CN113806862A - Unmanned vehicle simulation method and device, storage medium and electronic equipment - Google Patents
Unmanned vehicle simulation method and device, storage medium and electronic equipment Download PDFInfo
- Publication number
- CN113806862A CN113806862A CN202111045958.9A CN202111045958A CN113806862A CN 113806862 A CN113806862 A CN 113806862A CN 202111045958 A CN202111045958 A CN 202111045958A CN 113806862 A CN113806862 A CN 113806862A
- Authority
- CN
- China
- Prior art keywords
- simulation
- scene
- target
- scenes
- sequence
- 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.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/10—Geometric CAD
- G06F30/15—Vehicle, aircraft or watercraft design
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/02—Reliability analysis or reliability optimisation; Failure analysis, e.g. worst case scenario performance, failure mode and effects analysis [FMEA]
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Geometry (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computer Hardware Design (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Aviation & Aerospace Engineering (AREA)
- Computational Mathematics (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Pure & Applied Mathematics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Traffic Control Systems (AREA)
Abstract
The disclosure relates to an unmanned vehicle simulation method, an unmanned vehicle simulation device, a storage medium and electronic equipment, wherein the method comprises the following steps: receiving a simulation request of a user, wherein the simulation request comprises a plurality of simulation requirements; determining a plurality of simulation scenarios corresponding to the plurality of simulation requirements from a set of simulation scenarios; splicing the plurality of simulation scenes to obtain a target simulation scene sequence; and sending the target simulation scene sequence to the unmanned vehicle, wherein the target simulation scene sequence is used for simulating the unmanned vehicle. By adopting the technical scheme, a plurality of simulation scenes can be automatically selected and matched according to the requirements of users in the unmanned vehicle simulation process, so that automatic and continuous multi-scene simulation is realized. In the process, the user does not need to manually issue the simulation test task. Therefore, the technical scheme can improve the simulation efficiency of the unmanned vehicle and reduce the labor cost in the simulation process.
Description
Technical Field
The present disclosure relates to the field of unmanned vehicle technology, and in particular, to an unmanned vehicle simulation method, apparatus, storage medium, and electronic device.
Background
With the development of unmanned driving technology, a trajectory planning prediction algorithm, a vehicle control algorithm and a software and hardware combination technology in an unmanned vehicle are continuously updated and iterated. In a relevant scene, the stability of the unmanned vehicle algorithm and the reliability of unmanned vehicle hardware can be verified by performing in-loop test on the unmanned vehicle. For example, a user can issue a simulation test task to the unmanned vehicle by inputting a test instruction, and then test and verify the software and hardware capabilities of the unmanned vehicle. However, such an approach may also have a problem of low simulation test efficiency.
Disclosure of Invention
An object of the present disclosure is to provide an unmanned vehicle simulation method, apparatus, storage medium, and electronic device to at least partially solve the above-mentioned problems in the related art.
In order to achieve the above object, according to a first aspect of embodiments of the present disclosure, there is provided an unmanned vehicle simulation method including:
receiving a simulation request of a user, wherein the simulation request comprises a plurality of simulation requirements;
determining a plurality of simulation scenarios corresponding to the plurality of simulation requirements from a set of simulation scenarios;
splicing the plurality of simulation scenes to obtain a target simulation scene sequence;
and sending the target simulation scene sequence to the unmanned vehicle, wherein the target simulation scene sequence is used for simulating the unmanned vehicle.
Optionally, each simulation scene corresponds to a simulation track, and the splicing the multiple simulation scenes to obtain a target simulation scene sequence includes:
splicing the plurality of simulation scenes to obtain a plurality of candidate simulation scene sequences;
aiming at each candidate simulation scene sequence, calculating a first area value of a simulation track corresponding to the candidate simulation scene sequence and a second area value of a convex hull of the simulation track;
calculating the ratio of the first area value to the second area value to obtain the area utilization rate of the candidate simulation scene sequence;
and taking the candidate simulation scene sequence with the highest area utilization rate as the target simulation scene sequence.
Optionally, the determining a plurality of simulation scenarios corresponding to the plurality of simulation requirements from the set of simulation scenarios comprises:
determining a plurality of sets of simulation scenarios from the set of simulation scenarios, each set of simulation scenarios comprising a plurality of simulation scenarios corresponding to the plurality of simulation requirements;
the splicing of the plurality of simulation scenes to obtain a target simulation scene sequence comprises the following steps:
splicing a plurality of simulation scenes in each group of simulation scenes to obtain a plurality of candidate simulation scene sequences corresponding to the group of simulation scenes; and are
Determining a target candidate simulation scene sequence corresponding to the set of simulation scenes based on the area utilization ratio of each candidate simulation scene sequence;
and determining the target simulation scene sequence from the target candidate simulation scene sequences of each group of simulation scenes.
Optionally, each simulation scene corresponds to a simulation track, and determining a target candidate simulation scene sequence corresponding to the group of simulation scenes based on an area utilization rate of each candidate simulation scene sequence includes:
aiming at each candidate simulation scene sequence, calculating a first area value of a simulation track corresponding to the candidate simulation scene sequence and a second area value of a convex hull of the simulation track;
calculating the ratio of the first area value to the second area value to obtain the area utilization rate of the candidate simulation scene sequence;
and taking the candidate simulation scene sequence with the highest area utilization rate as a target candidate simulation scene sequence of the group of simulation scenes.
Optionally, the determining the target simulation scene sequence from the target candidate simulation scene sequences of the respective sets of simulation scenes includes:
and determining the target simulation scene sequence from the target candidate simulation scene sequences of each group of simulation scenes according to at least one of the area utilization rate of the target candidate simulation scene sequences, the length of the transition track, the priority of the simulation scenes and the quantity value of the transition scenes.
Optionally, the determining a plurality of simulation scenarios corresponding to the plurality of simulation requirements from the set of simulation scenarios comprises:
aiming at each simulation requirement, dividing a plurality of simulation scene types;
randomly determining a target simulation scene type from the plurality of simulation scene types;
and sampling from the simulation scene set based on each target simulation scene type to obtain a plurality of simulation scenes.
Optionally, the dividing, for each simulation requirement, a plurality of simulation scene types further includes:
acquiring the quantity value of simulation scene samples in the simulation scene set;
reducing the number of simulated scene types when the number value of the simulated scene samples is less than a number threshold.
According to a second aspect of the embodiments of the present disclosure, there is provided an unmanned vehicle simulation apparatus including:
the simulation system comprises a receiving module, a simulation module and a simulation module, wherein the receiving module is used for receiving a simulation request of a user, and the simulation request comprises a plurality of simulation requirements;
a simulation trajectory determination module for determining a plurality of simulation scenarios corresponding to the plurality of simulation requirements from a set of simulation scenarios;
the simulation track splicing module is used for splicing the plurality of simulation scenes to obtain a target simulation scene sequence;
and the simulation track sending module is used for sending the target simulation scene sequence to the unmanned vehicle, and the target simulation scene sequence is used for simulating the unmanned vehicle.
Optionally, each simulation scene corresponds to a simulation track, and the simulation track splicing module includes:
the first splicing submodule is used for splicing the plurality of simulation scenes to obtain a plurality of candidate simulation scene sequences;
the first calculation submodule is used for calculating a first area value of a simulation track corresponding to each candidate simulation scene sequence and a second area value of a convex hull of the simulation track according to the candidate simulation scene sequence;
the second calculation submodule is used for calculating the ratio of the first area value to the second area value to obtain the area utilization rate of the candidate simulation scene sequence;
and the first execution sub-module is used for taking the candidate simulation scene sequence with the highest area utilization rate as the target simulation scene sequence.
Optionally, the simulation trajectory determination module includes:
a first determining sub-module, configured to determine multiple sets of simulation scenarios from the set of simulation scenarios, each set of simulation scenarios comprising multiple simulation scenarios corresponding to the multiple simulation requirements;
the simulation track splicing module comprises:
the second splicing submodule is used for splicing a plurality of simulation scenes in each group of simulation scenes to obtain a plurality of candidate simulation scene sequences corresponding to the group of simulation scenes;
a second determining submodule, configured to determine, based on an area utilization rate of each candidate simulation scene sequence, a target candidate simulation scene sequence corresponding to the group of simulation scenes;
and the third determining submodule is used for determining the target simulation scene sequence from the target candidate simulation scene sequences of each group of simulation scenes.
Optionally, each simulation scene corresponds to a simulation trajectory, and the second determining sub-module includes:
the first calculating subunit is configured to calculate, for each candidate simulation scene sequence, a first area value of a simulation trajectory corresponding to the candidate simulation scene sequence and a second area value of a convex hull of the simulation trajectory;
the second calculating subunit is configured to calculate a ratio of the first area value to the second area value, so as to obtain an area utilization rate of the candidate simulation scene sequence;
and the first execution subunit is used for taking the candidate simulation scene sequence with the highest area utilization rate as a target candidate simulation scene sequence of the group of simulation scenes.
Optionally, the third determining sub-module is configured to:
and determining the target simulation scene sequence from the target candidate simulation scene sequences of each group of simulation scenes according to at least one of the area utilization rate of the target candidate simulation scene sequences, the length of the transition track, the priority of the simulation scenes and the quantity value of the transition scenes.
Optionally, the simulation trajectory determination module includes:
the partitioning submodule is used for partitioning a plurality of simulation scene types according to each simulation requirement;
a fourth determining submodule, configured to randomly determine a target simulation scene type from the multiple simulation scene types;
and the sampling sub-module is used for sampling from the simulation scene set based on each target simulation scene type to obtain a plurality of simulation scenes.
Optionally, the partitioning sub-module further includes:
the acquiring subunit is used for acquiring the quantity value of the simulation scene samples in the simulation scene set;
a second execution subunit, configured to reduce the number of simulation scene types when the number value of the simulation scene samples is less than a number threshold.
According to a third aspect of embodiments of the present disclosure, there is provided a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of the method of any one of the above-mentioned first aspects.
According to a fourth aspect of the embodiments of the present disclosure, there is provided an electronic apparatus including:
a memory having a computer program stored thereon;
a processor for executing the computer program in the memory to implement the steps of the method of any of the first aspects above.
By taking the method as an example for the server, when a user needs to simulate the unmanned vehicle in various scenes, a simulation request can be sent to the server, and the simulation request comprises a plurality of simulation requirements. In this way, after receiving the simulation request, the server may determine a plurality of simulation scenarios corresponding to the plurality of simulation requirements from the simulation scenario set, and splice the plurality of simulation scenarios to obtain a target simulation scenario sequence. That is to say, the server can automatically match the simulation scenes according to the simulation requirements of the user, and splice and plan the matched simulation scenes, so as to obtain a target simulation scene sequence capable of meeting the simulation requirements of the user. Therefore, the target simulation scene sequence is sent to the unmanned vehicle, the unmanned vehicle can automatically and continuously perform multi-scene simulation, and the simulation requirements of users are met.
By adopting the technical scheme, a plurality of simulation scenes can be automatically selected and matched according to the requirements of users in the unmanned vehicle simulation process, so that automatic and continuous multi-scene simulation is realized. In the process, the user does not need to manually issue the simulation test task. Therefore, the technical scheme can improve the simulation efficiency of the unmanned vehicle and reduce the labor cost in the simulation process.
Additional features and advantages of the disclosure will be set forth in the detailed description which follows.
Drawings
The accompanying drawings, which are included to provide a further understanding of the disclosure and are incorporated in and constitute a part of this specification, illustrate embodiments of the disclosure and together with the description serve to explain the disclosure without limiting the disclosure. In the drawings:
fig. 1 is a flowchart illustrating an unmanned vehicle simulation method according to an exemplary embodiment of the present disclosure.
FIG. 2 is a schematic diagram of a polygon of a simulated track and a convex hull of the simulated track according to an exemplary embodiment of the disclosure.
Fig. 3 is a flowchart illustrating an unmanned vehicle simulation method according to an exemplary embodiment of the present disclosure.
Fig. 4 is a flow chart illustrating an unmanned vehicle simulation according to an exemplary embodiment of the present disclosure.
Fig. 5 is a block diagram of an unmanned vehicle simulation apparatus according to an exemplary embodiment of the present disclosure.
FIG. 6 is a block diagram of an electronic device shown in an exemplary embodiment of the present disclosure.
Detailed Description
The following detailed description of specific embodiments of the present disclosure is provided in connection with the accompanying drawings. It should be understood that the detailed description and specific examples, while indicating the present disclosure, are given by way of illustration and explanation only, not limitation.
