Traffic flow simulation scene construction method and system based on real data

Abstract

The present invention relates to the technical field of traffic simulation, and provides a method and system for constructing a traffic flow simulation scene based on real data. The method comprises: obtaining real traffic flow data; under collision constraints, calculating the corrected motion state of the real-scene non-reference vehicle according to the original motion state of the real-scene non-reference vehicle in the real traffic flow data and the simulated motion state of the simulated scene reference vehicle in the simulation information; and obtaining the traffic flow simulation scene construction result according to the corrected motion state of the real-scene non-reference vehicle. The present invention corrects the motion state of the non-reference vehicle in the real traffic flow data to obtain a traffic flow simulation scene based on simulation information, thereby avoiding the complex calculation process from scratch in the traditional simulation scene construction, and can more efficiently provide an environmental basis for the development and testing of autonomous driving or assisted driving.

Description

Technical Field

[0001] The present invention relates to the technical field of traffic simulation, and in particular to a method and system for constructing a traffic flow simulation scene based on real data. Background Art

[0002] Autonomous driving, also known as unmanned driving, computer driving or wheeled mobile robot, is a cutting-edge technology that relies on computers and artificial intelligence technology to complete complete, safe and effective driving without human control.

[0003] In the 21st century, due to the continuous increase in car users, road traffic is facing more and more serious problems such as congestion and safety accidents. With the support of vehicle networking technology and artificial intelligence technology, autonomous driving technology can coordinate travel routes and planning time, thereby greatly improving travel efficiency and reducing energy consumption to a certain extent. Autonomous driving can also help avoid safety hazards such as drunk driving and fatigue driving, reduce driver errors, and improve safety. Therefore, autonomous driving has become a research and development focus of various countries in recent years.

[0004] However, autonomous driving also faces many challenges, such as bad weather, complex traffic conditions, etc. Therefore, its performance in some scenarios may not be comparable to that of human drivers, and there may even be new and more serious accident risks (such as cyber attacks).

[0005] Some analyses show that with 95% confidence, an autonomous driving system would need to be tested on about 5 billion miles of roads to prove that its accident rate is significantly lower than that of human drivers. This means that 100 vehicles would need to be tested for about 225 years, 24 hours a day, 365 days a year, and at an average speed of 25 miles per hour.

[0006] It can be seen that in the long run, in the scenarios of autonomous driving or assisted driving, test development in simulation environments must account for a higher proportion in order to meet development and testing needs.

[0007] However, existing simulation scene construction methods usually require relatively complex calculations, resulting in a bottleneck in their construction efficiency. Therefore, how to provide a simulation scene construction method more efficiently has become a technical problem that needs to be urgently solved in the industry. Summary of the invention

[0008] The present invention provides a method and system for constructing a traffic flow simulation scene based on real data, so as to solve the defect of low efficiency in constructing simulation scenes in the prior art and realize efficient construction of simulation scenes based on real data.

[0009] The present invention provides a method for constructing a traffic flow simulation scene based on real data, comprising:

[0010] Acquire real traffic flow data; the real traffic flow data is collected by real scene benchmark vehicles;

[0011] Under the collision constraint, according to the original motion state of the real-scene non-reference vehicle in the real traffic flow data and the simulated motion state of the simulated-scene reference vehicle in the simulation information, a modified motion state of the real-scene non-reference vehicle is calculated; the change amount of the modified motion state relative to the original motion state belongs to a set change amount interval;

[0012] According to the corrected motion state of the non-reference vehicle in the real scene, a traffic flow simulation scene construction result is obtained.

[0013] According to a method for constructing a traffic flow simulation scene based on real data provided by the present invention, the simulation information is a single frame of data acquired in real time during a test; the real traffic flow data is a single frame of data corresponding one-to-one to the simulation information; the traffic flow simulation scene construction result is a single frame of data corresponding one-to-one to an input quantity; the input quantity includes the simulation information and the real traffic flow data.

[0014] According to a method for constructing a traffic flow simulation scene based on real data provided by the present invention, the collision constraint means that the distance between the real scene non-reference vehicle and the simulation scene reference vehicle is greater than a collision threshold; the collision threshold is calculated based on the size and motion state of the real scene non-reference vehicle and the simulation scene reference vehicle.

[0015] According to a method for constructing a traffic flow simulation scene based on real data provided by the present invention, the step of calculating the corrected motion state of the non-reference vehicle in the real scene according to the original motion state of the non-reference vehicle in the real traffic flow data and the simulated motion state of the reference vehicle in the simulation scene in the simulation information under the collision constraint comprises:

[0016] Determine the allowed motion state of the real-scene non-reference vehicle according to the original motion state of the real-scene non-reference vehicle in the real traffic flow data; the allowed motion state is a discrete value, and the change amount of the allowed motion state relative to the original motion state belongs to a set change amount interval;

[0017] Taking the distance between the real-scene non-reference vehicle and the simulation-scene reference vehicle in the allowed motion state as the collision constraint parameter and the motion state change of the real-scene non-reference vehicle relative to the simulation-scene reference vehicle in the allowed motion state as the change constraint parameter, the allowed motion state in which the collision constraint parameter is greater than the collision threshold and the change constraint parameter is less than the change threshold is calculated as the corrected motion state.

[0018] According to a method for constructing a traffic flow simulation scene based on real data provided by the present invention, the calculation obtains the allowed motion state in which the collision constraint parameter is greater than the collision threshold and the variation constraint parameter is less than the variation threshold, and the step of correcting the motion state includes:

[0019] Calculate the allowed motion state V p :

[0020] V p =min[w1×|vv r |+w2×e -d(v) ]

[0021] Where min is the minimum function; w1 is the change constraint weight; w2 is the collision constraint weight; v is the corrected motion state of the non-reference vehicle in the real scene; v r is the motion state of the non-reference vehicle in the real scene; |vv r | is a variation constraint parameter; d(v) is a collision constraint parameter, which is positively correlated with the distance between the non-reference vehicle after the real scene motion state is corrected and the reference vehicle in the simulation scene; e is the base of the natural logarithm.

[0022] According to a method for constructing a traffic flow simulation scene based on real data provided by the present invention, the motion state includes any one or any combination of a velocity vector, an acceleration vector, a vehicle size, and a vehicle position.

[0023] The present invention also provides a traffic flow simulation scene construction system based on real data, comprising:

[0024] An acquisition module is used to acquire real traffic flow data; the real traffic flow data is collected by real scene benchmark vehicles;

[0025] A correction module is used to calculate, under collision constraints, a corrected motion state of the real-scene non-reference vehicle according to the original motion state of the real-scene non-reference vehicle in the real traffic flow data and the simulated motion state of the simulated-scene reference vehicle in the simulation information; the change amount of the corrected motion state relative to the original motion state belongs to a set change amount interval;

[0026] The construction module is used to obtain a traffic flow simulation scene construction result according to the corrected motion state of the non-reference vehicle in the real scene.

[0027] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the steps of any of the above-mentioned methods for constructing a traffic flow simulation scene based on real data are implemented.

[0028] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the steps of the method for constructing a traffic flow simulation scene based on real data as described in any one of the above are implemented.

[0029] The present invention also provides a computer program product, comprising a computer program, which, when executed by a processor, implements the steps of any of the above-mentioned methods for constructing a traffic flow simulation scene based on real data.

[0030] The method and system for constructing a traffic flow simulation scene based on real data provided by the present invention obtain a traffic flow simulation scene based on simulation information by correcting the motion state of non-reference vehicles in real traffic flow data, thereby avoiding the complex calculation process from scratch in traditional simulation scene construction, and being able to more efficiently provide an environmental basis for the development and testing of autonomous driving or assisted driving. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0032] Figure 1 It is a flow chart of a method for constructing a traffic flow simulation scene based on real data provided by the present invention;

[0033] Figure 2 It is a structural schematic diagram of a traffic flow simulation scene construction system based on real data provided by the present invention;

[0034] Figure 3 It is a structural schematic diagram of the electronic device provided by the present invention.

[0035] Reference numerals:

[0036] 1: Get module; 2: Modify module; 3: Build module;

[0037] 310: processor; 320: communication interface; 330: memory;

[0038] 340: Communication bus. DETAILED DESCRIPTION

[0039] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0040] Combine the following Figure 1 The present invention describes a method for constructing a traffic flow simulation scene based on real data.

[0041] like Figure 1 As shown, an embodiment of the present invention provides a method for constructing a traffic flow simulation scene based on real data, comprising:

[0042] Step 101, obtaining real traffic flow data; the real traffic flow data is collected by real scene benchmark vehicles;

[0043] Step 103, under the collision constraint, according to the original motion state of the real scene non-reference vehicle in the real traffic flow data and the simulated motion state of the simulated scene reference vehicle in the simulation information, a modified motion state of the real scene non-reference vehicle is calculated; the change amount of the modified motion state relative to the original motion state belongs to a set change amount interval;

[0044] Step 105, obtaining a traffic flow simulation scene construction result according to the corrected motion state of the non-reference vehicle in the real scene.

[0045] In this embodiment, the real traffic flow data described in step 101 is selected real traffic flow data whose motion state of the real scene reference vehicle is similar to that of the simulation scene reference vehicle. For example, for the simulation requirement of a highway scene involving ramps and a speed limit of 120 kilometers per hour with an unmanned truck, the real traffic flow data of a highway scene involving ramps and a speed limit of 120 kilometers per hour with a real scene reference vehicle being a truck should be selected, and the motion state of the real scene reference vehicle, such as the motion speed, should be similar to that of the simulation scene reference vehicle in the simulation information (i.e., the difference / standard deviation is less than the set threshold).

[0046] The simulation scene construction result output by this embodiment essentially reflects the driving strategy of the non-reference vehicle in the simulation scene (the original information of the non-reference vehicle comes from real data) for the simulation scene reference vehicle, and cooperates with the driving strategy control of the simulation scene reference vehicle for the non-reference vehicle during the development and testing process, which more accurately simulates the actual situation of autonomous driving or assisted driving.

[0047] In a preferred embodiment, the method of this embodiment can iteratively update the traffic flow simulation scene construction method based on real data, thereby improving the performance of the assisted driving program:

[0048] The assisted driving program assists the driver in controlling the set vehicle to collect and obtain real traffic flow data;

[0049] Using the traffic flow simulation scene construction method based on real data, a traffic flow simulation scene is constructed according to the real traffic flow data;

[0050] Running the assisted driving program to perform a test in the traffic flow simulation scenario and recording the test results;

[0051] The assisted driving program is adjusted according to the test results.

[0052] The beneficial effects of this embodiment are:

[0053] By correcting the motion state of non-reference vehicles in real traffic flow data, a traffic flow simulation scenario based on simulation information is obtained, avoiding the complex calculation process from scratch in traditional simulation scenario construction, and providing an environmental basis for the development and testing of autonomous driving or assisted driving more efficiently.

[0054] According to the above embodiment, in this embodiment:

[0055] The simulation information is a single frame of data acquired in real time during the test; the real traffic flow data is a single frame of data corresponding one-to-one to the simulation information; the traffic flow simulation scene construction result is a single frame of data corresponding one-to-one to the input quantity; the input quantity includes the simulation information and the real traffic flow data.

[0056] It is worth noting that, in this embodiment, the collision constraint not only considers the possibility of collision in the current frame, thereby avoiding the overlapping and interlacing of vehicles, but also considers the predicted possibility of collision in future frames, thereby adjusting the motion state of non-reference vehicles more timely to be more in line with the vehicle control actions in actual driving scenarios.

[0057] The beneficial effects of this embodiment are:

[0058] This embodiment provides a real-time online method for constructing a traffic flow simulation scenario based on real data, so that non-reference vehicles in the simulation scenario (the original information of the non-reference vehicles comes from real data) can adjust their own driving strategies according to the real-time control strategies of the reference vehicles in the simulation scenario during the test, thereby simulating real traffic conditions more timely and accurately.

[0059] According to any of the above embodiments, in this embodiment:

[0060] The collision constraint means that the distance between the real-scene non-reference vehicle and the simulation-scene reference vehicle is greater than a collision threshold; the collision threshold is calculated based on the size and motion state of the real-scene non-reference vehicle and the simulation-scene reference vehicle.

[0061] The step of calculating the corrected motion state of the real-scene non-reference vehicle under the collision constraint according to the original motion state of the real-scene non-reference vehicle in the real traffic flow data and the simulated motion state of the simulated-scene reference vehicle in the simulation information comprises:

[0062] Determine the allowed motion state of the real-scene non-reference vehicle according to the original motion state of the real-scene non-reference vehicle in the real traffic flow data; the allowed motion state is a discrete value, and the change amount of the allowed motion state relative to the original motion state belongs to a set change amount interval;

[0063] Taking the distance between the real-scene non-reference vehicle and the simulation-scene reference vehicle in the allowed motion state as the collision constraint parameter and the motion state change of the real-scene non-reference vehicle relative to the simulation-scene reference vehicle in the allowed motion state as the change constraint parameter, the allowed motion state in which the collision constraint parameter is greater than the collision threshold and the change constraint parameter is less than the change threshold is calculated as the corrected motion state.

[0064] The step of calculating the allowed motion state in which the collision constraint parameter is greater than the collision threshold and the variation constraint parameter is less than the variation threshold as a step of correcting the motion state includes:

[0065] Calculate the allowed motion state V p :

[0066] V p =min[w1×|vv r |+w2×e -d(v) ]

[0067] Where min is the minimum function; w1 is the change constraint weight; w2 is the collision constraint weight; v is the corrected motion state of the non-reference vehicle in the real scene; v r is the motion state of the non-reference vehicle in the real scene; |vv r | is a variation constraint parameter; d(v) is a collision constraint parameter, which is positively correlated with the distance between the non-reference vehicle after the real scene motion state is corrected and the reference vehicle in the simulation scene; e is the base of the natural logarithm.

[0068] The motion state includes any one or any combination of a velocity vector, an acceleration vector, a vehicle size, and a vehicle position.

[0069] In summary, when selecting a scene set, the method of this embodiment selects a scene set in which the target speed of the vehicle in the simulation is close to the target speed of the vehicle in the scene. The motion state of the surrounding vehicles is determined by the motion state in the original data and the motion state of the vehicle in the simulation. The speed v of a certain vehicle in the surrounding area at a certain moment is calculated to be as close to the original data as possible. At the same time, collision avoidance with the vehicle is considered, an optimization model is established, and the final simulation scene construction result is obtained.

[0070] The beneficial effects of this embodiment are:

[0071] Simply considering extracting scene sets from real data for simulation testing has the following problems:

[0072] There is no interaction between the surrounding vehicles and the autonomous vehicle, resulting in collision and interweaving of the vehicle behind it, or the speed of the vehicle in the simulation is too different from the speed of the vehicle actually collecting data, resulting in no vehicles around the simulated vehicle.

[0073] Therefore, this embodiment takes into account the interaction between the vehicle and surrounding vehicles on the basis of the real scene, and based on the motion state of the reference vehicle and the motion state of the non-reference vehicle, additional weights are calculated to obtain the optimal motion state of the non-reference vehicle.

[0074] The following is a description of a traffic flow simulation scene construction device based on real data provided by the present invention. The traffic flow simulation scene construction device based on real data described below and the traffic flow simulation scene construction method based on real data described above can be referenced to each other.

[0075] The embodiment of the present invention further provides a traffic flow simulation scene construction system based on real data, comprising:

[0076] Acquisition module 1, used to acquire real traffic flow data; the real traffic flow data is collected by real scene benchmark vehicles;

[0077] Correction module 2 is used to calculate the corrected motion state of the real scene non-reference vehicle according to the original motion state of the real scene non-reference vehicle in the real traffic flow data and the simulated motion state of the simulated scene reference vehicle in the simulation information under the collision constraint; the change amount of the corrected motion state relative to the original motion state belongs to the set change amount interval;

[0078] The construction module 3 is used to obtain the traffic flow simulation scene construction result according to the corrected motion state of the non-reference vehicle in the real scene.

[0079] Furthermore, the correction module 2 comprises:

[0080] The allowed state submodule is used to determine the allowed motion state of the real scene non-reference vehicle according to the original motion state of the real scene non-reference vehicle in the real traffic flow data; the allowed motion state is a discrete value, and the change amount of the allowed motion state relative to the original motion state belongs to a set change amount interval;

[0081] The correction state submodule is used to use the distance between the real scene non-reference vehicle and the simulation scene reference vehicle in the allowed motion state as a collision constraint parameter and the change in the motion state of the real scene non-reference vehicle relative to the simulation scene reference vehicle in the allowed motion state as a change constraint parameter, and calculate the allowed motion state in which the collision constraint parameter is greater than the collision threshold and the change constraint parameter is less than the change threshold as the correction motion state.

[0082] The correction status submodule comprises:

[0083] Calculation unit, used to calculate the allowed motion state V p :

[0084] V p =min[w1×|vv r |+w2×e -d(v) ]

[0085] Where min is the minimum function; w1 is the change constraint weight; w2 is the collision constraint weight; v is the corrected motion state of the non-reference vehicle in the real scene; v r is the motion state of the non-reference vehicle in the real scene; |vv r | is a variation constraint parameter; d(v) is a collision constraint parameter, which is positively correlated with the distance between the non-reference vehicle after the real scene motion state is corrected and the reference vehicle in the simulation scene; e is the base of the natural logarithm.

[0086] Figure 3 An example of a physical structure diagram of an electronic device is shown in FIG. Figure 3As shown, the electronic device may include: a processor 310, a communication interface 320, a memory 330 and a communication bus 340, wherein the processor 310, the communication interface 320 and the memory 330 communicate with each other through the communication bus 340. The processor 310 may call the logic instructions in the memory 330 to execute a method for constructing a traffic flow simulation scene based on real data, the method comprising: obtaining real traffic flow data; the real traffic flow data is collected by a real scene reference vehicle; under collision constraints, according to the original motion state of the real scene non-reference vehicle in the real traffic flow data and the simulated motion state of the simulated scene reference vehicle in the simulation information, the modified motion state of the real scene non-reference vehicle is calculated; the change amount of the modified motion state relative to the original motion state belongs to a set change amount interval; according to the modified motion state of the real scene non-reference vehicle, the traffic flow simulation scene construction result is obtained.

[0087] In addition, the logic instructions in the above-mentioned memory 330 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0088] On the other hand, the present invention also provides a computer program product, which includes a computer program, which can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the traffic flow simulation scene construction method based on real data provided by the above-mentioned methods, the method including: obtaining real traffic flow data; the real traffic flow data is collected by real scene benchmark vehicles; under collision constraints, according to the original motion state of the real scene non-benchmark vehicle in the real traffic flow data, and the simulated motion state of the simulated scene benchmark vehicle in the simulation information, the corrected motion state of the real scene non-benchmark vehicle is calculated; the change of the corrected motion state relative to the original motion state belongs to a set change range; according to the corrected motion state of the real scene non-benchmark vehicle, the traffic flow simulation scene construction result is obtained.

[0089] On the other hand, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to execute the traffic flow simulation scene construction method based on real data provided by the above-mentioned methods, the method comprising: obtaining real traffic flow data; the real traffic flow data is collected by real scene benchmark vehicles; under collision constraints, according to the original motion state of the real scene non-benchmark vehicle in the real traffic flow data, and the simulated motion state of the simulated scene benchmark vehicle in the simulation information, a corrected motion state of the real scene non-benchmark vehicle is calculated; the change in the corrected motion state relative to the original motion state belongs to a set change range; according to the corrected motion state of the real scene non-benchmark vehicle, a traffic flow simulation scene construction result is obtained.

[0090] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0091] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0092] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for constructing a traffic flow simulation scene based on real data, characterized in that: include: Obtain real traffic flow data; The real traffic flow data is collected by real scene benchmark vehicles; Under the collision constraint, according to the original motion state of the real-scene non-reference vehicle in the real traffic flow data and the simulated motion state of the simulated-scene reference vehicle in the simulation information, a corrected motion state of the real-scene non-reference vehicle is calculated; The variation of the modified motion state relative to the original motion state belongs to a set variation range; Obtaining a traffic flow simulation scene construction result according to the corrected motion state of the non-reference vehicle in the real scene; The step of calculating the corrected motion state of the real-scene non-reference vehicle under the collision constraint according to the original motion state of the real-scene non-reference vehicle in the real traffic flow data and the simulated motion state of the simulated-scene reference vehicle in the simulation information comprises: Determine the allowed motion state of the real-scene non-reference vehicle according to the original motion state of the real-scene non-reference vehicle in the real traffic flow data; the allowed motion state is a discrete value, and the change amount of the allowed motion state relative to the original motion state belongs to a set change amount interval; Taking the distance between the real-scene non-reference vehicle and the simulation-scene reference vehicle in the allowed motion state as a collision constraint parameter and the motion state change amount of the real-scene non-reference vehicle relative to the simulation-scene reference vehicle in the allowed motion state as a change constraint parameter, the allowed motion state in which the collision constraint parameter is greater than a collision threshold and the change constraint parameter is less than the change threshold is calculated as a corrected motion state; The step of calculating the allowed motion state in which the collision constraint parameter is greater than the collision threshold and the variation constraint parameter is less than the variation threshold as a step of correcting the motion state includes: Calculate the allowed motion state V p : V p =min[w1×|vv r |+w2×e -d(v) ] Where min is the minimum function; w1 is the change constraint weight; w2 is the collision constraint weight; v is the corrected motion state of the non-reference vehicle in the real scene; v r is the motion state of the non-reference vehicle in the real scene; |vv r | is a variation constraint parameter; d(v) is a collision constraint parameter, which is positively correlated with the distance between the non-reference vehicle after the motion state of the non-reference vehicle in the real scene is corrected and the reference vehicle in the simulation scene; e is the base of the natural logarithm.

2. The method for constructing a traffic flow simulation scene based on real data according to claim 1, characterized in that: The simulation information is a single frame of data acquired in real time during the test; the real traffic flow data is a single frame of data corresponding one-to-one to the simulation information; the traffic flow simulation scene construction result is a single frame of data corresponding one-to-one to the input quantity; the input quantity includes the simulation information and the real traffic flow data.

3. The method for constructing a traffic flow simulation scene based on real data according to claim 1, characterized in that: The collision constraint means that the distance between the real scene non-reference vehicle and the simulation scene reference vehicle is greater than the collision threshold; The collision threshold is calculated based on the size and motion state of the non-reference vehicle in the real scene and the reference vehicle in the simulation scene.

4. The method for constructing a traffic flow simulation scene based on real data according to any one of claims 1 to 3, characterized in that: The motion state includes any one or any combination of a velocity vector, an acceleration vector, a vehicle size, and a vehicle position.

5. A traffic flow simulation scene construction system based on real data, characterized in that: include: Acquisition module, used to obtain real traffic flow data; The real traffic flow data is collected by real scene benchmark vehicles; A correction module, used for calculating, under collision constraints, a corrected motion state of the real-scene non-reference vehicle according to the original motion state of the real-scene non-reference vehicle in the real traffic flow data and the simulated motion state of the simulated-scene reference vehicle in the simulation information; The variation of the modified motion state relative to the original motion state belongs to a set variation range; A construction module, used to obtain a traffic flow simulation scene construction result according to the corrected motion state of the non-reference vehicle in the real scene; The correction module calculates the corrected motion state of the real scene non-reference vehicle according to the original motion state of the real scene non-reference vehicle in the real traffic flow data and the simulated motion state of the simulated scene reference vehicle in the simulation information under the collision constraint, and the steps include: Determine the allowed motion state of the real-scene non-reference vehicle according to the original motion state of the real-scene non-reference vehicle in the real traffic flow data; the allowed motion state is a discrete value, and the change amount of the allowed motion state relative to the original motion state belongs to a set change amount interval; Taking the distance between the real-scene non-reference vehicle and the simulation-scene reference vehicle in the allowed motion state as a collision constraint parameter and the motion state change amount of the real-scene non-reference vehicle relative to the simulation-scene reference vehicle in the allowed motion state as a change constraint parameter, the allowed motion state in which the collision constraint parameter is greater than a collision threshold and the change constraint parameter is less than the change threshold is calculated as a corrected motion state; The correction module calculates and obtains the allowed motion state in which the collision constraint parameter is greater than the collision threshold and the variation constraint parameter is less than the variation threshold, and the step of correcting the motion state includes: Calculate the allowed motion state V p : V p =min[w1×|vv r |+w2×e -d(v) ] Where min is the minimum function; w1 is the change constraint weight; w2 is the collision constraint weight; v is the corrected motion state of the non-reference vehicle in the real scene; v r is the motion state of the non-reference vehicle in the real scene; |vv r | is a variation constraint parameter; d(v) is a collision constraint parameter, which is positively correlated with the distance between the non-reference vehicle after the motion state of the non-reference vehicle in the real scene is corrected and the reference vehicle in the simulation scene; e is the base of the natural logarithm.

6. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the steps of the method for constructing a system for traffic flow simulation scenarios based on real data as described in any one of claims 1 to 4 are implemented.

7. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method for constructing a system for traffic flow simulation scenarios based on real data as claimed in any one of claims 1 to 4 are implemented.

8. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method for constructing a system for traffic flow simulation scenarios based on real data as claimed in any one of claims 1 to 4 are implemented.

Images