200 .
  • Wireless communication system 246 may wirelessly communicate with one or more devices, either directly or via a communication network.
  • wireless communication system 246 may use 3G cellular communications, such as CDMA, EVDO, GSM/GPRS, or 4G cellular communications, such as LTE. Or 5G cellular communications.
  • the wireless communication system 246 may communicate with a wireless local area network (WLAN) using WiFi.
  • WLAN wireless local area network
  • the wireless communication system 246 may communicate directly with the device using an infrared link, Bluetooth, or ZigBee.
  • Other wireless protocols, such as various vehicle communication systems, for example, wireless communication system 246 may include one or more dedicated short range communications (DSRC) devices, which may include a combination of vehicle and/or roadside stations. public and/or private data communications between them.
  • DSRC dedicated short range communications
  • Power supply 210 may provide power to various components of intelligent vehicle 200 .
  • the power source 210 may be a rechargeable lithium-ion or lead-acid battery.
  • One or more battery packs of such batteries may be configured as a power source to provide power to various components of the intelligent vehicle 200 .
  • power source 210 and energy source 219 may be implemented together, such as in some all-electric vehicles.
  • Computer system 212 may include at least one processor 213 that executes instructions 215 stored in a non-transitory computer readable medium such as data storage device 214 .
  • Computer system 212 may also be multiple computing devices that control individual components or subsystems of intelligent vehicle 200 in a distributed fashion.
  • the processor 213 may be any conventional processor, such as a commercially available CPU. Alternatively, the processor may be a dedicated device such as an ASIC or other hardware-based processor.
  • FIG. 3B functionally illustrates a processor, memory, and other elements of the computer 120 in the same block, one of ordinary skill in the art will understand that the processor, computer, or memory may actually include a processor, a computer, or a memory that may or may not Multiple processors, computers, or memories stored within the same physical enclosure.
  • the memory may be a hard drive or other storage medium located within an enclosure other than computer 120.
  • reference to a processor or computer will be understood to include reference to a collection of processors or computers or memories that may or may not operate in parallel.
  • some components such as the steering and deceleration components may each have their own processor that only performs computations related to component-specific functions .
  • a processor may be located remotely from the vehicle and in wireless communication with the vehicle. In other aspects, some of the processes described herein are performed on a processor disposed within the vehicle while others are performed by a remote processor, including taking steps necessary to perform a single maneuver.
  • data storage 214 may include instructions 215 (eg, program logic) executable by processor 213 to perform various functions of intelligent vehicle 200, including those described above.
  • Data storage 224 may also contain additional instructions, including sending data to, receiving data from, interacting with, and/or performing operations on one or more of propulsion system 202 , sensor system 204 , control system 206 , and peripherals 208 control commands.
  • memory 214 may store data such as road maps, route information, vehicle location, direction, speed, and other such vehicle data, among other information. Such information may be used by intelligent vehicle 200 and computer system 212 during operation of intelligent vehicle 200 in autonomous, semi-autonomous, and/or manual modes.
  • the data stored in the memory 214 may further include preset behavior definition rules, and the behavior definition rules may define rules for behavior elements such as straight driving, left turn, and right turn.
  • the behavior definition rules may include characteristics of preset behavior elements.
  • the processor 213 can identify the behavior data in the road condition data according to the behavior definition rule, for example, identify straight driving behavior data, left-turn behavior data, right-turn behavior data, etc. in the road condition data.
  • the location of the behavior data in the road condition data such as the start time and the end time, can also be marked in the road condition data, and the motion parameters of the behavior data can also be marked and parameter values.
  • the memory 214 may also store data such as scene data and motion behaviors required for each traffic scene (ie, a test scene that passes the test).
  • User interface 216 for providing information to or receiving information from a user of intelligent vehicle 200 .
  • user interface 216 may include one or more input/output devices within the set of peripheral devices 208 , such as wireless communication system 246 , onboard computer 248 , microphone 250 and speaker 252 .
  • Computer system 212 may control functions of intelligent vehicle 200 based on input received from various subsystems (eg, wireless communication system 246 , travel system 202 , sensor system 204 , and control system 206 ) and from user interface 216 .
  • the computer system 212 may utilize input from the wireless communication system 246 to plan lane lines at intersections that need to be passed in autonomous driving by which obstacles at the intersection can be avoided.
  • computer system 212 is operable to provide control of various aspects of intelligent vehicle 200 and its subsystems.
  • computer system 212 may also receive information from, or transfer information to, other computer systems.
  • computer system 212 may transfer sensor data collected from sensor system 204 of intelligent vehicle 200 to another computer system remotely, and have the data processed by another computer system, such as by another computer system on the sensor system In 204 , data collected by each sensor is fused, and then the data or analysis result obtained after fusion is returned to the computer system 212 .
  • data from computer system 212 may be transmitted via a network to a cloud-side computer system for further processing.
  • Networks and intermediate nodes may include various configurations and protocols, including the Internet, the World Wide Web, Intranets, Virtual Private Networks, Wide Area Networks, Local Area Networks, private networks using one or more of the company's proprietary communication protocols, Ethernet, WiFi and HTTP, and various combinations of the foregoing.
  • Such communications may be by any device capable of transferring data to and from other computers, such as modems and wireless interfaces.
  • the remote computer system that interacts with the computer system 212 in the intelligent vehicle 200 may include a server having multiple computers, such as a load balancing server farm, in order to receive, from the computer system 212 , The purpose of processing and transmitting data, which exchanges information with different nodes of the network.
  • the server may have processors, memory, instructions and data, and the like.
  • the data of the server may include providing weather-related information.
  • the server may receive, monitor, store, update, and transmit various information related to the weather. This information may include, for example, precipitation, cloud, and/or temperature information in the form of reports, radar information, forecasts, and the like.
  • the data of the server can also include high-precision map data, traffic information of the road ahead (such as real-time traffic congestion and traffic accidents, etc.), and the server can send the high-precision map data and traffic information to the computer system 212 , so that the intelligent vehicle 200 can be assisted to better perform automatic driving and ensure driving safety.
  • one or more of these components described above may be installed or associated with the intelligent vehicle 200 separately.
  • data storage device 214 may exist partially or completely separate from intelligent vehicle 200 .
  • the above-described components may be communicatively coupled together in a wired and/or wireless manner.
  • the above component is just an example.
  • components in each of the above modules may be added or deleted according to actual needs, and FIG. 3B should not be construed as a limitation on the embodiments of the present application.
  • a self-driving car traveling on a road can recognize objects within its surroundings to determine an adjustment to the current speed.
  • the objects may be other vehicles, traffic control equipment, or other types of objects.
  • each identified object may be considered independently, and based on the object's respective characteristics, such as its current speed, acceleration, distance from the vehicle, etc., may be used to determine the speed at which the autonomous vehicle is to adjust.
  • the autonomous vehicle smart vehicle 200 or a computing device associated with the autonomous vehicle smart vehicle 200 may be based on the characteristics of the identified objects and the surrounding environment. state (eg, traffic, rain, ice on the road, etc.) to predict the behavior of the identified object.
  • each identified object is dependent on the behavior of the other, so it is also possible to predict the behavior of a single identified object by considering all identified objects together.
  • the intelligent vehicle 200 can adjust its speed based on the predicted behavior of the identified object.
  • the self-driving car can determine what steady state the vehicle will need to adjust to (eg, accelerate, decelerate, or stop) based on the predicted behavior of the object.
  • other factors may also be considered to determine the speed of the intelligent vehicle 200, such as the lateral position of the intelligent vehicle 200 in the road being traveled, the curvature of the road, the proximity of static and dynamic objects, and the like.
  • the computing device may also provide instructions to modify the steering angle of the intelligent vehicle 200 so that the self-driving car follows a given trajectory and/or maintains contact with objects in the vicinity of the self-driving car ( For example, safe lateral and longitudinal distances for cars in adjacent lanes on the road.
  • the above-mentioned intelligent vehicles 200 can be cars, trucks, motorcycles, buses, boats, airplanes, helicopters, lawn mowers, recreational vehicles, playground vehicles, construction equipment, trams, golf carts, trains, trolleys, etc.
  • the application examples are not particularly limited.
  • the function diagram of the smart vehicle 200 in FIG. 3B is only an exemplary implementation in the embodiments of the present application, and the smart vehicle 200 in the embodiments of the present application includes but is not limited to the above structures.
  • FIG. 4 is a schematic flowchart of an embodiment of a test scenario construction method provided by the present application.
  • the present application provides method operation steps as shown in the following embodiments or drawings, more or less operation steps may be included in the method based on routine or without inventive effort. In steps that logically do not have a necessary causal relationship, the execution order of these steps is not limited to the execution order provided by the embodiments of the present application.
  • the method may be executed sequentially or in parallel (for example, in a parallel processor or multi-threaded processing environment) according to the methods shown in the embodiments or the accompanying drawings during the construction process of the actual test scene or when the method is executed.
  • test scenario construction method provided by the present application is shown in FIG. 4 , and the method may include:
  • S401 Determine the motion behavior of the traffic moving object required to construct a preset traffic test scene, where the motion behavior is composed of at least one behavior element.
  • the traffic test is to simulate a traffic test scene on a terminal device, and test the responsiveness of the vehicle model in the traffic test scene, so as to evaluate the performance of the vehicle model in a real traffic environment.
  • the preset traffic test scene may include traffic moving objects and motion behaviors of the traffic moving objects.
  • the traffic moving objects may include moving objects on the road, such as cars, trucks, buses, trams, trains, motorcycles, electric vehicles, bicycles, pedestrians, animals, and the like.
  • many motion behaviors can occur on the road.
  • a motor vehicle can have at least one of the following motion behaviors on the road: overtaking, going straight in the intersection, turning in the intersection, merging into the traffic flow, pedestrians passing through sidewalk.
  • the motion behavior may be composed of at least one behavior element.
  • FIG. 5 shows a schematic diagram of the overtaking motion behavior.
  • the traffic moving object 501 may include behavior elements such as left lane change, straight acceleration, right lane change, and lane keeping in the overtaking motion behavior.
  • behavior elements such as straight-line deceleration and straight-line acceleration may be included.
  • the movement behavior of left turn at the intersection it can include behavior elements such as straight-line deceleration, left-turn deceleration, stop and wait, left-turn, and straight-line acceleration.
  • traffic motion objects, the motion behaviors, and the behavior elements are not limited to the above examples, and any motion objects that can appear on roads or places where vehicles may travel, such as roads and garages, belong to the implementation of this application.
  • the protection scope of the example, any movement behavior that can be performed by a traffic moving object on the road or place where the vehicle may travel also belongs to the protection scope implemented by this application.
  • S403 Respectively obtain a behavior data set corresponding to the at least one behavior element, the behavior data set includes a plurality of behavior data whose similarity is higher than a preset threshold, and the behavior data is set to be obtained from real road condition data extracted.
  • a behavior data set corresponding to the at least one behavior element may be acquired respectively.
  • the motion behavior of overtaking it can include behavior elements such as left lane change, straight acceleration, right lane change, lane keeping, etc.
  • the collection device 101 can collect at least one behavior data of at least one traffic moving object in the real road condition data, and send the at least one behavior data to the test scene construction device 103, specifically, the behavior data Collections are set up to be constructed as follows:
  • S503 Extract at least one behavior data of at least one traffic moving object from the real road condition data, where the one behavior data includes at least one motion parameter information;
  • S505 For different traffic moving objects, perform cluster analysis on at least one behavior data of the traffic moving objects, and generate a behavior data set corresponding to at least one behavior element.
  • the collecting device 101 can collect real road condition data, and identify at least one traffic moving object and at least one behavior data of the traffic moving object from the real road condition data.
  • real road condition data various behavior data can be included, but not all behavior data are suitable for testing scenarios.
  • the collection device 101 may include preset behavior definition rules, and the behavior definition rules may define rules for motion behaviors such as straight driving, left turning, and right turning.
  • the behavior definition rule may include a feature of a preset behavior element, where the behavior element may be used as a class name of a class of behavior data, and the behavior element and the behavior data are related The difference is that the behavior data includes specific motion parameters and parameter values of the behavior, and the behavior elements are used to divide different categories of behavior data.
  • the collecting device 101 can mine behavior data that conforms to the characteristics of the preset behavior elements from the real road condition data. In the process of identifying the behavior data, the operating parameter information corresponding to each behavior data can also be determined.
  • the collecting device 101 identifies the straight-line driving behavior of the motor vehicle A from the real road condition data, and the straight-line driving behavior
  • the collecting device 101 may perform cluster analysis on at least one behavior data of the traffic moving object for different traffic moving objects, and generate at least one behavior data of the traffic moving object.
  • different traffic moving objects have different behavioral characteristics.
  • the behavioral characteristics of cars are relatively flexible, and the behavioral characteristics of heavy vehicles (such as trucks) are large inertia and relatively inflexible.
  • the at least one behavior data may be clustered according to the traffic moving objects.
  • the clustering algorithm used for clustering the at least one behavioral data may include K-means clustering algorithm, mean-shift clustering algorithm, density-based clustering algorithm, max. Clustering algorithms, etc. are expected, and this application does not limit it here.
  • FIG. 7 shows a process of extracting a behavior data set for at least one behavior element of a car by using real road condition data.
  • a behavior data set corresponding to at least one behavior element can be generated.
  • the behavior elements may include, for example, left switching lanes, right switching lanes, straight driving, left right-angle turn, right right-angle turn, parking, etc., and each behavior element also corresponds to a behavior data set, as shown in FIG.
  • the lateral speed/acceleration of each behavior data is different.
  • Straight line driving can also be divided into behavior elements such as acceleration driving, deceleration driving, lane keeping, etc., wherein acceleration driving can also correspond to a behavior data set composed of a plurality of behavior data with different distances/accelerations.
  • the collection device 101 may execute S501, may also execute S501 and S503, and may also execute S501-S503, which is not limited in this application.
  • the acquisition device 101 executes S501 or executes S501 and S503, all the remaining steps or part of the steps can be executed by the test scene construction device 103, and of course, can also be executed by any other device with data processing capability, the present application is here No restrictions.
  • S405 Combine behavior data in different sets of behavior data into at least one motion behavior of the traffic moving object.
  • the behavior data in different sets of behavior data may be combined into the At least one movement behavior of a traffic moving object. Since each behavior data set further includes at least one kind of behavior data, by combining the behavior data in different behavior data sets, multiple possibilities of the exercise behavior can be obtained. For example, as shown in FIG.
  • the left lane changing behavior data set 601 contains M behavior data
  • the linear acceleration behavior data set 603 contains N behavior data
  • the right lane changing behavior data set 605 contains P behavior data
  • the lane keeping behavior data set 607 contains Q behavior data, so in theory, (M ⁇ N ⁇ P ⁇ Q) kinds of overtaking motion behaviors can be generated in combination, providing abundant data for the preset traffic test scene.
  • the combination in the process of combining behavior data in different behavior data sets, as shown in FIG. 6 , the combination may be performed in the following manner:
  • S601 Select behavior data from different sets of behavior data respectively
  • S603 According to the occurrence sequence of the at least one behavior element, connect the selected behavior data into a motion behavior.
  • the test scene construction apparatus 103 not only needs to acquire the behavior data set corresponding to the at least one behavior element, but also needs to automatically combine the behavior data in the behavior data set into the motion behavior. Specifically, in the process of combining the behavior data, the test scene constructing device 103 may first select behavior data from different sets of behavior data, for example, in the above-mentioned overtaking test scene, you can change from left One behavior data is selected from the lane behavior data set 601 , the straight-line acceleration behavior data set 603 , the right lane changing behavior data set 605 , and the lane keeping behavior data set 607 respectively.
  • the selected behavior data is connected to generate the overtaking motion behavior.
  • the behavior data is visualized as motion trajectories in the test scene schematic diagram.
  • the overtaking test scene it may include the left turn lane 801 of the traffic running object 501 , the straight line acceleration 803 , and the right lane change.
  • the tail end of the trajectory is connected with the head end of the visible movement trajectory of the left lane change, until all the behavior data are concatenated into the overtaking movement behavior.
  • the selected behavior data in order to enhance the continuity and smoothness between different behavior data, may be smoothly connected according to changes in motion parameters included in adjacent behavior data.
  • a smooth transition section may be made between the behavior data A and the behavior data B, and the smooth transition section may be based on the The change process of the motion parameters of the behavior data A and the behavior data B is generated. As shown in FIG.
  • the behavior data A is a left lane change 801
  • acceleration 2m/s 2
  • the behavior data B is linear acceleration 803
  • the movement behavior after the movement behavior is generated, the movement behavior may also be set in a traffic test scene. After the at least one movement behavior of the traffic moving object, the method further includes:
  • S701 Acquire scene data of the preset traffic test scene, where the scene data includes at least one of road information, traffic facility control information, environmental information, and initialization information of a test object;
  • S703 Construct the preset traffic test scene according to the scene data
  • S705 Set the at least one motion behavior in the preset traffic test scene respectively, test the test object, and obtain a test result.
  • scene data of the preset traffic test scene may be acquired first.
  • the scene data includes at least one of road information, traffic facility control information, environmental information, and initial positions of traffic moving objects.
  • the road information may include the number of lanes, lane types (straight roads, turning roads, etc.), intersections, etc.
  • the traffic facility control information may include traffic lights and their operating parameters, speed limit signs, zebra crossings, etc.
  • the environmental information may include information such as weather and obstacles
  • the initialization information of the test object may include information such as the initial position and initial speed of the test object.
  • the scene data is not limited to the above examples, and any information that may appear in an actual traffic scene belongs to the protection scope of the scene data.
  • the preset traffic test scene may be constructed, and the preset traffic test scene may be initialized by using the scene data. Then, the at least one motion behavior can be set in the preset traffic test scene, the test object is tested, and a test result is obtained.
  • the acquired scene data may include information such as the initial position, initial speed, number of lanes, and weather conditions of the test vehicle. Then, a traffic test scene can be arranged according to the scene data, the at least one motion behavior can be set in the traffic test scene, the test vehicle can be tested, and a test result can be obtained.
  • the number of test results matches the at least one motor behavior.
  • the response capability and abnormal condition of the test object can be acquired according to the test result.
  • FIG. 10 shows the visualization interface of the overtaking test scene, and the visualization interface shows the visualized trajectories of each behavioral element of the overtaking motion behavior of the traffic moving object 501 , that is, showing the left turn lane 801 , the straight line acceleration 803 , the right lane change 805 and Multiple possible visualization motion trajectories for lane keeping 807 .
  • Various possible initialization positions 1001 of the test object are also displayed in the visual interface, as shown by the triangles in FIG. 10 . It can be seen that, by using the method for constructing a test scenario provided by the embodiment of the present application, multiple test cases can be quickly constructed, and thus rich test results can be obtained.
  • the at least one motion behavior is set in the preset traffic test scene, the test object is tested, and the test result is obtained, including:
  • the motion behavior in the process of setting the at least one motion behavior in the predicted traffic test scene for testing, it may be first determined whether the motion behavior conforms to the scene characteristics of the preset traffic test scene.
  • a traffic moving object enters the lane to accelerate after switching lanes to the left, and then switches to the original lane after accelerating in the lane for 50 to 100 meters.
  • the generated motion behavior is that the traffic behavior changes lanes on the left, the lane accelerates for 3 kilometers, and then switches to the original lane on the right. It can be seen that the above motion behavior obviously does not conform to the scene characteristics of the overtaking test scene.
  • the scene feature of the preset traffic test scene may include behavior constraints of the motion behavior of the traffic moving object.
  • the driving distance of the linear acceleration of the behavior element may be set within a range of 50 meters to 100 meters.
  • the rationality of the motion behavior set in the preset traffic test scene can be guaranteed.
  • the motion behavior of traffic moving objects may also be unconventional.
  • the behavior data set further includes a plurality of first behavior data whose similarity with the plurality of behavior data is less than a first preset threshold, and the plurality of first behavior data are The ratio of the number of behavior data to the plurality of first behavior data is not less than a preset ratio threshold. That is to say, the behavior data set not only includes a plurality of behavior data whose similarity is higher than a preset threshold, but may also include some first behavior data whose similarity is smaller than a first preset threshold.
  • the proportion of the number of the multiple first behavior data in the behavior data set is not high, for example, the ratio of the number of the multiple behavior data to the multiple first behavior data is not less than 9.
  • the ratio of the plurality of first behavior data in the behavior data set may be set by using an ⁇ -greedy algorithm.
  • a threshold value of 0 ⁇ 1 is set, and the plurality of first behavior data and the number of the plurality of behavior data are set in a ratio of 1- ⁇ : ⁇ , which satisfies to a certain extent
  • the richness of the behavioral dataset enhances the robustness of the test scenarios.
  • the present application also provides a simulation scene construction method from the perspective of an in-vehicle simulation scene construction device. As shown in FIG. 11 , the method may include:
  • S1103 Extract at least one behavior data of at least one traffic moving object from the real road condition data, where the one behavior data includes at least one motion parameter information.
  • the device for constructing the simulation scene can collect abundant real road condition data, and provide many rich and real data bases for the test scene.
  • the vehicle can also extract behavior data of different traffic moving objects from the real road condition data, and the behavior data includes at least one motion parameter information.
  • the embodiment of the present application can automatically realize the extraction of behavior data, reduce the cost of extracting behavior data, and improve the efficiency of extracting behavior data.
  • the driver can use the simulation scene construction device to simulate the driving to increase the experience.
  • the method further includes:
  • cluster analysis is performed on at least one behavior data of the traffic moving objects, and a behavior data set corresponding to at least one behavior element is generated.
  • test scenario construction apparatus 103 may include:
  • a motion behavior determination module 1201 configured to determine the motion behavior of the traffic moving object required for constructing a preset traffic test scene, where the motion behavior is composed of at least one behavior element;
  • a data set acquisition module 1203, configured to acquire the behavior data sets corresponding to the at least one behavior element respectively, the behavior data sets include a plurality of behavior data whose similarity is higher than a preset threshold, and the behavior data is set It is extracted from real road condition data;
  • the behavior data combining module 1205 is configured to combine the behavior data in different sets of behavior data into at least one movement behavior of the traffic moving object.
  • the data processing apparatus 1200 may be set on the server side or the cloud.
  • the behavior data set is set to be constructed according to the following modules:
  • the road condition data acquisition module is used to acquire real road condition data
  • a behavior data extraction module configured to extract at least one behavior data of at least one traffic moving object from the real road condition data, where the one behavior data includes at least one motion parameter information;
  • the behavior data clustering module is configured to perform cluster analysis on at least one behavior data of the traffic moving objects for different traffic moving objects, and generate a behavior data set corresponding to at least one behavior element.
  • the behavior data clustering module is specifically used for:
  • For different traffic moving objects select at least one target behavior data that conforms to the characteristics of preset behavior elements from at least one behavior data of the traffic moving objects;
  • the behavior data combination module is specifically used for:
  • the selected behavior data is connected into a motion behavior.
  • the behavior data combination module is also used for:
  • the selected behavior data is smoothly connected according to the changes of the motion parameters contained in the adjacent behavior data.
  • the device further includes:
  • a scene data acquisition module configured to acquire scene data of the preset traffic test scene, where the scene data includes at least one of road information, traffic facility control information, environmental information, and initial positions of traffic moving objects;
  • test scene construction module configured to construct the preset traffic test scene according to the scene data
  • a test result acquisition module configured to respectively set the at least one motion behavior in the preset traffic test scene, test the test object, and acquire the test result.
  • test result acquisition module is specifically used for:
  • the motion behavior When it is determined that the motion behavior conforms to the scene characteristics, the motion behavior is set in the preset traffic test scene, the test object is tested, and a test result is obtained.
  • the behavior data set further includes a plurality of first behavior data whose similarity with the plurality of behavior data is less than a first preset threshold.
  • the ratio of the number of pieces of behavior data to the plurality of first behavior data is not less than a preset ratio threshold.
  • the behavior data includes at least one of the following motion parameter information: travel direction speed, travel lateral speed, travel acceleration, travel lateral acceleration, travel distance, turning radius, Travel time, travel speed, travel acceleration, travel time.
  • the traffic moving objects include at least one of the following: cars, trucks, buses, trams, trains, motorcycles, electric vehicles, bicycles, pedestrians, and animals.
  • the motion behavior includes at least one of the following: overtaking, going straight at an intersection, turning at an intersection, merging into a traffic flow, and pedestrians passing a sidewalk.
  • the behavior elements include at least one of the following: driving in a straight line, switching lanes to the left, switching lanes to the right, turning at right angles to the left, turning at right angles to the right, and parking.
  • the device further includes:
  • the test scene acquisition module is used to acquire the preset traffic test scene selected by the user.
  • the collection device 101 includes:
  • the road condition data acquisition module 1301 is used to acquire real road condition data
  • the behavior data extraction module 1303 is configured to extract at least one behavior data of at least one traffic moving object from the real road condition data, where the one behavior data includes at least one motion parameter information.
  • it also includes:
  • the behavior data clustering module 1305 is configured to perform cluster analysis on at least one behavior data of the traffic moving objects for different traffic moving objects, and generate a behavior data set corresponding to at least one behavior element.
  • An embodiment of the present application provides a device, as shown in FIG. 13 , including: a processor and a memory for storing instructions executable by the processor; wherein the processor is configured to implement the above apparatus when executing the instructions .
  • Device 800 includes memory 801 , processor 802 , bus 803 and communication interface 804 .
  • the memory 801 , the processor 802 and the communication interface 804 communicate through the bus 801 .
  • the bus 803 may be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus or the like.
  • the bus can be divided into address bus, data bus, control bus and so on. For ease of representation, only one thick line is shown in FIG. 13, but it does not mean that there is only one bus or one type of bus.
  • the communication interface 804 is used for external communication.
  • the processor 802 may be a central processing unit (central processing unit, CPU).
  • the memory 801 may include volatile memory, such as random access memory (RAM).
  • RAM random access memory
  • the memory 801 may also include non-volatile memory, such as read-only memory (ROM), flash memory, HDD or SSD.
  • Executable code is stored in the memory 801, and the processor 802 executes the executable code to execute the foregoing test scenario construction method.
  • Embodiments of the present application provide a non-volatile computer-readable storage medium on which computer program instructions are stored, and when the computer program instructions are executed by a processor, implement the foregoing apparatus.
  • Embodiments of the present application provide a computer program product, including computer-readable codes, or a non-volatile computer-readable storage medium carrying computer-readable codes, when the computer-readable codes are stored in a processor of an electronic device When running in the electronic device, the processor in the electronic device executes the above-mentioned means.
  • example computer program product 600 is provided using signal bearing medium 601 .
  • the signal bearing medium 601 may include one or more program instructions 602 that, when executed by one or more processors, may provide the functions or portions of the functions described above with respect to FIG. 4 or FIG. 11 .
  • program instructions 602 in FIG. 6 also describe example instructions.
  • the signal bearing medium 601 may include a computer readable medium 603 such as, but not limited to, a hard drive, a compact disc (CD), a digital video disc (DVD), a digital tape, a memory, a read only memory (Read) -Only Memory, ROM) or random access memory (Random Access Memory, RAM) and so on.
  • the signal bearing medium 601 may include a computer recordable medium 604, such as, but not limited to, memory, read/write (R/W) CDs, R/W DVDs, and the like.
  • signal bearing medium 601 may include communication medium 605, such as, but not limited to, digital and/or analog communication media (eg, fiber optic cables, waveguides, wired communication links, wireless communication links, etc.).
  • the signal bearing medium 601 may be conveyed by a wireless form of communication medium 605 (eg, a wireless communication medium conforming to the IEEE 802.11 standard or other transmission protocol).
  • the one or more program instructions 602 may be, for example, computer-executable instructions or logic-implemented instructions.
  • a computing device such as the computing device described with respect to FIG. 4 or FIG.
  • 11 may be configured to, in response to communication via one or more of computer readable medium 603 , computer recordable medium 604 , and/or communication medium 605 , Program instructions 602 communicated to a computing device to provide various operations, functions, or actions.
  • Program instructions 602 communicated to a computing device to provide various operations, functions, or actions.
  • the arrangements described herein are for illustrative purposes only. Thus, those skilled in the art will understand that other arrangements and other elements (eg, machines, interfaces, functions, sequences, and groups of functions, etc.) can be used instead and that some elements may be omitted altogether depending on the desired results . Additionally, many of the described elements are functional entities that may be implemented as discrete or distributed components, or in conjunction with other components in any suitable combination and position.
  • each block in the flowchart or block diagrams may represent a module, segment, or portion of instructions, which comprises one or more functions for implementing the specified logical function(s) executable instructions.
  • the functions noted in the blocks may occur out of the order noted in the figures. For example, two blocks in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved.
  • each block of the block diagrams and/or flowchart illustrations, and combinations of blocks in the block diagrams and/or flowchart illustrations can be implemented in hardware (eg, circuits or ASICs (Application) that perform the corresponding functions or actions. Specific Integrated Circuit, application-specific integrated circuit)), or can be implemented by a combination of hardware and software, such as firmware.

Landscapes

  • Engineering & Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Evolutionary Computation (AREA)
  • General Physics & Mathematics (AREA)
  • Artificial Intelligence (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • General Engineering & Computer Science (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Evolutionary Biology (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Medical Informatics (AREA)
  • Software Systems (AREA)
  • Computer Hardware Design (AREA)
  • Geometry (AREA)
  • Traffic Control Systems (AREA)

Abstract

L'invention concerne un procédé et un dispositif (103) de construction d'environnement de test. Le procédé de construction d'environnement de test consiste à : déterminer le comportement de mouvement d'un objet mobile de trafic (501) requis pour construire un environnement de test de trafic prédéfini, le comportement de mouvement étant composé d'au moins un élément de comportement (S401) ; obtenir un ensemble de données de comportement correspondant à l'au moins un élément de comportement, l'ensemble de données de comportement comprenant de multiples données de comportement ayant des similarités supérieures à un seuil prédéfini, les données de comportement étant extraites à partir de données de condition de route réelle (S403) ; et combiner les données de comportement dans différents ensembles de données de comportement en au moins un comportement de mouvement de l'objet mobile de trafic (501) (S405).
PCT/CN2021/132797 2021-01-29 2021-11-24 Procédé et dispositif de construction d'environnement de test WO2022160900A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202110124849.X 2021-01-29
CN202110124849.XA CN114813157A (zh) 2021-01-29 2021-01-29 一种测试场景构建方法及装置

Publications (1)

Publication Number Publication Date
WO2022160900A1 true WO2022160900A1 (fr) 2022-08-04

Family

ID=82525650

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2021/132797 WO2022160900A1 (fr) 2021-01-29 2021-11-24 Procédé et dispositif de construction d'environnement de test

Country Status (2)

Country Link
CN (1) CN114813157A (fr)
WO (1) WO2022160900A1 (fr)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115017198A (zh) * 2022-08-08 2022-09-06 国汽智控(北京)科技有限公司 车辆数据处理方法、装置和设备
CN117607756A (zh) * 2024-01-18 2024-02-27 杭州布雷科电气有限公司 基于对抗神经网络的熔断器性能测试平台

Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2016133422A1 (fr) * 2015-02-20 2016-08-25 Общество С Ограниченной Ответственностью "Логос - Агентные Технологии" Procédé de mise en oeuvre d'un modèle imitant le mouvement de flux de transport et de piétons
US9836895B1 (en) * 2015-06-19 2017-12-05 Waymo Llc Simulating virtual objects
CN109948217A (zh) * 2019-03-12 2019-06-28 中国汽车工程研究院股份有限公司 一种基于自然驾驶数据的危险场景库构建方法
US20190355245A1 (en) * 2017-04-12 2019-11-21 Robert Bosch Gmbh Method for ascertaining data of a traffic scenario
CN110795818A (zh) * 2019-09-12 2020-02-14 腾讯科技（深圳）有限公司 一种确定虚拟测试场景方法、装置、电子设备和存储介质
CN111123920A (zh) * 2019-12-10 2020-05-08 武汉光庭信息技术股份有限公司 一种自动驾驶仿真测试场景生成方法和装置
CN111144015A (zh) * 2019-12-30 2020-05-12 吉林大学 一种自动驾驶汽车虚拟场景库构建方法
CN111680362A (zh) * 2020-05-29 2020-09-18 北京百度网讯科技有限公司 一种自动驾驶仿真场景获取方法、装置、设备及存储介质
CN111859618A (zh) * 2020-06-16 2020-10-30 长安大学 多端在环的虚实结合交通综合场景仿真测试系统及方法
CN111841012A (zh) * 2020-06-23 2020-10-30 北京航空航天大学 一种自动驾驶模拟仿真系统及其测试资源库建设方法

Patent Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2016133422A1 (fr) * 2015-02-20 2016-08-25 Общество С Ограниченной Ответственностью "Логос - Агентные Технологии" Procédé de mise en oeuvre d'un modèle imitant le mouvement de flux de transport et de piétons
US9836895B1 (en) * 2015-06-19 2017-12-05 Waymo Llc Simulating virtual objects
US20190355245A1 (en) * 2017-04-12 2019-11-21 Robert Bosch Gmbh Method for ascertaining data of a traffic scenario
CN109948217A (zh) * 2019-03-12 2019-06-28 中国汽车工程研究院股份有限公司 一种基于自然驾驶数据的危险场景库构建方法
CN110795818A (zh) * 2019-09-12 2020-02-14 腾讯科技（深圳）有限公司 一种确定虚拟测试场景方法、装置、电子设备和存储介质
CN111123920A (zh) * 2019-12-10 2020-05-08 武汉光庭信息技术股份有限公司 一种自动驾驶仿真测试场景生成方法和装置
CN111144015A (zh) * 2019-12-30 2020-05-12 吉林大学 一种自动驾驶汽车虚拟场景库构建方法
CN111680362A (zh) * 2020-05-29 2020-09-18 北京百度网讯科技有限公司 一种自动驾驶仿真场景获取方法、装置、设备及存储介质
CN111859618A (zh) * 2020-06-16 2020-10-30 长安大学 多端在环的虚实结合交通综合场景仿真测试系统及方法
CN111841012A (zh) * 2020-06-23 2020-10-30 北京航空航天大学 一种自动驾驶模拟仿真系统及其测试资源库建设方法

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115017198A (zh) * 2022-08-08 2022-09-06 国汽智控(北京)科技有限公司 车辆数据处理方法、装置和设备
CN115017198B (zh) * 2022-08-08 2022-10-14 国汽智控(北京)科技有限公司 车辆数据处理方法、装置和设备
CN117607756A (zh) * 2024-01-18 2024-02-27 杭州布雷科电气有限公司 基于对抗神经网络的熔断器性能测试平台
CN117607756B (zh) * 2024-01-18 2024-04-05 杭州布雷科电气有限公司 基于对抗神经网络的熔断器性能测试平台

Also Published As

Publication number Publication date
CN114813157A (zh) 2022-07-29

Similar Documents

Publication Publication Date Title
WO2022027304A1 (fr) Procédé et appareil de test de véhicule autonome
WO2021135371A1 (fr) Procédé de conduite automatique, dispositif associé et support de stockage lisible par ordinateur
WO2021027568A1 (fr) Procédé et dispositif d'évitement d'obstacles
WO2021102955A1 (fr) Procédé et appareil de planification de trajet pour véhicule
CN113968216B (zh) 一种车辆碰撞检测方法、装置及计算机可读存储介质
WO2021103511A1 (fr) Procédé et appareil de détermination de domaine de conception opérationnelle (odd), et dispositif associé
CN113792566A (zh) 一种激光点云的处理方法及相关设备
CN113160547B (zh) 一种自动驾驶方法及相关设备
WO2022160900A1 (fr) Procédé et dispositif de construction d'environnement de test
WO2022148172A1 (fr) Procédé de planification de ligne de voie de circulation et appareil associé
CN112543877B (zh) 定位方法和定位装置
CN113511204B (zh) 一种车辆换道行为识别方法及相关设备
WO2021189210A1 (fr) Procédé de changement de voie de véhicule et dispositif associé
US20230048680A1 (en) Method and apparatus for passing through barrier gate crossbar by vehicle
WO2022051951A1 (fr) Procédé de détection de ligne de voie de circulation, dispositif associé et support de stockage lisible par ordinateur
CN114693540A (zh) 一种图像处理方法、装置以及智能汽车
CN112513951A (zh) 一种场景文件的获取方法以及装置
CN113885045A (zh) 车道线的检测方法和装置
WO2022052881A1 (fr) Procédé de construction de carte et dispositif informatique
CN113859265A (zh) 一种驾驶过程中的提醒方法及设备
US20230324863A1 (en) Method, computing device and storage medium for simulating operation of autonomous vehicle
WO2022151839A1 (fr) Procédé et appareil de planification d'itinéraire de virage de véhicule
CN113741384A (zh) 检测自动驾驶系统的方法和装置
CN112829762A (zh) 一种车辆行驶速度生成方法以及相关设备
CN113022573A (zh) 道路结构检测方法及装置

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 21922490

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 21922490

Country of ref document: EP

Kind code of ref document: A1