Before introducing the unmanned vehicle simulation method, the unmanned vehicle simulation device, the storage medium and the electronic device of the present disclosure, an application scenario of the present disclosure is first introduced. Embodiments provided by the present disclosure may be used to simulate an unmanned vehicle, where the unmanned vehicle may be, for example, a delivery unmanned vehicle, an unmanned taxi, and the like.
Unmanned vehicle driving systems typically include algorithmic modules for perception, prediction, positioning, planning, and control. The planning and control module is dependent on the outputs of the sensing module, the prediction module and the positioning module. In some scenarios, the planning and control module may be tested by way of real-vehicle simulation in an open field. For example, a user may select a simulation scenario by inputting an instruction and issue a simulation task including the simulation scenario. Therefore, the simulation scene data is played back on the unmanned vehicle, and the planning and control algorithm module can be tested and verified by combining the perception data of the unmanned vehicle.
It should be noted that the mode of manually issuing simulation tasks one by relying on a user may not meet the requirement of a simulation test with a large magnitude, thereby affecting the simulation efficiency.
To this end, the present disclosure provides an unmanned vehicle simulation method, which may be used for related devices involved in an unmanned vehicle simulation process, such as a simulation server, a control terminal, and the like, for example. Fig. 1 is a flow chart of an unmanned vehicle simulation method illustrated in the present disclosure, and referring to fig. 1, the method includes:
in step 11, a simulation request of a user is received, the simulation request including a plurality of simulation requirements.
The simulation requirement may include, for example, a trajectory scene type required by the user, such as a straight-ahead scene, a left-turn scene, a right-turn scene, a turning scene, and the like, and the simulation requirement may further include a control scene type required by the user, such as an extreme turning scene, an acceleration scene, and the like. In some implementation scenarios, the simulation requirements may also include, for example, the type of obstacle that the user desires, which the present disclosure does not limit.
In step 12, a plurality of simulation scenarios corresponding to the plurality of simulation requirements is determined from a set of simulation scenarios.
Here, various types of simulation scenes may be included in the simulation scene set, such as a simulation scene of a left turn, a simulation scene of a straight run, and the like. Each simulation scene may include simulation track information, and information of some or all track points in the simulation track, such as acceleration, vehicle speed, brake signal, direction angle, and the like at the track point. In this way, a plurality of simulation scenarios corresponding to the plurality of simulation requirements may be determined from the set of simulation scenarios. For example, when the simulation request of the user includes simulation requirements of 2 straight-going scenes and simulation requirements of 2 left-turning scenes, 2 straight-going simulation scenes and 2 left-turning simulation scenes may be determined from the simulation scene set, and a straight-going simulation scene 1, a straight-going simulation scene 2, a left-turning simulation scene 1, and a left-turning simulation scene 2 are obtained.
In step 13, the plurality of simulation scenes are spliced to obtain a target simulation scene sequence.
And when the simulation scene is spliced, the information of the test site can be combined. For example, the length and width of the test site can be considered when splicing the simulation scenes, so that the range of the spliced simulation scene sequence is prevented from exceeding the range of the test site.
For example, in some embodiments, a transition scenario may be generated based on the size of the test site. The simulation scenes are connected through the transition scenes, so that the range of the spliced simulation scene sequences can be prevented from exceeding the range of the test site. Taking a simulation test site as an example with a length of 200 meters and a width of 100 meters, if the simulation requirements of the user include two continuous straight scenes with a length of 200 meters, a turning-around transition scene can be generated when the two straight scenes with the length of 200 meters are spliced, and the two straight scenes with the length of 200 meters are connected through the turning-around transition scene, so that the spliced simulation scene sequence can meet the requirements of the test site. It is noted that in this case, the transition scenario may also be included in the target simulation scenario sequence.
In addition, in some implementation scenes, transition scenes generated in the process of splicing the simulation scenes can be added to the simulation scene set, so that the types of the simulation scenes in the simulation scene set are enriched. Of course, when the two simulation scenes cannot be directly spliced, the transition scene can also be searched from the simulation scene set, so that the two simulation scenes can be conveniently spliced.
In addition, in some embodiments, the spliced simulation scene sequence may be selected by using an area utilization rate. In this case, the stitching the plurality of simulation scenes to obtain a target simulation scene sequence (step 13) includes:
and splicing the plurality of simulation scenes to obtain a plurality of candidate simulation scene sequences. Continuing with the above example, when splicing the straight simulation scene 1, the straight simulation scene 2, the left-turn simulation scene 1, and the left-turn simulation scene 2, different candidate simulation scene sequences may be obtained. For example, under the condition that there is no sequential limitation among simulation requirements of users, a candidate simulation scene sequence can be obtained by sequentially splicing the straight-going simulation scene 1, the straight-going simulation scene 2, the left-turn simulation scene 1 and the left-turn simulation scene 2; and sequentially splicing the straight-going simulation scene 2, the left-turning simulation scene 1, the straight-going simulation scene 1 and the left-turning simulation scene 2 to obtain another candidate simulation scene sequence. Or, in a case that the simulation scenes cannot be directly spliced (for example, the limitation of a test site is exceeded in the case of direct splicing), connecting the plurality of simulation scenes by using different transition scenes may also obtain different candidate simulation scene sequences.
Then, for each candidate simulation scene sequence, calculating a first area value of a simulation track corresponding to the candidate simulation scene sequence and a second area value of a convex hull of the simulation track. Wherein, referring to the definition in the related art, the convex hull of a point on a set of planes is the smallest convex polygon containing the set of points. Fig. 2 is a schematic diagram of a polygon of a simulation track and a convex hull of the simulation track shown in this disclosure, and in a specific implementation, a track polygon (for example, a minimum bounding rectangle is constructed for all track points of the simulation track) may be constructed for the simulation track corresponding to each candidate simulation scene sequence, and the convex hull of the simulation track may be constructed. Thus, the area of the track polygon of each simulation track can be calculated to obtain the first area value, and the area value of the convex hull can be calculated to obtain the second area value.
After the first area value and the second area value are obtained, the ratio of the first area value to the second area value is calculated, and the area utilization rate of the candidate simulation scene sequence is obtained. By comparing the area utilization rate of each candidate simulation scene sequence, the candidate simulation scene sequence with the highest area utilization rate can be used as the target simulation scene sequence. By adopting the mode, the candidate simulation scene sequence with the highest area utilization rate can be selected as the target simulation scene sequence for the simulation of the unmanned vehicle, so that the utilization rate of a test field in the simulation process of the unmanned vehicle can be increased, and the simulation efficiency is improved.
In step 14, the target simulation scene sequence is sent to the unmanned vehicle, and the target simulation scene sequence is used for the unmanned vehicle to simulate.
In some implementation scenarios, the simulation result of the unmanned vehicle can be received and uploaded to the cloud for storage. Or, the simulation result can be fed back to the user side.
By adopting the technical scheme, a plurality of simulation scenes can be automatically selected and matched according to the requirements of users in the unmanned vehicle simulation process, so that automatic and continuous multi-scene simulation is realized. In the process, the user does not need to manually issue the simulation test task. Therefore, the technical scheme can improve the simulation efficiency of the unmanned vehicle and reduce the labor cost in the simulation process.
Fig. 3 is a flow chart illustrating a method of unmanned vehicle simulation as disclosed in this disclosure, the method comprising, as shown in fig. 3:
in step 31, a simulation request of a user is received, the simulation request including a plurality of simulation requirements.
In step 32, a plurality of sets of simulation scenarios are determined from the set of simulation scenarios, each set of simulation scenarios comprising a plurality of simulation scenarios corresponding to the plurality of simulation requirements.
For example, a plurality of simulation scenario types may be partitioned for each of the simulation requirements. For example, for the simulation requirement dimension of the track length, the simulation scene types including 1-100 meters, 100-200 meters, 200-300 meters, and the like can be divided. For another example, each simulation scenario may be prioritized, so as to obtain a simulation requirement dimension, i.e., an execution priority, and further, multiple simulation scenario types may be divided from a priority perspective. The priority of the simulation scene can be set according to application requirements. For example, a simulation scenario with multiple faults can be determined by counting historical simulation results, and the priority of the simulation scenario is set to be higher, so that more simulation data of the simulation scenario can be acquired, and the fault cause can be analyzed.
In addition, in some implementation scenarios, when a plurality of simulation scene types are divided for each simulation requirement, a quantity value of simulation scene samples in the simulation scene set may also be obtained, and when the quantity value of simulation scene samples is less than a quantity threshold, the number of simulation scene types is reduced.
It should be appreciated that dividing more simulation scene types may increase the sampling difficulty when the number of simulation scene samples is small. Therefore, the type of the simulation scene type can be dynamically adjusted according to the number of simulation scene samples in the simulation scene set. And when the number of the simulation scene samples is less, reducing the number of the simulation scene types so as to improve the sampling speed. And when the number of the simulation scene samples is large, increasing the number of the simulation scene types so as to improve the diversity of sampling results.
After the plurality of simulation scene types are divided, a target simulation scene type can be randomly determined from the plurality of simulation scene types.
For example, if the simulation requirement of the user is a straight-line simulation and a high priority, the simulation scene set may be counted to obtain a probability quality function P of the straight-line simulation scene1And probability quality function P of high priority simulation scenario2Obtaining the probability mass function P ═ P1，P2]. The corresponding cumulative distribution function is F ═ F1，F2]，Ft∈ＮL+1→ R. And L is the maximum value of the number of the simulation scene types obtained by dividing each simulation requirement. For example, if the types of the direct-moving simulation scenarios are 5, and the types of the high-priority simulation scenarios are 3, the value of L is 5. It should be understood that for each simulation demand dimension, its corresponding respective simulation scenario type may have a value of the corresponding cumulative distribution function.
Thus, in some implementation scenarios, U may be evenly distributed from 2 dimensions2(0, 1) to obtain a random number sample u ═ u1，u2]. Of course, when the user's simulation requirements include T dimensions, U may be evenly distributed from the T dimensionsT(0, 1) to obtain a sample u ═ u1，u2，…，uT]This disclosure will not be repeated herein.
In this way, the type of the straight-ahead simulation scenario that needs to be sampled and the type of the high-priority simulation scenario can be determined based on the random number. For example, if the types of the straight-driving simulation scenarios are 50-100 m, 100-200 m and 200-250 m 3, the corresponding cumulative distribution functions are F, which are F respectively11、F12And F13. In this case, if F11≤u1＜F12Then it may be determined that the type of straight-ahead simulation scenario to be extracted is 50-100 meters.
In this way, a plurality of simulation scenes can be obtained by sampling from the simulation scene set based on each target simulation scene type and can be used as a group of simulation scenes. It should be appreciated that by repeatedly performing the above steps, multiple sets of simulation scenarios may be obtained.
In step 33, for each set of simulation scenes, a plurality of simulation scenes in the set of simulation scenes are stitched to obtain a plurality of candidate simulation scene sequences corresponding to the set of simulation scenes.
In step 34, a target candidate simulation scene sequence corresponding to the set of simulation scenes is determined based on the area utilization of each of the candidate simulation scene sequences.
For example, for each of the candidate simulation scene sequences, a first area value of a simulation trajectory corresponding to the candidate simulation scene sequence and a second area value of a convex hull of the simulation trajectory may be calculated. Referring to fig. 2, in a specific implementation, a track polygon (e.g., a minimum bounding rectangle for all track points of a simulation track) may be constructed for each simulation track, and a convex hull of the simulation track may be constructed. Thus, the area of the track polygon of each simulation track can be calculated to obtain the first area value, and the area value of the convex hull can be calculated to obtain the second area value.
After the first area value and the second area value are obtained, a ratio of the first area value to the second area value may be calculated to obtain an area utilization rate of the candidate simulation scene sequence. By comparing the area utilization rate of each candidate simulation scene sequence, the candidate simulation scene sequence with the highest area utilization rate can be used as the target candidate simulation scene sequence of the group of simulation scenes. By adopting the mode, the candidate simulation scene sequence with the highest area utilization rate can be selected as the target simulation scene sequence for the simulation of the unmanned vehicle, so that the utilization rate of a test field in the simulation process of the unmanned vehicle can be increased, and the simulation efficiency is improved.
In step 35, a sequence of target simulation scenes is determined from each sequence of target candidate simulation scenes.
In one possible implementation, the target simulation scene sequence may be determined from each target candidate simulation scene sequence according to an area utilization rate of the target candidate simulation scene sequence. For example, the target candidate simulation scene sequence with the largest area utilization rate in the target candidate simulation scene sequences of each group of simulation scenes may be used as the target simulation scene sequence, so as to improve the utilization rate of the test site.
In a possible implementation manner, the target simulation scene sequence may also be determined from each target candidate simulation scene sequence according to the length of the transition trajectory (i.e., the trajectory corresponding to the transition scene) of the target candidate simulation scene sequence. For example, the target candidate simulation scene sequence with the shortest transition trajectory among the target candidate simulation scene sequences may be used as the target simulation scene sequence, so as to improve the utilization rate of the test site.
In a possible implementation manner, the target simulation scene sequence may also be determined from each target candidate simulation scene sequence according to the priority of the simulation scenes of the target candidate simulation scene sequence. For example, the target candidate simulation scene sequence with the highest priority of the simulation scenes (e.g., the priority of each simulation scene in the accumulated target candidate simulation scene sequence) in each target candidate simulation scene sequence may be used as the target simulation scene sequence, so as to meet the priority requirement in the simulation process.
In one possible implementation, the target simulation scene sequence may also be determined from each target candidate simulation scene sequence according to the quantity value of transition scenes of the target candidate simulation scene sequence. For example, the target simulation trajectory with the least number of transition scenes in each target candidate simulation scene sequence may be used as the target simulation scene sequence, so as to improve the utilization rate of the test site.
Of course, in some possible embodiments, multiple ones of the area utilization, the length of the transition trajectory, the priority of the simulation scenario, and the number of transition scenarios may be combined to determine the target simulation scenario sequence. For example, a corresponding weight value may be determined for each factor, so as to integrate the weight value of each factor to measure each target candidate simulation scene sequence, thereby determining the target simulation scene sequence.
In step 36, the target simulation scene sequence is sent to the unmanned vehicle, and the target simulation scene sequence is used for the unmanned vehicle to simulate.
By adopting the technical scheme, the simulation track can be automatically selected and matched according to the requirements of the user in the unmanned vehicle simulation process, namely, the user does not need to manually issue a simulation test task. Therefore, the technical scheme can improve the simulation efficiency of the unmanned vehicle. In addition, in the above technical solution, factors such as an area utilization rate and a length of a transition trajectory are also combined when selecting a target simulation scene sequence. Through such a mode, can promote the utilization ratio in test place, also help promoting test efficiency.
Fig. 4 is a flowchart illustrating an unmanned vehicle simulation according to the present disclosure, and referring to fig. 4, a user terminal may initiate a simulation task request to a server when the unmanned vehicle is required to perform a simulation test. Here, the server may be configured as a real vehicle simulation scheduling platform, and the simulation task request may include, for example, simulation requirements of the user.
After receiving the simulation task request, the server may obtain M groups of simulation scene lists by discrete sampling from the simulation scene pool according to the simulation requirements of the user. For example, if the simulation requirement of the user is to test the straight-going limit acceleration of the unmanned vehicle, it may be determined that the simulation requirement of the user is straight-going, and M groups of straight-going simulation scene lists are obtained by discrete sampling from the simulation scene pool.
Following the above example, each group of the list of rectilinear simulation scenes may include, for example, a plurality of rectilinear simulation scenes, and each of the rectilinear simulation scenes may correspond to a segment of the rectilinear simulation trajectory. In this way, an optimal simulation scene sequence for each list of rectilinear simulation scenes may be determined based on the plurality of rectilinear simulation scenes. For example, for the direct-line simulation scene list 1, a plurality of direct-line simulation scenes in the direct-line simulation scene list 1 may be spliced to obtain a plurality of candidate simulation scene sequences, and an area utilization rate of each candidate simulation scene sequence is calculated (please refer to the above embodiment). In this way, the candidate simulation scene sequence with the highest area utilization rate can be used as the optimal simulation scene sequence of the straight-going scene list 1.
After the optimal simulation scene sequence 1-M corresponding to the scene list 1-M is obtained, a target simulation scene sequence can be determined from the optimal simulation scene sequence 1-M. For example, the target simulation scene sequence may be determined from the optimal simulation scene sequences 1-M in combination with one or more of the area utilization of each optimal simulation scene sequence, the length of the transition trajectory, the priority of the simulation scene, and the quantity value of the transition scene. For example, a corresponding weight value may be determined for each factor, so that the weight value of each factor is synthesized to measure each optimal trajectory sequence, and the target simulation scene sequence is determined. Therefore, the target simulation scene sequence is sent to the unmanned vehicle, and the simulation requirements of the user can be met.
It is worth mentioning that alternative sequences of scenes may also be generated by the alternative sequence generator. Here, the alternative scene sequence may be for the unmanned vehicle to reset from the current position to the starting position. For example, when each optimal simulation scenario sequence cannot meet the preset simulation requirement, the server may adopt the alternative scenario sequence. The candidate scene sequence is sent to the unmanned vehicle, so that the pose of the unmanned vehicle can be reset, and the subsequent simulation process is facilitated.
By adopting the technical scheme, a plurality of simulation scenes can be automatically selected and matched according to the requirements of users in the unmanned vehicle simulation process, so that automatic and continuous multi-scene simulation is realized. In the process, the user does not need to manually issue the simulation test task. Therefore, the technical scheme can improve the simulation efficiency of the unmanned vehicle and reduce the labor cost in the simulation process.
Based on the same invention concept, the invention also provides an unmanned vehicle simulation device. Fig. 5 is a block diagram of an unmanned vehicle simulation apparatus shown in the present disclosure, and as shown in fig. 5, the apparatus 500 includes:
a receiving module 501, configured to receive a simulation request of a user, where the simulation request includes multiple simulation requirements;
a simulation trajectory determination module 502 for determining a plurality of simulation scenarios corresponding to the plurality of simulation requirements from a set of simulation scenarios;
a simulation trajectory splicing module 503, configured to splice the multiple simulation scenes to obtain a target simulation scene sequence;
a simulation track sending module 504, configured to send the target simulation scene sequence to an unmanned vehicle, where the target simulation scene sequence is used for simulation of the unmanned vehicle.
Taking the above device as an example for a server, when a user needs an unmanned vehicle to perform simulation in various scenes, a simulation request may be sent to the server, where the simulation request includes a plurality of simulation requirements. In this way, after receiving the simulation request, the server may determine a plurality of simulation scenarios corresponding to the plurality of simulation requirements from the simulation scenario set, and splice the plurality of simulation scenarios to obtain a target simulation scenario sequence. That is to say, the server can automatically match the simulation scenes according to the simulation requirements of the user, and splice and plan the matched simulation scenes, so as to obtain a target simulation scene sequence capable of meeting the simulation requirements of the user. Therefore, the target simulation scene sequence is sent to the unmanned vehicle, the unmanned vehicle can automatically and continuously perform multi-scene simulation, and the simulation requirements of users are met.
By adopting the technical scheme, a plurality of simulation scenes can be automatically selected and matched according to the requirements of users in the unmanned vehicle simulation process, so that automatic and continuous multi-scene simulation is realized. In the process, the user does not need to manually issue the simulation test task. Therefore, the technical scheme can improve the simulation efficiency of the unmanned vehicle and reduce the labor cost in the simulation process.
Optionally, each simulation scene corresponds to a simulation track, and the simulation track stitching module 503 includes:
the first splicing submodule is used for splicing the plurality of simulation scenes to obtain a plurality of candidate simulation scene sequences;
the first calculation submodule is used for calculating a first area value of a simulation track corresponding to each candidate simulation scene sequence and a second area value of a convex hull of the simulation track according to the candidate simulation scene sequence;
the second calculation submodule is used for calculating the ratio of the first area value to the second area value to obtain the area utilization rate of the candidate simulation scene sequence;
and the first execution sub-module is used for taking the candidate simulation scene sequence with the highest area utilization rate as the target simulation scene sequence.
Optionally, the simulation trajectory determining module 502 includes:
a first determining sub-module, configured to determine multiple sets of simulation scenarios from the set of simulation scenarios, each set of simulation scenarios comprising multiple simulation scenarios corresponding to the multiple simulation requirements;
the simulation track splicing module comprises:
the second splicing submodule is used for splicing a plurality of simulation scenes in each group of simulation scenes to obtain a plurality of candidate simulation scene sequences corresponding to the group of simulation scenes;
a second determining submodule, configured to determine, based on an area utilization rate of each candidate simulation scene sequence, a target candidate simulation scene sequence corresponding to the group of simulation scenes;
and the third determining submodule is used for determining the target simulation scene sequence from the target candidate simulation scene sequences of each group of simulation scenes.
Optionally, each simulation scene corresponds to a simulation trajectory, and the second determining sub-module includes:
the first calculating subunit is configured to calculate, for each candidate simulation scene sequence, a first area value of a simulation trajectory corresponding to the candidate simulation scene sequence and a second area value of a convex hull of the simulation trajectory;
the second calculating subunit is configured to calculate a ratio of the first area value to the second area value, so as to obtain an area utilization rate of the candidate simulation scene sequence;
and the first execution subunit is used for taking the candidate simulation scene sequence with the highest area utilization rate as a target candidate simulation scene sequence of the group of simulation scenes.
Optionally, the third determining sub-module is configured to:
and determining the target simulation scene sequence from the target candidate simulation scene sequences of each group of simulation scenes according to at least one of the area utilization rate of the target candidate simulation scene sequences, the length of the transition track, the priority of the simulation scenes and the quantity value of the transition scenes.
Optionally, the simulation trajectory determining module 502 includes:
the partitioning submodule is used for partitioning a plurality of simulation scene types according to each simulation requirement;
a fourth determining submodule, configured to randomly determine a target simulation scene type from the multiple simulation scene types;
and the sampling sub-module is used for sampling from the simulation scene set based on each target simulation scene type to obtain a plurality of simulation scenes.
Optionally, the partitioning sub-module further includes:
the acquiring subunit is used for acquiring the quantity value of the simulation scene samples in the simulation scene set;
a second execution subunit, configured to reduce the number of simulation scene types when the number value of the simulation scene samples is less than a number threshold.
With regard to the apparatus in the above-described embodiment, the specific manner in which each module performs the operation has been described in detail in the embodiment related to the method, and will not be elaborated here.
The present disclosure also provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the steps of the unmanned vehicle simulation method provided by the present disclosure.
The present disclosure also provides an electronic device, comprising:
a memory having a computer program stored thereon;
a processor for executing the computer program in the memory to implement the steps of the unmanned vehicle simulation method provided by the present disclosure.
Fig. 6 is a block diagram illustrating an electronic device 600 according to an example embodiment. For example, the electronic device 600 may be provided as a server. Referring to fig. 6, the electronic device 600 includes a processor 622, which may be one or more in number, and a memory 632 for storing computer programs executable by the processor 622. The computer program stored in memory 632 may include one or more modules that each correspond to a set of instructions. Further, the processor 622 may be configured to execute the computer program to perform the above-described unmanned vehicle simulation method.
Additionally, electronic device 600 may also include a power component 626 that may be configured to perform power management of electronic device 600 and a communication component 650 that may be configured to enable communication, e.g., wired or wireless communication, of electronic device 600. The electronic device 600 may also include input/output (I/O) interfaces 658. The electronic device 600 may operate based on an operating system, such as Windows Server, stored in the memory 632TM，Mac OS XTM，UnixTM，LinuxTMAnd so on.
In another exemplary embodiment, a computer readable storage medium comprising program instructions which, when executed by a processor, implement the steps of the above-described method of unmanned vehicle simulation is also provided. For example, the computer readable storage medium may be the memory 632 described above that includes program instructions executable by the processor 622 of the electronic device 600 to perform the above-described method of unmanned vehicle simulation.
In another exemplary embodiment, a computer program product is also provided, which comprises a computer program executable by a programmable apparatus, the computer program having code portions for performing the above-described method of unmanned vehicle simulation when executed by the programmable apparatus.
The preferred embodiments of the present disclosure are described in detail with reference to the accompanying drawings, however, the present disclosure is not limited to the specific details of the above embodiments, and various simple modifications may be made to the technical solution of the present disclosure within the technical idea of the present disclosure, and these simple modifications all belong to the protection scope of the present disclosure.
It should be noted that, in the foregoing embodiments, various features described in the above embodiments may be combined in any suitable manner, and in order to avoid unnecessary repetition, various combinations that are possible in the present disclosure are not described again.
In addition, any combination of various embodiments of the present disclosure may be made, and the same should be considered as the disclosure of the present disclosure, as long as it does not depart from the spirit of the present disclosure.
Claims (10)
1. An unmanned vehicle simulation method is characterized by comprising the following steps:
receiving a simulation request of a user, wherein the simulation request comprises a plurality of simulation requirements;
determining a plurality of simulation scenarios corresponding to the plurality of simulation requirements from a set of simulation scenarios;
splicing the plurality of simulation scenes to obtain a target simulation scene sequence;
and sending the target simulation scene sequence to the unmanned vehicle, wherein the target simulation scene sequence is used for simulating the unmanned vehicle.
2. The method according to claim 1, wherein each simulation scene corresponds to a simulation track, and the stitching the plurality of simulation scenes to obtain a target simulation scene sequence comprises:
splicing the plurality of simulation scenes to obtain a plurality of candidate simulation scene sequences;
aiming at each candidate simulation scene sequence, calculating a first area value of a simulation track corresponding to the candidate simulation scene sequence and a second area value of a convex hull of the simulation track;
calculating the ratio of the first area value to the second area value to obtain the area utilization rate of the candidate simulation scene sequence;
and taking the candidate simulation scene sequence with the highest area utilization rate as the target simulation scene sequence.
3. The method of claim 1, wherein determining a plurality of simulation scenarios from the set of simulation scenarios that correspond to the plurality of simulation requirements comprises:
determining a plurality of sets of simulation scenarios from the set of simulation scenarios, each set of simulation scenarios comprising a plurality of simulation scenarios corresponding to the plurality of simulation requirements;
the splicing of the plurality of simulation scenes to obtain a target simulation scene sequence comprises the following steps:
splicing a plurality of simulation scenes in each group of simulation scenes to obtain a plurality of candidate simulation scene sequences corresponding to the group of simulation scenes; and are
Determining a target candidate simulation scene sequence corresponding to the set of simulation scenes based on the area utilization ratio of each candidate simulation scene sequence;
and determining the target simulation scene sequence from the target candidate simulation scene sequences of each group of simulation scenes.
4. The method of claim 3, wherein each simulation scenario corresponds to a simulation trajectory, and wherein determining a target candidate simulation scenario sequence corresponding to the set of simulation scenarios based on an area utilization of each candidate simulation scenario sequence comprises:
aiming at each candidate simulation scene sequence, calculating a first area value of a simulation track corresponding to the candidate simulation scene sequence and a second area value of a convex hull of the simulation track;
calculating the ratio of the first area value to the second area value to obtain the area utilization rate of the candidate simulation scene sequence;
and taking the candidate simulation scene sequence with the highest area utilization rate as a target candidate simulation scene sequence of the group of simulation scenes.
5. The method of claim 3, wherein determining the sequence of target simulation scenes from the sequence of target candidate simulation scenes for each set of simulation scenes comprises:
and determining the target simulation scene sequence from the target candidate simulation scene sequences of each group of simulation scenes according to at least one of the area utilization rate of the target candidate simulation scene sequences, the length of the transition track, the priority of the simulation scenes and the quantity value of the transition scenes.
6. The method of claim 1, wherein determining a plurality of simulation scenarios from the set of simulation scenarios that correspond to the plurality of simulation requirements comprises:
aiming at each simulation requirement, dividing a plurality of simulation scene types;
randomly determining a target simulation scene type from the plurality of simulation scene types;
and sampling from the simulation scene set based on each target simulation scene type to obtain a plurality of simulation scenes.
7. The method of claim 1, wherein said partitioning a plurality of simulation scenario types for each of said simulation requirements, further comprises:
acquiring the quantity value of simulation scene samples in the simulation scene set;
reducing the number of simulated scene types when the number value of the simulated scene samples is less than a number threshold.
8. An unmanned vehicle simulation apparatus, comprising:
the simulation system comprises a receiving module, a simulation module and a simulation module, wherein the receiving module is used for receiving a simulation request of a user, and the simulation request comprises a plurality of simulation requirements;
a simulation trajectory determination module for determining a plurality of simulation scenarios corresponding to the plurality of simulation requirements from a set of simulation scenarios;
the simulation track splicing module is used for splicing the plurality of simulation scenes to obtain a target simulation scene sequence;
and the simulation track sending module is used for sending the target simulation scene sequence to the unmanned vehicle, and the target simulation scene sequence is used for simulating the unmanned vehicle.
9. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of the method according to any one of claims 1 to 7.
10. An electronic device, comprising:
a memory having a computer program stored thereon;
a processor for executing the computer program in the memory to carry out the steps of the method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111045958.9A CN113806862B (en) | 2021-09-07 | 2021-09-07 | Unmanned vehicle simulation method and device, storage medium and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111045958.9A CN113806862B (en) | 2021-09-07 | 2021-09-07 | Unmanned vehicle simulation method and device, storage medium and electronic equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113806862A true CN113806862A (en) | 2021-12-17 |
| CN113806862B CN113806862B (en) | 2022-08-30 |
Family
ID=78940817
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111045958.9A Active CN113806862B (en) | 2021-09-07 | 2021-09-07 | Unmanned vehicle simulation method and device, storage medium and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113806862B (en) |
Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100064373A1 (en) * | 2008-09-05 | 2010-03-11 | Iowa State University Research Foundation, Inc. | Cloaking with footprints to provide location privacy protection in location-based services |
| US20100250001A1 (en) * | 2009-03-24 | 2010-09-30 | Disney Enterprises | Systems and methods for tracking and balancing robots for imitating motion capture data |
| US20190138671A1 (en) * | 2017-11-07 | 2019-05-09 | Renesas Electronics Corporation | Simulation device and program |
| US20190146893A1 (en) * | 2017-11-13 | 2019-05-16 | Renesas Electronics Corporation | Simulation device, simulation system, simulation method, and simulation program |
| CN110807219A (en) * | 2019-10-16 | 2020-02-18 | 湖北亿咖通科技有限公司 | Three-dimensional simulation modeling method, device, terminal and storage medium for road network |
| CN110991022A (en) * | 2019-11-25 | 2020-04-10 | 西安工业大学 | Embedded city design scene simulation system and method |
| CN111324945A (en) * | 2020-01-20 | 2020-06-23 | 北京百度网讯科技有限公司 | Sensor scheme determination method, device, equipment and storage medium |
| US20210019946A1 (en) * | 2019-07-15 | 2021-01-21 | Samsung Electronics Co., Ltd. | System and method for augmented reality scenes |
| CN112307566A (en) * | 2020-11-12 | 2021-02-02 | 安徽江淮汽车集团股份有限公司 | Vehicle simulation test method, device, equipment and storage medium |
| US20210078590A1 (en) * | 2019-09-12 | 2021-03-18 | Baidu Online Network Technology (Beijing) Co., Ltd. | Method for constructing test scenario library, electronic device and medium |
| CN112668153A (en) * | 2020-12-11 | 2021-04-16 | 国汽(北京)智能网联汽车研究院有限公司 | Method, device and equipment for generating automatic driving simulation scene |
| CN112732585A (en) * | 2021-01-19 | 2021-04-30 | 北京三快在线科技有限公司 | Simulation test method and device |
| CN112818497A (en) * | 2021-04-19 | 2021-05-18 | 腾讯科技（深圳）有限公司 | Traffic simulation method, traffic simulation device, computer equipment and storage medium |
| CN113343425A (en) * | 2021-05-08 | 2021-09-03 | 北京三快在线科技有限公司 | Simulation test method and device |
-
2021
- 2021-09-07 CN CN202111045958.9A patent/CN113806862B/en active Active
Patent Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100064373A1 (en) * | 2008-09-05 | 2010-03-11 | Iowa State University Research Foundation, Inc. | Cloaking with footprints to provide location privacy protection in location-based services |
| US20100250001A1 (en) * | 2009-03-24 | 2010-09-30 | Disney Enterprises | Systems and methods for tracking and balancing robots for imitating motion capture data |
| US20190138671A1 (en) * | 2017-11-07 | 2019-05-09 | Renesas Electronics Corporation | Simulation device and program |
| US20190146893A1 (en) * | 2017-11-13 | 2019-05-16 | Renesas Electronics Corporation | Simulation device, simulation system, simulation method, and simulation program |
| US20210019946A1 (en) * | 2019-07-15 | 2021-01-21 | Samsung Electronics Co., Ltd. | System and method for augmented reality scenes |
| US20210078590A1 (en) * | 2019-09-12 | 2021-03-18 | Baidu Online Network Technology (Beijing) Co., Ltd. | Method for constructing test scenario library, electronic device and medium |
| CN110807219A (en) * | 2019-10-16 | 2020-02-18 | 湖北亿咖通科技有限公司 | Three-dimensional simulation modeling method, device, terminal and storage medium for road network |
| CN110991022A (en) * | 2019-11-25 | 2020-04-10 | 西安工业大学 | Embedded city design scene simulation system and method |
| CN111324945A (en) * | 2020-01-20 | 2020-06-23 | 北京百度网讯科技有限公司 | Sensor scheme determination method, device, equipment and storage medium |
| CN112307566A (en) * | 2020-11-12 | 2021-02-02 | 安徽江淮汽车集团股份有限公司 | Vehicle simulation test method, device, equipment and storage medium |
| CN112668153A (en) * | 2020-12-11 | 2021-04-16 | 国汽(北京)智能网联汽车研究院有限公司 | Method, device and equipment for generating automatic driving simulation scene |
| CN112732585A (en) * | 2021-01-19 | 2021-04-30 | 北京三快在线科技有限公司 | Simulation test method and device |
| CN112818497A (en) * | 2021-04-19 | 2021-05-18 | 腾讯科技（深圳）有限公司 | Traffic simulation method, traffic simulation device, computer equipment and storage medium |
| CN113343425A (en) * | 2021-05-08 | 2021-09-03 | 北京三快在线科技有限公司 | Simulation test method and device |
Non-Patent Citations (6)
| Title |
|---|
| ZHENGZHENG DONG等: "Real-time Motion Planning Based on MPC With Obstacle Constraint Convexification For Autonomous Ground Vehicles", 《2020 3RD INTERNATIONAL CONFERENCE ON UNMANNED SYSTEMS (ICUS)》 * |
| 唐霈: "LTE-M***隧道场景性能仿真评估", 《都市快轨交通》 * |
| 张勇等: "虚拟目标轨迹参数化设计与可视化仿真", 《***仿真学报》 * |
| 杨华: "基于视频的城市道路车辆自动检测与跟踪", 《中国优秀硕士学位论文全文数据库 (信息科技辑)》 * |
| 王冬宁: "面向混合仿真的无人车作战运用仿真通信设计与实现", 《价值工程》 * |
| 钱程扬: "融合时空特征的轨迹表征建模方法研究", 《中国博士学位论文全文数据库 (基础科学辑)》 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113806862B (en) | 2022-08-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP3614225B1 (en) | Method and apparatus for positioning autonomous vehicle | |
| CN113264066A (en) | Obstacle trajectory prediction method and device, automatic driving vehicle and road side equipment | |
| CN115167182B (en) | Automatic driving simulation test method, device, equipment and computer readable medium | |
| CN113093569A (en) | Automatic driving simulation test method, device, equipment and storage medium | |
| CN112671487B (en) | Vehicle testing method, server and testing vehicle | |
| CN108959805B (en) | Automatic-driving hardware-in-loop simulation cloud platform and method | |
| CN113119999B (en) | Method, device, equipment, medium and program product for determining automatic driving characteristics | |
| CN114694123A (en) | Traffic signal lamp sensing method, device, equipment and storage medium | |
| CN113806862B (en) | Unmanned vehicle simulation method and device, storage medium and electronic equipment | |
| CN111966111B (en) | Automatic power distribution based mobile charging equipment formation control method, system and device | |
| CN109711035A (en) | City model construction method and device | |
| CN112767211A (en) | Rescue resource recommendation method and device, electronic equipment and storage medium | |
| CN111381575B (en) | Automatic test method, device, server, electronic equipment and storage medium | |
| CN113946729B (en) | Data processing method and device for vehicle, electronic equipment and medium | |
| CN109827610A (en) | Method and apparatus for check sensor fusion results | |
| CN113460040B (en) | Parking path determination method and device, vehicle and storage medium | |
| CN114489996A (en) | Task scheduling method and device, electronic equipment and automatic driving vehicle | |
| CN111175055B (en) | Automatic driving distributed collaborative simulation method and device and terminal | |
| CN111091581B (en) | Pedestrian track simulation method, device and storage medium based on generation countermeasure network | |
| CN113470067A (en) | Data processing method, device, storage medium and processor | |
| CN110826584B (en) | Simulation image processing method and device, storage medium and electronic equipment | |
| CN112747756B (en) | Map construction method and device | |
| CN113432885B (en) | Method, apparatus, and storage medium for determining lane test route of unmanned vehicle | |
| CN115587496B (en) | Test method, device, equipment, system and storage medium based on vehicle-road cooperation | |
| CN113126620B (en) | Path planning model training method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |