CN110793784B - Test method and device for automatic driving vehicle, storage medium and electronic device - Google Patents
Test method and device for automatic driving vehicle, storage medium and electronic device Download PDFInfo
- Publication number
- CN110793784B CN110793784B CN201910872939.XA CN201910872939A CN110793784B CN 110793784 B CN110793784 B CN 110793784B CN 201910872939 A CN201910872939 A CN 201910872939A CN 110793784 B CN110793784 B CN 110793784B
- Authority
- CN
- China
- Prior art keywords
- virtual
- driving
- vehicle
- autonomous
- target
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- 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
- 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
Abstract
The invention discloses a test method and device for an automatic driving vehicle, a storage medium and an electronic device. Wherein, the method comprises the following steps: generating a virtual autonomous vehicle based on an autonomous driving algorithm and a vehicle dynamics model; adding the virtual automatic driving vehicle into a game scene of a pre-established game platform, wherein the game platform is used for supporting a plurality of player accounts to control the virtual manual driving vehicle in the game scene, and the virtual automatic driving vehicle is used as an interference vehicle or a background vehicle of the virtual manual driving vehicle; acquiring first automatic driving data of a virtual automatic driving vehicle in a game scene; it is determined whether there is a driving operation of the virtual autonomous vehicle that does not match the driving scenario according to the first autonomous driving data. The invention solves the technical problem of low efficiency of the automatic driving ability evaluation mode in the prior art.
Description
Technical Field
The invention relates to the field of computers, in particular to a method and a device for testing an automatic driving vehicle, a storage medium and an electronic device.
Background
With the gradual rise of automatic driving technologies, evaluation of automatic driving capabilities based on traffic flow simulation technologies is becoming increasingly important.
At present, road traffic data is mainly collected. And in the simulation platform, constructing a traffic flow model based on the labeled traffic data. And evaluating the running capability of the automatic driving vehicle by the established simulation system. However, a large amount of manpower and material resources are wasted for collecting road traffic data, and a large amount of time and a long period are often required for collecting actual road traffic data. In addition, under the actual traffic condition, most drivers obey the traffic rules, the driving behaviors are stable, a traffic scene with aggressive behaviors is difficult to construct based on the collected data, and the capability of the automatic driving vehicle for coping with the complex traffic scene is difficult to verify.
Aiming at the technical problem that the automatic driving capability evaluation mode in the prior art is low in efficiency in the related art, an effective solution is not provided at present.
Disclosure of Invention
The embodiment of the invention provides a method and a device for testing an automatic driving vehicle, a storage medium and an electronic device, which at least solve the technical problem of low efficiency of an automatic driving capability evaluation mode in the prior art.
According to an aspect of an embodiment of the present invention, there is provided a test method of an autonomous vehicle, including: generating a virtual autonomous vehicle based on an autonomous driving algorithm and a vehicle dynamics model; adding the virtual automatic driving vehicle into a game scene of a pre-built game platform, wherein the game platform is used for supporting a plurality of player accounts to control a virtual manual driving vehicle in the game scene, and the virtual automatic driving vehicle is used as an interference vehicle or a background vehicle of the virtual manual driving vehicle; obtaining first autopilot data of the virtual autopilot vehicle in the game scene; determining whether there is a driving operation of the virtual autonomous vehicle that does not match a driving scenario according to the first autonomous driving data.
Optionally, the method further comprises: in the pre-established game platform, acquiring manual driving data formed by the plurality of player accounts for controlling the virtual manual driving vehicle in the game scene; and generating a traffic flow model according to the manual driving data.
Optionally, the generating a traffic flow model according to the artificial driving data includes: acquiring first target manual driving data generated by the virtual manual driving vehicle running on a preset driving area from the manual driving data; when abnormal driving parameters exist in the driving parameters of the virtual manual driving vehicle indicated by the first target manual driving data, adjusting the abnormal driving parameters to be within a preset parameter range to obtain second target manual driving data, wherein the driving parameters comprise the driving speed and/or the driving track of the virtual manual driving vehicle; according to a target mapping relation between a game map in the game scene and a preset model map used for generating the traffic flow model, mapping a running track indicated by the second target artificial driving data to a target running track in the preset model map, mapping a starting position of the artificial driving vehicle in the game map to a target starting position in the model map, and determining a running speed indicated by the second target artificial driving data as a target running speed in the preset model map; and configuring the traffic flow model according to the target starting position, the target running speed and the target running track so that the simulated vehicles in the traffic flow model run along the target running track from the target starting position according to the target running speed in the preset model map.
Optionally, the method further comprises: in the pre-established game platform, acquiring manual driving data formed by the plurality of player accounts in the game scene through controlling the virtual manual driving vehicle, and first automatic driving data of the virtual automatic driving vehicle in the game scene; and generating a traffic flow model according to the manual driving data and the first automatic driving data.
Optionally, the generating a traffic flow model from the artificial driving data and the first automatic driving data comprises: according to a target mapping relationship between a game map in the game scene and a predetermined model map for generating the traffic flow model, mapping a first travel track indicated by the manual driving data to a first target travel track in the predetermined model map, mapping a second travel track indicated by first automatic driving data to a second target travel track in the predetermined model map, mapping a first start position of the virtual manual driving vehicle in the game map to a first target start position in the model map, mapping a second start position of the virtual automatic driving vehicle in the game map to a second target start position in the model map, determining a first travel speed indicated by the manual driving data as a first target travel speed in the predetermined model map, determining a second travel speed indicated by the first autopilot data as a second target travel speed in the predetermined model map; configuring the traffic flow model based on the first target start position, the first target travel speed, and the first target travel track, and the second target start position, the second target travel speed, and the second target travel track, such that a first simulated vehicle in the traffic flow model travels from the first target start position along the first target travel track at the first target travel speed in the predetermined model map, and a second simulated vehicle in the traffic flow model travels from the second target start position along the second target travel track at the second target travel speed in the predetermined model map.
Optionally, determining from the first autonomous driving data whether there is a driving operation of the virtual autonomous vehicle that does not match a driving scenario comprises at least one of: determining that a driving operation of the virtual autonomous vehicle does not match a driving scenario in an instance in which the first autonomous driving data indicates that the virtual autonomous vehicle has a collision event in the driving scenario; determining that a driving operation of the virtual autonomous vehicle does not match a driving scenario in a case where a preset destination is not included in a travel trajectory of the virtual autonomous vehicle indicated by the first autonomous driving data; determining that a driving operation of the virtual autonomous vehicle does not match a driving scenario when a travel speed of the virtual autonomous vehicle indicated by the first autonomous driving data is greater than a first preset speed and/or less than a second preset speed; determining that a driving operation of the virtual autonomous vehicle does not match a driving scenario in a case where the virtual autonomous vehicle indicated by the first autonomous driving data does not travel according to a travel parameter required by a predetermined identifier; determining that the driving operation of the virtual autonomous vehicle does not match the driving scenario when the virtual autonomous vehicle driving trajectory indicated by the first autonomous driving data does not travel along a route matching the real-time road condition in the game scenario.
Optionally, after determining that there is a driving operation of the virtual autonomous vehicle that does not match the driving scenario, the method further comprises: recording driving data of the virtual autonomous vehicle and the virtual human-driven vehicle during a collision event in the event that the first autonomous driving data indicates that the virtual autonomous vehicle has a collision event in the driving scenario; recording a travel trajectory of the virtual autonomous vehicle in a case where a preset destination is not included in the travel trajectory of the virtual autonomous vehicle indicated by the first autonomous driving data; recording the running speed of the virtual autonomous vehicle in the case that the running speed of the virtual autonomous vehicle indicated by the first autonomous driving data is greater than a first preset speed and/or less than a second preset speed; recording preset running parameters of the virtual autonomous vehicle when the virtual autonomous vehicle runs to a preset identifier under the condition that the virtual autonomous vehicle indicated by the first autonomous driving data does not run according to the running parameters required by the preset identifier; recording the driving track of the virtual automatic driving vehicle under the condition that the driving track of the virtual automatic driving vehicle indicated by the first automatic driving data does not drive according to a route matched with the real-time road condition in the game scene.
Optionally, after determining that there is a driving operation of the virtual autonomous vehicle that does not match the driving scenario, the method further comprises: in the event that the first autonomous driving data indicates that a collision event occurs in the driving scenario for the virtual autonomous vehicle, obtaining driving data for the virtual autonomous vehicle and the virtual manually driven vehicle during the collision event, and adjusting the autonomous driving algorithm according to the driving data so as to avoid the collision event; acquiring a running track of the virtual autonomous vehicle under the condition that a preset destination is not included in the running track of the virtual autonomous vehicle indicated by the first autonomous driving data, and adjusting the autonomous driving algorithm according to the running track of the virtual autonomous vehicle so that the preset destination is included in the running track of the virtual autonomous vehicle; acquiring the running speed of the virtual autonomous vehicle under the condition that the running speed of the virtual autonomous vehicle indicated by the first autonomous driving data is greater than a first preset speed and/or less than a second preset speed, and adjusting the autonomous driving algorithm according to the running speed of the virtual autonomous vehicle so that the running speed of the virtual autonomous vehicle is less than or equal to the first preset speed and greater than or equal to the second preset speed; when the virtual automatic driving vehicle indicated by the first automatic driving data does not run according to the running parameters required by the preset identification, acquiring preset running parameters of the virtual automatic driving vehicle when the virtual automatic driving vehicle runs to the preset identification, and adjusting the automatic driving algorithm according to the preset running parameters so that the virtual automatic driving vehicle runs according to the running parameters required by the preset identification; and under the condition that the running track of the virtual automatic driving vehicle indicated by the first automatic driving data does not run according to the route matched with the real-time road condition in the game scene, obtaining the running track of the virtual automatic driving vehicle, and adjusting the automatic driving algorithm according to the running track, so that the virtual automatic driving vehicle runs according to the route matched with the real-time road condition in the game scene.
According to another aspect of the embodiments of the present invention, there is also provided a test apparatus of an autonomous vehicle, including: a generation module for generating a virtual autonomous vehicle based on an autonomous driving algorithm and a vehicle dynamics model; the joining module is used for joining the virtual automatic driving vehicle into a game scene of a pre-built game platform, wherein the game platform is used for supporting a plurality of player accounts to control a virtual manual driving vehicle in the game scene, and the virtual automatic driving vehicle is used as an interference vehicle or a background vehicle of the virtual manual driving vehicle; a first obtaining module, configured to obtain first autopilot data of the virtual autopilot vehicle in the game scene; a determination module to determine whether a driving operation of the virtual autonomous vehicle exists that does not match a driving scenario according to the first autonomous driving data.
Optionally, the apparatus further comprises: the second acquisition module is used for acquiring manual driving data formed by the plurality of player accounts for controlling the virtual manual driving vehicle in the game scene in the pre-established game platform; and the generating module is used for generating a traffic flow model according to the manual driving data.
According to a further aspect of the embodiments of the present invention, there is also provided a computer-readable storage medium having a computer program stored therein, wherein the computer program is configured to execute the above-mentioned test method of an autonomous vehicle when running.
According to another aspect of the embodiments of the present invention, there is also provided an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor executes the above test method for an autonomous vehicle through the computer program.
In the embodiment of the invention, a virtual automatic driving vehicle generated based on an automatic driving algorithm and a vehicle dynamic model is added into a game scene of a pre-built game platform, first automatic driving data of the virtual automatic driving vehicle is obtained in the game scene, and whether the driving operation of the virtual automatic driving vehicle which is not matched with the driving scene exists is determined according to the first automatic driving data. And furthermore, the driving capacity of the virtual automatic driving vehicle is evaluated in a game scene, so that the technical problem of low efficiency of an automatic driving capacity evaluation mode in the prior art is solved. Therefore, the technical effects of saving manpower and material resources and improving the efficiency of evaluating the automatic driving capacity are achieved.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the invention and together with the description serve to explain the invention without limiting the invention. In the drawings:
FIG. 1 is a schematic illustration of an environment in which an alternative method of testing an autonomous vehicle may be used, according to an embodiment of the invention;
FIG. 2 is a flow chart of a method of testing an autonomous vehicle according to an embodiment of the invention;
FIG. 3 is a schematic illustration of an adjustment to an abnormal travel trajectory in accordance with an alternative embodiment of the present invention;
FIG. 4 is a schematic illustration of the adjustment of the trajectory of a virtual human-driven vehicle according to an alternative embodiment of the invention;
FIG. 5 is a schematic diagram of a cut-in scenario according to an alternative embodiment of the present invention;
FIG. 6 is a flow diagram of a game-based simulated traffic flow generation and autonomous vehicle evaluation scheme in accordance with an alternative embodiment of the present invention;
FIG. 7 is a flow diagram of another game-based simulated traffic flow generation and autonomous vehicle evaluation scheme in accordance with an alternative embodiment of the present invention;
fig. 8 is a block diagram of a test apparatus of an autonomous vehicle according to an embodiment of the present invention.
Detailed Description
In order to make the technical solutions of the present invention better understood, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. 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.
It should be noted that the terms "first," "second," and the like in the description and claims of the present invention and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the invention described herein are capable of operation in sequences other than those illustrated or described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
According to an aspect of an embodiment of the present invention, there is provided a method for testing an autonomous vehicle, optionally as an alternative implementation, the method for testing an autonomous vehicle may be applied, but not limited to, in an environment as shown in fig. 1.
Optionally, in this embodiment, the test method for the autonomous vehicle may be, but is not limited to, applied to the server 104, and is configured to determine whether there is a driving operation of the virtual autonomous vehicle that does not match the driving scenario according to first autonomous driving data of the virtual autonomous vehicle in the game scenario in the game platform built in advance. The pre-established game platform may be but is not limited to be run in the user equipment 102, and the user equipment 102 may be but is not limited to a mobile phone, a tablet computer, a notebook computer, a PC, and other terminal equipment supporting running of an application client. The server 104 and the user device 102 may, but are not limited to, enable data interaction via a network, which may include, but is not limited to, a wireless network or a wired network. Wherein, this wireless network includes: bluetooth, WIFI, and other networks that enable wireless communication. Such wired networks may include, but are not limited to: wide area networks, metropolitan area networks, and local area networks. The above is merely an example, and this is not limited in this embodiment.
Optionally, as an optional implementation manner, fig. 2 is a flowchart of a testing method of an autonomous vehicle according to an embodiment of the present invention, and as shown in fig. 2, the flowchart includes the following steps:
step S202, generating a virtual automatic driving vehicle based on an automatic driving algorithm and a vehicle dynamic model;
step S204, adding the virtual automatic driving vehicle into a game scene of a pre-established game platform, wherein the game platform is used for supporting a plurality of player accounts to control a virtual manual driving vehicle in the game scene, and the virtual automatic driving vehicle is used as an interference vehicle or a background vehicle of the virtual manual driving vehicle;
the pre-established game platform can be used for racing driving games of vehicles, and players can operate vehicles corresponding to accounts by registering the accounts in the game platform, wherein the virtual manual driving vehicle is an object controlled by the players, and the virtual automatic driving vehicle is a virtual automatic driving vehicle simulated in the game platform based on an automatic driving algorithm and a vehicle dynamics model. The virtual driving vehicle can be used as a background vehicle and an interference vehicle in a game scene, so that a highly intelligent interference effect is provided for a player, the game difficulty is improved, and the entertainment is increased.
Step S206, acquiring first automatic driving data of the virtual automatic driving vehicle in the game scene;
the virtual automatic driving vehicle is an automatic driving vehicle controlled by an automatic driving algorithm, the automatic driving algorithm can comprise a pattern recognition algorithm, an obstacle avoidance algorithm, a regression algorithm, a decision algorithm and the like, environmental data on a driving road can be sensed based on the pattern recognition algorithm, and for example, obstacles, road marks and driving conditions of other vehicles can be recognized through pattern recognition. The obstacle avoidance algorithm enables the automatic driving vehicle to automatically avoid the obstacle under the unmanned control condition. The regression algorithm may predict events using environmental data. Braking or steering of the vehicle is contingent and a decision algorithm can make decisions on events. The first autopilot data is data generated by a virtual autopilot vehicle traveling in a game scene and may include: the running speed, running track, etc. of the virtual autonomous vehicle.
Step S208, determining whether the driving operation of the virtual automatic driving vehicle which is not matched with the driving scene exists according to the first automatic driving data.
The driving operation which is not matched with the driving scene comprises the driving scene which can not be dealt with by the virtual driving vehicle and the driving scene which can not be dealt with reasonably. The irresponsible scenarios may include: the vehicle collision event occurs with the virtual manual driving vehicle, or the vehicle collision event occurs with other obstacles on the road, or the vehicle does not run according to the indication of the indication mark, or the vehicle runs with the line pressing and outgoing. Unreasonable coping scenarios include: the way of dealing with the scene is not the best way. For example, it is not reasonable to cope with the situation that a certain traveling vehicle is hidden, or it is not reasonable to cope with the situation that a virtual autonomous vehicle travels from a start position to an end position including a plurality of travel routes and travels from the start position to the end position without following the optimal travel route.
Through the steps, the virtual automatic driving vehicle generated based on the automatic driving algorithm and the vehicle dynamics model is added into a game scene of a pre-built game platform, first automatic driving data of the virtual automatic driving vehicle are obtained in the game scene, and whether the driving operation of the virtual automatic driving vehicle which is not matched with the driving scene exists is determined according to the first automatic driving data. And furthermore, the driving capacity of the virtual automatic driving vehicle is evaluated in a game scene, so that the technical problem of low efficiency of an automatic driving capacity evaluation mode in the prior art is solved. Therefore, the technical effects of saving manpower and material resources and improving the efficiency of evaluating the automatic driving capacity are achieved.
In an alternative embodiment, the method further comprises: in the pre-established game platform, acquiring manual driving data formed by the plurality of player accounts for controlling the virtual manual driving vehicle in the game scene; and generating a traffic flow model according to the manual driving data. In this embodiment, various driving roads can be set in the game platform, the start point and the stop point of the virtual manually-driven vehicle driven by each game player are set, and manual driving data formed by each game player operating the virtual manually-driven vehicle is collected, so that a simulated vehicle with subjective controllability of the driver is constructed based on a large number of virtual manually-driven vehicles operated by the game players. Further, a traffic flow model may be generated from human driving data generated from a large number of virtual human driven vehicles operated by game players.
In an alternative embodiment, the generating a traffic flow model from the artificial driving data comprises: acquiring first target manual driving data generated by the virtual manual driving vehicle running on a preset driving area from the manual driving data; when abnormal driving parameters exist in the driving parameters of the virtual manual driving vehicle indicated by the first target manual driving data, adjusting the abnormal driving parameters to be within a preset parameter range to obtain second target manual driving data, wherein the driving parameters comprise the driving speed and/or the driving track of the virtual manual driving vehicle; according to a target mapping relation between a game map in the game scene and a preset model map used for generating the traffic flow model, mapping a running track indicated by the second target artificial driving data to a target running track in the preset model map, mapping a starting position of the artificial driving vehicle in the game map to a target starting position in the model map, and determining a running speed indicated by the second target artificial driving data as a target running speed in the preset model map; and configuring the traffic flow model according to the target starting position, the target running speed and the target running track so that the simulated vehicles in the traffic flow model run along the target running track from the target starting position according to the target running speed in the preset model map. In this embodiment, since there may be some situations deviating from the real traffic road scene in the game scene, for example, some players are in an on-hook state, or some players have an operation error, which causes the virtual driving vehicle operated by some players to run out of the driving road, in this case, it is necessary to filter the manual driving data generated by the virtual driving vehicle operated by the players, remove the data of the running-out driving road, and keep the first target manual driving data generated by the driving on the driving road. However, the game scene is different from the real scene, for example, for the game effect, the driving speed of the vehicle is often high in the game scene, and the vehicle turns a curve at a larger angle and even drifts. However, in real-world scenarios this does not occur. Therefore, the first target manual driving data screened in the game scene needs to be preprocessed. For example, for a virtual manually-driven vehicle whose traveling speed is high or low in a game scene, the speed thereof is adjusted to be within a traveling speed range that matches the actual situation. Or, for a larger curve or a drift, the driving track is adjusted to be in accordance with the actual scene. For example, as shown in fig. 3, which is a schematic diagram illustrating an abnormal travel track being adjusted according to an alternative embodiment of the present invention, in fig. 3, if a first vehicle is about to overtake a previous vehicle, the overtake operation may be performed according to the travel track indicated by an arrow in a game scene, while in a real scene, the travel track needs to be completed in a short time, the speed of the first vehicle needs to be fast, and such a aggressive travel track is difficult to occur in the real scene, so for such a situation, the travel track needs to be adjusted to a relatively slow travel track as shown in fig. 4. For another example, in fig. 3, when the second vehicle makes a right turn, it is usually possible to realize a drift in a game scene, but it is not allowed in a real traffic scene, and therefore, a deceleration process is required for these manual driving data, so that the virtual manual driving vehicle travels in conformity with the real scene. In this embodiment, the map in the traffic flow model is a map corresponding to an actual traffic scene, the map in the game scene and the map in the traffic flow model satisfy a corresponding mapping relationship, and the map in the game scene may be a map transformed according to the actual traffic scene, for example, a road in the actual scene may be shortened and mapped to the game scene, or a predetermined number of curves may be added to the traffic scene in the actual scene and mapped to the game scene, or a complexity of the curves in the actual scene may be added and mapped to the game scene. According to the mapping relation, the running track and the running speed of the virtual manually-driven vehicle in the game scene and the initial position in the game map are mapped to the traffic flow model, so that the traffic flow which accords with the actual traffic scene is constructed in the traffic flow model. Because the driving behavior of the simulated vehicle in the traffic flow model is more consistent with the real traffic scene, a simulation platform can be constructed based on the traffic flow model, and the driving capability of the automatic driving vehicle can be further evaluated in the simulation platform.
In an alternative embodiment, the method further comprises: in the pre-established game platform, acquiring manual driving data formed by the plurality of player accounts in the game scene through controlling the virtual manual driving vehicle, and first automatic driving data of the virtual automatic driving vehicle in the game scene; and generating a traffic flow model according to the manual driving data and the first automatic driving data. In this embodiment, a traffic flow model may be further constructed according to virtual manually driven vehicles and virtual automatically driven vehicles in a game scene, and for automatically driven vehicles included in the traffic flow model as well as manually driven vehicles, the model may be used to evaluate the driving capabilities of other automatically driven vehicles.
