A method and device for developing an autonomous driving system, and a storage medium

Abstract

The application discloses a development method and device of an automatic driving system and a storage medium. The method comprises the following steps: acquiring a target driving scene and a plurality of preset detection items, wherein the target driving scene is any one of a plurality of driving scenes; determining detection information corresponding to the target driving scene under the plurality of preset detection items; and obtaining development information of the automatic driving system according to the detection information corresponding to the plurality of driving scenes. The technical solution provided in the application can assist in developing the automatic driving system and improve the efficiency of vehicle driving function development.

Description

Technical Field

[0001] This application relates to the field of intelligent connected vehicle technology, and in particular to a development method, apparatus and storage medium for an autonomous driving system. Background Technology

[0002] Since autonomous vehicles will face a variety of driving scenarios while driving on the road, they need to have the ability to cope with all possible and ever-changing driving scenarios in order to achieve a level of autonomous driving with a safety level of L3 or higher.

[0003] The investigation found that while some autonomous driving software or platforms in the industry have developed functions to cope with different driving scenarios, these functions only cover a portion of all possible and ever-changing scenarios. Furthermore, developers cannot grasp the full picture of the driving scenarios that the vehicle can handle, as well as the corresponding functional requirements. Without this understanding, it is difficult to determine whether existing driving scenarios meet the needs of urban autonomous driving. In addition, developers cannot utilize effective development resources to quickly expand the range of scenarios that can be handled, leading to problems such as low development efficiency.

[0004] Therefore, an auxiliary development technology solution for autonomous driving systems is needed to solve the problems existing in the above-mentioned technologies. Summary of the Invention

[0005] To address the problems of the prior art, this application provides a technical solution for the development method, apparatus, and storage medium of an autonomous driving system, as follows:

[0006] On the one hand, a development method for an autonomous driving system is provided, the method comprising:

[0007] Acquire a target driving scenario and multiple preset detection items, wherein the target driving scenario is any one of the multiple driving scenarios;

[0008] Determine the detection information corresponding to the target driving scenario under the multiple preset detection items;

[0009] The development information of the autonomous driving system is obtained based on the detection information corresponding to the multiple driving scenarios.

[0010] Furthermore, the development information includes development status information of the target driving scenario; obtaining the development information of the autonomous driving system based on the detection information includes:

[0011] The development status information of the target driving scenario is obtained based on the detection information.

[0012] Further, obtaining the development status information of the target driving scenario based on the detection information includes:

[0013] If the detection information of the target driving scenario under the multiple preset detection items all indicate a completed state, then the development status information of the target driving scenario is marked as a developed state.

[0014] Furthermore, after the step of obtaining the development information of the autonomous driving system based on the detection information corresponding to the multiple driving scenarios, the method further includes:

[0015] The ratio of the number of target driving scenarios whose development status information is in the developed state to the number of multiple driving scenarios is determined to obtain a first ratio result, which represents the development progress of the multiple driving scenarios.

[0016] Further, obtaining the development status information of the target driving scenario based on the detection information includes:

[0017] If the target driving scenario does not indicate a completed status in any of the multiple preset detection items, then the development status information of the target driving scenario is marked as undeveloped or under development.

[0018] Furthermore, it also includes:

[0019] The target driving scenario whose development status information indicates it is either undeveloped or under development.

[0020] Based on a first preset value of the target driving scenario, priority development information for the target detection item among a plurality of preset detection items to be developed is determined, wherein the first preset value represents the preset importance of the target driving scenario.

[0021] Further, the development information includes development information for the detection items corresponding to the target detection item, where the target detection item is any one of the plurality of preset detection items; obtaining the development information of the autonomous driving system based on the detection information includes:

[0022] Based on the detection development status corresponding to the detection information under the target detection item, determine the detection item development information corresponding to the target detection item.

[0023] Further, determining the detection information corresponding to the target driving scenario under the multiple preset detection items includes:

[0024] Determine the target detection item under the plurality of preset detection items corresponding to the target driving scenario;

[0025] Determine the detection development information corresponding to the target detection item.

[0026] On the other hand, a development apparatus for an autonomous driving system is provided, the apparatus comprising:

[0027] Acquisition module: used to acquire the target driving scene and multiple preset detection items, wherein the target driving scene is any one of the multiple driving scenes;

[0028] Detection information determination module: used to determine the detection information corresponding to the target driving scenario under the multiple preset detection items;

[0029] Development information determination module: used to obtain the development information of the autonomous driving system based on the detection information corresponding to the multiple driving scenarios.

[0030] On the other hand, a development device for an autonomous driving system is provided. The development device for an autonomous driving system includes a processor and a memory. The memory stores at least one instruction, at least one program, code set, or instruction set. The at least one instruction, the at least one program, the code set, or the instruction set is loaded and executed by the processor to implement the development method of the autonomous driving system as described above.

[0031] On the other hand, a computer-readable storage medium is provided, wherein at least one instruction, at least one program, code set, or instruction set is stored therein, wherein the at least one instruction, the at least one program, the code set, or the instruction set is loaded and executed by a processor to implement the development method of the autonomous driving system described above.

[0032] This application provides a development method, apparatus, and storage medium for an autonomous driving system, which has the following technical advantages:

[0033] This application embodiment obtains a target driving scenario and multiple preset detection items, wherein the target driving scenario is any one of the multiple driving scenarios, so as to associate the target driving scenario and the multiple preset detection items, thereby determining the detection information corresponding to the target driving scenario under the multiple preset detection items, so as to obtain the development information of the autonomous driving system based on the detection information corresponding to the multiple driving scenarios. The technical solution provided by this application can assist in the development of autonomous driving systems and improve the efficiency of vehicle driving function development. Attached Figure Description

[0034] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0035] Figure 1 A flowchart illustrating a development method for an autonomous driving system provided in an embodiment of this application;

[0036] Figure 2 A flowchart illustrating the analysis basis for generating driving scenarios provided in this application embodiment;

[0037] Figure 3 This is a proportional distribution diagram of algorithm coverage for driving scenarios provided in the embodiments of this application;

[0038] Figure 4 This is a flowchart illustrating the method for determining priority development information provided in an embodiment of this application.

[0039] Figure 5 A proportional distribution diagram of the algorithm coverage of each preset detection item in the embodiments of this application;

[0040] Figure 6 A schematic diagram of the structure of a development apparatus for an autonomous driving system provided in an embodiment of this application;

[0041] Figure 7 This is a schematic diagram of the structure of a server provided in an embodiment of this application. Detailed Implementation

[0042] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of this application.

[0043] It should be noted that this specification provides the operational steps of the methods described in the embodiments or flowcharts, but based on conventional or non-inventive labor, more or fewer operational steps may be included. The order of steps listed in the embodiments is merely one possible execution order among many steps and does not represent the only execution order.

[0044] Please see Figure 1 This is a flowchart illustrating a development method for an autonomous driving system provided in an embodiment of this application. The following is a summary of the process. Figure 1 The technical solution of this application is described in detail.

[0045] This application provides a method for developing an autonomous driving system, which specifically includes the following steps:

[0046] S101: Obtain the target driving scene and multiple preset detection items, wherein the target driving scene is any one of the multiple driving scenes.

[0047] In this embodiment, the target driving scenario is the driving scenario that the autonomous vehicle needs to deal with. The target driving scenario is a driving scenario composed of road information and target perception environment information. By obtaining a comprehensive and extensive target driving scenario that the autonomous vehicle may encounter during driving, a relatively complete driving scenario for the autonomous vehicle is generated, thereby improving the safety performance of the autonomous vehicle.

[0048] Specifically, road information can be the road data that the autonomous vehicle takes along in the global planning path from the starting point to the destination. For example, road information can be the lane information, lane change information, and driving status information of the autonomous vehicle. Among them, lane change information can be changing lanes to the left, changing lanes to the right, entering or exiting a ramp, etc., and driving status information can be going straight, turning left, turning right, making a U-turn, exiting the road, entering a roundabout, or parking, etc.

[0049] When autonomous vehicles are driving, they not only encounter complex and ever-changing road information, but also target perception environmental information that changes their driving trajectory. Specifically, target perception environmental information includes weather environmental factors, object factors, and road facility factors. Among them, weather environmental factors can be weather factors that affect the accurate identification of sensors or weather factors that affect the friction coefficient of the road surface. Object factors can be whether there are objects around the vehicle, the types of objects, the state of the objects, or the relative relationships between the objects and the autonomous vehicle, as well as between objects. Road facility factors can be whether there are traffic lights, the types of traffic lights, traffic facilities, or signs.

[0050] In practical applications, each target driving scenario can include any combination of road information and one or more target perception environment information. By arranging and combining road information and target perception environment information, driving scenarios that autonomous vehicles may encounter as much as possible during driving can be formed. By setting driving scenarios in advance, the driving stability of autonomous vehicles during driving can be effectively improved.

[0051] Specifically, such as Figure 2 As shown, it is a flowchart illustrating the process of generating analysis data corresponding to driving scenarios provided in an embodiment of this application. Figure 2 The arrangement and combination of road information and target perception environmental information are used to obtain a comprehensive driving scenario, enabling autonomous vehicles to cope with a variety of complex and ever-changing driving scenarios.

[0052] In another embodiment, the preset detection items are detection items set to address driving scenarios. Specifically, the preset detection items include perception items, prediction items, decision items, and trajectory production items. Perception items are used to perceive road information and target perception environment information present in the driving scenario. Prediction items are used to predict the information perceived by the perception items. Decision items are used to make judgments based on the prediction results. Trajectory production items are used to generate corresponding trajectories based on the judgment results. In practical applications, the prediction items required for different driving scenarios are determined so that corresponding algorithms can be developed based on the preset detection items, enabling autonomous vehicles to drive safely in the target driving scenario according to the corresponding algorithms.

[0053] S102: Determine the detection information corresponding to the target driving scenario under multiple preset detection items;

[0054] In an optional implementation, step S102 may include:

[0055] S1021: Determine the target detection items under multiple preset detection items corresponding to the target driving scenario.

[0056] S1022: Determine the detection development information corresponding to the target detection item.

[0057] In this embodiment of the application, the detection information is the detection item information required for the target driving scenario. Based on the target detection item corresponding to the determined target driving scenario and the detection development status corresponding to the target detection item, the development information of the target detection item corresponding to the target driving scenario is obtained, and then the development progress of the target driving scenario is determined. This allows algorithm developers to determine the undeveloped detection items corresponding to the target driving scenario based on the algorithm development status of the target driving scenario, thereby improving the development efficiency of the detection items by algorithm developers.

[0058] S103: Obtain development information for the autonomous driving system based on detection information corresponding to multiple driving scenarios.

[0059] In an optional implementation, the development information includes development status information of the target driving scenario; then step S103 may include:

[0060] S1031: Obtain the development status information of the target driving scenario based on the detection information.

[0061] In this embodiment, the development status information includes a developed state, a development in progress state, and an undeveloped state. Based on the development status information of the target driving scenario, the driving scenarios that the autonomous vehicle can handle and those that it cannot handle are determined. By statistically processing the development status information required for the target driving scenario, corresponding algorithms are developed for the target driving scenarios that are in the undeveloped state and those that are in the development in progress, so as to improve the autonomous vehicle's ability to handle more driving scenarios and improve the safety of the autonomous vehicle.

[0062] In another alternative implementation, step S1031 may include:

[0063] If the detection information of the target driving scenario under multiple preset detection items all indicate a completed state, then the development status information of the target driving scenario is marked as developed.

[0064] In another alternative implementation, step S1031 may further include:

[0065] If any detection information under multiple preset detection items for the target driving scenario does not indicate a completed status, then the development status information of the target driving scenario is marked as undeveloped or under development.

[0066] In this embodiment, by analyzing the algorithm development status of any detection information under multiple preset detection items for the target driving scenario, the target driving scenario that the autonomous vehicle can currently handle is determined. Based on the target driving scenarios that the autonomous vehicle can currently handle, a development strategy for the detection items is formulated so as to develop algorithms for preset detection items that are in the process of algorithm development or have not yet been developed. This allows the autonomous vehicle to handle more target driving scenarios, thereby enabling autonomous driving in complex, variable, and obstacle-ridden target driving scenarios and improving the safety of the autonomous vehicle.

[0067] Specifically, if the detection information for multiple target detection items in the target driving scenario indicates a completed state, that is, the multiple target detection items required for the target driving scenario are all in the algorithm development completed state, then the development status information of the target driving scenario is determined to be in the developed state; if any detection information for multiple target detection items in the target driving scenario does not indicate a completed state, that is, the detection information for any of the multiple target detection items required for the target driving scenario is in the algorithm development or algorithm not developed state, then the development status information of the target driving scenario is determined to be in the undeveloped state or in the development process, so that algorithm developers can develop algorithms for target driving scenarios in the undeveloped state or in the development process, and formulate algorithm development strategies to develop more target driving scenarios that autonomous vehicles can handle in an extreme time.

[0068] In practical applications, the correspondence between the development status information of the target driving scenario and the prediction items required for the target driving scenario is shown in Table 1. Specifically, Table 1 is as follows:

[0069]

[0070] The embodiments of this application will be described below using driving scenarios 1 and 5 as examples. As can be seen from Table 1, driving scenario 1 is a driving scenario with speed limit signs. The preset detection items required for driving scenario 1 include perception items, decision items, and trajectory production items. Among them, the perception item is used to identify the speed limit sign, the decision item is used to make an acceleration / deceleration judgment based on the current speed of the autonomous vehicle when the speed limit sign is perceived, and the trajectory production item is used to generate a planned trajectory for acceleration / deceleration based on the output of the decision item. In the detection items required for driving scenario 1, the algorithm development status corresponding to the perception item, the algorithm development status corresponding to the decision item, and the algorithm development status corresponding to the trajectory production item are all in the development completed state. Therefore, the development status information of driving scenario 1 is in the developed state. Thus, there is no need to develop the algorithm corresponding to the detection items required for driving scenario 1. That is, the autonomous vehicle can cope with driving scenario 1 and can drive normally in driving scenario 1.

[0071] Furthermore, as shown in Table 1, driving scenario 5 is a scenario where there is a static object in the lane the vehicle is traveling in and a vehicle is traveling in the adjacent lane to its left rear. The detection items required for driving scenario 5 include perception, prediction, decision, and trajectory production. The perception item is used to identify the static object and the vehicle; the prediction item is used to predict the driving intention of the vehicle in motion; the decision item is used to make a detour / deceleration decision based on the prediction result when the driving intention of the vehicle is predicted; and the trajectory production item is used to generate a corresponding planned trajectory based on the decision result. The corresponding planned trajectory can be deceleration and stopping, waiting for the vehicle to pass. After lane change, in the preset detection items required for driving scenario 5, at least one of the following must be in the algorithm development stage: the perception item, the decision item, and the trajectory production item. If there is no undeveloped algorithm, then the algorithm development stage corresponding to the detection item required for driving scenario 5 is in the algorithm development stage. Therefore, the detection items in the algorithm development stage need to be developed. It is understandable that autonomous vehicles cannot cope with driving scenario 5 and cannot drive normally in driving scenario 5. Therefore, algorithm developers need to develop algorithms for the detection items in driving scenario 5 that are not in the algorithm development completion stage to improve the efficiency of vehicle driving function development.

[0072] In an optional implementation, after step S103, the method may further include:

[0073] The ratio of the number of target driving scenarios with the development status information of "developed" to the total number of driving scenarios is determined to obtain the first ratio result, which represents the development progress of multiple driving scenarios.

[0074] In this embodiment of the application, by calculating the first ratio result representing the development progress of multiple driving scenarios, the proportion of target driving scenarios that the autonomous vehicle can cope with is determined, so as to assist algorithm developers in developing autonomous driving systems, enabling autonomous vehicles to cope with more driving scenarios, so as to cover more driving scenarios, and to fully grasp the algorithm development progress of each driving scenario, and then adjust development resources in a timely manner.

[0075] Specifically, the coverage of the target driving scenario is determined by the first ratio result, such as... Figure 3 As shown, from Figure 3 The system clearly shows the target driving scenario as being in a developed state, which helps in the development of autonomous driving systems, enabling functional developers to have a comprehensive understanding of the driving scenarios that autonomous vehicles can handle.

[0076] In one alternative implementation, such as Figure 4 The diagram shown is a flowchart illustrating a method for determining priority development information provided in an embodiment of this application. The method may further include:

[0077] S401: Obtain the development status information for the target driving scenario as either undeveloped or under development.

[0078] S402: Based on the first preset value of the target driving scenario, determine the priority development information of the target detection item among the multiple preset detection items to be developed, wherein the first preset value represents the importance of the target driving scenario.

[0079] In this embodiment, based on a first preset value of the target driving scenario, i.e., the preset importance of the target driving scenario, the algorithm development status of any one of the multiple target detection items is adjusted. Based on the adjusted algorithm development status of any one of the multiple target detection items, the ratio of the number of target driving scenarios with the adjusted development status information as developed to the number of multiple driving scenarios is calculated to obtain a second ratio result. Based on the first ratio result and the second ratio result, the rate of change of algorithm coverage of the target driving scenario is determined, and then the priority development information of the target detection items among the multiple preset detection items to be developed is determined, so as to improve development efficiency and develop more driving scenarios in the same time.

[0080] Specifically, the algorithm development status of any one of the multiple target detection items is adjusted, that is, the detection item that is in the undeveloped or under-development state is adjusted to the completed state. The preset importance of the target driving scenario can be determined in the order of driving performance, safety, riding experience, and intelligence. By adjusting the algorithm development status of the detection item and comparing the adjusted second ratio result with the original first ratio result, the change rate of algorithm coverage of the target driving scenario is obtained, that is, the change in algorithm coverage before and after the adjustment. Based on the change in algorithm coverage before and after the adjustment, an algorithm development strategy is formulated. The algorithm development strategy can be based on the magnitude of the change in the algorithm coverage of the target driving scenario that the autonomous vehicle can cope with before and after the adjustment, and the algorithm development order can be determined accordingly. That is, the greater the change in the algorithm coverage of the target driving scenario that the autonomous vehicle can cope with before and after the adjustment, the higher the priority of algorithm development, so as to improve the development efficiency of functional developers.

[0081] In an optional implementation, the development information includes development information for the target detection item, where the target detection item is any one of a plurality of preset detection items; then step S103 may include:

[0082] S1032: Determine the development information of the target detection item based on the development status of the detection information under the target detection item.

[0083] In this embodiment, the development information of the detection item refers to the development information corresponding to the detection item. This development information can be determined by the development status of the target detection item. Specifically, the algorithm coverage of each target detection item in the algorithm development completion state is calculated, i.e., the ratio of the number of detection items in the algorithm development completion state to the total number of target detection items is calculated, resulting in a third ratio. This third ratio represents the development progress of the target detection item, allowing algorithm developers to make reasonable resource allocations. For example, such as... Figure 5 As shown, from Figure 5 It can be seen that the algorithm coverage for decision-making and trajectory planning functions is low. We can increase the investment in algorithm development resources for decision-making and trajectory planning functions to improve the coverage of driving scenarios that autonomous vehicles can deal with during driving.

[0084] In one optional implementation, the perception function of the perceived item is realized through a preset sensor. The preset sensor can be one or more of LiDAR, millimeter-wave radar, camera, or ultrasonic radar. In practical applications, multiple preset sensors are set on autonomous vehicles. Since different preset sensors may have the same perception range or perceived object, the development status information corresponding to the perception information of different preset sensors is obtained. If the environmental information perceived by different preset sensors in the same driving scenario is consistent, and the development status information corresponding to the environmental information perceived by different preset sensors includes a development completed state, then the development status information of the perceived item required for the driving scenario is an algorithm development completed state. If the environmental information perceived by different preset sensors in the same driving scenario is consistent, and the development status information corresponding to the environmental information perceived by different preset sensors includes an algorithm development in progress state but no algorithm development completed state, then the development status information of the perceived item required for the target driving scenario is an algorithm development in progress state. This can avoid the repeated development of the perceived item corresponding to the driving scenario and improve the efficiency of algorithm development.

[0085] As can be seen from the above technical solutions of the embodiments of this application, the following technical effects are achieved:

[0086] This application embodiment obtains a target driving scenario and multiple preset detection items, wherein the target driving scenario is any one of the multiple driving scenarios, so as to associate the target driving scenario and the multiple preset detection items, thereby determining the detection information corresponding to the target driving scenario under the multiple preset detection items, so as to obtain the development information of the autonomous driving system based on the detection information corresponding to the multiple driving scenarios. The technical solution provided by this application can assist in the development of autonomous driving systems and improve the efficiency of vehicle driving function development.

[0087] This application also provides a development apparatus for an autonomous driving system, such as... Figure 6 As shown, this is a structural schematic diagram of a development device for an autonomous driving system provided in this embodiment. The device specifically includes the following modules:

[0088] Acquisition Module 10: Used to acquire the target driving scene and multiple preset detection items. The target driving scene can be any one of the multiple driving scenes.

[0089] Detection information determination module 20: used to determine the detection information corresponding to the target driving scenario under multiple preset detection items.

[0090] Development Information Determination Module 30: Used to obtain development information for the autonomous driving system based on detection information corresponding to multiple driving scenarios.

[0091] Preferably, the development information includes the development status information of the target driving scenario; therefore, the development information determination module 30 may include:

[0092] Development status information determination module 301: Obtains the development status information of the target driving scenario based on the detection information.

[0093] Preferably, the development status information determination module 301 includes:

[0094] First state marking module 3011: If the detection information of the target driving scene under multiple preset detection items all indicate a completed state, then mark the development state information of the target driving scene as a developed state.

[0095] Preferably, the device further includes:

[0096] The first ratio result determination module is used to determine the ratio of the number of target driving scenarios with the development status information of "developed" to the number of multiple driving scenarios, and obtain the first ratio result. The first ratio result represents the development progress of multiple driving scenarios.

[0097] Preferably, the development status information determination module 301 includes:

[0098] The second state marking module 3012 is used to mark the development status information of the target driving scenario as undeveloped or under development if any detection information under multiple preset detection items does not indicate a completed state.

[0099] Preferably, the device further includes:

[0100] Target driving scenario acquisition module: used to acquire target driving scenarios that are in an undeveloped state or under development.

[0101] Priority Development Information Determination Module: Based on a first preset value of the target driving scenario, this module determines the priority development information of the target detection item among multiple preset detection items to be developed. The first preset value represents the preset importance of the target driving scenario.

[0102] Preferably, the development information includes the development information of the detection item corresponding to the target detection item, and the target detection item is any one of a plurality of preset detection items; then the development information determination module 30 includes:

[0103] The detection item development information determination module is used to determine the detection item development information corresponding to the target detection item based on the detection development status corresponding to the detection information under the target detection item.

[0104] Preferably, the detection information determination module 20 includes:

[0105] The first determination module is used to determine the target detection items under multiple preset detection items corresponding to the target driving scenario.

[0106] The second determination module is used to determine the detection development information corresponding to the target detection item.

[0107] Regarding the apparatus in the above embodiments, the specific manner in which each module performs its operation has been described in detail in the embodiments related to the method, and will not be elaborated upon here.

[0108] This application provides a development apparatus for an autonomous driving system. The development apparatus includes a processor and a memory. The memory stores at least one instruction, at least one program, a code set, or an instruction set. The at least one instruction, the at least one program, the code set, or the instruction set is loaded and executed by the processor to implement the development method of the autonomous driving system provided in the above method embodiments.

[0109] Memory can be used to store software programs and modules. The processor executes various functional applications and data processing by running the software programs and modules stored in memory. Memory can mainly include a program storage area and a data storage area. The program storage area can store the operating system, application programs required for functions, etc.; the data storage area can store data created based on the use of the device, etc.

[0110] The development equipment for the autonomous driving system can be a server. This application embodiment also provides a schematic diagram of the server structure. Please refer to [link / reference]. Figure 7 The server 700 is used to implement the data processing method provided in the above embodiments. The server 700 can vary significantly due to different configurations or performance, and may include one or more processors 710 (e.g., one or more processors) and storage 730, and one or more storage media 720 (e.g., one or more mass storage devices) for storing applications 723 or data 722. The memory 730 and storage media 720 can be temporary or persistent storage. The program stored in the storage media 720 may include one or more modules, each module including a series of instruction operations on the server. Furthermore, the processor 710 may be configured to communicate with the storage media 720 and execute a series of instruction operations in the storage media 720 on the server 700. The server 700 may also include one or more power supplies 770, one or more wired or wireless network interfaces 750, one or more input / output interfaces 740, and / or one or more operating systems 721, such as Windows Server™, Mac OS X™, Unix™, Linux™, FreeBSD™, etc.

[0111] Embodiments of this application also provide a computer-readable storage medium, which can be disposed in a server to store at least one instruction, at least one program, code set, or instruction set related to the development method of an autonomous driving system in the method embodiment. The at least one instruction, the at least one program, the code set, or the instruction set is loaded and executed by the processor to implement the development method of the autonomous driving system provided in the above method embodiment.

[0112] It should be noted that the order of the embodiments described above is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. Furthermore, specific embodiments have been described above. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps described in the claims can be performed in a different order than that shown in the embodiments and still achieve the desired result. Additionally, the processes depicted in the drawings do not necessarily require a specific or sequential order to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0113] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, the system and server embodiments are basically similar to the method embodiments, so the descriptions are relatively simple; relevant parts can be referred to the descriptions of the method embodiments.

[0114] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A method for developing an autonomous driving system, characterized in that, The method includes: The system acquires a target driving scenario and multiple preset detection items. The target driving scenario is any one of multiple driving scenarios. The target driving scenario is a driving scenario composed of road information and target perception environment information. The multiple preset detection items include perception items, prediction items, decision items, and trajectory production items. Determine the detection information corresponding to the target driving scenario under the multiple preset detection items; The step of determining the detection information corresponding to the target driving scenario under the multiple preset detection items includes the following steps: Determine the target detection items under the plurality of preset detection items corresponding to the target driving scenario; Determine the detection development information corresponding to the target detection item; The development information of the autonomous driving system is obtained based on the detection information corresponding to the multiple driving scenarios, and the development information includes the development status information of the target driving scenario; The target driving scenario whose development status information is either undeveloped or under development. Based on a first preset value for the target driving scenario whose development status information is either undeveloped or under development, the algorithm development status of any one of the multiple target detection items is adjusted. The first preset value represents the importance of the target driving scenario. Based on the adjusted algorithm development status of any one of the multiple target detection items, the ratio of the number of target driving scenarios whose development status information is developed after adjustment to the number of multiple driving scenarios is calculated, and a second ratio result is obtained. Based on the ratio of the number of target driving scenarios whose development status information is developed before adjustment to the number of multiple driving scenarios, and the second ratio result, the priority development information of the target detection items among the multiple preset detection items to be developed is determined.

2. The method according to claim 1, characterized in that, The step of obtaining the development information of the autonomous driving system based on the detection information includes: The development status information of the target driving scenario is obtained based on the detection information.

3. The method according to claim 2, characterized in that, The step of obtaining the development status information of the target driving scenario based on the detection information includes: If the detection information of the target driving scenario under the multiple preset detection items all indicate a completed state, then the development status information of the target driving scenario is marked as a developed state.

4. The method according to claim 3, characterized in that, After the step of obtaining the development information of the autonomous driving system based on the detection information corresponding to the multiple driving scenarios, the method further includes: The ratio of the number of target driving scenarios whose development status information is in the developed state to the number of multiple driving scenarios is determined to obtain a first ratio result, which represents the development progress of the multiple driving scenarios.

5. The method according to claim 2, characterized in that, The step of obtaining the development status information of the target driving scenario based on the detection information includes: If the target driving scenario does not indicate a completed status in any of the multiple preset detection items, then the development status information of the target driving scenario is marked as undeveloped or under development.

6. The method according to claim 1, characterized in that, The development information includes development information for the detection item corresponding to the target detection item, wherein the target detection item is any one of the plurality of preset detection items; The step of obtaining the development information of the autonomous driving system based on the detection information includes: Based on the detection development status corresponding to the detection information under the target detection item, determine the detection item development information corresponding to the target detection item.

7. A development apparatus for an autonomous driving system, characterized in that, The device includes: Acquisition module: used to acquire the target driving scene and multiple preset detection items. The target driving scene is any one of multiple driving scenes. The target driving scene is a driving scene composed of road information and target perception environment information. The multiple preset detection items include perception items, prediction items, decision items and trajectory production items. Detection information determination module: used to determine the detection information corresponding to the target driving scenario under the multiple preset detection items; The detection information determination module includes a first determination module and a second determination module; The first determining module is used to determine the target detection item under the plurality of preset detection items corresponding to the target driving scenario; The second determining module is used to determine the detection development information corresponding to the target detection item; Development information determination module: used to obtain the development information of the autonomous driving system based on the detection information corresponding to the multiple driving scenarios, wherein the development information includes the development status information of the target driving scenario; Target driving scenario acquisition module: used to acquire target driving scenarios where the development status information is in an undeveloped state or under development; Priority Development Information Determination Module: Based on a first preset value indicating that the target driving scenario is in an undeveloped or developing state, adjust the algorithm development status of any one of the multiple target detection items, where the first preset value represents the importance of the target driving scenario. Based on the adjusted algorithm development status of any one of the multiple target detection items, calculate the ratio of the number of target driving scenarios with developed status information after adjustment to the total number of driving scenarios, and obtain a second ratio result. Based on the ratio of the number of target driving scenarios with developed status information before adjustment to the total number of driving scenarios, and the second ratio result, determine the priority development information of the target detection items among the multiple preset detection items to be developed.

8. A computer-readable storage medium, characterized in that, The storage medium stores at least one instruction or at least one program segment, which is loaded and executed by a processor to implement the development method of the autonomous driving system as described in any one of claims 1 to 6.

Images