Fuel consumption simulation test method and device, electronic equipment and storage medium

By simulating fuel consumption test scenarios obtained from a scenario library in autonomous freight trucks, the problem of high fuel consumption testing costs for autonomous driving algorithms is solved, and efficient and low-cost fuel consumption optimization and problem discovery are achieved.

CN115880808BActive Publication Date: 2025-11-21ALIBABA DAMO (HANGZHOU) TECH CO LTD
View PDF 2 Cites 0 Cited by

Patent Information

Application Number
CN202211648670.5
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2022-12-21
Publication Date
2025-11-21
Estimated Expiration
2042-12-21

AI Technical Summary

Technical Problem

Fuel consumption testing of autonomous freight trucks is costly and difficult to conduct efficiently. Existing simulation testing methods cannot effectively optimize autonomous driving algorithms to reduce fuel consumption.

Method used

By acquiring fuel consumption test scenarios from the scenario library, conducting simulation tests, obtaining fuel consumption information and determining the effectiveness of the scenarios, and selecting targeted further test scenarios, the simulation test of the autonomous driving algorithm can be realized.

Benefits of technology

Autonomous driving algorithms can be tested efficiently and at low cost without actual road testing, quickly identifying fuel consumption control issues and improving testing efficiency and accuracy.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN115880808B_ABST
    Figure CN115880808B_ABST
Patent Text Reader

Abstract

Embodiments of the present application provide an oil consumption simulation test method and device, electronic equipment and storage medium. The oil consumption simulation test method comprises: obtaining at least one first oil consumption test scene from each oil consumption test scene included in a scene library; performing simulation test on the automatic driving algorithm to be tested through the at least one first oil consumption test scene, and obtaining first oil consumption information of the automatic driving algorithm; determining scene effectiveness information of the automatic driving algorithm according to the first oil consumption information, wherein the scene effectiveness information is used to indicate the oil consumption distribution of the automatic driving algorithm on each type of first oil consumption test scene; obtaining at least one second oil consumption test scene from the scene library according to the scene effectiveness information; and performing simulation test on the automatic driving algorithm through the at least one second oil consumption test scene, and obtaining second oil consumption information of the automatic driving algorithm. The present scheme can efficiently test the automatic driving algorithm at a lower cost.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] This application relates to the field of autonomous driving technology, and in particular to a fuel consumption simulation test method, apparatus, electronic device, and storage medium. Background Technology

[0002] Before autonomous driving devices (such as vehicles and robots) can be truly commercialized, they need to undergo extensive road testing to meet commercial requirements. However, optimizing autonomous driving algorithms through actual road testing is both time-consuming and costly, and reproducing extreme traffic conditions and scenarios is difficult, posing safety risks during the testing process. Therefore, simulation testing based on scenario libraries has emerged. Simulation testing simulates the operation of autonomous driving devices in real-world driving environments, thus requiring the construction of simulated scenarios that mirror the real world; this can be specifically implemented as a simulation testing platform.

[0003] Fuel consumption costs account for a significant portion of total logistics costs for freight trucks. The fuel-saving performance of autonomous driving algorithms is of paramount importance for autonomous freight trucks. By testing the fuel consumption of autonomous freight trucks, the autonomous driving algorithms can be optimized based on the test results to reduce fuel consumption. Therefore, how to conduct efficient and low-cost testing of the fuel consumption of autonomous freight trucks is a pressing technical problem that needs to be solved. Summary of the Invention

[0004] In view of this, embodiments of this application provide a fuel consumption simulation test method, apparatus, electronic device, and storage medium to at least partially solve the above-mentioned problems.

[0005] According to a first aspect of the embodiments of this application, a fuel consumption simulation test method is provided, comprising: obtaining at least one first fuel consumption test scenario from a fuel consumption test scenario included in a scenario library, wherein the fuel consumption test scenario includes map information and driving behavior information; performing a simulation test on an autonomous driving algorithm to be tested through the at least one first fuel consumption test scenario to obtain first fuel consumption information of the autonomous driving algorithm; determining scenario validity information of the autonomous driving algorithm based on the first fuel consumption information, wherein the scenario validity information is used to indicate the fuel consumption distribution of the autonomous driving algorithm in various types of first fuel consumption test scenarios; obtaining at least one second fuel consumption test scenario from the scenario library based on the scenario validity information; and performing a simulation test on the autonomous driving algorithm through the at least one second fuel consumption test scenario to obtain second fuel consumption information of the autonomous driving algorithm.

[0006] According to a second aspect of the embodiments of this application, a fuel consumption simulation testing apparatus is provided, comprising: a first acquisition module, configured to acquire at least one first fuel consumption test scenario from a fuel consumption test scenario included in a scenario library, wherein the fuel consumption test scenario includes map information and driving behavior information; a first testing module, configured to perform simulation testing on an autonomous driving algorithm to be tested through the at least one first fuel consumption test scenario to obtain first fuel consumption information of the autonomous driving algorithm; an analysis module, configured to determine scenario effectiveness information of the autonomous driving algorithm based on the first fuel consumption information, wherein the scenario effectiveness information is used to indicate the fuel consumption distribution of the autonomous driving algorithm in various types of first fuel consumption test scenarios; a second acquisition module, configured to acquire at least one second fuel consumption test scenario from the scenario library based on the scenario effectiveness information; and a second testing module, configured to perform simulation testing on the autonomous driving algorithm through the at least one second fuel consumption test scenario to obtain second fuel consumption information of the autonomous driving algorithm.

[0007] According to a third aspect of the present application, an electronic device is provided, including: a processor, a memory, a communication interface, and a communication bus, wherein the processor, the memory, and the communication interface communicate with each other through the communication bus; the memory is used to store at least one executable instruction, which causes the processor to perform the operation corresponding to the method described in the first aspect.

[0008] According to a fourth aspect of the embodiments of this application, a computer storage medium is provided, on which a computer program is stored, which, when executed by a processor, implements the method described in the first aspect above.

[0009] According to a fifth aspect of the embodiments of this application, a computer program product is provided, including computer instructions that instruct a computing device to perform the method described in the first aspect above.

[0010] As can be seen from the above technical solution, after simulating and testing the autonomous driving algorithm in the first fuel consumption test scenario to obtain the first fuel consumption information, the scenario effectiveness information is determined based on the first fuel consumption information. The scenario effectiveness information can indicate the fuel consumption distribution of the autonomous driving algorithm in various types of first fuel consumption test scenarios. Then, based on the scenario effectiveness information, a second fuel consumption test scenario can be obtained from the scenario library, and the autonomous driving algorithm is then simulated and tested in the second fuel consumption test scenario to obtain the second fuel consumption information. By simulating and testing the autonomous driving algorithm in the first fuel consumption test scenario, the fuel consumption control effect of the autonomous driving algorithm in various fuel consumption test scenario types can be determined. Then, the second fuel consumption test scenario can be selected in a targeted manner to further simulate and test the autonomous driving algorithm, identify the problems existing in the autonomous driving algorithm, and test the autonomous driving algorithm efficiently and at low cost without conducting actual road tests. Attached Figure Description

[0011] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings.

[0012] Figure 1 This is a schematic diagram of an exemplary system applied in one embodiment of this application;

[0013] Figure 2 This is a flowchart of a fuel consumption simulation test method according to an embodiment of this application;

[0014] Figure 3 This is a schematic diagram of a fuel consumption simulation testing device according to an embodiment of this application;

[0015] Figure 4 This is a schematic diagram of an electronic device according to an embodiment of this application. Detailed Implementation

[0016] The present application is described below based on embodiments, but it is not limited to these embodiments. In the detailed description of the present application below, certain specific details are described in detail. Those skilled in the art can fully understand the present application without these details. To avoid obscuring the essence of the present application, well-known methods, processes, and flows are not described in detail. Furthermore, the accompanying drawings are not necessarily drawn to scale.

[0017] First, some nouns or terms that appear in the description of the embodiments of this application shall be interpreted as follows.

[0018] Fuel consumption: Fuel consumption refers to the volume of fuel consumed by a vehicle while traveling a certain distance on the road, such as the volume of fuel consumed per kilometer or per 100 kilometers. The volume of fuel consumed per 100 kilometers is called fuel consumption per 100 kilometers.

[0019] Simulation testing: Simulation testing simulates the operation of autonomous driving equipment in a real driving environment. A pre-built fuel consumption test scenario is input into the autonomous driving algorithm, which outputs corresponding control commands. The autonomous driving algorithm is then verified based on the control commands.

[0020] Map information: Map information is a component of the fuel consumption test scenario, used to indicate the lane lines, driving direction, slope, ramp curvature, etc. of the road the vehicle is traveling on.

[0021] Driving behavior information: Driving behavior information is another component of the fuel consumption test scenario, used to indicate the vehicle's driving conditions, such as smooth traffic, congestion, stop-and-go traffic, etc.

[0022] Exemplary System

[0023] Figure 1 An exemplary system for a fuel consumption simulation test method applicable to embodiments of this application is shown. For example... Figure 1 As shown, the system may include a cloud server 102, a communication network 104, and at least one user device 106. Figure 1 The example shown is multiple user devices 106. It should be noted that the solution in this embodiment can be applied to both the cloud server 102 and the user devices 106.

[0024] The cloud server 102 can be any suitable device for storing information, data, programs, and / or any other suitable type of content, including but not limited to distributed storage system devices, server clusters, computing cloud server clusters, etc. In some embodiments, the cloud server 102 can perform any suitable function. For example, in some embodiments, the cloud server 102 can be used for fuel consumption simulation testing. As an optional example, in some embodiments, the cloud server 102 can select fuel consumption test scenarios from the scenario library in two separate steps to selectively choose fuel consumption test scenarios for simulating autonomous driving algorithms, thereby discovering problems with autonomous driving algorithms more quickly and improving the efficiency of simulating autonomous driving algorithms.

[0025] Communication network 104 can be any suitable combination of one or more wired and / or wireless networks. For example, communication network 104 can include any one or more of the following: the Internet, intranet, wide area network (WAN), local area network (LAN), wireless network, digital subscriber line (DSL) network, frame relay network, asynchronous transfer mode (ATM) network, virtual private network (VPN), and / or any other suitable communication network. User equipment 106 can be connected to communication network 104 via one or more communication links (e.g., communication link 112), and communication network 104 can be linked to cloud server 102 via one or more communication links (e.g., communication link 114). Communication links can be any communication link suitable for transmitting data between cloud server 102 and user equipment 106, such as network links, dial-up links, wireless links, hardwired links, any other suitable communication links, or any suitable combination of such links.

[0026] User device 106 may include any one or more user devices suitable for interaction. In some embodiments, when fuel consumption simulation testing is performed by cloud server 102, user device 106 may send a fuel consumption simulation test request to cloud server 102, specifying a scenario library and the autonomous driving algorithm to be tested in the request. This triggers cloud server 102 to read the fuel consumption test scenario from the scenario library according to the request, perform simulation testing on the corresponding autonomous driving algorithm, and feed back the simulation test results to user device 106. In other embodiments, user device 106 may perform fuel consumption simulation testing locally. User device 106 may include any suitable type of device; for example, user device 106 may include mobile devices, tablet computers, laptop computers, desktop computers, wearable computers, vehicle systems, and / or any other suitable type of user device.

[0027] This application embodiment mainly focuses on the process of fuel consumption simulation testing on cloud server 102 or user equipment 106. The fuel consumption simulation testing method will be described in detail later.

[0028] Fuel consumption simulation test method

[0029] Based on the above system, this application provides a fuel consumption simulation test method, which will be described in detail below through multiple embodiments.

[0030] Figure 2 This is a flowchart of a fuel consumption simulation test method according to an embodiment of this application. Figure 2 As shown, the fuel consumption simulation test method includes the following steps:

[0031] Step 201: Obtain at least one first fuel consumption test scenario from the fuel consumption test scenarios included in the scenario library.

[0032] The scenario library is a collection of multiple fuel consumption test scenarios; that is, the scenario library includes multiple fuel consumption test scenarios. The scenario library can be a local database or a cloud database, and this embodiment of the application does not limit this.

[0033] When simulating and testing autonomous driving algorithms, fuel consumption test scenarios serve as input. Based on these scenarios, the algorithms can simulate real-world driving environments to test the operation of autonomous driving equipment and output fuel consumption information. This information instructs the algorithms to control the fuel consumption of the autonomous driving equipment under the corresponding test scenarios. Fuel consumption test scenarios include map information and driving behavior information. Map information indicates road conditions, such as road type, gradient, turning radius, lane width, number of lanes, and lane direction. Driving behavior information indicates vehicle driving conditions, such as whether the road is clear, congested, or experiencing stop-and-go traffic.

[0034] When conducting fuel consumption simulation tests on autonomous driving algorithms, at least one fuel consumption test scenario is selected from the scenario library as the first fuel consumption test scenario for the autonomous driving algorithm. The fuel consumption test scenarios stored in the scenario library can be a combination of map information and driving behavior information, or they can be stored separately. If the scenario library stores fuel consumption test scenarios in the form of a combination of map information and driving behavior information, then one or more combined fuel consumption test scenarios are directly obtained from the scenario library as the first fuel consumption test scenario. If the scenario library stores map information and driving behavior information separately, then the map information and driving behavior information are obtained separately from the scenario library, and then combined to obtain one or more first fuel consumption test scenarios.

[0035] Step 202: Simulate and test the autonomous driving algorithm under test through each first fuel consumption test scenario to obtain the first fuel consumption information of the autonomous driving algorithm.

[0036] After obtaining the first fuel consumption test scenario, the autonomous driving algorithm to be tested is simulated and tested sequentially through each first fuel consumption test scenario to obtain the first fuel consumption information, including the test results corresponding to each first fuel consumption test scenario.

[0037] When simulating the autonomous driving algorithm using the first fuel consumption test scenario, the first fuel consumption test scenario is used as the input of the autonomous driving algorithm. The autonomous driving algorithm simulates the real driving environment based on the first fuel consumption test scenario to test the operation of the autonomous driving equipment and outputs test results including fuel consumption data.

[0038] Step 203: Based on the first fuel consumption information, determine the scenario effectiveness information of the autonomous driving algorithm.

[0039] Both map information and driving behavior information come in various types. Based on the different types of map information and driving behavior information included, fuel consumption test scenarios in the scenario library can be divided into different fuel consumption test scenario types. If two fuel consumption test scenarios include the same type of map information and the same type of driving behavior information, then these two fuel consumption test scenarios belong to the same fuel consumption test scenario type. If two fuel consumption test scenarios include different types of map information and / or different types of driving behavior information, then these two fuel consumption test scenarios belong to different fuel consumption test scenario types.

[0040] The first fuel consumption information includes the test results corresponding to each first fuel consumption test scenario. The test results include fuel consumption data. Based on the first fuel consumption information, the fuel consumption corresponding to each first fuel consumption test scenario can be statistically analyzed according to the type of fuel consumption test scenario, and the scenario validity information used to indicate the fuel consumption distribution of autonomous driving algorithms in each type of first fuel consumption test scenario can be determined.

[0041] Before calculating the fuel consumption for each first fuel consumption test scenario according to its type, the first fuel consumption test scenarios can be filtered to remove those whose fuel consumption exceeds a reasonable range. These filtered-out scenarios will not participate in the fuel consumption statistics based on the test scenario type. In some embodiments, a reasonable fuel consumption range can be predefined; if the fuel consumption of a first fuel consumption test scenario exceeds this range, that scenario is filtered out. In another embodiment, the first fuel consumption test scenarios to be filtered out can be determined manually.

[0042] Step 204: Based on the valid information of the scenario, obtain at least one second fuel consumption test scenario from the scenario library.

[0043] Since scenario validity information can indicate the fuel consumption distribution of autonomous driving algorithms in different fuel consumption test scenario types, the fuel consumption control effect of autonomous driving algorithms on each fuel consumption test scenario type can be determined based on the scenario validity information. Then, a second fuel consumption test scenario can be selected from the scenario library in a targeted manner based on the scenario validity information, and the autonomous driving algorithm can be further simulated and tested through the second fuel consumption test scenario.

[0044] In some cases, one or more target fuel consumption test scenario types with higher fuel consumption can be determined based on scenario validity information, and one or more fuel consumption test scenarios belonging to each target fuel consumption test scenario type can be selected from the scenario library as the second fuel consumption test scenario.

[0045] Step 205: Simulate and test the autonomous driving algorithm through various second fuel consumption test scenarios to obtain the second fuel consumption information of the autonomous driving algorithm.

[0046] After obtaining the second fuel consumption test scenario, the autonomous driving algorithm is simulated and tested sequentially through each second fuel consumption test scenario to obtain the second fuel consumption information, including the test results corresponding to each second fuel consumption test scenario.

[0047] Similar to the process of simulating and testing the autonomous driving algorithm through the first fuel consumption test scenario, when simulating and testing the autonomous driving algorithm through the second fuel consumption test scenario, the second fuel consumption test scenario is used as the input of the autonomous driving algorithm. The autonomous driving algorithm simulates the real driving environment based on the second fuel consumption test scenario to test the operation of the autonomous driving equipment and outputs test results including fuel consumption data.

[0048] In this embodiment, the autonomous driving algorithm is simulated and tested using a first fuel consumption test scenario to obtain first fuel consumption information. Based on this information, scenario validity information is determined. This validity information indicates the fuel consumption distribution of the autonomous driving algorithm across various types of first fuel consumption test scenarios. Then, a second fuel consumption test scenario is retrieved from a scenario library based on this validity information. The autonomous driving algorithm is then simulated and tested using this second scenario to obtain second fuel consumption information. Simulating and testing the autonomous driving algorithm using the first fuel consumption test scenario determines its fuel consumption control effectiveness across different test scenario types. This allows for targeted selection of a second fuel consumption test scenario for further simulation testing, identifying any problems with the algorithm. This approach enables efficient and low-cost testing of the autonomous driving algorithm without the need for actual road testing.

[0049] In one possible implementation, the number of first fuel consumption test scenarios is less than the number of second test scenarios. After simulating and testing the autonomous driving algorithm using the first fuel consumption test scenarios, the scenario effectiveness information is determined based on the first fuel consumption information. This scenario effectiveness information can then be used to determine the fuel consumption control effect of the autonomous driving algorithm on various types of fuel consumption test scenarios. Furthermore, it can identify the types of fuel consumption test scenarios where the autonomous driving algorithm performs poorly in fuel consumption control, quickly pinpointing the problems with the autonomous driving algorithm. Subsequently, a larger number of second fuel consumption test scenarios can be selected from these poorly performing fuel consumption test scenario types. These second fuel consumption test scenarios allow for more detailed simulation testing of the autonomous driving algorithm, ensuring both testing efficiency and the accuracy of the test results.

[0050] In one possible implementation, when obtaining the first fuel consumption test scenario from the various fuel consumption test scenarios included in the scenario library, m×n types of fuel consumption test scenarios can be obtained from the scenario library as the first fuel consumption test scenario based on the types of map information and driving behavior information included in the fuel consumption test scenario. Here, m represents the number of map information types, and n represents the number of driving behavior information types. Different types of fuel consumption test scenarios correspond to different combinations of map information and driving behavior information.

[0051] Fuel consumption test scenarios include map information and driving behavior information. Both map information and driving behavior information have multiple types. If the number of map information types is m and the number of driving behavior information types is n, the total number of fuel consumption test scenario types is m×n, depending on the combination of map information and driving behavior information types. Fuel consumption test scenarios of the same type include the same type of map information and the same type of driving behavior information. For each of the m×n fuel consumption test scenario types, at least one fuel consumption test scenario can be selected from the multiple fuel consumption test scenarios included in that type as the first fuel consumption test scenario.

[0052] When selecting the first fuel consumption test scenario from the various fuel consumption test scenarios included in a fuel consumption test scenario type, one or more fuel consumption test scenarios can be randomly selected from the various fuel consumption test scenarios included in the fuel consumption test scenario type as the first fuel consumption test scenario. Alternatively, one or more fuel consumption test scenarios with more difficult fuel consumption control can be selected as the first fuel consumption test scenario based on the difficulty of fuel consumption control among the various fuel consumption test scenarios included in the fuel consumption test scenario type.

[0053] When selecting the first fuel consumption test scenario from various fuel consumption test scenario types, the number of scenarios selected from different types can be the same or different. In one example, 200 first fuel consumption test scenarios are selected from fuel consumption test scenario type A, and 100 first fuel consumption test scenarios are selected from fuel consumption test scenario type B. In another example, 200 first fuel consumption test scenarios are selected from both fuel consumption test scenario type A and fuel consumption test scenario type B.

[0054] In this embodiment, depending on the different combinations of map information and driving behavior information included, there are m×n fuel consumption test scenario types in the scenario library. A first fuel consumption test scenario is selected from each fuel consumption test scenario type, so that the selected first fuel consumption test scenario can cover each fuel consumption test scenario type. Then, the autonomous driving algorithm is simulated and tested through various types of fuel consumption test scenarios to ensure the comprehensiveness of the simulation test of the autonomous driving algorithm and to discover the problems existing in the autonomous driving algorithm.

[0055] In one possible implementation, when determining the scenario effectiveness information of the autonomous driving algorithm based on the first fuel consumption information, the test fuel consumption corresponding to each fuel consumption test scenario type can be determined based on the first fuel consumption information. Then, based on the test fuel consumption corresponding to each fuel consumption test scenario type, a first score corresponding to that fuel consumption test scenario type is determined, thereby generating scenario effectiveness information including the first scores corresponding to each fuel consumption test scenario type. The first score is positively correlated with the test fuel consumption corresponding to the corresponding fuel consumption test scenario type.

[0056] The first fuel consumption information includes the fuel consumption corresponding to each first fuel consumption test scenario. Based on the first fuel consumption information and the fuel consumption test scenario type to which each first fuel consumption test scenario belongs, the test fuel consumption corresponding to each fuel consumption test scenario type can be determined. The test fuel consumption can reflect the overall fuel consumption of each first fuel consumption test scenario included in the corresponding fuel consumption test scenario type. After obtaining the test fuel consumption corresponding to the fuel consumption test scenario type, the first score corresponding to that fuel consumption test scenario type can be determined based on the test fuel consumption. The determined first score is positively correlated with the test fuel consumption.

[0057] In this embodiment, the test fuel consumption corresponding to each fuel consumption test scenario type is determined based on the first fuel consumption information. Then, a first score for the corresponding fuel consumption test scenario type is determined based on the test fuel consumption, generating scenario validity information including the first scores for each fuel consumption test scenario type. Since the first score is positively correlated with the corresponding test fuel consumption, the generated scenario validity information can accurately reflect the fuel consumption distribution of the autonomous driving algorithm across different fuel consumption test scenario types. This allows for targeted selection of a second fuel consumption test scenario from the scenario library based on the scenario validity information, improving the efficiency of simulation testing of the autonomous driving algorithm. Furthermore, the generation of scenario validity information including the first score, which is numerical data, facilitates subsequent processing based on the scenario validity information.

[0058] In one possible implementation, when determining the test fuel consumption corresponding to each fuel consumption test scenario type based on the first fuel consumption information, the average value of the fuel consumption corresponding to each first fuel consumption test scenario included in each fuel consumption test scenario type can be calculated based on the first fuel consumption information, and the settlement result can be determined as the test fuel consumption corresponding to that fuel consumption test scenario type.

[0059] The first fuel consumption information includes the fuel consumption corresponding to each first fuel consumption test scenario. Therefore, based on the first fuel consumption information and the fuel consumption test scenario type to which each first fuel consumption test scenario belongs, the average fuel consumption of each first fuel consumption test scenario included in each fuel consumption test scenario type can be calculated, and then the calculated average fuel consumption can be determined as the test fuel consumption corresponding to that fuel consumption test scenario type.

[0060] In this embodiment of the application, the average fuel consumption of each first fuel consumption test scenario included in the fuel consumption test scenario type is calculated as the test fuel consumption corresponding to the fuel consumption test scenario type. This allows the test fuel consumption to reflect the fuel consumption of each first fuel consumption test scenario included in the fuel consumption test scenario type as a whole, thereby reflecting the fuel consumption control effect of the autonomous driving algorithm on different types of fuel consumption test scenarios. This ensures the accuracy of the scenario validity information generated based on the test fuel consumption, and enables the scenario validity information to accurately reflect the fuel consumption distribution of the autonomous driving algorithm in each type of first fuel consumption test scenario.

[0061] In one possible implementation, when obtaining the second fuel consumption test scenario based on scenario validity information, m×n types of fuel consumption test scenarios can be obtained from the scenario library as the second fuel consumption test scenarios. Specifically, if the first score corresponding to a certain fuel consumption test scenario type is greater than a preset first score threshold, then the number of second fuel consumption test scenarios obtained from that fuel consumption test scenario type is greater than the number of first fuel consumption test scenarios obtained from that fuel consumption test scenario type. Conversely, if the first score corresponding to a certain fuel consumption test scenario type is less than or equal to the first score threshold, then the number of second fuel consumption test scenarios obtained from that fuel consumption test scenario type is less than the number of first fuel consumption test scenarios obtained from that fuel consumption test scenario type.

[0062] As described in the above embodiments, the number of map information types is m, and the number of driving behavior information types is n. Depending on the different combinations of map information and driving behavior information types, the number of fuel consumption test scenario types in the scenario library is m×n. For each of the m×n fuel consumption test scenario types, when selecting a second fuel consumption test scenario from that fuel consumption test scenario type based on scenario validity information, if the first score corresponding to that fuel consumption test scenario type is greater than the first score threshold, then the number of second fuel consumption test scenarios selected from that fuel consumption test scenario type is greater than the number of first fuel consumption test scenarios selected from that fuel consumption test scenario type. For example, the number of first fuel consumption test scenarios selected from that fuel consumption test scenario type is 200, and the number of second fuel consumption test scenarios selected from that fuel consumption test scenario type is 2000. If the first score corresponding to the fuel consumption test scenario type is less than or equal to the first score threshold, then the number of second fuel consumption test scenarios selected from the fuel consumption test scenario type is less than the number of first fuel consumption test scenario types selected from the fuel consumption test scenario type. For example, the number of first fuel consumption test scenarios selected from the fuel consumption test scenario type is 200, and the number of second fuel consumption test scenarios selected from the fuel consumption test scenario type is 50.

[0063] When there are multiple fuel consumption test scenario types for which the first score is greater than the first score threshold, the number of second fuel consumption test scenarios selected from these multiple fuel consumption test scenario types can be the same or different, and this embodiment of the application does not limit this. In one example, the first scores corresponding to fuel consumption test scenario type A and fuel consumption test scenario type B are both greater than the first score threshold, the number of second fuel consumption test scenarios selected from fuel consumption test scenario type A is 1000, and the number of second fuel consumption test scenarios selected from fuel consumption test scenario type B is 2000. In another example, the first scores corresponding to fuel consumption test scenario type A and fuel consumption test scenario type B are both greater than the first score threshold, and 1500 second fuel consumption test scenarios are selected from fuel consumption test scenario type A and fuel consumption test scenario type B respectively.

[0064] When there are multiple fuel consumption test scenario types for which the first score is less than or equal to the first score threshold, the number of second fuel consumption test scenarios selected from these multiple fuel consumption test scenario types may be the same or different, and this application embodiment does not limit this.

[0065] In this embodiment, if the first score corresponding to the fuel consumption test scenario type is less than or equal to the first score threshold, it indicates that the autonomous driving algorithm has low fuel consumption in that fuel consumption test scenario type. Therefore, it is unnecessary to conduct large-scale simulation tests on the autonomous driving algorithm using the fuel consumption test scenarios included in that fuel consumption test scenario type. Thus, a smaller number of second fuel consumption test scenarios are selected from that fuel consumption test scenario type to improve the efficiency of simulation testing of the autonomous driving algorithm. Conversely, if the first score corresponding to the fuel consumption test scenario type is greater than the first score threshold, it indicates that the autonomous driving algorithm has high fuel consumption in that fuel consumption test scenario type. More detailed and comprehensive testing using the fuel consumption test scenarios included in that fuel consumption test scenario type is required. Therefore, a larger number of second fuel consumption test scenarios are selected from that fuel consumption test scenario type to ensure the comprehensiveness of the simulation test of the autonomous driving algorithm and to identify any problems with the autonomous driving algorithm.

[0066] In one possible implementation, for each fuel consumption test scenario in the scenario library, a second score can be obtained when simulating multiple autonomous driving algorithms through that fuel consumption test scenario. This second score indicates the effectiveness of simulating the autonomous driving algorithms through the corresponding fuel consumption test scenario. If the sum of all the second scores for a certain fuel consumption test scenario is less than a preset second score threshold, then that fuel consumption test scenario is marked as unavailable.

[0067] After simulating and testing an autonomous driving algorithm through a fuel consumption test scenario, a second score for that fuel consumption test scenario can be generated based on the test results. The second score can indicate the effectiveness of simulating and testing the autonomous driving algorithm through that fuel consumption test scenario. If the second score is low, it means that the autonomous driving algorithm cannot be effectively simulated and tested through that fuel consumption test scenario.

[0068] For each fuel consumption test scenario, after obtaining multiple second scores corresponding to that scenario, the scores are summed. The sum is then compared to a preset second score threshold. If the sum is less than the threshold, the fuel consumption test scenario is marked as unavailable. Fuel consumption test scenarios marked as unavailable will not be selected as the first or second fuel consumption test scenario, thus optimizing and updating the fuel consumption test scenarios in the scenario library.

[0069] In this embodiment, after each simulation test of the autonomous driving algorithm using a fuel consumption test scenario, a second score for that fuel consumption test scenario can be determined based on the test results. This second score indicates the effectiveness of the simulation test of the autonomous driving algorithm using that fuel consumption test scenario. After summing the second scores for a fuel consumption test scenario, if the summation result is less than the second score threshold, it indicates that the fuel consumption test scenario is too simple or has inherent problems, making it unsuitable for effectively simulating different versions of the fuel consumption test algorithm. Therefore, the fuel consumption test scenario is marked as unusable, preventing it from being selected for subsequent fuel consumption simulation tests, thus improving the efficiency of simulating the autonomous driving algorithm.

[0070] In one possible implementation, for each fuel consumption test scenario, a third score for that scenario can be obtained by summing the second scores of each scenario. When retrieving the first fuel consumption test scenario from the scenario library, the N fuel consumption test scenarios with the largest third scores can be selected as the first fuel consumption test scenario based on the third scores of each scenario in the scenario library, where N is a positive integer greater than or equal to 1.

[0071] When determining the second score for a fuel consumption test scenario, if the fuel consumption during simulation testing of the autonomous driving algorithm in that scenario exceeds a preset fuel consumption threshold, then the second score for that fuel consumption test scenario is determined as the first standard score. If the fuel consumption during simulation testing of the autonomous driving algorithm in that scenario is less than or equal to the fuel consumption threshold, then the second score for that fuel consumption test scenario is determined as the second standard score. If the fuel consumption test scenario is marked as invalid, then the second score for that fuel consumption test scenario is determined as the third standard score. The first standard score is greater than the second standard score, and the second standard score is greater than the third standard score.

[0072] If the test fuel consumption in the fuel consumption test scenario is greater than the fuel consumption threshold, it indicates that the autonomous driving algorithm has greater difficulty controlling fuel consumption in this scenario. Therefore, this fuel consumption test scenario can effectively test the autonomous driving algorithm, and the larger first standard score is determined as the second score for this fuel consumption test scenario. If the test fuel consumption in the fuel consumption test scenario is less than or equal to the fuel consumption threshold, it indicates that the autonomous driving algorithm has less difficulty controlling fuel consumption in this scenario. Therefore, the simulation test effect of this fuel consumption test scenario is poor, and the smaller second standard score is determined as the second score for this fuel consumption test scenario.

[0073] When simulating an autonomous driving algorithm using a fuel consumption test scenario, if the fuel consumption test scenario is marked as invalid by the user, it means that the autonomous driving algorithm cannot be successfully simulated using the fuel consumption test scenario, or the test results obtained are not meaningful. In this case, the lower third standard score will be determined as the second score for the fuel consumption test scenario.

[0074] In one example, the first standard is scored as 1, the second standard as -1, and the third standard as -2.

[0075] It should be noted that when selecting the second fuel consumption test scenario from the scenario library, the process is similar to selecting the first fuel consumption test scenario; you can also prioritize selecting the fuel consumption test scenario with the highest third score as the second fuel consumption test scenario. Additionally, when selecting the first or second fuel consumption test scenario based on the fuel consumption test scenario type, you can select the fuel consumption test scenario with the highest third score for each fuel consumption test scenario type as the first or second fuel consumption test scenario.

[0076] In this embodiment, a second score is determined based on the test fuel consumption corresponding to each fuel consumption test scenario. Fuel consumption test scenarios with test fuel consumption greater than a fuel consumption threshold receive a higher second score, while those with test fuel consumption less than or equal to the threshold receive a lower second score. Fuel consumption test scenarios marked as invalid receive an even lower second score. By summing the second scores for each fuel consumption test scenario, a third score can be obtained. When selecting fuel consumption test scenarios from the scenario library to simulate autonomous driving algorithms, priority is given to fuel consumption test scenarios with higher third scores. This allows for faster identification of problems in autonomous driving algorithms and improves the efficiency of simulation testing.

[0077] In one possible implementation, map information includes highway hub map information, ramp map information, etc., and driving behavior information includes congested driving behavior information, stop-and-go driving behavior information, etc.

[0078] In this application embodiment, highway hubs, interchanges, ramps, and slopes are map scenarios that have a significant impact on fuel consumption, while congestion and stop-and-go traffic are driving behaviors that have a significant impact on fuel consumption. By constructing fuel consumption test scenarios based on these representative map scenarios and representative driving behaviors that have a significant impact on fuel consumption, the fuel consumption performance of autonomous driving algorithms can be evaluated quickly and effectively, thereby improving the efficiency of fuel consumption simulation testing of autonomous driving algorithms.

[0079] In one possible implementation, the first fuel consumption information and / or the second fuel consumption information can be displayed using a preset information display template.

[0080] In this embodiment, after simulating the autonomous driving algorithm in a first fuel consumption test scenario and obtaining first fuel consumption information, the first fuel consumption information can be displayed using an information display template. Similarly, after simulating the autonomous driving algorithm in a second fuel consumption test scenario and obtaining second fuel consumption information, the second fuel consumption information can be displayed using an information display template. The information display template provides various templates such as graphs, tables, and curves to display the first and second fuel consumption information, facilitating a comprehensive evaluation and analysis of the fuel consumption of the autonomous driving algorithm and improving the user experience.

[0081] Fuel consumption simulation testing device

[0082] Corresponding to the above method embodiments, Figure 3 A schematic diagram of a fuel consumption simulation test apparatus according to an embodiment of this application is shown.

[0083] like Figure 3 As shown, the fuel consumption simulation test device includes:

[0084] The first acquisition module 301 is used to acquire at least one first fuel consumption test scenario from the various fuel consumption test scenarios included in the scenario library, wherein the fuel consumption test scenario includes map information and driving behavior information;

[0085] The first test module 302 is used to perform simulation tests on the autonomous driving algorithm to be tested through at least one first fuel consumption test scenario to obtain the first fuel consumption information of the autonomous driving algorithm.

[0086] Analysis module 303 is used to determine the scenario effectiveness information of the autonomous driving algorithm based on the first fuel consumption information, wherein the scenario effectiveness information is used to indicate the fuel consumption distribution of the autonomous driving algorithm in various types of first fuel consumption test scenarios;

[0087] The second acquisition module 304 is used to acquire at least one second fuel consumption test scenario from the scenario library based on scenario validity information.

[0088] The second test module 305 is used to perform simulation tests on the autonomous driving algorithm through at least one second fuel consumption test scenario to obtain the second fuel consumption information of the autonomous driving algorithm.

[0089] In this embodiment, the first testing module 302 simulates and tests the autonomous driving algorithm using a first fuel consumption test scenario to obtain first fuel consumption information. Then, the analysis module 303 determines scenario validity information based on the first fuel consumption information. Scenario validity information indicates the fuel consumption distribution of the autonomous driving algorithm across various types of first fuel consumption test scenarios. Subsequently, the second acquisition module 304 obtains a second fuel consumption test scenario from the scenario library based on the scenario validity information. The second testing module 305 then simulates and tests the autonomous driving algorithm using the second fuel consumption test scenario to obtain second fuel consumption information. By simulating and testing the autonomous driving algorithm using the first fuel consumption test scenario, the fuel consumption control effect of the autonomous driving algorithm in various fuel consumption test scenario types can be determined. This allows for targeted selection of the second fuel consumption test scenario for further simulation and testing of the autonomous driving algorithm, identifying existing problems. This allows for efficient and low-cost testing of the autonomous driving algorithm without the need for actual road testing.

[0090] It should be noted that the fuel consumption simulation test device in this embodiment is used to implement the corresponding fuel consumption simulation test method in the aforementioned method embodiment, and has the beneficial effects of the corresponding method embodiment, which will not be repeated here.

[0091] electronic devices

[0092] Figure 4 This is a schematic block diagram of an electronic device provided in an embodiment of this application. Specific embodiments of this application do not limit the specific implementation of the electronic device. Figure 4 As shown, the electronic device may include: a processor 402, a communications interface 404, a memory 406, and a communication bus 408. Wherein:

[0093] The processor 402, communication interface 404, and memory 406 communicate with each other via communication bus 408.

[0094] Communication interface 404 is used to communicate with other electronic devices or servers.

[0095] The processor 402 is used to execute program 410, specifically to execute the relevant steps in any of the aforementioned fuel consumption simulation test method embodiments.

[0096] Specifically, program 410 may include program code that includes computer operation instructions.

[0097] Processor 402 may be a CPU, an Application Specific Integrated Circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of this application. The smart device includes one or more processors, which may be processors of the same type, such as one or more CPUs; or processors of different types, such as one or more CPUs and one or more ASICs.

[0098] RISC-V is an open-source instruction set architecture based on the Reduced Instruction Set Computing (RISC) principle. It can be applied to various aspects of microcontrollers and FPGA chips, specifically in areas such as IoT security, industrial control, mobile phones, and personal computers. Because its design considers small size, speed, and low power consumption, it is particularly suitable for modern computing devices such as warehouse-scale cloud computers, high-end mobile phones, and tiny embedded systems. With the rise of AIoT (Artificial Intelligence of Things), the RISC-V instruction set architecture is receiving increasing attention and support and is expected to become the next generation of widely used CPU architecture.

[0099] The computer operation instructions in this embodiment can be computer operation instructions based on the RISC-V instruction set architecture. Correspondingly, the processor 402 can be designed based on the RISC-V instruction set. Specifically, the processor chip in the electronic device provided in this embodiment can be a chip designed using the RISC-V instruction set. This chip can execute executable code based on the configured instructions, thereby realizing the fuel consumption simulation test method in the above embodiment.

[0100] Memory 406 is used to store program 410. Memory 406 may include high-speed RAM memory, and may also include non-volatile memory, such as at least one disk storage device.

[0101] Specifically, program 410 can be used to cause processor 402 to execute the fuel consumption simulation test method in any of the foregoing embodiments.

[0102] The specific implementation of each step in program 410 can be found in the corresponding steps and units described in any of the aforementioned fuel consumption simulation test method embodiments, and will not be repeated here. Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working process of the equipment and modules described above can be referred to the corresponding process descriptions in the aforementioned method embodiments, and will not be repeated here.

[0103] The electronic device in this application embodiment performs simulation testing on an autonomous driving algorithm through a first fuel consumption test scenario. After obtaining first fuel consumption information, scenario validity information is determined based on the first fuel consumption information. The scenario validity information can indicate the fuel consumption distribution of the autonomous driving algorithm in various types of first fuel consumption test scenarios. Then, a second fuel consumption test scenario can be obtained from a scenario library based on the scenario validity information. The autonomous driving algorithm is then simulated and tested through the second fuel consumption test scenario to obtain second fuel consumption information. By simulating and testing the autonomous driving algorithm through the first fuel consumption test scenario, the fuel consumption control effect of the autonomous driving algorithm in various fuel consumption test scenario types can be determined. Then, the second fuel consumption test scenario can be selected in a targeted manner to further simulate and test the autonomous driving algorithm, identify the problems existing in the autonomous driving algorithm, and test the autonomous driving algorithm efficiently and at low cost without conducting actual road tests.

[0104] Computer storage media

[0105] This application also provides a computer-readable storage medium storing instructions for causing a machine to perform the fuel consumption simulation test method as described herein. Specifically, a system or apparatus equipped with a storage medium storing software program code that implements the functions of any of the embodiments described above, and enabling the computer (or CPU or MPU) of the system or apparatus to read and execute the program code stored in the storage medium.

[0106] In this case, the program code read from the storage medium can itself implement the function of any of the above embodiments, and therefore the program code and the storage medium storing the program code constitute part of this application.

[0107] Examples of storage media used to provide program code include floppy disks, hard disks, magneto-optical disks, optical disks (such as CD-ROM, CD-R, CD-RW, DVD-ROM, DVD-RAM, DVD-RW, DVD+RW), magnetic tapes, non-volatile memory cards, and ROMs. Alternatively, program code can be downloaded from a server computer via a communication network.

[0108] Computer program products

[0109] This application also provides a computer program product, including computer instructions that instruct a computing device to perform any corresponding operation in the above-described plurality of method embodiments.

[0110] It should be noted that, depending on the implementation needs, the various components / steps described in the embodiments of this application can be broken down into more components / steps, or two or more components / steps or parts of the operation of components / steps can be combined into new components / steps to achieve the purpose of the embodiments of this application.

[0111] The methods described in the embodiments of this application can be implemented in hardware, firmware, or as software or computer code that can be stored in a recording medium (such as a CD-ROM, RAM, floppy disk, hard disk, or magneto-optical disk), or as computer code downloaded over a network that is originally stored in a remote recording medium or a non-transitory machine-readable medium and will be stored in a local recording medium. Thus, the methods described herein can be processed by software stored on a recording medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware (such as an ASIC or FPGA). It is understood that the computer, processor, microprocessor controller, or programmable hardware includes storage components (e.g., RAM, ROM, flash memory, etc.) capable of storing or receiving software or computer code that, when accessed and executed by the computer, processor, or hardware, implements the methods described herein. Furthermore, when a general-purpose computer accesses code used to implement the methods shown herein, the execution of the code transforms the general-purpose computer into a dedicated computer for executing the methods shown herein.

[0112] Those skilled in the art will recognize that the units and method steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the embodiments of this application.

[0113] The above embodiments are only used to illustrate the embodiments of this application, and are not intended to limit the embodiments of this application. Those skilled in the art can make various changes and modifications without departing from the spirit and scope of the embodiments of this application. Therefore, all equivalent technical solutions also fall within the scope of the embodiments of this application, and the patent protection scope of the embodiments of this application should be defined by the claims.

Claims

1. A fuel consumption simulation test method, comprising: Obtain at least one first fuel consumption test scenario from the various fuel consumption test scenarios included in the scenario library, wherein the fuel consumption test scenario includes map information and driving behavior information; The autonomous driving algorithm to be tested is simulated and tested through at least one first fuel consumption test scenario to obtain the first fuel consumption information of the autonomous driving algorithm. Based on the first fuel consumption information, the scenario effectiveness information of the autonomous driving algorithm is determined, wherein the scenario effectiveness information is used to indicate the fuel consumption distribution of the autonomous driving algorithm in various types of the first fuel consumption test scenarios; Based on the scenario validity information, at least one second fuel consumption test scenario is obtained from the scenario library; The autonomous driving algorithm is simulated and tested using at least one second fuel consumption test scenario to obtain the second fuel consumption information of the autonomous driving algorithm. The step of obtaining at least one first fuel consumption test scenario from the fuel consumption test scenarios included in the scenario library includes: obtaining m×n types of fuel consumption test scenarios as the first fuel consumption test scenarios according to the types of map information and driving behavior information included in the fuel consumption test scenarios, where m is the number of types of map information and n is the number of types of driving behavior information, and different types of fuel consumption test scenarios correspond to different combinations of map information and driving behavior information; the step of determining the scenario effectiveness information of the autonomous driving algorithm according to the first fuel consumption information includes: determining the test fuel consumption corresponding to each fuel consumption test scenario type according to the first fuel consumption information; determining the first score corresponding to each fuel consumption test scenario type according to the test fuel consumption corresponding to each fuel consumption test scenario type, wherein the first score is positively correlated with the test fuel consumption corresponding to the corresponding fuel consumption test scenario type; and generating the scenario effectiveness information including the first score corresponding to each of the fuel consumption test scenario types; The step of obtaining at least one second fuel consumption test scenario from the scenario library based on the scenario validity information includes: obtaining m×n types of fuel consumption test scenarios from the scenario library as the second fuel consumption test scenarios based on the scenario validity information, wherein the number of second fuel consumption test scenarios included in the fuel consumption test scenario type corresponding to the first score being greater than a preset first score threshold is greater than the number of first fuel consumption test scenarios included in that fuel consumption test scenario type, and the number of second fuel consumption test scenarios included in the fuel consumption test scenario type corresponding to the first score being less than or equal to the first score threshold is less than or equal to the number of first fuel consumption test scenarios included in that fuel consumption test scenario type.

2. The method according to claim 1, wherein, The step of determining the test fuel consumption corresponding to each fuel consumption test scenario type based on the first fuel consumption information includes: Based on the first fuel consumption information, the average fuel consumption of each of the first fuel consumption test scenarios included in each fuel consumption test scenario type is calculated, and the calculation result is determined as the test fuel consumption corresponding to that fuel consumption test scenario type.

3. The method according to claim 1, wherein, The method further includes: For each of the fuel consumption test scenarios in the scenario library, a second score is obtained when at least two autonomous driving algorithms are simulated and tested through the fuel consumption test scenario, wherein the second score is used to indicate the effectiveness of simulating and testing the autonomous driving algorithm through the corresponding fuel consumption test scenario; If the sum of the second scores for each fuel consumption test scenario is less than a preset second score threshold, then the fuel consumption test scenario is marked as unavailable.

4. The method according to claim 3, wherein, The method further includes: for each fuel consumption test scenario, summing the second scores of each fuel consumption test scenario to obtain a third score for the fuel consumption test scenario, wherein if the test fuel consumption when simulating the autonomous driving algorithm through the fuel consumption test scenario is greater than a preset fuel consumption threshold, then the second score of the fuel consumption test scenario is determined to be a first standard score; if the test fuel consumption when simulating the autonomous driving algorithm through the fuel consumption test scenario is less than or equal to the fuel consumption threshold, then the second score of the fuel consumption test scenario is determined to be a second standard score; if the fuel consumption test scenario is marked as invalid, then the second score of the fuel consumption test scenario is determined to be a third standard score, wherein the first standard score is greater than the second standard score, and the second standard score is greater than the third standard score; The step of obtaining at least one first fuel consumption test scenario from the fuel consumption test scenarios included in the scenario library includes: The N fuel consumption test scenarios with the largest corresponding third scores in the scenario library are determined as the first fuel consumption test scenarios, where N is a positive integer greater than or equal to 1.

5. The method according to claim 1, wherein, The map information includes highway hub map information or ramp map information, and the driving behavior information includes congested driving behavior information.

6. The method according to any one of claims 1-5, wherein, The method further includes: The first fuel consumption information is displayed using a preset information display template, and / or the second fuel consumption information is displayed using the same information display template.

7. A fuel consumption simulation testing device, comprising: The first acquisition module is used to acquire at least one first fuel consumption test scenario from the various fuel consumption test scenarios included in the scenario library, wherein the fuel consumption test scenario includes map information and driving behavior information; The first test module is used to perform simulation tests on the autonomous driving algorithm to be tested through the at least one first fuel consumption test scenario, and obtain the first fuel consumption information of the autonomous driving algorithm. An analysis module is used to determine the scenario effectiveness information of the autonomous driving algorithm based on the first fuel consumption information, wherein the scenario effectiveness information is used to indicate the fuel consumption distribution of the autonomous driving algorithm in various types of the first fuel consumption test scenarios; The second acquisition module is used to acquire at least one second fuel consumption test scenario from the scenario library based on the scenario validity information. The second testing module is used to perform simulation testing on the autonomous driving algorithm through at least one second fuel consumption test scenario to obtain the second fuel consumption information of the autonomous driving algorithm. The step of obtaining at least one first fuel consumption test scenario from the fuel consumption test scenarios included in the scenario library includes: obtaining m×n types of fuel consumption test scenarios as the first fuel consumption test scenarios according to the types of map information and driving behavior information included in the fuel consumption test scenarios, where m is the number of types of map information and n is the number of types of driving behavior information, and different types of fuel consumption test scenarios correspond to different combinations of map information and driving behavior information; the step of determining the scenario effectiveness information of the autonomous driving algorithm according to the first fuel consumption information includes: determining the test fuel consumption corresponding to each fuel consumption test scenario type according to the first fuel consumption information; determining the first score corresponding to each fuel consumption test scenario type according to the test fuel consumption corresponding to each fuel consumption test scenario type, wherein the first score is positively correlated with the test fuel consumption corresponding to the corresponding fuel consumption test scenario type; and generating the scenario effectiveness information including the first score corresponding to each of the fuel consumption test scenario types; The step of obtaining at least one second fuel consumption test scenario from the scenario library based on the scenario validity information includes: obtaining m×n types of fuel consumption test scenarios from the scenario library as the second fuel consumption test scenarios based on the scenario validity information, wherein the number of second fuel consumption test scenarios included in the fuel consumption test scenario type corresponding to the first score being greater than a preset first score threshold is greater than the number of first fuel consumption test scenarios included in that fuel consumption test scenario type, and the number of second fuel consumption test scenarios included in the fuel consumption test scenario type corresponding to the first score being less than or equal to the first score threshold is less than or equal to the number of first fuel consumption test scenarios included in that fuel consumption test scenario type.

8. An electronic device, comprising: The processor, memory, communication interface, and communication bus communicate with each other through the communication bus. The memory is used to store at least one executable instruction that causes the processor to perform the operation corresponding to any one of the methods in claims 1-6.

9. A computer storage medium having a computer program stored thereon, which, when executed by a processor, implements the method of any one of claims 1-6.

10. A computer program product comprising computer instructions that instruct a computing device to perform the method of any one of claims 1-6.

Citation Information

Patent Citations

  • Simulation scene generation method and device

    CN114239301A

  • Scene library construction method and device, electronic equipment and storage medium

    CN114896166A