In an alternative embodiment, the generating a traffic flow model from the artificial driving data and the first autonomous driving data comprises: according to a target mapping relationship between a game map in the game scene and a predetermined model map for generating the traffic flow model, mapping a first travel track indicated by the manual driving data to a first target travel track in the predetermined model map, mapping a second travel track indicated by first automatic driving data to a second target travel track in the predetermined model map, mapping a first start position of the virtual manual driving vehicle in the game map to a first target start position in the model map, mapping a second start position of the virtual automatic driving vehicle in the game map to a second target start position in the model map, determining a first travel speed indicated by the manual driving data as a first target travel speed in the predetermined model map, determining a second travel speed indicated by the first autopilot data as a second target travel speed in the predetermined model map; configuring the traffic flow model based on the first target start position, the first target travel speed, and the first target travel track, and the second target start position, the second target travel speed, and the second target travel track, such that a first simulated vehicle in the traffic flow model travels from the first target start position along the first target travel track at the first target travel speed in the predetermined model map, and a second simulated vehicle in the traffic flow model travels from the second target start position along the second target travel track at the second target travel speed in the predetermined model map. In this embodiment, the map in the game scene and the map in the traffic flow model satisfy a corresponding mapping relationship, and the initial positions, the travel tracks, and the travel speeds of the virtual manually-driven vehicles and the virtual automatically-driven vehicles in the game scene in the map in the traffic flow model are mapped according to the mapping relationship. So that a traffic flow comprised of virtual manually driven vehicles and virtual automatically driven vehicles in the game scene is mapped into the traffic flow model, a first simulated vehicle in the traffic flow model corresponding to a virtual manually driven vehicle in the game scene and a second simulated vehicle corresponding to a virtual automatically driven vehicle in the game scene. The driving parameters of the first simulated vehicle and the second simulated vehicle in the traffic flow model can be screened or adjusted according to actual conditions, for example, the driving parameters of the first simulated vehicle and the second simulated vehicle which accord with actual traffic scenes are screened from the traffic flow model, and adaptive adjustment is performed on the driving speed and/or the driving track.
In an alternative embodiment, determining whether there is a driving operation of the virtual autonomous vehicle that does not match a driving scenario from the first autonomous driving data comprises at least one of: determining that a driving operation of the virtual autonomous vehicle does not match a driving scenario in an instance in which the first autonomous driving data indicates that the virtual autonomous vehicle has a collision event in the driving scenario; determining that a driving operation of the virtual autonomous vehicle does not match a driving scenario in a case where a preset destination is not included in a travel trajectory of the virtual autonomous vehicle indicated by the first autonomous driving data; determining that a driving operation of the virtual autonomous vehicle does not match a driving scenario when a travel speed of the virtual autonomous vehicle indicated by the first autonomous driving data is greater than a first preset speed and/or less than a second preset speed; determining that a driving operation of the virtual autonomous vehicle does not match a driving scenario in a case where the virtual autonomous vehicle indicated by the first autonomous driving data does not travel according to a travel parameter required by a predetermined identifier; determining that the driving operation of the virtual autonomous vehicle does not match the driving scenario when the virtual autonomous vehicle driving trajectory indicated by the first autonomous driving data does not travel along a route matching the real-time road condition in the game scenario. In the present embodiment, the driving operation of the virtual autonomous vehicle that does not match the driving scene includes: the virtual autonomous vehicle can not cope with traffic scenarios and cope with unreasonable traffic scenarios. Among them, the ones that can't deal with include: the collision event, the speed is too fast or too slow, the destination is not reached, the vehicle does not run according to the traffic sign, and the like, and the collision event comprises the following steps: a collision, or collision with other structures in the road, not following a traffic sign, comprising: not traveling in the manner indicated by the traffic lights, not traveling at the travel speed indicated by the traffic signs, etc. Unreasonable coping scenarios include: in the driving process, a plurality of selectable driving modes are included, and the driving mode which is most matched with the current traffic scene is not selected. For example, the driving scheme from the starting position a to the destination B includes 3 schemes, wherein the driving route of the scheme 1 is the shortest, and the road condition is the best compared with the other two schemes, namely the best driving scheme among the three schemes. The driving mode of the virtual automatic driving vehicle is not scheme 1, but scheme 2 or scheme 3, and the virtual automatic driving vehicle can not cope with unreasonable scenes for the traffic scene. For another example, as shown in fig. 5, a schematic diagram of a passing scenario according to an alternative embodiment of the present invention is shown, in which a first vehicle needs to pass through a traffic scenario for which an optimal passing scenario is to travel to the right lane as shown in fig. 5, and for which an unreasonable scenario is to be dealt with if the first vehicle selects another travel manner, such as the manner indicated in fig. 5 to travel in the left lane direction.
In one optional embodiment, after determining that there is a driving operation of the virtual autonomous vehicle that does not match the driving scenario, the method further comprises: recording driving data of the virtual autonomous vehicle and the virtual human-driven vehicle during a collision event in the event that the first autonomous driving data indicates that the virtual autonomous vehicle has a collision event in the driving scenario; recording a travel trajectory of the virtual autonomous vehicle in a case where a preset destination is not included in the travel trajectory of the virtual autonomous vehicle indicated by the first autonomous driving data; recording the running speed of the virtual autonomous vehicle in the case that the running speed of the virtual autonomous vehicle indicated by the first autonomous driving data is greater than a first preset speed and/or less than a second preset speed; recording preset running parameters of the virtual autonomous vehicle when the virtual autonomous vehicle runs to a preset identifier under the condition that the virtual autonomous vehicle indicated by the first autonomous driving data does not run according to the running parameters required by the preset identifier; recording the driving track of the virtual automatic driving vehicle under the condition that the driving track of the virtual automatic driving vehicle indicated by the first automatic driving data does not drive according to a route matched with the real-time road condition in the game scene. In the embodiment, after determining that there is a driving operation of the virtual autonomous vehicle that does not match the driving scene, it is necessary to record the traffic scene that the virtual autonomous vehicle cannot or cannot cope with unreasonable, and the coping style of such traffic scene, so as to subsequently optimize the autonomous driving algorithm, so that the optimized algorithm can cope with such traffic scene in an optimal driving style.
In one optional embodiment, after determining that there is a driving operation of the virtual autonomous vehicle that does not match the driving scenario, the method further comprises: in the event that the first autonomous driving data indicates that a collision event occurs in the driving scenario for the virtual autonomous vehicle, obtaining driving data for the virtual autonomous vehicle and the virtual manually driven vehicle during the collision event, and adjusting the autonomous driving algorithm according to the driving data so as to avoid the collision event; acquiring a running track of the virtual autonomous vehicle under the condition that a preset destination is not included in the running track of the virtual autonomous vehicle indicated by the first autonomous driving data, and adjusting the autonomous driving algorithm according to the running track of the virtual autonomous vehicle so that the preset destination is included in the running track of the virtual autonomous vehicle; acquiring the running speed of the virtual autonomous vehicle under the condition that the running speed of the virtual autonomous vehicle indicated by the first autonomous driving data is greater than a first preset speed and/or less than a second preset speed, and adjusting the autonomous driving algorithm according to the running speed of the virtual autonomous vehicle so that the running speed of the virtual autonomous vehicle is less than or equal to the first preset speed and greater than or equal to the second preset speed; when the virtual automatic driving vehicle indicated by the first automatic driving data does not run according to the running parameters required by the preset identification, acquiring preset running parameters of the virtual automatic driving vehicle when the virtual automatic driving vehicle runs to the preset identification, and adjusting the automatic driving algorithm according to the preset running parameters so that the virtual automatic driving vehicle runs according to the running parameters required by the preset identification; and under the condition that the running track of the virtual automatic driving vehicle indicated by the first automatic driving data does not run according to the route matched with the real-time road condition in the game scene, obtaining the running track of the virtual automatic driving vehicle, and adjusting the automatic driving algorithm according to the running track, so that the virtual automatic driving vehicle runs according to the route matched with the real-time road condition in the game scene.
The present application is illustrated by the following specific examples
FIG. 6 is a flow chart of a game-based simulated traffic flow generation and autonomous vehicle assessment scheme according to an alternative embodiment of the present invention, wherein the steps are as follows:
step 1: generating a virtual autonomous vehicle; specifically, a virtual automatic driving vehicle with automatic driving capability is generated based on an automatic driving algorithm and a vehicle dynamics model;
step 2: adding the virtual automatic driving vehicle into a pre-established game platform;
specifically, a game platform is built based on technologies such as a three-dimensional reconstruction technology, a vehicle dynamics model and three-dimensional rendering, and the virtual automatic driving vehicle is randomly added into a game scene of the game platform to serve as an interference vehicle or a background vehicle of a player.
And step 3: and evaluating the driving capability of the virtual driving vehicle based on the game platform.
And 4, step 4: and updating the automatic driving algorithm. Specifically, the automatic driving algorithm is adjusted according to the evaluation result of the driving ability of the virtual driving vehicle at the game platform. And generating a virtual automatic driving vehicle based on the updated automatic driving algorithm, adding the virtual automatic driving vehicle to the game platform again, and evaluating the updated automatic driving algorithm.
And 5: collecting and processing information of a game player operating a virtual man-driven vehicle;
step 6: and generating a traffic flow model. Specifically, a map in the game scene is mapped to a map in the traffic flow model, and driving parameters such as a driving track and a driving speed of the virtual manually-driven vehicle in the game scene are mapped to the traffic flow model.
And 7: evaluating an automatic driving algorithm of the simulated vehicle based on the traffic flow model; specifically, the automatic driving capability of a simulated vehicle generated based on an automatic driving algorithm is evaluated through a traffic flow model;
and 8: and updating the automatic driving algorithm based on the evaluation result of the traffic flow model on the automatic driving capability. And generating a virtual automatic driving vehicle based on the updated automatic driving algorithm, and rejoining the virtual automatic driving vehicle to the game platform.
Fig. 7 is a flow chart illustrating another game-based simulated traffic flow generation and autonomous vehicle evaluation scheme according to an alternative embodiment of the present invention, which differs from the flow chart illustrated in fig. 6 in that in this embodiment, a traffic flow model is generated based on manual driving data of a player manipulating a virtual manual vehicle and autonomous driving data of the virtual autonomous vehicle. That is to say, in the traffic flow model in this embodiment, simulated vehicles corresponding to the virtual manually-driven vehicles and the virtual automatically-driven vehicles are included, and through such a continuous iteration manner, data in the traffic flow model can be increased, and the automatic driving algorithm can be evaluated through a more complicated traffic scene.
It should be noted that, for simplicity of description, the above-mentioned method embodiments are described as a series of acts or combination of acts, but those skilled in the art will recognize that the present invention is not limited by the order of acts, as some steps may occur in other orders or concurrently in accordance with the invention. Further, those skilled in the art should also appreciate that the embodiments described in the specification are preferred embodiments and that the acts and modules referred to are not necessarily required by the invention.
According to another aspect of the embodiment of the present invention, there is also provided a test apparatus for an autonomous vehicle for implementing the test method for an autonomous vehicle described above. Fig. 8 is a block diagram showing a configuration of a test apparatus for an autonomous vehicle according to an embodiment of the present invention, the apparatus including: a generation module 82 for generating a virtual autonomous vehicle based on an autonomous driving algorithm and a vehicle dynamics model; a joining module 84, configured to join the virtual autonomous driving vehicle into a game scene of a pre-established game platform, where the game platform is configured to support a plurality of player accounts to control a virtual manually-driven vehicle in the game scene, and the virtual autonomous driving vehicle is used as an interfering vehicle or a background vehicle of the virtual manually-driven vehicle; a first obtaining module 86, configured to obtain first autopilot data of the virtual autopilot vehicle in the game scenario; a determination module 88 for determining whether there is a driving operation of the virtual autonomous vehicle that does not match a driving scenario according to the first autonomous driving data.
In an alternative embodiment, the apparatus further comprises: the second acquisition module is used for acquiring manual driving data formed by the plurality of player accounts for controlling the virtual manual driving vehicle in the game scene in the pre-established game platform; and the generating module is used for generating a traffic flow model according to the manual driving data.
In an optional embodiment, the generating module is further configured to obtain, in the manual driving data, first target manual driving data generated by the virtual manual driving vehicle traveling on a predetermined driving area; when abnormal driving parameters exist in the driving parameters of the virtual manual driving vehicle indicated by the first target manual driving data, adjusting the abnormal driving parameters to be within a preset parameter range to obtain second target manual driving data, wherein the driving parameters comprise the driving speed and/or the driving track of the virtual manual driving vehicle; according to a target mapping relation between a game map in the game scene and a preset model map used for generating the traffic flow model, mapping a running track indicated by the second target artificial driving data to a target running track in the preset model map, mapping a starting position of the artificial driving vehicle in the game map to a target starting position in the model map, and determining a running speed indicated by the second target artificial driving data as a target running speed in the preset model map; and configuring the traffic flow model according to the target starting position, the target running speed and the target running track so that the simulated vehicles in the traffic flow model run along the target running track from the target starting position according to the target running speed in the preset model map.
In an optional embodiment, the device is further configured to, in the pre-established game platform, acquire manual driving data formed by the plurality of player accounts operating the virtual manual driving vehicle in the game scene, and first automatic driving data of the virtual automatic driving vehicle in the game scene; and generating a traffic flow model according to the manual driving data and the first automatic driving data.
In an alternative embodiment, the above apparatus is further configured to map a first travel trajectory indicated by the manual driving data to a first target travel trajectory in a predetermined model map used for generating the traffic flow model, map a second travel trajectory indicated by first automated driving data to a second target travel trajectory in the predetermined model map, map a first start position of the virtual manual driving vehicle in the game map to a first target start position in the model map, map a second start position of the virtual automatic driving vehicle in the game map to a second target start position in the model map, determine a first travel speed indicated by the manual driving data as a first target travel speed in the predetermined model map, determining a second travel speed indicated by the first autopilot data as a second target travel speed in the predetermined model map; configuring the traffic flow model based on the first target start position, the first target travel speed, and the first target travel track, and the second target start position, the second target travel speed, and the second target travel track, such that a first simulated vehicle in the traffic flow model travels from the first target start position along the first target travel track at the first target travel speed in the predetermined model map, and a second simulated vehicle in the traffic flow model travels from the second target start position along the second target travel track at the second target travel speed in the predetermined model map.
In an alternative embodiment, the determining module is further configured to determine that the driving operation of the virtual autonomous vehicle does not match the driving scenario in the event that the first autonomous vehicle indicates a collision event of the virtual autonomous vehicle in the driving scenario; determining that a driving operation of the virtual autonomous vehicle does not match a driving scenario in a case where a preset destination is not included in a travel trajectory of the virtual autonomous vehicle indicated by the first autonomous driving data; determining that a driving operation of the virtual autonomous vehicle does not match a driving scenario when a travel speed of the virtual autonomous vehicle indicated by the first autonomous driving data is greater than a first preset speed and/or less than a second preset speed; determining that a driving operation of the virtual autonomous vehicle does not match a driving scenario in a case where the virtual autonomous vehicle indicated by the first autonomous driving data does not travel according to a travel parameter required by a predetermined identifier; determining that the driving operation of the virtual autonomous vehicle does not match the driving scenario when the virtual autonomous vehicle driving trajectory indicated by the first autonomous driving data does not travel along a route matching the real-time road condition in the game scenario.
In an alternative embodiment, the apparatus is further configured to, after determining that there is a driving operation of the virtual autonomous vehicle that does not match a driving scenario, record driving data of the virtual autonomous vehicle and the virtual human-driven vehicle during a collision event in the event that the first autonomous driving data indicates that the virtual autonomous vehicle has a collision event in the driving scenario; recording a travel trajectory of the virtual autonomous vehicle in a case where a preset destination is not included in the travel trajectory of the virtual autonomous vehicle indicated by the first autonomous driving data; recording the running speed of the virtual autonomous vehicle in the case that the running speed of the virtual autonomous vehicle indicated by the first autonomous driving data is greater than a first preset speed and/or less than a second preset speed; recording preset running parameters of the virtual autonomous vehicle when the virtual autonomous vehicle runs to a preset identifier under the condition that the virtual autonomous vehicle indicated by the first autonomous driving data does not run according to the running parameters required by the preset identifier; recording the driving track of the virtual automatic driving vehicle under the condition that the driving track of the virtual automatic driving vehicle indicated by the first automatic driving data does not drive according to a route matched with the real-time road condition in the game scene.
In an alternative embodiment, the above apparatus is further configured to, after determining that there is a driving operation of the virtual autonomous vehicle that does not match a driving scenario, in a case where the first autonomous driving data indicates that a collision event occurs with the virtual autonomous vehicle in the driving scenario, acquire driving data of the virtual autonomous vehicle and the virtual human-driven vehicle during the collision event, and adjust the autonomous driving algorithm according to the driving data such that the collision event is avoided; acquiring a running track of the virtual autonomous vehicle under the condition that a preset destination is not included in the running track of the virtual autonomous vehicle indicated by the first autonomous driving data, and adjusting the autonomous driving algorithm according to the running track of the virtual autonomous vehicle so that the preset destination is included in the running track of the virtual autonomous vehicle; acquiring the running speed of the virtual autonomous vehicle under the condition that the running speed of the virtual autonomous vehicle indicated by the first autonomous driving data is greater than a first preset speed and/or less than a second preset speed, and adjusting the autonomous driving algorithm according to the running speed of the virtual autonomous vehicle so that the running speed of the virtual autonomous vehicle is less than or equal to the first preset speed and greater than or equal to the second preset speed; when the virtual automatic driving vehicle indicated by the first automatic driving data does not run according to the running parameters required by the preset identification, acquiring preset running parameters of the virtual automatic driving vehicle when the virtual automatic driving vehicle runs to the preset identification, and adjusting the automatic driving algorithm according to the preset running parameters so that the virtual automatic driving vehicle runs according to the running parameters required by the preset identification; and under the condition that the running track of the virtual automatic driving vehicle indicated by the first automatic driving data does not run according to the route matched with the real-time road condition in the game scene, obtaining the running track of the virtual automatic driving vehicle, and adjusting the automatic driving algorithm according to the running track, so that the virtual automatic driving vehicle runs according to the route matched with the real-time road condition in the game scene.
It should be noted that, the above modules may be implemented by software or hardware, and for the latter, the following may be implemented, but not limited to: the modules are all positioned in the same processor; alternatively, the modules are respectively located in different processors in any combination.
Embodiments of the present invention also provide a storage medium having a computer program stored therein, wherein the computer program is arranged to perform the steps of any of the above method embodiments when executed.
Alternatively, in the present embodiment, the storage medium may be configured to store a computer program for executing the steps of:
s1, generating a virtual automatic driving vehicle based on an automatic driving algorithm and a vehicle dynamic model;
s2, adding the virtual automatic driving vehicle into a game scene of a pre-built game platform, wherein the game platform is used for supporting a plurality of player accounts to control a virtual manual driving vehicle in the game scene, and the virtual automatic driving vehicle is used as an interference vehicle or a background vehicle of the virtual manual driving vehicle;
s3, acquiring first automatic driving data of the virtual automatic driving vehicle in the game scene;
s4, determining whether the driving operation of the virtual automatic driving vehicle which is not matched with the driving scene exists according to the first automatic driving data.
Optionally, in this embodiment, the storage medium may include, but is not limited to: various media capable of storing computer programs, such as a usb disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a removable hard disk, a magnetic disk, or an optical disk.
Embodiments of the present invention also provide an electronic device comprising a memory having a computer program stored therein and a processor arranged to run the computer program to perform the steps of any of the above method embodiments.
Optionally, the electronic apparatus may further include a transmission device and an input/output device, wherein the transmission device is connected to the processor, and the input/output device is connected to the processor.
Optionally, in this embodiment, the processor may be configured to execute the following steps by a computer program:
s1, generating a virtual automatic driving vehicle based on an automatic driving algorithm and a vehicle dynamic model;
s2, adding the virtual automatic driving vehicle into a game scene of a pre-built game platform, wherein the game platform is used for supporting a plurality of player accounts to control a virtual manual driving vehicle in the game scene, and the virtual automatic driving vehicle is used as an interference vehicle or a background vehicle of the virtual manual driving vehicle;
s3, acquiring first automatic driving data of the virtual automatic driving vehicle in the game scene;
s4, determining whether the driving operation of the virtual automatic driving vehicle which is not matched with the driving scene exists according to the first automatic driving data.
Optionally, the specific examples in this embodiment may refer to the examples described in the above embodiments and optional implementation manners, and this embodiment is not described herein again.
It will be apparent to those skilled in the art that the modules or steps of the present invention described above may be implemented by a general purpose computing device, they may be centralized on a single computing device or distributed across a network of multiple computing devices, and alternatively, they may be implemented by program code executable by a computing device, such that they may be stored in a storage device and executed by a computing device, and in some cases, the steps shown or described may be performed in an order different than that described herein, or they may be separately fabricated into individual integrated circuit modules, or multiple ones of them may be fabricated into a single integrated circuit module. Thus, the present invention is not limited to any specific combination of hardware and software.
The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, or improvement made within the principle of the present invention should be included in the protection scope of the present invention.
Claims (8)
1. A method of testing an autonomous vehicle, comprising:
generating a virtual autonomous vehicle based on an autonomous driving algorithm and a vehicle dynamics model;
adding the virtual automatic driving vehicle into a game scene of a pre-built game platform, wherein the game platform is used for supporting a plurality of player accounts to control a virtual manual driving vehicle in the game scene, and the virtual automatic driving vehicle is used as an interference vehicle or a background vehicle of the virtual manual driving vehicle;
obtaining first autopilot data of the virtual autopilot vehicle in the game scene;
determining whether there is a driving operation of the virtual autonomous vehicle that does not match a driving scenario according to the first autonomous driving data;
the method further comprises the following steps:
in the pre-established game platform, acquiring manual driving data formed by the plurality of player accounts for controlling the virtual manual driving vehicle in the game scene;
and generating a traffic flow model according to the manual driving data.
2. The method of claim 1, wherein generating a traffic flow model from the artificial driving data comprises:
acquiring first target manual driving data generated by the virtual manual driving vehicle running on a preset driving area from the manual driving data;
when abnormal driving parameters exist in the driving parameters of the virtual manual driving vehicle indicated by the first target manual driving data, adjusting the abnormal driving parameters to be within a preset parameter range to obtain second target manual driving data, wherein the driving parameters comprise the driving speed and/or the driving track of the virtual manual driving vehicle;
according to a target mapping relation between a game map in the game scene and a preset model map used for generating the traffic flow model, mapping a running track indicated by the second target artificial driving data to a target running track in the preset model map, mapping a starting position of the artificial driving vehicle in the game map to a target starting position in the model map, and determining a running speed indicated by the second target artificial driving data as a target running speed in the preset model map;
and configuring the traffic flow model according to the target starting position, the target running speed and the target running track so that the simulated vehicles in the traffic flow model run along the target running track from the target starting position according to the target running speed in the preset model map.
3. The method of claim 1, further comprising:
in the pre-established game platform, acquiring manual driving data formed by the plurality of player accounts in the game scene through controlling the virtual manual driving vehicle, and first automatic driving data of the virtual automatic driving vehicle in the game scene;
and generating a traffic flow model according to the manual driving data and the first automatic driving data.
4. The method of claim 3, wherein generating a traffic flow model from the artificial driving data and the first autonomous driving data comprises:
according to a target mapping relationship between a game map in the game scene and a predetermined model map for generating the traffic flow model, mapping a first travel track indicated by the manual driving data to a first target travel track in the predetermined model map, mapping a second travel track indicated by first automatic driving data to a second target travel track in the predetermined model map, mapping a first start position of the virtual manual driving vehicle in the game map to a first target start position in the model map, mapping a second start position of the virtual automatic driving vehicle in the game map to a second target start position in the model map, determining a first travel speed indicated by the manual driving data as a first target travel speed in the predetermined model map, determining a second travel speed indicated by the first autopilot data as a second target travel speed in the predetermined model map;
configuring the traffic flow model based on the first target start position, the first target travel speed, and the first target travel track, and the second target start position, the second target travel speed, and the second target travel track, such that a first simulated vehicle in the traffic flow model travels from the first target start position along the first target travel track at the first target travel speed in the predetermined model map, and a second simulated vehicle in the traffic flow model travels from the second target start position along the second target travel track at the second target travel speed in the predetermined model map.
5. The method of any of claims 1-4, wherein determining whether there is a driving operation of the virtual autonomous vehicle that does not match a driving scenario from the first autonomous driving data comprises at least one of:
determining that a driving operation of the virtual autonomous vehicle does not match a driving scenario in an instance in which the first autonomous driving data indicates that the virtual autonomous vehicle has a collision event in the driving scenario;
determining that a driving operation of the virtual autonomous vehicle does not match a driving scenario in a case where a preset destination is not included in a travel trajectory of the virtual autonomous vehicle indicated by the first autonomous driving data;
determining that a driving operation of the virtual autonomous vehicle does not match a driving scenario when a travel speed of the virtual autonomous vehicle indicated by the first autonomous driving data is greater than a first preset speed and/or less than a second preset speed;
determining that a driving operation of the virtual autonomous vehicle does not match a driving scenario in a case where the virtual autonomous vehicle indicated by the first autonomous driving data does not travel according to a travel parameter required by a predetermined identifier;
determining that the driving operation of the virtual autonomous vehicle does not match the driving scenario when the virtual autonomous vehicle driving trajectory indicated by the first autonomous driving data does not travel along a route matching the real-time road condition in the game scenario.
6. The method of claim 5, wherein after determining that there is a driving operation of the virtual autonomous vehicle that does not match a driving scenario, the method further comprises:
recording driving data of the virtual autonomous vehicle and the virtual human-driven vehicle during a collision event in the event that the first autonomous driving data indicates that the virtual autonomous vehicle has a collision event in the driving scenario;
recording a travel trajectory of the virtual autonomous vehicle in a case where a preset destination is not included in the travel trajectory of the virtual autonomous vehicle indicated by the first autonomous driving data;
recording the running speed of the virtual autonomous vehicle in the case that the running speed of the virtual autonomous vehicle indicated by the first autonomous driving data is greater than a first preset speed and/or less than a second preset speed;
recording preset running parameters of the virtual autonomous vehicle when the virtual autonomous vehicle runs to a preset identifier under the condition that the virtual autonomous vehicle indicated by the first autonomous driving data does not run according to the running parameters required by the preset identifier;
recording the driving track of the virtual automatic driving vehicle under the condition that the driving track of the virtual automatic driving vehicle indicated by the first automatic driving data does not drive according to a route matched with the real-time road condition in the game scene.
7. The method of claim 6, wherein after determining that there is a driving operation of the virtual autonomous vehicle that does not match a driving scenario, the method further comprises:
in the event that the first autonomous driving data indicates that a collision event occurs in the driving scenario for the virtual autonomous vehicle, obtaining driving data for the virtual autonomous vehicle and the virtual manually driven vehicle during the collision event, and adjusting the autonomous driving algorithm according to the driving data so as to avoid the collision event;
acquiring a running track of the virtual autonomous vehicle under the condition that a preset destination is not included in the running track of the virtual autonomous vehicle indicated by the first autonomous driving data, and adjusting the autonomous driving algorithm according to the running track of the virtual autonomous vehicle so that the preset destination is included in the running track of the virtual autonomous vehicle;
acquiring the running speed of the virtual autonomous vehicle under the condition that the running speed of the virtual autonomous vehicle indicated by the first autonomous driving data is greater than a first preset speed and/or less than a second preset speed, and adjusting the autonomous driving algorithm according to the running speed of the virtual autonomous vehicle so that the running speed of the virtual autonomous vehicle is less than or equal to the first preset speed and greater than or equal to the second preset speed;
when the virtual automatic driving vehicle indicated by the first automatic driving data does not run according to the running parameters required by the preset identification, acquiring preset running parameters of the virtual automatic driving vehicle when the virtual automatic driving vehicle runs to the preset identification, and adjusting the automatic driving algorithm according to the preset running parameters so that the virtual automatic driving vehicle runs according to the running parameters required by the preset identification;
and under the condition that the running track of the virtual automatic driving vehicle indicated by the first automatic driving data does not run according to the route matched with the real-time road condition in the game scene, obtaining the running track of the virtual automatic driving vehicle, and adjusting the automatic driving algorithm according to the running track, so that the virtual automatic driving vehicle runs according to the route matched with the real-time road condition in the game scene.
8. A test apparatus for an autonomous vehicle, comprising:
a generation module for generating a virtual autonomous vehicle based on an autonomous driving algorithm and a vehicle dynamics model;
the joining module is used for joining the virtual automatic driving vehicle into a game scene of a pre-built game platform, wherein the game platform is used for supporting a plurality of player accounts to control a virtual manual driving vehicle in the game scene, and the virtual automatic driving vehicle is used as an interference vehicle or a background vehicle of the virtual manual driving vehicle;
a first obtaining module, configured to obtain first autopilot data of the virtual autopilot vehicle in the game scene;
a determination module to determine whether a driving operation of the virtual autonomous vehicle does not match a driving scenario exists according to the first autonomous driving data;
the device further comprises:
the second acquisition module is used for acquiring manual driving data formed by the plurality of player accounts for controlling the virtual manual driving vehicle in the game scene in the pre-established game platform;
and the generating module is used for generating a traffic flow model according to the manual driving data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910872939.XA CN110793784B (en) | 2019-09-16 | 2019-09-16 | Test method and device for automatic driving vehicle, storage medium and electronic device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910872939.XA CN110793784B (en) | 2019-09-16 | 2019-09-16 | Test method and device for automatic driving vehicle, storage medium and electronic device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110793784A CN110793784A (en) | 2020-02-14 |
| CN110793784B true CN110793784B (en) | 2021-10-26 |
Family
ID=69427205
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910872939.XA Active CN110793784B (en) | 2019-09-16 | 2019-09-16 | Test method and device for automatic driving vehicle, storage medium and electronic device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110793784B (en) |
Families Citing this family (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2021232229A1 (en) * | 2020-05-19 | 2021-11-25 | 深圳元戎启行科技有限公司 | Virtual scene generation method and apparatus, computer device and storage medium |
| CN111783230A (en) * | 2020-07-02 | 2020-10-16 | 北京赛目科技有限公司 | Simulation test method and device for automatic driving algorithm |
| CN111744197B (en) * | 2020-08-07 | 2022-03-15 | 腾讯科技（深圳）有限公司 | Data processing method, device and equipment and readable storage medium |
| CN112256590B (en) * | 2020-11-12 | 2022-04-29 | 腾讯科技（深圳）有限公司 | Virtual scene effectiveness judgment method and device and automatic driving system |
| CN112785842B (en) * | 2020-12-25 | 2022-04-12 | 际络科技(上海)有限公司 | Online traffic flow simulation system |
| CN113569378B (en) * | 2021-06-16 | 2024-01-05 | 阿波罗智联(北京)科技有限公司 | Simulation scene generation method and device, electronic equipment and storage medium |
| CN113268428B (en) * | 2021-06-16 | 2023-08-18 | 一汽解放汽车有限公司 | Test method and system of fleet management system, storage medium and electronic device |
| KR102310500B1 (en) * | 2021-07-02 | 2021-10-08 | 주식회사 스프링클라우드 | Quantitative evaluation device and method for integrated driving performance of autonomous shuttle based on multiple test environments |
| CN113781785B (en) * | 2021-11-10 | 2022-02-08 | 禾多科技（北京）有限公司 | Random traffic flow control method for simulation test |
| CN114743385B (en) * | 2022-04-12 | 2023-04-25 | 腾讯科技（深圳）有限公司 | Vehicle processing method and device and computer equipment |
| CN116644585B (en) * | 2023-05-30 | 2024-01-09 | 清华大学 | Dangerous state scene data generation method and device based on target vehicle danger degree |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107991898A (en) * | 2016-10-26 | 2018-05-04 | 法乐第(北京)网络科技有限公司 | A kind of automatic driving vehicle simulating test device and electronic equipment |
| CN108595901A (en) * | 2018-07-09 | 2018-09-28 | 黄梓钥 | A kind of autonomous driving vehicle normalized security simulating, verifying model data base system |
| CN108829087A (en) * | 2018-07-19 | 2018-11-16 | 山东省科学院自动化研究所 | A kind of intelligent test system and test method of autonomous driving vehicle |
| CN109520744A (en) * | 2018-11-12 | 2019-03-26 | 百度在线网络技术（北京）有限公司 | The driving performance test method and device of automatic driving vehicle |
| WO2019065409A1 (en) * | 2017-09-29 | 2019-04-04 | 日立オートモティブシステムズ株式会社 | Automatic driving simulator and map generation method for automatic driving simulator |
| CN109632339A (en) * | 2018-12-28 | 2019-04-16 | 同济大学 | A kind of automatic driving vehicle traffic coordinating real steering vectors system and method |
| CN109726426A (en) * | 2018-11-12 | 2019-05-07 | 初速度（苏州）科技有限公司 | A kind of Vehicular automatic driving virtual environment building method |
| CN109765060A (en) * | 2018-12-29 | 2019-05-17 | 同济大学 | A kind of automatic driving vehicle traffic coordinating virtual test system and method |
| CN110174274A (en) * | 2019-05-28 | 2019-08-27 | 初速度（苏州）科技有限公司 | A kind of modification method and device of intelligent driving algorithm |
| CN110209146A (en) * | 2019-05-23 | 2019-09-06 | 杭州飞步科技有限公司 | Test method, device, equipment and the readable storage medium storing program for executing of automatic driving vehicle |
-
2019
- 2019-09-16 CN CN201910872939.XA patent/CN110793784B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107991898A (en) * | 2016-10-26 | 2018-05-04 | 法乐第(北京)网络科技有限公司 | A kind of automatic driving vehicle simulating test device and electronic equipment |
| WO2019065409A1 (en) * | 2017-09-29 | 2019-04-04 | 日立オートモティブシステムズ株式会社 | Automatic driving simulator and map generation method for automatic driving simulator |
| CN108595901A (en) * | 2018-07-09 | 2018-09-28 | 黄梓钥 | A kind of autonomous driving vehicle normalized security simulating, verifying model data base system |
| CN108829087A (en) * | 2018-07-19 | 2018-11-16 | 山东省科学院自动化研究所 | A kind of intelligent test system and test method of autonomous driving vehicle |
| CN109520744A (en) * | 2018-11-12 | 2019-03-26 | 百度在线网络技术（北京）有限公司 | The driving performance test method and device of automatic driving vehicle |
| CN109726426A (en) * | 2018-11-12 | 2019-05-07 | 初速度（苏州）科技有限公司 | A kind of Vehicular automatic driving virtual environment building method |
| CN109632339A (en) * | 2018-12-28 | 2019-04-16 | 同济大学 | A kind of automatic driving vehicle traffic coordinating real steering vectors system and method |
| CN109765060A (en) * | 2018-12-29 | 2019-05-17 | 同济大学 | A kind of automatic driving vehicle traffic coordinating virtual test system and method |
| CN110209146A (en) * | 2019-05-23 | 2019-09-06 | 杭州飞步科技有限公司 | Test method, device, equipment and the readable storage medium storing program for executing of automatic driving vehicle |
| CN110174274A (en) * | 2019-05-28 | 2019-08-27 | 初速度（苏州）科技有限公司 | A kind of modification method and device of intelligent driving algorithm |
Non-Patent Citations (2)
| Title |
|---|
| "基于场景的自动驾驶汽车虚拟测试研究进展";朱冰等;《中国公路学报》;20190630;第32卷(第6期);第1-19页 * |
| "自动驾驶汽车测试技术与应用进展";余卓平等;《同济大学学报（自然科学版）》;20190430;第47卷(第4期);第540-547页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110793784A (en) | 2020-02-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110793784B (en) | Test method and device for automatic driving vehicle, storage medium and electronic device | |
| US10642268B2 (en) | Method and apparatus for generating automatic driving strategy | |
| CN110197027B (en) | Automatic driving test method and device, intelligent equipment and server | |
| CN111591306B (en) | Driving track planning method of automatic driving vehicle, related equipment and storage medium | |
| CN110406530B (en) | Automatic driving method, device, equipment and vehicle | |
| CN110245406B (en) | Driving simulation method, device and storage medium | |
| CN109876444B (en) | Data display method and device, storage medium and electronic device | |
| JP6850324B2 (en) | Obstacle distribution simulation method, device, terminal and program based on multi-model | |
| CN110444018B (en) | Control method and device for simulated city system, storage medium and electronic device | |
| JP6850325B2 (en) | Obstacle distribution simulation methods, devices, terminals, storage media, and programs based on probability plots | |
| CN112249035B (en) | Automatic driving method, device and equipment based on general data flow architecture | |
| CN113415288B (en) | Sectional type longitudinal vehicle speed planning method, device, equipment and storage medium | |
| CN112382165B (en) | Driving strategy generation method, device, medium, equipment and simulation system | |
| CN113375689A (en) | Navigation method, navigation device, terminal and storage medium | |
| CN111368409A (en) | Vehicle flow simulation processing method, device, equipment and storage medium | |
| CN112671487A (en) | Vehicle testing method, server and testing vehicle | |
| CN115136081A (en) | Method for training at least one algorithm for a controller of a motor vehicle, method for optimizing a traffic flow in a region, computer program product and motor vehicle | |
| CN115176297A (en) | Method for training at least one algorithm for a control unit of a motor vehicle, computer program product and motor vehicle | |
| CN111381575B (en) | Automatic test method, device, server, electronic equipment and storage medium | |
| CN111816022A (en) | Simulation method and device for simulation scene, storage medium and electronic equipment | |
| US20230222268A1 (en) | Automated Generation and Refinement of Variation Parameters for Simulation Scenarios | |
| CN115148028A (en) | Method and device for constructing vehicle drive test scene according to historical data and vehicle | |
| CN111340234B (en) | Video data processing method, apparatus, electronic device and computer readable medium | |
| CN114419758A (en) | Vehicle following distance calculation method and device, vehicle and storage medium | |
| CN114117944A (en) | Model updating method, device, equipment and readable storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| REG | Reference to a national code |
Ref country code: HK Ref legal event code: DE Ref document number: 40018291 Country of ref document: HK |
|
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |