CN116795720A - Unmanned driving system credibility evaluation method and device based on scene - Google Patents
Unmanned driving system credibility evaluation method and device based on scene Download PDFInfo
- Publication number
- CN116795720A CN116795720A CN202310853356.9A CN202310853356A CN116795720A CN 116795720 A CN116795720 A CN 116795720A CN 202310853356 A CN202310853356 A CN 202310853356A CN 116795720 A CN116795720 A CN 116795720A
- Authority
- CN
- China
- Prior art keywords
- unmanned
- credibility
- index
- unmanned system
- bayesian network
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000011156 evaluation Methods 0.000 title claims abstract description 144
- 238000013210 evaluation model Methods 0.000 claims abstract description 73
- 238000011990 functional testing Methods 0.000 claims abstract description 56
- 238000012360 testing method Methods 0.000 claims abstract description 50
- 230000006870 function Effects 0.000 claims abstract description 43
- 238000000034 method Methods 0.000 claims abstract description 41
- 238000004088 simulation Methods 0.000 claims abstract description 24
- 238000004364 calculation method Methods 0.000 claims description 18
- 238000012549 training Methods 0.000 claims description 15
- 238000004590 computer program Methods 0.000 claims description 11
- 238000010276 construction Methods 0.000 claims description 7
- 238000004422 calculation algorithm Methods 0.000 description 16
- 238000010586 diagram Methods 0.000 description 14
- 230000008569 process Effects 0.000 description 9
- 239000004973 liquid crystal related substance Substances 0.000 description 8
- 230000008447 perception Effects 0.000 description 7
- 238000005516 engineering process Methods 0.000 description 6
- 230000003287 optical effect Effects 0.000 description 6
- 238000012790 confirmation Methods 0.000 description 4
- 238000011161 development Methods 0.000 description 4
- 238000005259 measurement Methods 0.000 description 4
- 101100272279 Beauveria bassiana Beas gene Proteins 0.000 description 3
- 238000004891 communication Methods 0.000 description 3
- 230000003068 static effect Effects 0.000 description 3
- 238000013473 artificial intelligence Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 230000001737 promoting effect Effects 0.000 description 2
- 230000000644 propagated effect Effects 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 238000012795 verification Methods 0.000 description 2
- 240000001987 Pyrus communis Species 0.000 description 1
- 239000000470 constituent Substances 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000013515 script Methods 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/36—Preventing errors by testing or debugging software
- G06F11/3668—Software testing
- G06F11/3672—Test management
- G06F11/3688—Test management for test execution, e.g. scheduling of test suites
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/29—Graphical models, e.g. Bayesian networks
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Quality & Reliability (AREA)
- Computer Hardware Design (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application relates to the technical field of unmanned aerial vehicle, and discloses a scene-based unmanned aerial vehicle system credibility evaluation method and device. According to the method, scene elements and functional test requirements are selected to be randomly combined according to specific functions to be tested of the unmanned system, and a functional test scene library is generated; determining an evaluation index of the unmanned system and an experience value of the evaluation index according to the functional test requirement; performing simulation test based on the functional test scene library and the experience value to obtain the failure rate of the unmanned system under the evaluation index; constructing a dynamic Bayesian network credibility evaluation model by using the failure rate, and obtaining the state probability of the unmanned system by using the output of the dynamic Bayesian network credibility evaluation model; and finally, calculating the credibility and the component importance of the unmanned system according to the state probability, and realizing the credibility evaluation of the unmanned system.
Description
Technical Field
The application relates to the technical field of unmanned aerial vehicle, in particular to a scene-based unmanned aerial vehicle system credibility evaluation method and device.
Background
Chinese artificial intelligence series white book-Intelligent driving (2017), issued by the Chinese artificial intelligence society, indicates: unmanned vehicles are an emerging technology in the context of a new technological revolution; the proposal of a series of strategic plans such as the "internet+" and intelligent manufacturing development planning in China 2025 also shows that the development of unmanned vehicles will become important in the future. At present, the unmanned system is influenced by a plurality of factors such as technical means shortage, limited understanding and acceptance degree of markets and consumers, ethical and related legal dilemma and the like when actually deployed, and the problems infinitely prolong the large-scale popularization process of the unmanned automobile.
One key step in developing and deploying unmanned vehicles is to comprehensively test and evaluate the trustworthiness of the unmanned systems, meeting the urgent needs of high-grade intelligent vehicles guided by safety, understandability, predictability, traceability. Through research on technical backgrounds at home and abroad, the credibility evaluation technology of the unmanned system of the automobile is still in a blank stage.
Disclosure of Invention
The embodiment of the application provides a scene-based unmanned system credibility evaluation method, which aims to solve the problem that in the prior art, the automobile unmanned system credibility evaluation technology is still in a blank stage and is difficult to meet urgent requirements of high-grade intelligent automobiles guided by safety, comprehensibility, predictability and traceability.
Correspondingly, the embodiment of the application also provides a scene-based unmanned driving system credibility evaluation device, an electronic device and a computer-readable storage medium, which are used for ensuring the realization and the application of the method.
In order to solve the technical problems, the embodiment of the application discloses a scene-based unmanned driving system credibility evaluation method, which comprises the following steps:
according to the specific function to be tested of the unmanned system, selecting scene elements and functional test requirements to be randomly combined, and generating a functional test scene library;
determining an evaluation index of the unmanned system and an index experience value of the evaluation index according to the functional test requirement;
performing simulation test based on the functional test scene library and the index experience value to obtain the failure rate of the unmanned system under the evaluation index;
constructing a dynamic Bayesian network credibility evaluation model by using the failure rate, and obtaining the state probability of the unmanned system by using the output of the dynamic Bayesian network credibility evaluation model;
and calculating the credibility and the component importance of the unmanned system according to the state probability.
The embodiment of the application also discloses a scene-based unmanned driving system credibility evaluation device, which comprises:
The function test scene confirming module is used for selecting scene elements and function test requirements to be randomly combined according to the specific function to be tested of the unmanned system, and generating a function test scene library;
the evaluation index generation module is used for determining an evaluation index of the unmanned system and an index experience value of the evaluation index according to the functional test requirement;
the system failure rate calculation module is used for performing simulation test based on the functional test scene library and the index experience value to obtain the failure rate of the unmanned system under the evaluation index;
the model construction training module is used for constructing a dynamic Bayesian network credibility evaluation model by using the failure rate, and obtaining the state probability of the unmanned system by using the output of the dynamic Bayesian network credibility evaluation model;
the system credibility calculation module is used for calculating credibility and component importance of the unmanned system according to the state probability.
The embodiment of the application also discloses an electronic device which comprises a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein the processor realizes one or more of the methods in the embodiment of the application when executing the program.
Embodiments of the present application also disclose a computer readable storage medium having stored thereon a computer program which, when executed by a processor, performs a method as described in one or more of the embodiments of the present application.
According to the embodiment of the application, according to the specific function to be tested of the unmanned system, scene elements and functional test requirements are selected for random combination, and a functional test scene library is generated; determining an evaluation index of the unmanned system and an index experience value of the evaluation index according to the functional test requirement; performing simulation test based on the functional test scene library and the index experience value to obtain the failure rate of the unmanned system under the evaluation index; constructing a dynamic Bayesian network credibility evaluation model by using the failure rate, and obtaining the state probability of the unmanned system by using the output of the dynamic Bayesian network credibility evaluation model; and finally, calculating the credibility and the component importance of the unmanned system according to the state probability, and realizing the credibility evaluation of the unmanned system.
Additional aspects and advantages of embodiments of the application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the application.
Drawings
The foregoing and/or additional aspects and advantages of the application will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings, in which:
fig. 1 is a flowchart of a method for evaluating the credibility of a scene-based unmanned driving system according to an embodiment of the present application;
FIG. 2 is a schematic diagram of a man-vehicle-road-environment system according to an embodiment of the present application;
FIG. 3 is a flowchart of selecting an evaluation index according to an embodiment of the present application;
fig. 4 is a schematic structural diagram of an unmanned system after disassembly according to an embodiment of the present application;
FIG. 5 is a schematic diagram of a dynamic Bayesian network graph structure according to an embodiment of the present application;
FIG. 6 is a diagram of a dynamic Bayesian network graph structure in an example provided by an embodiment of the present application;
fig. 7 is a schematic structural diagram of a scene-based unmanned driving system credibility evaluation device according to an embodiment of the present application;
fig. 8 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
Detailed Description
Embodiments of the present application are described in detail below, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to like or similar elements or elements having like or similar functions throughout. The embodiments described below by referring to the drawings are illustrative only and are not to be construed as limiting the application.
As used herein, the singular forms "a", "an", "the" and "the" are intended to include the plural forms as well, unless expressly stated otherwise, as understood by those skilled in the art. It will be further understood that the terms "comprises" and/or "comprising," when used in this specification, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof. It will be understood that when an element is referred to as being "connected" or "coupled" to another element, it can be directly connected or coupled to the other element or intervening elements may also be present. Further, "connected" or "coupled" as used herein may include wirelessly connected or wirelessly coupled. The term "and/or" as used herein includes all or any element and all combination of one or more of the associated listed items.
It will be understood by those skilled in the art that all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs unless defined otherwise. It will be further understood that terms, such as those defined in commonly used dictionaries, should be interpreted as having a meaning that is consistent with their meaning in the context of the prior art and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein.
The scheme provided by the embodiment of the application can be executed by any electronic equipment, such as terminal equipment, and can also be a server, wherein the server can be an independent physical server, a server cluster or a distributed system formed by a plurality of physical servers, and a cloud server for providing cloud computing service. The terminal may be, but is not limited to, a smart phone, a tablet computer, a notebook computer, a desktop computer, a smart speaker, a smart watch, etc. The terminal and the server may be directly or indirectly connected through wired or wireless communication, and the present application is not limited herein. Aiming at the technical problems in the prior art, the application provides a scene-based unmanned driving system credibility evaluation method, a scene-based unmanned driving system credibility evaluation device and electronic equipment, which aim at solving at least one of the technical problems in the prior art.
The following describes the technical scheme of the present application and how the technical scheme of the present application solves the above technical problems in detail with specific embodiments. The following embodiments may be combined with each other, and the same or similar concepts or processes may not be described in detail in some embodiments. Embodiments of the present application will be described below with reference to the accompanying drawings.
The embodiment of the application provides a possible implementation manner, as shown in fig. 1, and provides a flow chart of a scene-based unmanned driving system credibility evaluation method, wherein the scheme can be executed by any electronic device, and optionally can be executed at a server side or terminal equipment.
As shown in fig. 1, the method may include the steps of:
and step 101, selecting scene elements and functional test requirements to be randomly combined according to the specific function to be tested of the unmanned system, and generating a functional test scene library.
The unmanned system in the embodiment of the application can be a 'man-car-road-environment system', and fig. 2 shows a schematic structural diagram of the man-car-road-environment system. As shown in fig. 2, scene elements in a person-vehicle-road-environment system may include, but are not limited to, traffic participants, environmental physical elements, weather conditions; functional test requirements include, but are not limited to, traffic sign recognition response, signal light recognition and response, pedestrian avoidance, roundabout traffic, side parking, and overtaking. According to the embodiment of the application, the function test scene library of the typical scene can be constructed by freely/randomly combining the various scene elements and the various function test requirements according to the function test requirements of the unmanned system under the selected typical scene.
Step 102, determining an evaluation index of the unmanned system and an index experience value of the evaluation index according to the functional test requirement.
Optionally, the determining, according to the functional test requirement, the evaluation index of the unmanned system and the index experience value of the evaluation index includes:
determining a functional module in the unmanned system according to the functional test requirement;
and determining the components contained in the functional module, and determining the evaluation index and the index experience value of the evaluation index according to the components.
Fig. 3 shows a flow chart for selecting an evaluation index. As shown in fig. 3, in the embodiment of the present application, firstly, the task to be completed by the unmanned system (i.e., the specific function to be tested of the unmanned system) in a typical scenario is specified, and then, the functional module used when the unmanned system completes the task is specified. And then disassembling the used functional modules, defining components (comprising hardware components and related algorithms) contained in the functional modules, and selecting related indexes for evaluating the task completion condition as evaluation indexes according to the disassembled components. And then combining preset standards (such as the existing standards commonly accepted in the prior policy or industry), forming an evaluation index system according to all the selected evaluation indexes, and obtaining relevant index experience values of all the evaluation indexes in the evaluation index system.
The index value is a quantized description defining an index completion criterion. The index experience value of the selected evaluation index is used for obtaining the index value widely accepted in the industry by combining the preset standard with the selected reliability evaluation index of the unmanned driving system based on the scene.
And step 103, performing simulation test based on the functional test scene library and the index experience value to obtain the failure rate of the unmanned system under the evaluation index.
Based on the functional test scene library and the index experience value, performing simulation test on a simulation platform, verifying and optimizing the index value through repeated massive test, and finally obtaining the failure rate of the unmanned system under each index. The simulation platform for testing can be selected according to actual application conditions.
And 104, constructing a dynamic Bayesian network credibility evaluation model by using the failure rate, and outputting and obtaining the state probability of the unmanned system by using the dynamic Bayesian network credibility evaluation model.
Bayesian Networks (BN), are uncertain knowledge reasoning models based on Bayesian theory. The bayesian network model consists of a graphical structure of nodes and conditional probability tables (conditional probability table, CPT) by which logical relationships between nodes can be intuitively described. The dynamic Bayesian network (dynamic Bayesian network, DBN) is an expansion of the Bayesian network, and can reflect the time-varying effect of the variable through a plurality of discrete time slices, and each time slice in the DBN structure corresponds to a static Bayesian network. Therefore, the DBN can realize dynamic prediction and data real-time update, can express and infer a dynamic random process, and has certain advantages in the application fields of dynamic system fault diagnosis, credibility evaluation and the like. In the embodiment of the application, a DBN is used as a framework for constructing a Bayesian network credibility evaluation model, and then the Bayesian network credibility evaluation model is utilized to output and obtain the state probability of the unmanned system.
Step 105, calculating the credibility and the component importance of the unmanned system according to the state probability.
According to the embodiment of the application, according to the specific function to be tested of the unmanned system, scene elements and functional test requirements are selected for random combination, and a functional test scene library is generated; determining an evaluation index of the unmanned system and an index experience value of the evaluation index according to the functional test requirement; performing simulation test based on the functional test scene library and the index experience value to obtain the failure rate of the unmanned system under the evaluation index; constructing a dynamic Bayesian network credibility evaluation model by using the failure rate, and obtaining the state probability of the unmanned system by using the output of the dynamic Bayesian network credibility evaluation model; and finally, calculating the credibility and the component importance of the unmanned system according to the state probability, and realizing the credibility evaluation of the unmanned system.
In addition, the embodiment of the application can closely correlate the test requirements of the unmanned system with the test scene, enrich the performance evaluation indexes of each functional module of the unmanned system, reduce the development and maintenance costs of the unmanned system, and improve the test efficiency of the unmanned system, thereby improving the safety of the unmanned technology and promoting the deployment application of high-level automatic driving on an actual road.
In an optional embodiment, the performing a simulation test based on the functional test scene library and the index experience value to obtain the failure rate of the unmanned system under the evaluation index includes:
determining an index experience value of each evaluation index under each functional module; setting the corresponding index experience value of the selected evaluation index as follows:
wherein: n is n i The number of the evaluation indexes in the ith functional module;is the index experience value of the nth index in the ith functional module.
And testing and verifying the index experience value, and obtaining the optimized index experience value as an evaluation index value.
Specifically, repeated testing and verification are carried out on the simulation platform until reaching a preset threshold value, and finally the optimized evaluation index value is obtained as follows:
wherein: n is n i The number of the evaluation indexes in the ith functional module;an index value optimized for an nth index in the ith functional module;
and testing the unmanned system according to the evaluation index value to obtain the failure rate of the unmanned system under the evaluation index.
By combining the optimized evaluation index values on the simulation platform, repeatedly testing the unmanned system to be tested in a large amount until reaching a preset threshold value, the failure rate of the unmanned system under the corresponding evaluation index can be obtained:
Wherein:the failure rate of the unmanned system under the nth index in the ith functional module is obtained.
The failure rate needs to be selected according to different testing scenes or testing requirements. The standard for measuring the failure rate of the selected unmanned system can be according to the mileage tested (hundred kilometers failure rate of the system/manual intervention rate), the duration tested (hundred hours failure rate of the system/manual intervention rate), the success or failure frequency according to the completion condition of the system task (failure frequency of the system), and the like.
In an optional embodiment, the constructing a dynamic bayesian network reliability evaluation model by using the failure rate, and obtaining the state probability of the unmanned system by using the output of the dynamic bayesian network reliability evaluation model includes:
performing function division and hierarchy division on the unmanned system to obtain a plurality of function modules and a plurality of system hierarchies;
determining a dynamic Bayesian network graph structure according to the functional module and the system level, and completing the construction of a dynamic Bayesian network credibility evaluation model;
calculating the conditional probability table parameters of all possible states of each node in the Bayesian network graph structure under each evaluation index based on the failure rate; wherein the conditional probability table parameters include probability values for each node in all possible states;
And taking the state probability value as the input of a dynamic Bayesian network credibility evaluation model, and acquiring the state probability of the unmanned system according to the output of the Bayesian network credibility evaluation model.
In the embodiment of the application, a DBN is used as a framework for constructing a credibility evaluation model. Since the reliability of the unmanned system is a function of time, the reliability of a complex unmanned system can dynamically change over time. In modeling the trustworthiness of a complex unmanned system, nodes in the DBN may represent the state of the system, components, while directed edges between nodes may represent the impact relationship between components and the system. The strength of association between variables, i.e., the conditional probability of each node relative to all possible states of its parent node, is quantitatively described by a conditional probability table.
Based on the above, in the embodiment of the present application, the dynamic bayesian network credibility evaluation model is constructed by the following method:
specifically, fig. 4 shows a schematic structural diagram of the unmanned system after disassembly. As shown in fig. 4, the unmanned system is first functionally and hierarchically divided.
In the aspect of function division, the unmanned system can be divided into three functional modules of a sensing module, a decision control module and a whole vehicle performance module from two aspects of system self and whole vehicle integration, wherein each functional module can be divided into components, and the components can be divided into hardware and related algorithms. For example: the sensing module can be divided into hardware and a sensing algorithm, and the hardware can be divided into a camera, a laser radar, a millimeter wave radar, an Inertial Measurement Unit (IMU), a Global Positioning System (GPS) and the like; the perception algorithm can be divided into algorithms of target detection, target tracking (positioning) and track prediction.
The decision control module can be divided into a decision algorithm and a control algorithm; decision algorithms can be divided into algorithms based on empirical rules, based on data driving, based on utility functions, taking into account uncertainty and interactivity; the control algorithm can be divided into a transverse control algorithm, a longitudinal control algorithm and a transverse and longitudinal cooperative control algorithm. The transverse control can be divided into a control method without a model, based on a vehicle kinematic model and based on a vehicle kinematic model; longitudinal control can be divided into a control method of constant-speed cruising, self-adaptive cruising and emergency braking; the transversal and longitudinal cooperative control can be divided into a distributed method and an integrated cooperative method.
The whole vehicle performance module needs to consider the performances such as stability, comfort, safety, high efficiency and the like.
The hierarchical division aspect can be divided into a system level (unmanned system), a subsystem level (perception module, decision control module, whole vehicle performance module) and a component level (hardware and related algorithm contained in the system).
From the functional modules and system hierarchy as shown in fig. 4, a dynamic bayesian network graph structure can be set:
FIG. 5 shows a schematic diagram of a dynamic Bayesian network graph structure, as shown in FIG. 5, the Bayesian network graph structure is divided into three parts of perception, decision and overall vehicle performance according to the functional division of the unmanned system in FIG. 4; the unmanned system is divided into three layers of system level, subsystem level and component level according to the hierarchy division of the unmanned system in fig. 4.
The composition of the nodes in the dynamic Bayesian network graph structure from top to bottom is respectively as follows:
TABLE 1 node composition of dynamic Bayesian network graph structure
It should be noted that the system in table 1 above refers to an unmanned system; the module part refers to a functional module part; the model refers to a dynamic Bayesian network credibility evaluation model.
Wherein, the liquid crystal display device comprises a liquid crystal display device,the data of the dynamic Bayesian network credibility evaluation model is updated in real time by the circulating arrow on the father node, and the updating interval time is 'unit 1', namely deltat=1; the prediction time interval set by the dynamic Bayesian network credibility evaluation model is T 0 The method comprises the steps of carrying out a first treatment on the surface of the The time setting of the whole dynamic Bayesian network credibility evaluation model meets the following conditions: t= {0,1, … T 0 }。
And then, based on the constructed dynamic Bayesian network graph structure, calculating the conditional probability of each node in the dynamic Bayesian network graph structure.
It should be noted that, in the embodiment of the present application, a DBN is used as a framework of a credibility evaluation model, where the DBN is a bayesian network fused with time information, and the DBN may be regarded as a structure in which time slices of a plurality of bayesian networks are unidirectionally connected together. The structure of the Bayesian network and the relation between nodes are all identical in each frame time slice, and the time slice network of the t frame is only related to the time slice networks of the t-1 frame and the t+1 frame and is not related to other network slices. The conditional probability table for each node is the same and remains unchanged regardless of the time t.
Optionally, the calculating the conditional probability table parameters of all possible states of each node in the dynamic bayesian network graph structure under each evaluation index based on the failure rate includes:
inputting failure rate into the dynamic Bayesian network credibility evaluation model;
taking the failure rate of the unmanned system under the corresponding evaluation index obtained in the step 103 as the training input of the whole Bayesian network credibility evaluation model:
wherein, the liquid crystal display device comprises a liquid crystal display device,the failure rate of the unmanned system under the nth evaluation index in the ith functional module is obtained.
Calculating the working probability of the unmanned system under each evaluation index;
wherein, the liquid crystal display device comprises a liquid crystal display device,the working probability of the unmanned system under the nth evaluation index in the ith functional module is obtained;
based on the working probability, calculating and outputting conditional probability table parameters of all possible states of each node in the Bayesian network graph structure under each evaluation index:
wherein: p (P) r { Ω } is a state probability value for the Ω node set, where Ω= { X 1 (t),X 2 (t),…X n (t)}；
n is the number of nodes contained in the omega node set;
T 0 for a set time interval;
is X i (t) conditional probability of a node;
is X i (t) all parent nodes of the node.
The state probability value is used as the input of a dynamic Bayesian network credibility evaluation model, and the state probability of the unmanned system is obtained according to the output of the dynamic Bayesian network credibility evaluation model, specifically:
Taking a state probability value of the system at the moment t under each evaluation index as the input of a dynamic Bayesian network credibility evaluation model:
wherein: n is n i The number of the evaluation indexes in the ith functional module;
a state probability value of the unmanned system under the nth evaluation index of the ith functional module part;
the output of the dynamic Bayesian network credibility evaluation model is the state probability S of the unmanned system predicted at the time t W (t)。
Based on the output of the constructed dynamic bayesian network reliability evaluation model (state probability S of unmanned system W (t)) calculating the credibility and the importance of the system components of the unmanned system.
In order to comprehensively describe the relationship between the reliability of the component and the reliability of the unmanned system, and to quantify the extent to which the change in the state of the component affects the reliability of the unmanned system, a metric needs to be introduced. The embodiment of the application introduces importance measurement (Birnbaum Importance Measures, BIMs) as a standard for measuring the influence degree of the reliability of the components on the reliability of the unmanned system.
The calculation process is as follows:
trustworthiness calculation of the unmanned system:
wherein: r is R S (t) is the credibility of the whole system at the time t;
P r {S W (t) =1 } is S W Probability of the node in a 1 state at time t (when the whole system is in a working state);
is S W All parent nodes of (t);
calculating the importance degree of the component:
wherein, the liquid crystal display device comprises a liquid crystal display device,representing the kth in the ith functional module i A plurality of components;
representation->Importance value of the component at time t;
to express +.>When the node is in a 1 state at the time t, S W Probability that the node is in the "1" state at time t (when +.>When the component is in the working state, the probability that the unmanned system is in the working state is increased; the value can beAs a known condition, the dynamic Bayesian network credibility evaluation model is obtained by output;
when C is represented by i When the node is in a 0 state at the time t, S W Probability that the node is in the "1" state at time t (when +.>When the component is in a failure state, the probability that the system is in a working state); the value may be +.>As a known condition, the result is obtained from the output of a dynamic bayesian network credibility evaluation model.
In an alternative embodiment, the method further comprises:
based on the collected observation data, the trustworthiness of the unmanned system is updated.
The reliability update for the unmanned system means that the reliability evaluation result of the unmanned system is updated by using the collected observation data. That is, when new observation data of the state of the unmanned system is collected, the new operation state probability S of the unmanned system is inferred through the dynamic Bayesian network credibility evaluation model W (t)。
In an alternative embodiment, the updating the trustworthiness of the unmanned system based on the collected observations includes:
receiving observation data, inputting the observation data into a dynamic Bayesian network credibility evaluation model, and outputting to obtain corresponding state probability;
and recalculating the credibility of the unmanned system according to the state probability.
Let the collected observation data be E, the observation data may be classified into single-stage observation data and multi-stage observation data.
Optionally, for trusted updates of single level observation data:
wherein: p (P) r {S W (t)|E(t 1 ) May be obtained by combining E (t) 1 ) As a known condition, outputting by a dynamic Bayesian network credibility evaluation model;
E(t 1 ) At t 1 Single-stage observations of time;
S W (t) is a predicted state probability of the unmanned system at time t, wherein: t is t>t 1 ；
Trusted updates to multi-level observation data:
wherein: p (P) r {S W (t)|E(t 1 ) May be achieved by combining E 1 (t 1 ),E 2 (t 1 ),…E m (t 1 ) As a known condition, outputting by a dynamic Bayesian network credibility evaluation model;
E 1 (t 1 ),E 2 (t 1 ),…E m (t 1 ) At t 1 A time-of-day multi-level observation;
S W (t) is a predicted state probability of the unmanned system at time t, wherein: t is t>t 1 。
As an example:
(1) In combination with the step 101, in the embodiment of the present application, three typical scenarios of an intersection, a roundabout, and a high-speed gateway of a city are taken as examples, and according to the structure of the man-vehicle-road-environment system shown in fig. 2, the main functions to be tested of the unmanned system in the selected typical scenario are listed, as shown in table 2:
TABLE 2 main function test point of unmanned system in urban typical scene and typical scene constituent elements
(2) In combination with the step 102, according to the defined functional test requirement, an evaluation index of the unmanned system and an index experience value of the evaluation index are determined.
Specifically, taking urban intersections as an example, selecting corresponding evaluation indexes of the unmanned system as shown in table 3:
table 3 evaluation index selection in intersection test scenario
/>
(3) And combining the step 103, performing simulation test based on the functional test scene library and the index experience value to obtain the failure rate of the unmanned system under the evaluation index. Specifically, the method comprises the following steps:
selecting SCANeR by a simulation platform for virtual test TM studio。
SCANeR TM The studio is a modular autopilot simulation platform that provides all tools and models needed to build the super real virtual world: road environment, vehicle dynamics, traffic, sensors, real/virtual drivers, vehiclesHeadlamps, weather conditions, and scene scripts. The universality is strong, and the functions are very powerful.
The whole flow of the simulation test is as follows:
(1) the corresponding index experience value of the evaluation index selected in the step (2) is known as follows:
(2) through repeated testing and verification on the simulation platform, the optimized evaluation index value is finally obtained as follows:
(3) By combining the optimized evaluation index values obtained in the step (2) on a simulation platform, repeatedly testing the unmanned system to be tested in a large number, and obtaining the failure rate of the unmanned system under the corresponding evaluation index values:
(4) And combining the step 104, constructing a dynamic Bayesian network credibility evaluation model by using the failure rate, and obtaining the state probability of the unmanned system by using the output of the dynamic Bayesian network credibility evaluation model.
The construction process of the dynamic Bayesian network credibility evaluation model is as follows:
(1) performing functional division and hierarchical division on the unmanned system:
in the aspect of function division, the unmanned system is divided into three functional modules of a perception module, a decision control module and a whole vehicle performance module from the system, wherein each functional module can be divided into components, and the components can be divided into hardware and related algorithms.
The hierarchical division aspect can be divided into a system level (unmanned system), a subsystem level (perception module, decision control module, whole vehicle performance module) and a component level (hardware and related algorithm contained in the system).
(2) According to the functional modules and the system level of the unmanned system, the dynamic Bayesian network graph structure is defined:
FIG. 6 shows a schematic diagram of a dynamic Bayesian network graph structure in an example. As shown in fig. 6, the dynamic bayesian network graph structure is divided into three parts of a perception module, a decision control module and a whole vehicle performance module according to the functional modules disassembled by the system; the system level, the subsystem level and the component level are separated according to the disassembled system level.
Wherein, the renting fields of the nodes in the dynamic Bayesian network graph structure are respectively from top to bottom:
table 4 DBN graphic structure node composition of unmanned system in intersection test scene
The updated interval time is set as "unit 1", i.e. Δt=1, and the predicted interval time set by the dynamic bayesian network reliability evaluation model is set as T 0 The method comprises the steps of carrying out a first treatment on the surface of the The time setting of the whole dynamic Bayesian network credibility evaluation model meets the following conditions: t= {0,1, … T 0 }。
(3) Based on the constructed dynamic Bayesian network graph structure, calculating conditional probability table parameters of all possible states of each node in the dynamic Bayesian network graph structure under each evaluation index:
the conditional probability table parameter calculation process of each node is as follows:
and (3) training and inputting the failure rate of the unmanned system obtained in the step (3) under the corresponding evaluation index value as a dynamic Bayesian network credibility evaluation model:
The working probability value of the unmanned system under the measurement of various evaluation indexes can be calculated:
/>
wherein:-the probability of operation of the unmanned system under the n-th evaluation index in the i-th functional module;
-failure rate of the unmanned system under the nth evaluation index in the ith functional module;
based on the obtained working probability, the conditional probability table parameters of all possible states of each node under each evaluation index can be calculated:
wherein: p (P) r { Ω } is a state probability value for the Ω node set, where Ω= { X 1 (t),X 2 (t),…X n (t)}；
n is the number of nodes contained in the omega node set;
T 0 for a set time interval;
is X i (t) conditional probability of a node;
is X i (t) nodeIs included in the parent node of (a).
(4) The dynamic Bayesian network credibility evaluation model is input as follows: state probability value of the system under the measurement of various evaluation indexes at the moment t:
(5) the output of the dynamic Bayesian network credibility evaluation model is as follows: state probability S of system predicted at time t W (t)。
(5) Based on the output of the constructed dynamic bayesian network reliability evaluation model (state probability S of unmanned system W (t)) calculating the credibility and the importance of the system components of the unmanned system.
The calculation process is as follows:
(1) trustworthiness calculation of the unmanned system:
(2) Calculation of unmanned system component level importance:
to be used forComponent (camera component of perception Module) for example, calculate +.>Importance of (3):
wherein:indicating when->When the node is in a 1 state at the time t, S W Probability that the node is in a "1" state at time t (probability that the system is in an operating state when the camera is in an operating state); the value can beAs a known condition, the dynamic Bayesian network credibility evaluation model is obtained by output;
indicating when->When the node is in a 0 state at the time t, S W Probability that the node is in a "1" state at time t (probability that the system is in an operating state when the camera is in a disabled state); the value can beAs a known condition, the dynamic Bayesian network credibility evaluation model is obtained by output;
(6) Based on the collected observation data, updating the system credibility is completed.
Let the collected observation data be:the observation data means that: t is t 1 Time->The assembly (camera) is in the working state, +.>The component is in a failure state (the stability of the vehicle is not up to standard) and belongs to multi-level observation data:
the credibility updating process is as follows:
wherein:the representation will->As a known condition, the output of the dynamic Bayesian network credibility evaluation model can be obtained;
S W (t) -predicting the state probability of the unmanned system for time t, wherein: t is t>t 1 。
Based on the same principle as the method provided by the embodiment of the application, the embodiment of the application also provides a scene-based unmanned driving system credibility evaluation device, as shown in fig. 7, which comprises:
the functional test scene confirmation module 701 is configured to select a scene element and a functional test requirement to be randomly combined according to a specific function to be tested of the unmanned system, so as to generate a functional test scene library;
the evaluation index generation module 702 is configured to determine an evaluation index of the unmanned system and an index experience value of the evaluation index according to the functional test requirement;
the system failure rate calculation module 703 is configured to perform a simulation test based on the functional test scene library and the index experience value, and obtain a failure rate of the unmanned system under the evaluation index;
the model construction training module 704 is configured to construct a dynamic bayesian network credibility evaluation model by using the failure rate, and obtain a state probability of the unmanned system by using the output of the dynamic bayesian network credibility evaluation model;
the system credibility calculation module 705 is configured to calculate credibility and component importance of the unmanned system according to the state probability.
In the embodiment of the application, a functional test scene confirmation module selects scene elements and functional test requirements for random combination according to the specific function to be tested of the unmanned system, and a functional test scene library is generated; the evaluation index generation module determines an evaluation index of the unmanned system and an index experience value of the evaluation index according to the functional test requirement; the system failure rate calculation module carries out simulation test based on the functional test scene library and the index experience value to obtain the failure rate of the unmanned system under the evaluation index; the model construction training module constructs a dynamic Bayesian network credibility evaluation model by using the failure rate, and obtains the state probability of the unmanned system by using the output of the dynamic Bayesian network credibility evaluation model; the system credibility calculation module calculates credibility and component importance of the unmanned system according to the state probability, and can realize credibility evaluation of the unmanned system.
In addition, the embodiment of the application can closely correlate the test requirements of the unmanned system with the test scene, enrich the performance evaluation indexes of each functional module of the unmanned system, reduce the development and maintenance costs of the unmanned system, and improve the test efficiency of the unmanned system, thereby improving the safety of the unmanned technology and promoting the deployment application of high-level automatic driving on an actual road.
In an alternative embodiment, the evaluation index generation module 702 includes:
the first evaluation index generation sub-module is used for determining a functional module in the unmanned system according to the functional test requirement;
and the second evaluation index generation sub-module is used for determining the components contained in the functional module and determining the evaluation index and the index experience value of the evaluation index according to the components.
In an alternative embodiment, the system failure rate calculation module 703 includes:
the first system failure rate calculation sub-module is used for determining index experience values of each evaluation index under each functional module;
the second system failure rate calculation sub-module is used for testing and verifying the index experience value and obtaining the optimized index experience value as an evaluation index value;
and the third system failure rate calculation sub-module is used for testing the unmanned system according to the evaluation index value to obtain the failure rate of the unmanned system under the evaluation index.
In an alternative embodiment, the model building training module 704 includes:
the first model is used for constructing a training sub-module for carrying out function division and hierarchy division on the unmanned system to obtain a plurality of function modules and a plurality of system hierarchies;
The second model building training sub-module is used for determining a dynamic Bayesian network graph structure according to the functional module and the system level and completing the building of a dynamic Bayesian network credibility evaluation model;
the third model builds a training sub-module for calculating the conditional probability table parameters of all possible states of each node in the dynamic Bayesian network graph structure under each evaluation index based on failure rate; the conditional probability table parameters include probability values for each node in all possible states;
and the fourth model builds a training sub-module, which is used for taking the state probability value as the input of the Bayesian network credibility evaluation model in winter, and acquiring the state probability of the unmanned system according to the output of the dynamic Bayesian network credibility evaluation model.
In an alternative embodiment, the third model building training submodule includes:
the first model building training unit is used for inputting failure rate into a dynamic Bayesian network credibility evaluation model;
the second model building training unit is used for calculating the working probability of the unmanned system under various evaluation indexes;
and the third model building training unit is used for calculating and outputting conditional probability table parameters of all possible states of each node in the dynamic Bayesian network graph structure under each evaluation index based on the working probability.
In an alternative embodiment, the apparatus further comprises:
and the credibility updating module is used for updating the credibility of the unmanned system based on the collected observation data.
In an alternative embodiment, the trusted upgrade module includes:
the first credibility updating sub-module is used for receiving the observation data, inputting the observation data into a dynamic Bayesian network credibility evaluation model, and outputting to obtain corresponding state probability;
and the second credibility updating sub-module is used for recalculating the credibility of the unmanned system according to the state probability.
The embodiment of the application provides a scene-based unmanned driving system credibility evaluation device, which can realize each process realized in the method embodiments of fig. 1 to 6, and is not repeated here for avoiding repetition.
The scenario-based unmanned aerial vehicle system reliability evaluation device according to the embodiment of the present application may execute the scenario-based unmanned aerial vehicle system reliability evaluation method according to the embodiment of the present application, and the implementation principle is similar, and actions executed by each module and unit in the scenario-based unmanned aerial vehicle system reliability evaluation device according to each embodiment of the present application correspond to steps in the scenario-based unmanned aerial vehicle system reliability evaluation method according to each embodiment of the present application, and detailed functional descriptions of each module of the scenario-based unmanned aerial vehicle system reliability evaluation device may be specifically referred to descriptions in the corresponding scenario-based unmanned aerial vehicle system reliability evaluation method shown in the foregoing, which are not repeated herein.
Based on the same principles as the methods shown in the embodiments of the present application, the embodiments of the present application also provide an electronic device that may include, but is not limited to: a processor and a memory; a memory for storing a computer program; and the processor is used for executing the scene-based unmanned driving system credibility evaluation method according to any optional embodiment of the application by calling the computer program. Compared with the prior art, the reliability evaluation method of the unmanned system based on the scene provided by the application has the advantages that according to the specific function to be tested of the unmanned system, scene elements and functional test requirements are selected to be randomly combined, and a functional test scene library is generated; determining an evaluation index of the unmanned system and an index experience value of the evaluation index according to the functional test requirement; performing simulation test based on the functional test scene library and the index experience value to obtain the failure rate of the unmanned system under the evaluation index; constructing a dynamic Bayesian network credibility evaluation model by using the failure rate, and obtaining the state probability of the unmanned system by using the output of the dynamic Bayesian network credibility evaluation model; and finally, calculating the credibility and the component importance of the unmanned system according to the state probability, and realizing the credibility evaluation of the unmanned system.
In an alternative embodiment, there is also provided an electronic device, as shown in fig. 8, where the electronic device 800 shown in fig. 8 may be a server, including: a processor 801 and a memory 803. The processor 801 is coupled to a memory 803, such as via a bus 802. Optionally, the electronic device 800 may also include a transceiver 804. It should be noted that, in practical applications, the transceiver 804 is not limited to one, and the structure of the electronic device 800 is not limited to the embodiment of the present application.
The processor 801 may be a CPU (Central Processing Unit ), general purpose processor, DSP (Digital Signal Processor, data signal processor), ASIC (Application Specific Integrated Circuit ), FPGA (Field Programmable GateArray, field programmable gate array) or other programmable logic device, transistor logic device, hardware components, or any combination thereof. Which may implement or perform the various exemplary logic blocks, modules and circuits described in connection with this disclosure. The processor 801 may also be a combination of computing functions, e.g., including one or more microprocessor combinations, a combination of a DSP and a microprocessor, etc.
Bus 802 may include a path to transfer information between the aforementioned components. Bus 802 may be a PCI (Peripheral Component Interconnect, peripheral component interconnect standard) bus or EISA (Extended Industry Standard Architecture ) bus, among others. Bus 802 may be classified as an address bus, a data bus, a control bus, etc. For ease of illustration, only one thick line is shown in fig. 8, but not only one bus or one type of bus.
The Memory 803 may be, but is not limited to, ROM (Read Only Memory) or other type of static storage device that can store static information and instructions, RAM (Random Access Memory ) or other type of dynamic storage device that can store information and instructions, EEPROM (Electrically Erasable Programmable Read Only Memory ), CD-ROM (Compact Disc Read Only Memory, compact disc Read Only Memory) or other optical disk storage, optical disk storage (including compact discs, laser discs, optical discs, digital versatile discs, blu-ray discs, etc.), magnetic disk storage media or other magnetic storage devices, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and that can be accessed by a computer.
The memory 803 is used to store application code for performing the aspects of the present application and is controlled by the processor 801 for execution. The processor 801 is configured to execute application code stored in the memory 803 to implement what is shown in the foregoing method embodiment.
Among them, electronic devices include, but are not limited to: mobile terminals such as mobile phones, notebook computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), in-vehicle terminals (e.g., in-vehicle navigation terminals), and stationary terminals such as digital TVs, desktop computers, and the like. The electronic device shown in fig. 8 is only an example and should not be construed as limiting the functionality and scope of use of the embodiments of the application.
The server provided by the application can be an independent physical server, a server cluster or a distributed system formed by a plurality of physical servers, and a cloud server for providing cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDNs, basic cloud computing services such as big data and artificial intelligent platforms and the like. The terminal may be, but is not limited to, a smart phone, a tablet computer, a notebook computer, a desktop computer, a smart speaker, a smart watch, etc. The terminal and the server may be directly or indirectly connected through wired or wireless communication, and the present application is not limited herein.
Embodiments of the present application provide a computer-readable storage medium having a computer program stored thereon, which when run on a computer, causes the computer to perform the corresponding method embodiments described above.
It should be understood that, although the steps in the flowcharts of the figures are shown in order as indicated by the arrows, these steps are not necessarily performed in order as indicated by the arrows. The steps are not strictly limited in order and may be performed in other orders, unless explicitly stated herein. Moreover, at least some of the steps in the flowcharts of the figures may include a plurality of sub-steps or stages that are not necessarily performed at the same time, but may be performed at different times, the order of their execution not necessarily being sequential, but may be performed in turn or alternately with other steps or at least a portion of the other steps or stages.
It should be noted that the computer readable storage medium according to the present application may also be a computer readable signal medium or a combination of a computer readable storage medium and a computer readable storage medium. The computer readable storage medium can be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples of the computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, 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 disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this document, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In the present application, however, the computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, with the computer-readable program code embodied therein. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination of the foregoing. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: electrical wires, fiber optic cables, RF (radio frequency), and the like, or any suitable combination of the foregoing.
The computer readable medium may be contained in the electronic device; or may exist alone without being incorporated into the electronic device.
The computer-readable medium carries one or more programs which, when executed by the electronic device, cause the electronic device to perform the methods shown in the above-described embodiments.
According to one aspect of the present application, there is provided a computer program product or computer program comprising computer instructions stored in a computer readable storage medium. The processor of the computer device reads the computer instructions from the computer readable storage medium, and the processor executes the computer instructions, so that the computer device executes a method and a device for evaluating the credibility of the unmanned driving system based on the scene provided in the various optional implementation modes.
Computer program code for carrying out operations of the present application may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, smalltalk, C ++ and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computer (for example, through the Internet using an Internet service provider).
The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present application. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
The modules involved in the embodiments of the present application may be implemented in software or in hardware. The name of the module does not form a limitation on the module itself in a certain case, for example, the functional test scene confirmation module may also be described as "a functional test scene confirmation module for selecting a scene element and a functional test requirement to be randomly combined according to a specific function to be tested of the unmanned system, and generating a functional test scene library".
The above description is only illustrative of the preferred embodiments of the present application and of the principles of the technology employed. It will be appreciated by persons skilled in the art that the scope of the disclosure referred to in the present application is not limited to the specific combinations of technical features described above, but also covers other technical features formed by any combination of the technical features described above or their equivalents without departing from the spirit of the disclosure. Such as the above-mentioned features and the technical features disclosed in the present application (but not limited to) having similar functions are replaced with each other.
Claims (10)
1. A method for evaluating the credibility of an unmanned driving system based on a scene, which is characterized by comprising the following steps:
according to the specific function to be tested of the unmanned system, selecting scene elements and functional test requirements to be randomly combined, and generating a functional test scene library;
according to the functional test requirement, determining an evaluation index of the unmanned system and an index experience value of the evaluation index;
performing simulation test based on the function test scene library and the index experience value to obtain failure rate of the unmanned driving system under the evaluated index;
Constructing a dynamic Bayesian network credibility evaluation model by using the failure rate, and outputting and obtaining the state probability of the unmanned system by using the dynamic Bayesian network credibility evaluation model;
and calculating the credibility and the component importance of the unmanned system according to the state probability.
2. The method for evaluating the credibility of the unmanned aerial vehicle system based on the scene as claimed in claim 1, wherein the step of determining the evaluation index of the unmanned aerial vehicle system and the index experience value of the evaluation index according to the functional test requirement comprises the following steps:
determining a functional module in the unmanned system according to the functional test requirement;
and determining components contained in the functional module, and determining an evaluation index and an index experience value of the evaluation index according to the components.
3. The method for evaluating the credibility of the unmanned aerial vehicle system based on the scene as claimed in claim 2, wherein the step of performing a simulation test based on the functional test scene library and the index experience value to obtain the failure rate of the unmanned aerial vehicle system under the evaluated index comprises the following steps:
determining an index experience value of each evaluation index under each functional module;
Testing and verifying the index experience value, and obtaining an optimized index experience value as an evaluation index value;
and testing the unmanned system according to the evaluation index value to obtain the failure rate of the unmanned system under the evaluation index.
4. The method for evaluating the reliability of the unmanned system based on the scene as claimed in claim 1, wherein the steps of constructing a dynamic bayesian network reliability evaluation model by using the failure rate and obtaining the state probability of the unmanned system by using the output of the dynamic bayesian network reliability evaluation model comprise:
performing function division and hierarchy division on the unmanned system to obtain a plurality of function modules and a plurality of system hierarchies;
determining a dynamic Bayesian network graph structure according to the functional module and the system level, and completing the construction of a dynamic Bayesian network credibility evaluation model;
calculating conditional probability table parameters of all possible states of each node in the dynamic Bayesian network graph structure under each evaluation index based on the failure rate; the conditional probability table parameters comprise probability values of each node in all possible states;
And taking the state probability value as the input of the dynamic Bayesian network credibility evaluation model, and acquiring the state probability of the unmanned system according to the output of the dynamic Bayesian network credibility evaluation model.
5. The method for evaluating the credibility of the unmanned system based on the scene as recited in claim 4, wherein calculating the conditional probability table parameters of all possible states of each node in the dynamic bayesian network graph structure under each evaluation index based on the failure rate comprises:
inputting the failure rate into the dynamic Bayesian network credibility evaluation model;
calculating the working probability of the unmanned system under each evaluation index;
based on the working probability, calculating and outputting the conditional probability table parameters of all possible states of each node in the dynamic Bayesian network graph structure under each evaluation index.
6. The method of evaluating the trustworthiness of a scene based unmanned system of claim 1, further comprising:
based on the collected observation data, the trustworthiness of the unmanned system is updated.
7. The method of evaluating the trustworthiness of a scene based unmanned system of claim 6, wherein updating the trustworthiness of the unmanned system based on the collected observations comprises:
Receiving the observation data, inputting the observation data into the dynamic Bayesian network credibility evaluation model, and outputting to obtain corresponding state probability;
and recalculating the credibility of the unmanned system according to the state probability.
8. A scene-based unmanned system credibility evaluation device, characterized in that the device comprises:
the function test scene confirming module is used for selecting scene elements and function test requirements to be randomly combined according to the specific function to be tested of the unmanned system, and generating a function test scene library;
the evaluation index generation module is used for determining an evaluation index of the unmanned system and an index experience value of the evaluation index according to the functional test requirement;
the system failure rate calculation module is used for performing simulation test based on the functional test scene library and the index experience value to obtain failure rate of the unmanned aerial vehicle system under the evaluation index;
the model construction training module is used for constructing a dynamic Bayesian network credibility evaluation model by utilizing the failure rate and obtaining the state probability of the unmanned system by utilizing the output of the dynamic Bayesian network credibility evaluation model;
And the system credibility calculation module is used for calculating credibility and component importance of the unmanned system according to the state probability.
9. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the method of any one of claims 1 to 7 when the program is executed.
10. A computer readable storage medium, characterized in that it has stored thereon a computer program which, when executed by a processor, implements the method of any of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310853356.9A CN116795720A (en) | 2023-07-12 | 2023-07-12 | Unmanned driving system credibility evaluation method and device based on scene |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310853356.9A CN116795720A (en) | 2023-07-12 | 2023-07-12 | Unmanned driving system credibility evaluation method and device based on scene |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116795720A true CN116795720A (en) | 2023-09-22 |
Family
ID=88049638
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310853356.9A Pending CN116795720A (en) | 2023-07-12 | 2023-07-12 | Unmanned driving system credibility evaluation method and device based on scene |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116795720A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117371655A (en) * | 2023-10-12 | 2024-01-09 | 中山大学 | Unmanned plane collaborative decision evaluation method, system, equipment and medium |
-
2023
- 2023-07-12 CN CN202310853356.9A patent/CN116795720A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117371655A (en) * | 2023-10-12 | 2024-01-09 | 中山大学 | Unmanned plane collaborative decision evaluation method, system, equipment and medium |
| CN117371655B (en) * | 2023-10-12 | 2024-06-18 | 中山大学 | Unmanned plane collaborative decision evaluation method, system, equipment and medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Tekouabou et al. | Improving parking availability prediction in smart cities with IoT and ensemble-based model | |
| JP7075366B2 (en) | Methods, devices, equipment and media for classifying driving scene data | |
| US20220105961A1 (en) | Method for automatic control of vehicle and method for training lane change intention prediction network | |
| US20210101619A1 (en) | Safe and scalable model for culturally sensitive driving by automated vehicles | |
| JP2021502541A (en) | Artificial intelligence systems and methods for predicting traffic accident locations | |
| CN111310828B (en) | Target detection model fine-tuning method and device for ADAS scene | |
| CN116795720A (en) | Unmanned driving system credibility evaluation method and device based on scene | |
| WO2022142574A1 (en) | Traffic prediction model training method and apparatus, and electronic device | |
| Gadepally et al. | A framework for estimating long term driver behavior | |
| CN114360239A (en) | Traffic prediction method and system for multilayer space-time traffic knowledge map reconstruction | |
| Zhu et al. | Road network abstraction approach for traffic analysis: framework and numerical analysis<? show [AQ ID= Q1]?> | |
| Wang et al. | TransWorldNG: Traffic simulation via foundation model | |
| CN114971093A (en) | Method, system, equipment and medium for predicting urban road traffic flow attribute | |
| Karimi et al. | Two‐fold calibration approach for microscopic traffic simulation models | |
| CN116861262B (en) | Perception model training method and device, electronic equipment and storage medium | |
| Zhang et al. | Multi-objective deep reinforcement learning approach for adaptive traffic signal control system with concurrent optimization of safety, efficiency, and decarbonization at intersections | |
| CN114444718A (en) | Training method of machine learning model, signal control method and device | |
| CN111507499B (en) | Method, device and system for constructing model for prediction and testing method | |
| JP2021076593A (en) | Dynamic map generation with focus on construction and localization field of technology | |
| WO2023045916A1 (en) | Ensuring proactive availability of vehicles for providing connected vehicle services | |
| Dakić | Importance of knowledge management for CI/CD and Security in Autonomous Vehicles Systems | |
| CN115366919A (en) | Trajectory prediction method, system, electronic device and storage medium | |
| Rahman et al. | MDLpark: available parking prediction for smart parking through mobile deep learning | |
| Gu et al. | A novel merging strategy model considering the remaining distance in the acceleration lane | |
| Panovski et al. | Public transportation prediction with convolutional neural networks |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |