An evaluation method and device for autonomous driving compliance

Abstract

The present invention discloses an evaluation method and device for autonomous driving compliance. A specific implementation manner of the method includes: obtaining current driving data generated by a target vehicle during autonomous driving; performing parsing processing on a preset compliance engine system configuration file to obtain a parsing result; based on the parsing result, calling a mathematical function library to perform compliance evaluation on the current driving data to generate a compliance evaluation result. This embodiment can convert legal language into logical descriptions and mathematical equivalence relationships; and generate software code in embedded language according to the logic and mathematical relationships, and then evaluate the current driving data of the target vehicle based on the software code to automatically generate a compliance evaluation result. Thereby, it is possible to automatically evaluate the compliance of autonomous driving based on the current driving data of the target vehicle; which not only meets the requirements of the target vehicle for autonomous driving, but also is applicable to different scenarios, improving the universality of the scheme application.

Description

Technical Field

[0001] The present invention belongs to the technical field of vehicle autonomous driving, and particularly relates to a method and device for evaluating the compliance of autonomous driving. Background Art

[0002] With the development of autonomous driving vehicles, autonomous driving vehicles and human-driven vehicles will share traffic facilities and should also jointly abide by the same traffic rules. However, the current traffic rules are compiled in natural language for human driving, and many of the languages are ambiguous, which easily leads to the inability of autonomous driving vehicles to accurately understand these traffic rules. Therefore, it is crucial to digitize the current traffic rules so that autonomous driving vehicles can understand and abide by the traffic rules. After digitizing the traffic rules, it is also convenient to realize the real-time compliance monitoring of the behavior of autonomous driving vehicles.

[0003] Currently, in order to monitor the compliance of the behavior of autonomous driving vehicles, a method and system for simulating the compliance test of traffic regulations for autonomous driving vehicles have been proposed. The system designs atomic propositions according to classification principles, writes and combines them in logical language to form formal traffic rules. By obtaining the information of traffic participants, corresponding to the formal traffic rules, and judging the truth or falsehood of the atomic propositions in the traffic rules based on the obtained information of traffic participants, it represents whether the traffic participants abide by the traffic rules. However, most atomic propositions are still ambiguous for autonomous driving vehicles, and the system has too high requirements for obtaining information, and many information is difficult to obtain or can only be obtained indirectly. The existing solution is only applicable to offline compliance judgment of the collected vehicle data, and has too high dependence on obtaining information, and cannot be used as the compliance monitoring of autonomous driving vehicles, and cannot meet the needs of vehicle autonomous driving.

[0004] There is also a method for monitoring the compliance of vehicle autonomous driving in the prior art, including obtaining the scene information where the target vehicle is located during the autonomous driving process, obtaining the trigger information corresponding to the compliance monitoring function during the autonomous driving process of the target vehicle from the scene information, and judging whether the trigger information meets the preset trigger conditions. If so, the compliance of the autonomous driving of the target vehicle is monitored by obtaining the corresponding monitoring information from the scene information through the compliance monitoring function. This monitoring method first analyzes the scene information, and then analyzes the relevant regulations that may appear and can be understood from the scene information. Therefore, this method can only monitor specific application scenarios, has limitations, and does not have universality. Summary of the Invention

[0005] In view of the above problems existing in the prior art, the embodiments of the present invention provide a method and device for evaluating the compliance of autonomous driving, which can automatically evaluate the compliance of autonomous driving based on the current driving data of the target vehicle, and meet the needs of the autonomous driving of the target vehicle.

[0006] According to the first aspect of the embodiments of the present invention, an evaluation method for autonomous driving compliance is provided. The method includes: obtaining current driving data generated by a target vehicle during autonomous driving; performing parsing processing on a preset compliance engine system configuration file to obtain a parsing result; based on the parsing result, calling a mathematical function library to perform compliance evaluation on the current driving data to generate a compliance evaluation result; where the current driving data at least includes: environmental perception data, self-vehicle state data, and path planning.

[0007] Optionally, the method further includes: converting a traffic regulation file corresponding to a target vehicle model in a target country into a machine-readable logical and formal language to generate a first condition library and a first rule library; establishing a mapping relationship between each legal field in the first condition library and a vehicle kinematic model to construct a condition analysis and modeling system; associating the condition analysis and modeling system with a mathematical model to output a system parameter table and a condition mathematical model library; determining the first condition library, the first rule library, and the system parameter table as a preset compliance engine system configuration file; converting the condition mathematical model library into a code generation system to generate a mathematical function library.

[0008] Optionally, the converting a traffic regulation file corresponding to a target vehicle model in a target country into a machine-readable logical and formal language to generate a first condition library and a first rule library includes: disassembling a traffic regulation file corresponding to a target vehicle model in a target country into a number of traffic law articles based on a regulation disassembler; for any target traffic law article among the number of traffic law articles: a semantic analysis model performs content filling processing on the target traffic law article to output a standard traffic law article; disassembling the standard traffic law article into a number of first conditions based on a law disassembler; generating a first condition library corresponding to the traffic regulation file based on the number of first conditions corresponding to each standard traffic law article; generating a corresponding first rule library by logically combining the first conditions in the first condition library based on a logical expression generator.

[0009] Optionally, the preset compliance engine system configuration file at least includes: a first condition library, a first rule library, and a system parameter table; the parsing process of the preset compliance engine system configuration file to obtain a parsing result includes: for any first rule in the first rule library: performing a rule parsing process on the first rule library and storing the rule parsing result according to the corresponding parsing value; the rule parsing result includes: at least two condition indexes and at least one logical operator; selecting a first condition corresponding to each condition index from the first condition library to generate a second condition library; for any first condition in the second condition library: performing a condition parsing process on the first condition and storing the condition parsing result according to the corresponding parsing value; the condition parsing result includes: at least one object and at least one function name; performing a parsing process on the system parameter table and outputting the parsed system parameter table; determining the parsed system parameter table, the rule parsing result, and the condition parsing result as the parsing result.

[0010] Optionally, the performing a rule parsing process on the first rule library and storing the rule parsing result according to the corresponding parsing value includes: obtaining the rule index number of the first rule; based on the rule index number, reading the fields in the first rule to obtain the current field; detecting the current field to obtain a first detection result; if the first detection result indicates that the current field is a logical operator, converting the logical operator to the corresponding parsing value for storage; if the first detection result indicates that the current field is not a logical operator, storing the condition index number when it is determined that the current field is a condition index number.

[0011] Optionally, the if the first detection result indicates that the current field is a logical operator, converting the logical operator to the corresponding parsing value for storage includes: if the first detection result indicates that the current field is a NOT operator, searching for the ending field of the NOT operator, and if the search result indicates that the ending field of the NOT operator is a parenthesis, converting the NOT operator and the adjacent parenthesis to the corresponding parsing value for storage; if the first detection result indicates that the current field is not a NOT operator, determining whether the current field is an AND or OR field; if the determination result indicates that the current field is an AND or OR field, converting the AND or OR field to the corresponding parsing value for storage.

[0012] Optionally, performing conditional parsing processing on the first condition and storing the conditional parsing result according to the corresponding parsed value includes: obtaining the condition index number of the first condition; based on the condition index number, performing a reading process on the fields in the first condition to obtain the current field; detecting the current field to obtain a second detection result; if the second detection result indicates that the current field is a valid mathematical operation quantity, storing the parsed value corresponding to the mathematical operation quantity; wherein the mathematical operation quantity at least includes: the name of a mathematical operator, and / or the name of a function, and / or a constant; if the second detection result indicates that the current field is not a valid mathematical operation quantity, storing the parsed value corresponding to the object when determining that the current field is an object.

[0013] Optionally, based on the parsing result, invoking a mathematical function library to perform a compliance evaluation on the current driving data and generating a compliance evaluation result includes: selecting a target object and a target function name corresponding to the current driving data from the parsing result; invoking a mathematical function corresponding to the target function name from the mathematical function library; based on the parsed system parameter list, using the mathematical function to evaluate the target object to generate a real-time condition evaluation result; performing a compliance evaluation on the condition evaluation result based on the rule parsing result to generate a real-time rule evaluation result.

[0014] Optionally, the method further includes: respectively generating corresponding real-time condition evaluation lists and real-time rule evaluation lists based on the real-time condition evaluation results and real-time rule evaluation results corresponding to each current driving data; performing traffic rule trigger analysis on the current driving data based on the real-time condition evaluation list to generate a regulation trigger report; performing violation analysis on the real-time rule evaluation list to output a compliance statistics report; and evaluating the current driving data based on the real-time rule evaluation list to output an event record report.

[0015] According to a second aspect of an embodiment of the present invention, there is also provided an apparatus for evaluating the compliance of an autonomous driving, where the apparatus includes: a collection module, configured to obtain current driving data generated by a target vehicle of the autonomous driving during driving; an analysis module, configured to perform an analysis process on a preset compliance engine system configuration file to obtain an analysis result; and an evaluation module, configured to, based on the analysis result, invoke a mathematical function library to perform a compliance evaluation on the current driving data and generate a compliance evaluation result.

[0016] According to a third aspect of an embodiment of the present invention, there is also provided an electronic device, including: a processor; a memory for storing executable instructions executable by the processor; the processor is configured to read the executable instructions from the memory and execute the instructions to implement the method as described in the first aspect.

[0017] According to a fourth aspect of the embodiments of the present invention, there is also provided a computer-readable medium, on which a computer program is stored, and when the program is executed by a processor, the method described in the first aspect is implemented.

[0018] The embodiments of the present invention provide a method and device for evaluating the compliance of autonomous driving. The method includes: First, obtain the current driving data generated by a target vehicle during driving; Second, perform parsing processing on a preset compliance engine system configuration file to obtain a parsing result; Then, based on the parsing result, call a mathematical function library to perform compliance evaluation on the current driving data to generate a compliance evaluation result. This embodiment can convert legal language into logical descriptions and mathematical equivalence relations; and generate software code in an embedded language according to this logic and mathematical relationship, and then evaluate the current driving data of the target vehicle based on this software code to automatically generate a compliance evaluation result. Thus, it is possible to automatically evaluate the compliance of autonomous driving based on the current driving data of the target vehicle; not only meeting the needs of the target vehicle for autonomous driving, but also being applicable to different scenarios and improving the universality of the scheme application. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Some specific embodiments of the present invention will be described in detail hereinafter with reference to the drawings in an exemplary but non-limiting manner. The same reference numerals in the drawings denote the same or similar components or parts. Those skilled in the art should understand that these drawings are not necessarily drawn to scale. In the drawings:

[0020] Figure 1 is a schematic flowchart of a method for evaluating the compliance of autonomous driving provided by an embodiment of the present invention;

[0021] Figure 2 is a schematic architecture diagram of a compliance engine system provided by an embodiment of the present invention;

[0022] Figure 3 is a schematic flowchart of rule parsing processing for a first rule in an embodiment of the present invention;

[0023] Figure 4 is a schematic flowchart of condition parsing processing for a first condition in an embodiment of the present invention;

[0024] Figure 5 is a schematic structural diagram of outputting a standard traffic law article after content filling processing in an embodiment of the present invention;

[0025] Figure 6 is a schematic diagram of the result of field disassembling and classification for a standard traffic law article;

[0026] Figure 7 is a schematic diagram of determining a physical model corresponding to function expression 2 in an embodiment of the present invention;

[0027] Figure 8 It is a schematic structural diagram of a system parameter table in an embodiment of the present invention;

[0028] Figure 9 It is a schematic structural diagram of a first rule library in an embodiment of the present invention;

[0029] Figure 10 It is a schematic structural diagram of a second condition library in an embodiment of the present invention;

[0030] Figure 11 It is a schematic diagram of a data flow in an evaluation method for autonomous driving compliance provided in another embodiment of the present invention;

[0031] Figure 12 It is a schematic structural diagram of an evaluation device for autonomous driving compliance provided in an embodiment of the present invention. Detailed implementation manners

[0032] To make the objectives, features, and advantages of the present invention more obvious and understandable, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative efforts shall fall within the protection scope of the present invention.

[0033] As Figure 1 shown, it is a schematic flowchart of an evaluation method for autonomous driving compliance provided in an embodiment of the present invention.

[0034] An evaluation method for autonomous driving compliance at least includes the following steps:

[0035] S101, obtaining current driving data generated by a target vehicle for autonomous driving during driving; wherein, the current driving data at least includes: environmental perception data, self-vehicle state data, and path planning;

[0036] S102, performing parsing processing on a preset compliance engine system configuration file to obtain a parsing result;

[0037] S103, based on the parsing result, calling a mathematical function library to perform compliance evaluation on the current driving data to generate a compliance evaluation result.

[0038] Specifically, the preset compliance engine system configuration file at least includes: a first condition library, a first rule library, and a system parameter table; wherein, the first condition library includes several first conditions, and the first conditions are used to indicate the logical judgment of specific scenarios included in the processing, analysis, and operation of objects in traffic laws; the first rules are used to indicate the logical judgment after combining at least two first conditions based on logical operators, as Figure 9 shown; the system parameter table is used to indicate the setting information of the compliance engine system itself and the constant information related to the autonomous vehicle itself, as Figure 8 shown; the mathematical function library is used to indicate a set of basic calculations composed of mathematical or geometric descriptions called for each first condition in the first condition library.

[0039] Such as Figure 8 shown, the setting information of the compliance engine system itself, such as the sampling frequency, the upper limit of the number of objects, etc., and the constant information related to the vehicle itself, such as the vehicle length, vehicle width, vehicle type, the maximum braking force reached by the vehicle, the braking force when expecting other vehicles to brake suddenly, etc., are stored in the system parameter table. These parameters will be assigned to the corresponding system constants during system initialization, converted into the unified International System of Units in the data processing unit, for example, the maximum speed limit on the highway: 120 km / h becomes 33.3 m / s, and stored in the memory.

[0040] Here, the compliance evaluation result can be a real-time rule evaluation list, and / or a real-time condition evaluation list, and / or a regulation trigger report, and / or a compliance statistics report, and / or an event record report.

[0041] Exemplarily, when the evaluation result is a real-time rule evaluation list and the real-time condition evaluation list;

[0042] Based on the parsing result, the mathematical function library is called to perform compliance evaluation on the current driving data, and a compliance evaluation result is generated; including: selecting a target object and a target function name corresponding to the current driving data from the parsing result; calling a mathematical function corresponding to the target function name from the mathematical function library; based on the parsed system parameter list, using the mathematical function to evaluate the target object to generate a real-time condition evaluation result; performing compliance evaluation on the condition evaluation result based on the rule parsing result to generate a real-time rule evaluation result. Based on the real-time condition evaluation result and the real-time rule evaluation result corresponding to each current driving data, a corresponding real-time condition evaluation list and a real-time rule evaluation list are respectively generated.

[0043] Exemplarily, when the evaluation result is a real-time rule evaluation list, a real-time condition evaluation list, a regulation trigger report, a compliance statistics report, and an event record report;

[0044] Based on the parsing result, call the mathematical function library to perform compliance evaluation on the current driving data, and generate a compliance evaluation result, including: selecting a target object and a target function name corresponding to the current driving data from the parsing result; calling a mathematical function corresponding to the target function name from the mathematical function library; based on the parsed system parameter list, using the mathematical function to evaluate the target object to generate a real-time condition evaluation result; performing compliance evaluation on the condition evaluation result based on the rule parsing result to generate a real-time rule evaluation result. Based on the real-time condition evaluation result and the real-time rule evaluation result corresponding to each current driving data, generate corresponding real-time condition evaluation lists and real-time rule evaluation lists respectively; perform traffic rule trigger analysis on the current driving data based on the real-time condition evaluation list to generate a regulation trigger report; perform violation analysis on the real-time rule evaluation list to output a compliance statistics report; evaluate the current driving data based on the real-time rule evaluation list to output an event record report.

[0045] In this embodiment, first load the preset compliance engine system configuration file in the target vehicle or related hardware, then receive the current driving data output by the corresponding environment perception module of the autonomous driving software stack, and analyze and process the current driving data to determine the violation behavior in the current driving scenario; thus, it is possible to automatically evaluate the compliance of autonomous driving based on the current driving data of the target vehicle; not only meets the requirements of vehicle autonomous driving, but also this solution can be applied to different scenarios, improving the universality of the solution application.

[0046] In a preferred implementation manner of this embodiment, feedback the evaluation result to the user; thereby improving the user experience.

[0047] In a preferred implementation manner of this embodiment, convert the traffic regulation file corresponding to the target vehicle model in the target country into a machine-readable logical and formal language to generate a first condition library and a first rule library; establish a mapping relationship between each legal field in the first condition library and the vehicle kinematics model to construct a condition analysis modeling system; associate the condition analysis modeling system with a mathematical model to output a system parameter table and a condition mathematical model library; determine the first condition library, the first rule library, and the system parameter table as the preset compliance engine system configuration file; convert the condition mathematical model library into a code generation system to generate a mathematical function library.

[0048] For example, convert all objects that are not measurement variable classes, such as dynamic objects like pedestrians, motor vehicles, trucks, etc., and static objects like zebra crossings, solid lines, dashed lines, no-go areas, traffic signs, etc. into corresponding geometric bodies, and use corresponding algebraic descriptions. For example, pedestrians can be described by rectangles, and motor vehicles, trucks, etc. can all be described by rectangular hexahedrons, and are described by the central coordinates, length, width, and height of the geometric body. The solid line on the ground can be described by a polyline, and is described by the coordinates of multiple points on the polyline. Based on this replacement, the two objects in the traffic law "motor vehicles are not allowed to drive on solid lines" (i.e., the solid line and the motor vehicle) are respectively converted into a polyline and a rectangle, and the physical discrimination of the object of driving on (the solid line) is transformed into a computational geometry problem of whether the polyline is inside the rectangle.

[0049] Exemplarily, converting the traffic regulation documents corresponding to the target vehicle models in the target country into machine-readable logical and formal languages to generate a first condition library and a first rule library includes: disassembling the traffic regulation documents corresponding to the target vehicle models in the target country into several traffic law articles based on a regulation disassembler; for any target traffic law article among the several traffic law articles: a semantic analysis model performs content filling processing on the target traffic law article and outputs a standard traffic law article; disassembling the standard traffic law article into several first conditions based on a law disassembler; generating a first condition library corresponding to the traffic regulation documents based on the several first conditions corresponding to each standard traffic law article; and generating a corresponding first rule library by logically combining the first conditions in the first condition library based on a logical expression generator.

[0050] Here, traffic regulation documents such as: Road Traffic Management Regulations, Road Traffic Law, UNECE R157 Automatic Lane Keeping System Regulations, judicial interpretations and case laws, etc. Target countries such as: China, the United States, the United Kingdom, Germany, etc.; target vehicle models such as: large trucks, cars, buses, coaches, etc.

[0051] For example: Based on the understanding of the traffic regulation documents by the semantic analysis model and the analysis of the target traffic law article, some information of the target traffic law article is supplemented to output a standard traffic law article; as Figure 5 shown, the blue part in the following text is the text supplemented by the semantic analysis model according to the context, which supplements the operating state described by the target traffic law article, and this operating state is essential for subsequent judgments.

[0052] As Figure 6 shown, disassembling the standard traffic law article into two conditions based on a law disassembler; each condition is parsed into an object and a logic (i.e., a function expression).

[0053] Condition 1: Whether (there is a vehicle in the same lane ahead (motor vehicle, lane) == true) == true;

[0054] Condition 2: (Is(Safe distance maintained with the vehicle ahead (the vehicle ahead, the following vehicle) == true) == true);

[0055] Is(There is a vehicle ahead in the same lane (motor vehicle, lane) == true) == true ∧ Is(Safe distance maintained with the vehicle ahead (the vehicle ahead, the following vehicle) == true) == true → Violation of regulations = true; where ∧, → are logical operators respectively; "Not" is represented as "And" is represented as ∧, "Condition" is represented as →, Is(...) == true is a comparison operator.

[0056] At this time, the logical meaning has changed from the original "When Condition 1 is satisfied, the system must execute or present the scenario described by Condition 2" to "When Condition 1 is satisfied and Condition 2 is not satisfied, the system's decision violates the corresponding regulations".

[0057] For each condition, the system will search for similar conditions in the previously defined condition library and give the corresponding description in formal language, as shown in the following example:

[0058] Condition described in words: When there is a motor vehicle driving in the same lane =>;

[0059] Condition described in formal language: Is(There is a vehicle ahead in the same lane (motor vehicle, lane) == true) == true;

[0060] Condition described in words: The following vehicle should maintain a sufficient distance from the vehicle ahead to take emergency braking measures =>;

[0061] Condition described in formal language: Is(Safe distance maintained with the vehicle ahead (the vehicle ahead, the following vehicle) == true) == true;

[0062] When there are no directly applicable conditions, based on the knowledge in the first condition library, the recommended expression for the new condition is generated. Then, the existing formal expression conditions are associated with known physical formulas, vehicle kinematic formulas, and mathematical models, and further converted into a geometric model to construct a machine-readable formal expression form, that is, a computable mathematical expression form.

[0063] As Figure 7 shown: The physical model of maintaining a safe distance from the vehicle ahead (the vehicle ahead, the following vehicle) is that the actual distance from the host vehicle to the vehicle ahead is greater than or equal to the safe distance x sufficient to take emergency braking measures 前车 ≥ x 安全 ; Here, the host vehicle is used to indicate the target vehicle of the autonomous driving.

[0064] And when further converted into a more detailed mathematical model (variable-based), there can be physical and geometric variable definitions as Figure 6 shown.

[0065] Is (Maintaining a safe distance from the vehicle in front (the vehicle in front, the vehicle behind) == true) == true

[0066] Function expression 1: Maintaining a safe distance from the vehicle in front (the vehicle in front, the vehicle behind);

[0067] x 安全 = Safe following distance (the vehicle in front, the vehicle behind), Equation (1);

[0068] if the vehicle in front.x 前车 ≥ x 安全 ;

[0069] Function expression 2: Safe following distance (the vehicle in front, the vehicle behind);

[0070]

[0071] Wherein,

[0072] x 安全 : Safe distance sufficient to take emergency braking measures;

[0073] t 反应 = t 硬 + t 软 : Reaction time;

[0074] t 硬 : Time required for the actuator of the corresponding vehicle braking system to generate the maximum braking force from the moment it receives the braking signal to the brake disc;

[0075] t 软 : Time required for the driver of the corresponding vehicle to identify an emergency and give a braking signal. In the case of a human driver, it is the human reaction time, while in the case of an autonomous driving software, it corresponds to the time required by the environment perception software stack and the autonomous driving decision software stack;

[0076] a 前车预期刹车力 : Maximum deceleration that can be applied when the vehicle in front is expected to brake;

[0077] a 自车可用最大刹车力 : Maximum deceleration that the planned own vehicle will apply during emergency braking;

[0078] v 自车 : Current driving speed of the own vehicle (the vehicle behind);

[0079] v 前车 : Current driving speed of the vehicle in front;

[0080] x 静止 : Longitudinal distance between the two vehicles when both vehicles in front and behind brake to a speed of zero.

[0081] In a preferred embodiment of the present embodiment, the method further includes: performing signal verification processing on the current driving data. If the verification result indicates that the current driving data passes the verification, performing signal conversion processing on the current driving data to generate converted driving data; performing noise reduction processing on the converted driving data to obtain noise-reduced driving data. Then, based on the parsing result, calling a mathematical function library to perform compliance evaluation on the noise-reduced driving data to generate a compliance evaluation result. Thereby, the accuracy of the compliance evaluation of the current driving data is improved.

[0082] In a preferred embodiment of the present embodiment, the preset compliance engine system configuration file at least includes: a first condition library, a first rule library, and a system parameter table.

[0083] For any first rule in the first rule library: performing rule parsing processing on the first rule library and storing the rule parsing result according to the corresponding parsing value; the rule parsing result includes: at least two condition indexes and at least one logical operator; selecting a first condition corresponding to each condition index from the first condition library to generate a second condition library; for any first condition in the second condition library: performing condition parsing processing on the first condition and storing the condition parsing result according to the corresponding parsing value; the condition parsing result includes: at least one object and at least one function name; performing parsing processing on the system parameter table to output the parsed system parameter table; determining the parsed system parameter table, the rule parsing result, and the condition parsing result as the parsing result. Thereby, in this embodiment, by performing initialization processing on the compliance engine system configuration file in the compliance engine, it is beneficial for the compliance engine to effectively evaluate the current driving data and improve the accuracy of the compliance evaluation of the target vehicle during the automatic driving process.

[0084] In a preferred embodiment of the present embodiment, the step of calling a mathematical function library to perform compliance evaluation on the current driving data based on the parsing result to generate a compliance evaluation result includes: selecting a target object and a target function name corresponding to the current driving data from the parsing result; calling a mathematical function corresponding to the target function name from the mathematical function library; based on the parsed system parameter list, using the mathematical function to evaluate the target object to generate a real-time condition evaluation result; performing compliance evaluation on the condition evaluation result based on the rule parsing result to generate a real-time rule evaluation result.

[0085] As Figure 2 shown, it is a schematic architecture diagram of a compliance engine system in an embodiment of the present invention.

[0086] The compliance engine system includes: a middle layer, and a compliance engine module communicatively connected to the middle layer; the compliance engine module includes: a data processing unit, a rule parser, a condition parser, a compliance judge, and a function call unit; the compliance judge includes a condition evaluator and a rule evaluator.

[0087] The middle layer is used for performing signal verification and signal conversion processing on the current driving data, and sending the converted driving data to the data processing unit;

[0088] The data processing unit is used for performing noise reduction processing on the converted driving data, and sending the noise-reduced driving data to the condition evaluator respectively;

[0089] The rule parser is used for performing rule parsing processing on the first rule library, and outputting a rule parsing result; and sending the rule parsing result to the condition parser and the rule judge respectively;

[0090] The condition parser is used for querying the first condition corresponding to the rule parsing result from the first condition library, generating a second condition library; and performing condition parsing processing on the first condition in the second condition library, and outputting a condition parsing result; then sending the condition parsing result to the condition evaluator and the function call unit respectively;

[0091] The condition evaluator is used for selecting a target object and a target function name corresponding to the noise-reduced driving data from the parsing result; based on the parsed system parameter list, using the mathematical function corresponding to the target function name to evaluate the target object, and generating a real-time condition evaluation result; then sending the real-time condition evaluation result to the rule evaluator;

[0092] The function call unit is used for calling the mathematical function corresponding to the target function name in the condition parsing result from the mathematical function library, and sending the called mathematical function to the condition evaluator;

[0093] The rule evaluator is used for based on the parsed system parameter list, using the mathematical function corresponding to the target function name to evaluate the target object, and generating a real-time condition evaluation result; then sending the real-time condition evaluation result to the rule evaluator;

[0094] Based on the rule parsing result, performing compliance evaluation on the real-time condition evaluation result, and generating a real-time rule evaluation result.

[0095] It should be noted that the final output of the rule evaluator is a rule evaluation represented in the form of "true" / "false", which is used for reporting or graphical display. The final output of the condition evaluator is a condition evaluation represented in the form of "true" / "false", which is used for reporting or graphical display.

[0096] Such as Figure 3As shown, it is a schematic flowchart of parsing and processing the first rule in an embodiment of the present invention.

[0097] Perform rule parsing and processing on the first rule library, and store the rule parsing results according to the corresponding parsed values; at least include the following steps:

[0098] S301, Obtain the rule index number of the first rule;

[0099] S302, Based on the rule index number, perform a read process on the fields in the first rule to obtain the current field;

[0100] S303, Detect the current field to obtain the first detection result;

[0101] S304, If the first detection result indicates that the current field is a logical operator, convert the logical operator into the corresponding parsed value for storage;

[0102] S305, If the first detection result indicates that the current field is not a logical operator, store the condition index number when it is determined that the current field is a condition index number.

[0103] Exemplarily, if the detection result indicates that the current field is a logical operator, then convert the logical operator into the corresponding parsed value for storage; includes: if the detection result indicates that the current field is a NOT operator, search for the ending field of the NOT operator, if the search result indicates that the ending field of the NOT operator is a parenthesis, then convert the NOT operator and the adjacent parenthesis into the corresponding parsed value for storage; if the detection result indicates that the current field is not a NOT operator, determine whether the current field is an AND or OR field; if the determination result indicates that the current field is an AND or OR field, then convert the AND or OR field into the corresponding parsed value for storage.

[0104] The specific steps are as follows:

[0105] S1, Obtain the rule index number of the first rule;

[0106] S2, Based on the rule index number, perform a read process on the fields in the first rule; if the read result indicates that the current field does not exist, determine that the previous current field is the end of the first rule, and store the parsed result of the completed parsing; if the read result indicates that the current field exists, then execute step S3;

[0107] S3, Detect whether the current field is a NOT operator; if so, then execute step S4; if not, then execute step S6;

[0108] S4. Search whether a parenthesis immediately appears after the NOT operator; if so, execute step S5; if not, return an error message.

[0109] S5. Convert the NOT operator and the adjacent parenthesis into corresponding parsed values for storage; continue to execute step S2.

[0110] S6. Determine whether the current field is an AND or OR field; if so, execute step S7; if not, execute step S8.

[0111] S7. Convert the AND or OR field into the corresponding parsed value for storage; continue to execute step S2.

[0112] S8. Determine whether the current field is a left parenthesis; if so, execute step S9, if not, execute step S10.

[0113] S9. Use a counter to increment the number of left parentheses by 1, and when it is determined that there is a corresponding right parenthesis after the search, convert the complete parentheses into a parsed value for storage; continue to execute step S2.

[0114] S10. Determine whether the current field is a right parenthesis; if so, execute step S11; if not, execute step S12.

[0115] S11. Use a counter to decrement the number of left parentheses by 1, and continue to execute step S2 when it is determined that the number of left parentheses is greater than or equal to 0; return an error message when it is determined that the number of left parentheses is less than 0.

[0116] S12. Determine whether the current field is a condition index number; if so, store the condition index number; if not, return an error message.

[0117] During software initialization, the compliance engine reads the first rule in the first rule library line by line, converts the first rule library into a truth table; at the same time, extracts all the conditions in the first rule library and constructs a second condition library based on the first condition library and stores it in the memory. Then, perform condition parsing on the first condition in the second condition library and output the condition parsing result; in each clock cycle, first calculate the condition evaluation result based on the current driving data, the condition parsing result, and the mathematical function library, and then map the condition evaluation result to the truth table through the compliance engine to calculate the rule evaluation result corresponding to the current driving data.

[0118] As Figure 4 shown, it is a schematic flowchart of the condition parsing process for the first condition in an embodiment of the present invention.

[0119] Perform condition parsing on the first condition and store the condition parsing result according to the corresponding parsed value; at least include the following steps:

[0120] S401. Obtain the condition index number of the first condition;

[0121] S402. Based on the condition index number, perform a read process on the fields in the first condition to obtain the current field;

[0122] S403. Detect the current field to obtain a second detection result;

[0123] S404. If the second detection result indicates that the current field is a valid mathematical operation quantity, store the corresponding parsed value of the mathematical operation quantity; wherein, the mathematical operation quantity at least includes: the name of a mathematical operator, and / or the name of a function, and / or a constant;

[0124] S405. If the second detection result indicates that the current field is not a valid mathematical operation quantity, store the corresponding parsed value of the object when it is determined that the current field is an object.

[0125] The specific steps are as follows:

[0126] S1. Obtain the condition index number of the first condition;

[0127] S2. Based on the condition index number, perform a read process on the fields in the first condition; if the read result indicates that the current field does not exist, determine that the previous current field is the end of the first condition, and store the parsed result that has been parsed; if the read result indicates that the current field exists, execute step S3;

[0128] S3. Detect whether the current field is a left parenthesis; if not, execute step S4; if so, increment the left parenthesis count using a counter, and execute step S2;

[0129] S4. Detect whether the current field is a right parenthesis; if so, decrement the left parenthesis count using a counter, and when it is determined that the remaining left parenthesis count is greater than or equal to 0, continue to execute step S2; when it is determined that the remaining left parenthesis count is less than 0, return an error message; if not, execute step S5;

[0130] S5. Determine whether the current field is the name of a mathematical operator; if so, find and store the corresponding index number of the name of the mathematical operator, and continue to execute step S2; if not, execute step S6;

[0131] S6. Determine whether the current field is the name of a function; if so, convert the name of the function into the corresponding parsed value for storage, and continue to execute step S2; if not, execute step S7;

[0132] S7. Determine whether the current field is a constant; if so, convert the constant into the corresponding parsed value for storage, and continue to execute step S2; if not, execute step S8;

[0133] S8. Determine whether the current field is an object; if so, convert the object into the corresponding parsed value for storage, and continue to execute step S2; if not, determine that the current field is an invalid field and return an error message.

[0134] Such as Figure 3 and Figure 4 The parser flow chart is shown. Generally speaking, the basis of parsing is to read the space-separated words and parse function names, logical operators, mathematical operator names, objects, and constants, etc.

[0135] The parsing process starts from the condition and rule text files. The condition text file is as shown in Figure 10 the second condition library; the second condition library consists of multiple lines of first conditions, each line starting with a condition ID followed by the condition name and its input. The first condition is, for example: "1: There is a vehicle in front in the same lane (motor vehicle, lane) == true".

[0136] The rule text file is as shown in Figure 9 the first rule library; the first rule library consists of multiple lines of first rules. Each first rule is defined as a logical combination of conditions, so each line in the file starts with a rule ID followed by the condition index IDs combined by logical operators (such as "AND", "OR", "NOT"). The first rule is, for example: "1: 1 AND NOT(2)". In this example, 1 and 2 are the condition IDs defined in the first condition library.

[0137] The condition parser first reads each line of the first condition in the second condition library and extracts the first condition ID. Then, it reads the field and checks whether the current field is a function name followed by an opening parenthesis; if so, it marks the current field as the function name; then it continues to read the fields following the function name until the closing parenthesis is read. The fields following the function name are used as the input of the function, which can be an object or a parameter. In this example, the motor vehicle and the lane are objects.

[0138] The rule parser reads the first rule; it first obtains the rule index ID corresponding to the first rule, and then reads the fields that are condition IDs or logical operators.

[0139] Such as Figure 11 , and the following will specifically describe this embodiment in combination with specific scenarios.

[0140] An evaluation method for autonomous driving compliance includes at least the following steps:

[0141] S1. Obtain the traffic regulation documents corresponding to the target vehicle model in the target country from the global traffic regulation self-driving regulation database; the traffic regulation documents are, for example, the Road Traffic Management Regulations, the Road Traffic Law, the UNECE R157 Automatic Lane Keeping System Regulations, judicial interpretations and case laws; send the traffic regulation documents to the natural language parsing and quantitative analysis system;

[0142] S2. In the natural language parsing and quantitative analysis system, the regulation disassembler disassembles the traffic regulation documents corresponding to the target vehicle model in the target country into several traffic law articles; for any target traffic law article among the several traffic law articles: the semantic analysis model performs content filling processing on the target traffic law article and outputs a standard traffic law article; the law disassembler disassembles the standard traffic law article into several first conditions; based on the several first conditions corresponding to each standard traffic law article, generate the first condition library corresponding to the traffic regulation documents; the logical expression generator performs logical combination on the first conditions in the first condition library to generate the corresponding first rule library.

[0143] Establish a mapping relationship between each legal field in the first condition library and the vehicle kinematics model to construct a condition analysis and modeling system; associate the condition analysis and modeling system with the mathematical model, and output a system parameter table and a condition mathematical model library; determine the first condition library, the first rule library, and the system parameter table as the preset compliance engine system configuration file; convert the condition mathematical model library into a code generation system to generate a mathematical function library.

[0144] The natural language parsing and quantitative analysis system sends the preset compliance engine system configuration file to the compliance engine system.

[0145] S3. The autonomous driving vehicle inputs the current driving data as an input signal into the compliance engine system; the current driving data at least includes: the environmental perception data collected by the environmental perception module, and the automatic software path planning;

[0146] S4. In the compliance engine system, the parser parses the preset compliance engine system configuration file, and sends the rule parsing result in the parsing result to the rule evaluator; sends the condition parsing result and the parsed system parameter table in the parsing result to the condition evaluator; the condition evaluator calls a mathematical function from the mathematical function library based on the condition parsing result; the condition evaluator performs condition evaluation based on the condition parsing result, the input signal, the mathematical function, and the parsed system parameter table, and outputs a real-time condition evaluation result; the condition evaluator sends the real-time condition evaluation result to the rule evaluator and the compliance report generator respectively; the rule evaluation machine performs rule evaluation based on the rule parsing result and the real-time condition evaluation result, and outputs a real-time rule evaluation result; and sends the real-time rule evaluation result to the compliance report generator. At the same time, the rule evaluator sends a real-time violation prompt to the autonomous driving vehicle based on the real-time rule evaluation result.

[0147] The compliance engine system sends the input signal to the compliance report generator.

[0148] S5. In the compliance report generator, based on the real-time condition evaluation results, generate a list of real-time condition evaluation results (Boolean type); based on the real-time rule evaluation results, generate a list of real-time rule evaluation results (Boolean type). The traffic trigger analyzer obtains the real-time condition evaluation list, and based on the real-time condition evaluation list, conducts traffic regulation trigger analysis on the input signal to generate a regulation trigger report; the violation analysis statistician obtains the real-time rule evaluation form and conducts violation analysis on the real-time rule evaluation list to output a compliance statistic report; the event recorder obtains the real-time rule evaluation form and the input signal, and based on the real-time rule evaluation list, evaluates the input signal to output an event record report.

[0149] The compliance report generator sends the regulation trigger report, the compliance statistic report, and the event record report to the compliance cloud respectively.

[0150] S6. The compliance cloud sends the above reports to the vehicle manufacturer, the operator, the regulatory department, and the insurance company respectively.

[0151] In this embodiment, based on the established word processing process and in cooperation with the machine learning algorithm, the legal language in traffic laws is converted into a machine-readable logical and formal language (combining geometry, algebra, and logical expressions). At the same time, the relevant case laws are converted into traffic scenarios and output in a specific description manner. Secondly, the system automatically generates corresponding mathematical and geometric expression forms based on the logical and formal language, and converts them into code, which is embedded in the compliance engine system in the form of rules to generate a compliance discrimination software module, and automatically generates an embedded plug-in corresponding to the interfaces of different simulation software or hardware chips. Finally, the generated software module is loaded in the vehicle or related hardware in the form of an SoC. By receiving and analyzing the output signals of the corresponding environment perception module of the autonomous driving software stack and the planned path or decision of the autonomous driving software, it can not only determine which relevant traffic regulations exist in the current driving scenario and make real-time records and statistics; but also determine whether the decision of the autonomous driving software violates traffic regulations, and output corresponding prompt feedback and record the data of violating traffic regulations. The method of this embodiment can also dynamically evaluate the compliance and safety of the autonomous driving software stack and give feedback and reports; in addition, it can also dynamically evaluate the working state of the vehicle hardware in combination with map information and give feedback and reports. Thus, the requirements for autonomous driving of the target vehicle are met.

[0152] Since the method of this embodiment is to convert the legal language in traffic laws into a machine-readable logical and formal language, and generate software code of the embedded language according to the logical and mathematical relationships; therefore, it has universality and is applicable to all autonomous driving scenarios.

[0153] As shown in Figure 12 the figure, it is a schematic structural diagram of an evaluation device for autonomous driving compliance provided by an embodiment of the present invention.

[0154] An evaluation device for autonomous driving compliance, the device 120 includes: a collection module 121, configured to obtain current driving data generated by a target vehicle for autonomous driving during driving; an analysis module 122, configured to perform parsing processing on a preset compliance engine system configuration file to obtain an analysis result; an evaluation module 123, configured to based on the analysis result, call a mathematical function library to perform compliance evaluation on the current driving data, and generate a compliance evaluation result.

[0155] In a preferred implementation manner of this embodiment, the device further includes: a first generation module, configured to convert a traffic regulation file corresponding to a target vehicle model in a target country into a machine-readable logical and formal language, and generate a first condition library and a first rule library; a construction module, configured to establish a mapping relationship between each legal field in the first condition library and an on-vehicle kinematic model, and construct a condition analysis modeling system; an association module, configured to associate the condition analysis modeling system with a mathematical model, and output a system parameter table and a condition mathematical model library; a determination module, configured to determine the first condition library, the first rule library, and the system parameter table as a preset compliance engine system configuration file; a second generation module, configured to convert the condition mathematical model library into a code generation system, and generate a mathematical function library.

[0156] In a preferred implementation manner of this embodiment, the first generation module includes: a regulation disassembling unit, configured to disassemble a traffic regulation file corresponding to a target vehicle model in a target country into a plurality of traffic regulations based on a regulation disassembler; a content filling unit, configured to for any target traffic regulation among the plurality of traffic regulations: perform content filling processing on the target traffic regulation by a semantic analysis model, and output a standard traffic regulation; disassemble the standard traffic regulation into a plurality of first conditions based on a regulation disassembler; a law disassembling unit, configured to generate a first condition library corresponding to the traffic regulation file based on the plurality of first conditions corresponding to each standard traffic regulation; a generation unit, configured to perform logical combination on the first conditions in the first condition library based on a logical expression generator, and generate a corresponding first rule library.

[0157] In a preferred implementation manner of this embodiment, the preset compliance engine system configuration file at least includes: a first condition library, a first rule library, and a system parameter table; the parsing module includes: a rule parsing processing unit, which is used for any first rule in the first rule library: perform rule parsing processing on the first rule library, and store the rule parsing result according to the corresponding parsing value; the rule parsing result includes: at least two condition indexes and at least one logical operator; a selection unit, which is used to select a first condition corresponding to each condition index from the first condition library to generate a second condition library; a condition parsing processing unit, which is used for any first condition in the second condition library: perform condition parsing processing on the first condition, and store the condition parsing result according to the corresponding parsing value; the condition parsing result includes: at least one object and at least one function name; a parameter parsing processing unit, which is used to parse the system parameter table and output the parsed system parameter table; a determination unit, which is used to determine the parsed system parameter table, the rule parsing result, and the condition parsing result as the parsing result.

[0158] In a preferred implementation manner of this embodiment, the rule parsing processing unit includes: an acquisition subunit, which is used to acquire the rule index number of the first rule; a reading processing subunit, which is used to read the fields in the first rule based on the rule index number to acquire the current field; a detection subunit, which is used to detect the current field to obtain a first detection result; a conversion processing subunit, which is used to, if the first detection result indicates that the current field is a logical operator, convert the logical operator into a corresponding parsing value for storage; a determination subunit, which is used to, if the first detection result indicates that the current field is not a logical operator, store the condition index number when determining that the current field is a condition index number.

[0159] In a preferred implementation manner of this embodiment, the conversion processing subunit includes: a first conversion unit, which is used to, if the first detection result indicates that the current field is a NOT operator, search for the ending field of the NOT operator, and if the search result indicates that the ending field of the NOT operator is a parenthesis, convert the NOT operator and the adjacent parenthesis into corresponding parsing values for storage; a second conversion unit, which is used to, if the first detection result indicates that the current field is not a NOT operator, determine whether the current field is an AND or OR field; if the determination result indicates that the current field is an AND or OR field, convert the AND or OR field into a corresponding parsing value for storage.

[0160] In a preferred embodiment of the present embodiment, the condition parsing processing unit includes: an acquisition subunit, configured to acquire the condition index number of the first condition; a reading subunit, configured to perform a reading process on the fields in the first condition based on the condition index number to acquire the current field; a detection subunit, configured to detect the current field to obtain a second detection result; a conversion processing subunit, configured to store the parsed value corresponding to the mathematical operation amount if the second detection result indicates that the current field is a valid mathematical operation amount; wherein the mathematical operation amount at least includes: a mathematical operator name, and / or a function name, and / or a constant; a determination subunit, configured to store the parsed value corresponding to the object if the second detection result indicates that the current field is not a valid mathematical operation amount and the current field is determined to be an object.

[0161] In a preferred embodiment of the present embodiment, the evaluation module includes: a selection unit, configured to select a target object and a target function name corresponding to the current driving data from the parsing result; a calling unit, configured to call a mathematical function corresponding to the target function name from a mathematical function library; a condition evaluation unit, configured to evaluate the target object by using the mathematical function based on the parsed system parameter list to generate a real-time condition evaluation result; a rule evaluation unit, configured to perform a compliance evaluation on the condition evaluation result based on the rule parsing result to generate a real-time rule evaluation result.

[0162] In a preferred embodiment of the present embodiment, the device further includes: a third generation module, configured to respectively generate a corresponding real-time condition evaluation list and a real-time rule evaluation list based on the real-time condition evaluation result and the real-time rule evaluation result corresponding to each current driving data; a traffic rule trigger analysis module, configured to perform a traffic rule trigger analysis on the current driving data based on the real-time condition evaluation list to generate a regulation trigger report; a violation analysis module, configured to perform a violation analysis on the real-time rule evaluation list and output a compliance statistics report; an event evaluation module, configured to evaluate the current driving data based on the real-time rule evaluation list and output an event record report.

[0163] The above device can execute the evaluation method for autonomous driving compliance provided by an embodiment of the present invention, and has corresponding functional modules and beneficial effects for executing the evaluation method for autonomous driving compliance. For technical details not described in detail in this embodiment, reference can be made to the evaluation method for autonomous driving compliance provided by an embodiment of the present invention.

[0164] The present invention further provides an electronic device, including: a processor; a memory for storing executable instructions that can be executed by the processor; the processor is configured to read the executable instructions from the memory and execute the instructions to implement the evaluation method for autonomous driving compliance according to the present invention.

[0165] In addition to the above methods and devices, an embodiment of the present application may also be a computer program product, which includes computer program instructions that, when executed by a processor, cause the processor to execute the steps in the methods according to various embodiments of the present application described in the "Exemplary Methods" section above of this specification.

[0166] The computer program product may be written in any combination of one or more programming languages for programming code to perform the operations of the embodiments of the present application. The programming languages include object-oriented programming languages such as Java, C++, etc., and also include conventional procedural programming languages such as the "C" language or similar programming languages. The programming code may be executed entirely on the user's computing device, partially on the user's device, executed as an independent software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0167] Furthermore, an embodiment of the present application may also be a computer-readable storage medium, on which computer program instructions are stored, and when the computer program instructions are executed by a processor, the processor is caused to execute the steps in the methods according to the following embodiments of the present application described in the "Exemplary Methods" section above of this specification.

[0168] The computer-readable storage medium may adopt any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium may, for example, include but is not limited to an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the above. More specific examples (non-exhaustive list) of the readable storage medium include: an electrical connection having one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0169] The basic principles of the present application have been described above in conjunction with specific embodiments. However, it should be noted that the advantages, benefits, effects, etc. mentioned in the present application are only examples and not limitations, and it cannot be considered that these advantages, benefits, effects, etc. are essential for each embodiment of the present application. In addition, the above-disclosed specific details are only for the purposes of illustration and facilitating understanding, rather than limitations. The above details do not limit the present application to necessarily adopt the above specific details for implementation.

[0170] The block diagrams of the devices, apparatuses, equipment, and systems involved in this application are only illustrative examples and are not intended to require or imply that they must be connected, arranged, and configured in the manner shown in the block diagrams. As those skilled in the art will recognize, these devices, apparatuses, equipment, and systems can be connected, arranged, and configured in any manner. Words such as "including", "comprising", "having", etc. are open-ended terms, meaning "including but not limited to", and can be used interchangeably with each other. The word "or" and "and" used herein refer to the word "and / or", and can be used interchangeably with it, unless the context clearly indicates otherwise. The phrase "such as" used herein refers to the phrase "such as but not limited to", and can be used interchangeably with it.

[0171] It should also be noted that in the devices, equipment, and methods of this application, each component or each step can be decomposed and / or recombined. These decompositions and / or recombinations should be regarded as equivalent solutions of this application.

[0172] The above description of the disclosed aspects is provided to enable any person skilled in the art to make or use this application. Various modifications to these aspects will be readily apparent to those skilled in the art, and the general principles defined herein can be applied to other aspects without departing from the scope of this application. Therefore, this application is not intended to be limited to the aspects shown herein, but rather to the broadest scope consistent with the principles and novel features disclosed herein.

[0173] The above description has been given for purposes of illustration and description. In addition, this description is not intended to limit the embodiments of this application to the forms disclosed herein. Although multiple example aspects and embodiments have been discussed above, those skilled in the art will recognize certain variations, modifications, changes, additions, and sub-combinations thereof.

[0174] In the description of this specification, the descriptions referring to terms such as "one embodiment", "some embodiments", "example", "specific example", or "some examples", etc. mean that the specific features, structures, materials, or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present invention. Moreover, the specific features, structures, materials, or characteristics described can be combined in a suitable manner in any one or more embodiments or examples. In addition, without contradiction, those skilled in the art can combine and combine the different embodiments or examples described in this specification and the features of different embodiments or examples.

[0175] Furthermore, the terms "first" and "second" are for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, features defined with "first" and "second" may explicitly or implicitly include at least one of such features. In the description of the present invention, "a plurality of" means two or more unless otherwise specifically defined.

[0176] As described above, the above are only specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention can easily think of changes or substitutions, which should be covered within the protection scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.

Claims

1. An evaluation method for autonomous driving compliance, characterized in that Including: Based on a regulation disassembler, disassemble the traffic regulation document corresponding to the target vehicle model in the target country into several traffic law articles; for any target traffic law article among the several traffic law articles: a semantic analysis model performs content filling processing on the target traffic law article and outputs a standard traffic law article; based on a law disassembler, disassemble the standard traffic law article into several first conditions; based on the several first conditions corresponding to each standard traffic law article, generate a first condition library corresponding to the traffic regulation document; Based on a logical expression generator, perform logical combination on the first conditions in the first condition library to generate a corresponding first rule library; Establish a mapping relationship between each legal field in the first condition library and a vehicle kinematics model to construct a condition analysis and modeling system; associate the condition analysis and modeling system with a mathematical model, and output a system parameter table and a condition mathematical model library; determine the first condition library, the first rule library, and the system parameter table as a preset compliance engine system configuration file; convert the condition mathematical model library into a code generation system to generate a mathematical function library; Obtain the current driving data generated by the target vehicle for autonomous driving during driving; wherein, the current driving data at least includes: environmental perception data collected by an environmental perception module, and automatic software path planning; perform parsing processing on the preset compliance engine system configuration file to obtain a parsing result; select a target object and a target function name corresponding to the current driving data from the parsing result; call a mathematical function corresponding to the target function name from the mathematical function library; based on the parsed system parameter list, use the mathematical function to evaluate the target object to generate a real-time condition evaluation result; perform compliance evaluation on the condition evaluation result based on a rule parsing result to generate a real-time rule evaluation result; wherein, the rule parsing result is used to indicate the result obtained by performing rule parsing processing on the first rule library.

2. The method according to claim 1, characterized in that, The preset compliance engine system configuration file at least includes: a first condition library, a first rule library, and a system parameter table; the performing parsing processing on the preset compliance engine system configuration file to obtain a parsing result includes: For any first rule in the first rule library: perform rule parsing processing on the first rule and store the rule parsing result according to the corresponding parsed value; the rule parsing result includes: at least two condition indexes and at least one logical operator; Select first conditions corresponding to each of the condition indexes from the first condition library to generate a second condition library; For any first condition in the second condition library: perform condition parsing processing on the first condition and store the condition parsing result according to the corresponding parsed value; the condition parsing result includes: at least one object and at least one function name; Perform parsing processing on the system parameter table to output a parsed system parameter table; Determine the parsed system parameter table, the rule parsing result, and the condition parsing result as the parsing result.

3. The method according to claim 2, characterized in that, The performing rule parsing processing on the first rule library and storing the rule parsing result according to the corresponding parsed value includes: Obtain the rule index number of the first rule; Based on the rule index number, perform a read process on the fields in the first rule to obtain the current field; Detect the current field to obtain a first detection result; If the first detection result indicates that the current field is a logical operator, convert the logical operator into a corresponding parsed value for storage; If the first detection result indicates that the current field is not a logical operator, store the condition index number when it is determined that the current field is a condition index number.

4. The method according to claim 3, wherein The step of, if the first detection result indicates that the current field is a logical operator, converting the logical operator into a corresponding parsed value for storage; includes: If the first detection result indicates that the current field is a NOT operator, search for the ending field of the NOT operator. If the search result indicates that the ending field of the NOT operator is a parenthesis, convert the NOT operator and the adjacent parenthesis into corresponding parsed values for storage; If the first detection result indicates that the current field is not a NOT operator, determine whether the current field is an AND or OR field; if the determination result indicates that the current field is an AND or OR field, convert the AND or OR field into a corresponding parsed value for storage.

5. The method according to claim 2, wherein The step of performing a condition parsing process on the first condition and storing the condition parsing result according to the corresponding parsed value; includes: Obtain the condition index number of the first condition; Based on the condition index number, perform a read process on the fields in the first condition to obtain the current field; Detect the current field to obtain a second detection result; If the second detection result indicates that the current field is a valid mathematical operation quantity, store the parsed value corresponding to the mathematical operation quantity; wherein, the mathematical operation quantity at least includes: the name of a mathematical operator, and / or the name of a function, and / or a constant; If the second detection result indicates that the current field is not a valid mathematical operation quantity, store the parsed value corresponding to the object when it is determined that the current field is an object.

6. The method according to claim 1, characterized in that, It further includes: Based on the real-time condition evaluation result and the real-time rule evaluation result corresponding to each current driving data, respectively generate a corresponding real-time condition evaluation list and a real-time rule evaluation list; Based on the real-time condition evaluation list, perform a traffic rule trigger analysis on the current driving data to generate a regulation trigger report; Perform a violation analysis on the real-time rule evaluation list and output a compliance statistics report; Based on the real-time rule evaluation list, evaluate the current driving data and output an event record report.

7. An evaluation device for autonomous driving compliance, characterized in that A first generation module for disassembling a traffic regulation document corresponding to a target vehicle model in a target country into a number of traffic laws based on a regulation disassembler; for any target traffic law among the number of traffic laws: a semantic analysis model performs content filling processing on the target traffic law and outputs a standard traffic law; based on a law disassembler, the standard traffic law is disassembled into a number of first conditions; based on the number of first conditions corresponding to each standard traffic law, a first condition library corresponding to the traffic regulation document is generated; Based on a logical expression generator, logical combination is performed on the first conditions in the first condition library to generate a corresponding first rule library; A construction module for establishing a mapping relationship between each legal field in the first condition library and a vehicle kinematics model to construct a condition analysis and modeling system; An association module for associating the condition analysis and modeling system with a mathematical model and outputting a system parameter table and a condition mathematical model library; A determination module for determining the first condition library, the first rule library, and the system parameter table as a preset compliance engine system configuration file; A second generation module for converting the condition mathematical model library into a code generation system to generate a mathematical function library; An acquisition module for acquiring current driving data generated by a target vehicle for autonomous driving during driving; An analysis module for performing analysis processing on a preset compliance engine system configuration file to obtain an analysis result; An evaluation module for selecting a target object and a target function name corresponding to the current driving data from the analysis result; Calling a mathematical function corresponding to the target function name from the mathematical function library; based on the analyzed system parameter list, using the mathematical function to evaluate the target object to generate a real-time condition evaluation result; performing compliance evaluation on the condition evaluation result based on a rule analysis result to generate a real-time rule evaluation result; wherein, the rule analysis result is used to indicate the result obtained by performing rule analysis processing on the first rule library.

8. A computer-readable medium having a computer program stored thereon, the program, when executed by a processor, implementing the method according to any one of claims 1 to 6.

Images