CN113232674A - Vehicle control method and device based on decision tree and Bayesian network - Google Patents
Vehicle control method and device based on decision tree and Bayesian network Download PDFInfo
- Publication number
- CN113232674A CN113232674A CN202110590796.0A CN202110590796A CN113232674A CN 113232674 A CN113232674 A CN 113232674A CN 202110590796 A CN202110590796 A CN 202110590796A CN 113232674 A CN113232674 A CN 113232674A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- surrounding
- bayesian network
- decision tree
- behavior
- 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
- 238000003066 decision tree Methods 0.000 title claims abstract description 46
- 238000000034 method Methods 0.000 title claims abstract description 43
- 238000013145 classification model Methods 0.000 claims abstract description 44
- 230000006399 behavior Effects 0.000 claims description 72
- 238000012549 training Methods 0.000 claims description 30
- 238000004590 computer program Methods 0.000 claims description 8
- 238000007635 classification algorithm Methods 0.000 claims description 7
- 238000007781 pre-processing Methods 0.000 claims description 7
- 230000007547 defect Effects 0.000 abstract description 8
- 238000010276 construction Methods 0.000 abstract description 7
- 230000002093 peripheral effect Effects 0.000 description 6
- 238000012360 testing method Methods 0.000 description 6
- 230000006870 function Effects 0.000 description 5
- 230000008569 process Effects 0.000 description 4
- 238000004422 calculation algorithm Methods 0.000 description 3
- 238000004088 simulation Methods 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 238000004880 explosion Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000035484 reaction time Effects 0.000 description 1
- 238000010187 selection method Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012800 visualization Methods 0.000 description 1
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W40/00—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models
- B60W40/02—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models related to ambient conditions
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W40/00—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models
- B60W40/10—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models related to vehicle motion
- B60W40/105—Speed
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W60/00—Drive control systems specially adapted for autonomous road vehicles
- B60W60/001—Planning or execution of driving tasks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/24323—Tree-organised classifiers
-
- 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
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
- B60W2050/0001—Details of the control system
- B60W2050/0043—Signal treatments, identification of variables or parameters, parameter estimation or state estimation
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W2520/00—Input parameters relating to overall vehicle dynamics
- B60W2520/10—Longitudinal speed
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W2530/00—Input parameters relating to vehicle conditions or values, not covered by groups B60W2510/00 or B60W2520/00
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W2554/00—Input parameters relating to objects
- B60W2554/80—Spatial relation or speed relative to objects
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W2555/00—Input parameters relating to exterior conditions, not covered by groups B60W2552/00, B60W2554/00
- B60W2555/20—Ambient conditions, e.g. wind or rain
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W2555/00—Input parameters relating to exterior conditions, not covered by groups B60W2552/00, B60W2554/00
- B60W2555/60—Traffic rules, e.g. speed limits or right of way
Abstract
The invention provides a vehicle control method and device based on a decision tree and a Bayesian network, wherein the vehicle control method based on the decision tree and the Bayesian network comprises the following steps: acquiring a behavior classification model of the manually driven vehicle; acquiring the conditions of the surrounding road, the surrounding vehicles and the surrounding environment of a target vehicle; obtaining a vehicle behavior decision model according to the conditions of surrounding roads and surrounding vehicles; performing online prediction according to surrounding environment information through a manual driving vehicle behavior classification model, and outputting a corresponding prediction result; and controlling the target vehicle according to the prediction result through the vehicle behavior decision model. According to the vehicle control method based on the decision tree and the Bayesian network, the time cost and the labor cost of model construction can be greatly reduced, and the condition that defects exist in knowledge acquisition and expression is effectively avoided.
Description
Technical Field
The invention relates to the technical field of vehicles, in particular to a vehicle control method based on a decision tree and a Bayesian network and a vehicle control device based on the decision tree and the Bayesian network.
Background
The behavior decision system of the automatic driving vehicle determines the safety and the reasonability of the unmanned vehicle in driving, so that the improvement of the intelligent behavior decision level is always the direction of effort of people, and although a lot of researches are carried out, the automatic driving vehicle still has many problems in autonomous driving under the urban road environment. Due to the particularity of urban structured road environments, autonomous driving of autonomous vehicles in such environments requires a multitude of complex, uncertain factors: the complexity is mainly reflected in the complexity of the road structure, the complexity of the road elements and the types of traffic participants, the complexity of the interaction among the traffic participants and between the traffic participants and the road elements; the uncertainty factor is mainly embodied in the uncertainty of the perception information, the partial observability of the hidden information (such as the driving intention of other vehicles or pedestrians), and the like. Urban traffic road environment has complexity and uncertainty, and under the environment, a behavior decision-making system of an automatic driving vehicle can give a behavior decision-making result with high reliability and high safety in real time. Automatic driving in an unregulated urban population is a significant challenge, particularly in the presence of many aggressive, high-speed traffic participants.
Since the traffic environment will still be the coexistence of autonomous vehicles and manned vehicles for some time in the future, the behavior of manned vehicles is not always rational and safe. The research on the driving behavior of manually driven vehicles in vehicle behavior decision making is becoming more and more popular, however, currently, there is no accurate definition for the prediction of the driving style, so there are many bases for classification, such as oil consumption, uniform speed, following behavior, etc., generally, the classification of the driving style is mostly divided into several classes corresponding to different discrete values, but there is also a continuous driving style classification algorithm, and currently, there are expert systems, fuzzy theories, artificial neural networks, etc., which all belong to rule-based knowledge expression methods, for the artificial intelligence methods of information knowledge acquisition and expression and rule inference. Although the method can simply and effectively express the knowledge, the knowledge cannot be automatically acquired, and the reasoning speed is low and the real-time performance is poor. The artificial neural network can automatically acquire knowledge, but has the problems of over-learning and under-learning, and the model has poor flexibility and low learning convergence speed.
Disclosure of Invention
In order to solve the technical problems, the invention provides a vehicle control method based on a decision tree and a Bayesian network, which can greatly reduce the time cost and the labor cost of model construction and effectively avoid the defects in knowledge acquisition and expression.
The technical scheme adopted by the invention is as follows:
a vehicle control method based on decision trees and Bayesian networks comprises the following steps: acquiring a behavior classification model of the manually driven vehicle; acquiring the surrounding road condition, the surrounding vehicle condition and the surrounding environment information of the target vehicle; obtaining a vehicle behavior decision model according to the surrounding road condition and the surrounding vehicle condition; performing online prediction according to the surrounding environment information through the artificial driving vehicle behavior classification model, and outputting a corresponding prediction result; and controlling the target vehicle according to the prediction result through the vehicle behavior decision model.
According to the manned vehicle behavior classification model, the method comprises the following steps: acquiring operation data of an automatic driving vehicle, relationship data of the automatic driving vehicle and a manual driving vehicle, first traffic scene information and first day air information; preprocessing the operation data of the automatic driving vehicle, the relation data of the automatic driving vehicle and a manual driving vehicle, the first traffic information and the first weather information to obtain a training data set; and training a decision tree classification algorithm according to the training data set to obtain the behavior classification model of the manually-driven vehicle.
The ambient information includes operation data information of the manually driven vehicle, relationship data information of the manually driven vehicle and the automatically driven vehicle, second traffic scene information, and second weather information.
Obtaining the vehicle behavior decision model according to the surrounding road condition and the surrounding vehicle condition comprises: establishing a Bayesian network structure according to the surrounding road condition and the surrounding vehicle condition; and inputting training data to the Bayesian network structure for training so as to obtain the vehicle behavior decision model.
A decision tree and bayesian network based vehicle control apparatus comprising: the first acquisition module is used for acquiring a behavior classification model of the manually driven vehicle; a second acquisition module for acquiring a surrounding road condition, a surrounding vehicle condition, and surrounding environment information of the target vehicle; a third obtaining module, configured to obtain a vehicle behavior decision model according to the surrounding road condition and the surrounding vehicle condition; the prediction module is used for carrying out online prediction according to the surrounding environment information through the artificial driving vehicle behavior classification model and outputting a corresponding prediction result; and the control module is used for controlling the target vehicle according to the prediction result through the vehicle behavior decision model.
A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the decision tree and bayesian network based vehicle control method described above when executing the computer program.
A non-transitory computer-readable storage medium, on which a computer program is stored, which when executed by a processor implements the decision tree and bayesian network based vehicle control method described above.
The invention has the beneficial effects that:
the invention can greatly reduce the time cost and the labor cost of model construction, and effectively avoid the condition of defects in knowledge acquisition and expression.
Drawings
FIG. 1 is a flow chart of a decision tree and Bayesian network based vehicle control method in accordance with an embodiment of the present invention;
FIG. 2 is a schematic logic diagram of obtaining a classification model of behavior of a human-driven vehicle according to an embodiment of the invention;
fig. 3 is a block diagram of a vehicle control device based on a decision tree and a bayesian network according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Fig. 1 is a flowchart of a decision tree and bayesian network based vehicle control method according to an embodiment of the present invention.
Wherein the vehicle may be a vehicle having an automatic driving function.
As shown in fig. 1, a decision tree and bayesian network based vehicle control method according to an embodiment of the present invention may include the steps of:
and S1, acquiring a behavior classification model of the manually driven vehicle.
According to one embodiment of the invention, a classification model for behavior of a vehicle according to human driving comprises: acquiring running data of an automatic driving vehicle, relation data of the automatic driving vehicle and a manual driving vehicle, first traffic scene information and first day air information; preprocessing operation data of the automatic driving vehicle and relationship data of the automatic driving vehicle and the manual driving vehicle to obtain a training data set, first traffic scene information and first weather information; and training the decision tree classification algorithm according to the training data set to obtain a behavior classification model of the manually-driven vehicle.
Specifically, the behavior classification model of the manually-driven vehicle adopts a decision tree classification algorithm of supervised learning, and the application process of the behavior classification model of the manually-driven vehicle is divided into three stages, namely a data preprocessing stage, an offline training stage and an online testing stage. That is to say, in the practical application process, the behavior classification model of the manually driven vehicle can be trained in the first two stages, namely the data preprocessing stage and the offline training stage, and stored, and when the behavior classification model of the manually driven vehicle needs to be used for online testing, the behavior classification model of the manually driven vehicle is directly called for online testing.
Specifically, as shown in fig. 2, in the data preprocessing stage, the operation data (speed, steering lamp operation data, etc.) of the autonomous vehicle, the relationship data (relative distance, relative speed, etc.) of the autonomous vehicle and the manually driven vehicle, and the environmental information (including the first traffic information, such as traffic light status information, and first day information) obtained by the vehicle-mounted sensor are subjected to a labeling operation to generate a labeled data set, and the labeled data set is preprocessed by the sample selection preprocessor to generate a training data set.
In the off-line training stage, a decision tree in the classification model is established by adopting an ID3 decision tree attribute selection method as a basis, and due to the lack of real experimental vehicles, data sets used in the off-line training stage are all from simulation experiments, so that an autopilot of an autopilot simulation tool PreScan is used for obtaining data, and a decision tree algorithm is trained to obtain a behavior classification model of the manually-driven vehicle. Specifically, the information gain of each attribute in an attribute candidate set (composed of attributes of data in a training data set) may be calculated first, and the attribute with the largest information gain is selected as a node to be added into a tree (decision tree), and then after the selected attribute is deleted in the attribute candidate set, the information gain of each attribute in the attribute candidate set is calculated, and the attribute with the largest information gain is selected as a node to be added into the tree, and the above steps are repeated, and finally a decision tree classification model (classification model of behavior of manually driven vehicles) is generated.
It can be understood that, after the classification model of the behavior of the manually driven vehicle is trained, in order to ensure the accuracy of the classification model, a grid search method can be used for parameter tuning of a decision tree classification algorithm, and the optimal classification model is derived for use in an online test stage.
S2, the road condition around the target vehicle, the vehicle condition around the target vehicle, and the surrounding environment information are acquired.
The surrounding environment information of the target vehicle includes operation data information (e.g., speed, turn signal condition, etc.) of the manually driven vehicle, relationship data information (e.g., relative distance, relative speed, etc.) of the manually driven vehicle and the automatically driven vehicle, traffic scene information (e.g., traffic light status, whether an obstacle is present, etc.), and weather information. The vehicle-mounted sensor can be used for acquiring surrounding environment information, namely real-time data are acquired through the vehicle sensor. Ambient road conditions may include lane, sidewalk, traffic lights, etc., and ambient vehicle conditions may include self-vehicle, other vehicles, pedestrians, etc.
And S3, acquiring a vehicle behavior decision model according to the surrounding road condition and the surrounding vehicle condition.
According to one embodiment of the invention, obtaining a vehicle behavior decision model based on the surrounding road conditions and the surrounding vehicle conditions comprises: establishing a Bayesian network structure according to the conditions of surrounding roads and surrounding vehicles; and inputting training data to the Bayesian network structure for training to obtain a vehicle behavior decision model.
Specifically, the vehicle behavior decision model is obtained by modeling a road scene by a Bayesian network supporting probability inference in combination with a driving style, and is realized based on a Bayesian network modeling tool Netica software, wherein the Bayesian network is composed of a structure (a directed acyclic graph) and parameters (a conditional probability table).
That is to say, when the target vehicle is in a traffic scene, the surrounding road condition and the surrounding vehicle condition of the target vehicle may be obtained first, and a bayesian network structure is established according to the surrounding road condition and the surrounding vehicle condition of the target vehicle, wherein a node in the bayesian network structure is composed of a node name and a probability value, and then training data is input to the bayesian network structure for training to obtain a vehicle behavior decision model, wherein the input training data may be implemented in a manner manually constructed for the road condition.
And S4, performing online prediction according to the surrounding environment information through the artificial driving vehicle behavior classification model, and outputting a corresponding prediction result.
Specifically, as shown in fig. 2, in the online testing stage, after the optimal classification model is searched out and derived by the grid search method, the real-time data acquired by the vehicle sensor may be input into the optimal decision tree classification model for online prediction, and a corresponding classification result (prediction result) is output. Wherein, the classification result can output the classification model of the behavior of the man-driven vehicle in the form of label and probability pair (classification model precision).
And S5, controlling the target vehicle according to the vehicle behavior decision model.
Specifically, when a vehicle is in a certain decision stage, the probability value of a node is changed according to real sensor data in the traffic environment, then when a prediction result output in the form of a label and probability pair (classification model precision) is input into a Bayesian network structure, the Bayesian network structure executes probability inference, and outputs an automatic driving vehicle behavior decision result in the form of a behavior and probability pair, and finally, a driving action is selected as a final decision selection of the automatic driving vehicle based on a maximum posterior probability criterion, so that the control of a target vehicle is realized.
In conclusion, the invention adopts the decision tree algorithm to realize the classification model of the behavior of the manually driven vehicle, and effectively solves the problem that the methods in the related technology have defects in knowledge acquisition and expression; the decision tree algorithm is a white-box model, so that the interpretability is strong, the visualization of the final spanning tree is supported, and the model adjustment is conveniently carried out by introducing expert experience; the method has the advantages that the problems of poor real-time performance and overlong result generation time are effectively solved in two stages of offline training and online testing of the manual driving vehicle behavior classification model, particularly in the field of automatic driving which has severe requirements on reaction time, meanwhile, the vehicle behavior decision model is realized by adopting a Bayesian network, and the vehicle behavior decision is executed through probabilistic reasoning, so that the problems of high rule complexity and state space explosion commonly existing in the rule-based model can be solved; in addition, the decision model is constructed in a data-driven mode, compared with a mode based on rules, the time cost and the labor cost for constructing the model are greatly reduced, in addition, the method is realized based on a simulation tool Prescan, the time required for acquiring data is less, the efficiency is high, particularly the time cost and the economic cost for acquiring data in experiments under extreme vehicle conditions are lower, and the cost of the method is further reduced.
According to the vehicle control method based on the decision tree and the Bayesian network, the artificial driving vehicle behavior classification model is obtained, the surrounding road condition, the surrounding vehicle condition and the surrounding environment information of the target vehicle are obtained, the vehicle behavior decision model is obtained according to the surrounding road condition and the surrounding vehicle condition, online prediction is carried out according to the surrounding environment information through the artificial driving vehicle behavior classification model, the corresponding prediction result is output, and the target vehicle is controlled according to the prediction result through the vehicle behavior decision model. Therefore, the time cost and the labor cost for model construction can be greatly reduced, and the condition that defects exist in knowledge acquisition and expression is effectively avoided.
The invention further provides a vehicle control device based on the decision tree and the Bayesian network, which corresponds to the vehicle control method based on the decision tree and the Bayesian network in the embodiment.
As shown in fig. 3, a decision tree and bayesian network-based vehicle control apparatus according to an embodiment of the present invention may include: a first acquisition module 100, a second acquisition module 200, a third acquisition module 300, a prediction module 400, and a control module 500.
The first obtaining module 100 is used for obtaining a classification model of the behavior of the man-driven vehicle; the second obtaining module 200 is configured to obtain a surrounding road condition, a surrounding vehicle condition, and surrounding environment information of the target vehicle; the third obtaining module 300 is configured to obtain a vehicle behavior decision model according to the surrounding road condition and the surrounding vehicle condition; the prediction module 400 is configured to perform online prediction according to the ambient environment information through the manual driving vehicle behavior classification model, and output a corresponding prediction result; the control module 500 is configured to control the target vehicle according to the prediction result through a vehicle behavior decision model.
According to an embodiment of the present invention, the first obtaining module 100 is specifically configured to: acquiring running data of an automatic driving vehicle, relation data of the automatic driving vehicle and a manual driving vehicle, first traffic scene information and first day air information; preprocessing operation data of an automatic driving vehicle, relationship data of the automatic driving vehicle and a manual driving vehicle, first traffic scene information and first weather information to obtain a training data set; and training the decision tree classification algorithm according to the training data set to obtain a behavior classification model of the manually-driven vehicle.
According to one embodiment of the present invention, the surrounding environment information includes operation data information of the manually driven vehicle, relationship data information of the manually driven vehicle and the automatically driven vehicle, second traffic scene information, and second weather information.
According to an embodiment of the present invention, the fourth obtaining module 500 is specifically configured to establish a bayesian network structure according to the conditions of the surrounding roads and the conditions of the surrounding vehicles; and inputting training data to the Bayesian network structure for training to obtain a vehicle behavior decision model.
It should be noted that, in a more specific implementation manner of the vehicle control device based on the decision tree and the bayesian network according to the embodiment of the present invention, reference may be made to the above-mentioned embodiment of the vehicle control method based on the decision tree and the bayesian network, and details thereof are not repeated herein.
According to the vehicle control device based on the decision tree and the Bayesian network, the first obtaining module is used for obtaining the artificial driving vehicle behavior classification model, the second obtaining module is used for obtaining the peripheral road condition, the peripheral vehicle condition and the peripheral environment information of the target vehicle, the third obtaining module is used for obtaining the vehicle behavior decision model according to the peripheral road condition and the peripheral vehicle condition, the prediction module is used for carrying out online prediction according to the peripheral environment information through the artificial driving vehicle behavior classification model, outputting the corresponding prediction result, and the control module is used for controlling the target vehicle according to the prediction result through the vehicle behavior decision model. Therefore, the time cost and the labor cost for model construction can be greatly reduced, and the condition that defects exist in knowledge acquisition and expression is effectively avoided.
The invention further provides a computer device corresponding to the embodiment.
The computer device of the embodiment of the invention comprises a memory, a processor and a computer program which is stored on the memory and can run on the processor, and when the processor executes the program, the vehicle control method based on the decision tree and the Bayesian network of the embodiment is realized.
According to the computer equipment provided by the embodiment of the invention, the time cost and the labor cost for model construction can be greatly reduced, and the condition that defects exist in knowledge acquisition and expression is effectively avoided.
The invention also provides a non-transitory computer readable storage medium corresponding to the above embodiment.
A non-transitory computer-readable storage medium of an embodiment of the present invention has stored thereon a computer program that, when executed by a processor, implements the decision tree and bayesian network-based vehicle control method described above.
According to the non-transitory computer-readable storage medium provided by the embodiment of the invention, the time cost and the labor cost of model construction can be greatly reduced, and the condition that defects exist in knowledge acquisition and expression is effectively avoided.
In the description of the present invention, the terms "first" and "second" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implying any number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. The meaning of "plurality" is two or more unless specifically limited otherwise.
In the present invention, unless otherwise expressly stated or limited, the terms "mounted," "connected," "secured," and the like are to be construed broadly and can, for example, be fixedly connected, detachably connected, or integrally formed; can be mechanically or electrically connected; either directly or indirectly through intervening media, either internally or in any other relationship. The specific meanings of the above terms in the present invention can be understood by those skilled in the art according to specific situations.
In the present invention, unless otherwise expressly stated or limited, the first feature "on" or "under" the second feature may be directly contacting the first and second features or indirectly contacting the first and second features through an intermediate. Also, a first feature "on," "over," and "above" a second feature may be directly or diagonally above the second feature, or may simply indicate that the first feature is at a higher level than the second feature. A first feature being "under," "below," and "beneath" a second feature may be directly under or obliquely under the first feature, or may simply mean that the first feature is at a lesser elevation than the second feature.
In the description herein, references to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, the schematic representations of the terms used above are not necessarily intended to refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, various embodiments or examples and features of different embodiments or examples described in this specification can be combined and combined by one skilled in the art without contradiction.
Any process or method descriptions in flow charts or otherwise described herein may be understood as representing modules, segments, or portions of code which include one or more executable instructions for implementing specific logical functions or steps of the process, and alternate implementations are included within the scope of the preferred embodiment of the present invention in which functions may be executed out of order from that shown or discussed, including substantially concurrently or in reverse order, depending on the functionality involved, as would be understood by those reasonably skilled in the art of the present invention.
The logic and/or steps represented in the flowcharts or otherwise described herein, e.g., an ordered listing of executable instructions that can be considered to implement logical functions, can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions. For the purposes of this description, a "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of the computer-readable medium would include the following: an electrical connection (electronic device) having one or more wires, a portable computer diskette (magnetic device), a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). Additionally, the computer-readable medium could even be paper or another suitable medium upon which the program is printed, as the program can be electronically captured, via for instance optical scanning of the paper or other medium, then compiled, interpreted or otherwise processed in a suitable manner if necessary, and then stored in a computer memory.
It should be understood that portions of the present invention may be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, the various steps or methods may be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, any one or combination of the following techniques, which are known in the art, may be used: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application specific integrated circuit having an appropriate combinational logic gate circuit, a Programmable Gate Array (PGA), a Field Programmable Gate Array (FPGA), or the like.
It will be understood by those skilled in the art that all or part of the steps carried by the method for implementing the above embodiments may be implemented by hardware related to instructions of a program, which may be stored in a computer readable storage medium, and when the program is executed, the program includes one or a combination of the steps of the method embodiments.
In addition, functional units in the embodiments of the present invention may be integrated into one processing module, or each unit may exist alone physically, or two or more units are integrated into one module. The integrated module can be realized in a hardware mode, and can also be realized in a software functional module mode. The integrated module, if implemented in the form of a software functional module and sold or used as a stand-alone product, may also be stored in a computer readable storage medium.
The storage medium mentioned above may be a read-only memory, a magnetic or optical disk, etc. Although embodiments of the present invention have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present invention, and that variations, modifications, substitutions and alterations can be made to the above embodiments by those of ordinary skill in the art within the scope of the present invention.
Claims (7)
1. A vehicle control method based on a decision tree and a Bayesian network is characterized by comprising the following steps:
acquiring a behavior classification model of the manually driven vehicle;
acquiring the surrounding road condition, the surrounding vehicle condition and the surrounding environment information of the target vehicle;
obtaining a vehicle behavior decision model according to the surrounding road condition and the surrounding vehicle condition;
performing online prediction according to the surrounding environment information through the artificial driving vehicle behavior classification model, and outputting a corresponding prediction result;
and controlling the target vehicle according to the prediction result through the vehicle behavior decision model.
2. The decision tree and bayesian network based vehicle control method according to claim 1, wherein classifying a model according to said human-driven vehicle behavior comprises:
acquiring operation data of an automatic driving vehicle, relationship data of the automatic driving vehicle and a manual driving vehicle, first traffic scene information and first day air information;
preprocessing the operation data of the automatic driving vehicle, the relation data of the automatic driving vehicle and a manual driving vehicle, the first traffic information and the first weather information to obtain a training data set;
and training a decision tree classification algorithm according to the training data set to obtain the behavior classification model of the manually-driven vehicle.
3. The decision tree and Bayesian network based vehicle control method of claim 2, wherein,
the ambient information includes operation data information of the manually driven vehicle, relationship data information of the manually driven vehicle and the automatically driven vehicle, second traffic scene information, and second weather information.
4. The decision tree and bayesian network based vehicle control method of claim 1, wherein deriving the vehicle behavior decision model based on the surrounding road conditions and the surrounding vehicle conditions comprises:
establishing a Bayesian network structure according to the surrounding road condition and the surrounding vehicle condition;
and inputting training data to the Bayesian network structure for training so as to obtain the vehicle behavior decision model.
5. A decision tree and bayesian network based vehicle control apparatus, comprising:
the first acquisition module is used for acquiring a behavior classification model of the manually driven vehicle;
a second acquisition module for acquiring a surrounding road condition, a surrounding vehicle condition, and surrounding environment information of the target vehicle;
a third obtaining module, configured to obtain a vehicle behavior decision model according to the surrounding road condition and the surrounding vehicle condition;
the prediction module is used for carrying out online prediction according to the surrounding environment information through the artificial driving vehicle behavior classification model and outputting a corresponding prediction result;
and the control module is used for controlling the target vehicle according to the prediction result through the vehicle behavior decision model.
6. A computer arrangement comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor, when executing the computer program, implements a decision tree and bayesian network based vehicle control method according to any of claims 1-4.
7. A non-transitory computer readable storage medium having stored thereon a computer program, wherein the program, when executed by a processor, implements the decision tree and bayesian network based vehicle control method according to any of claims 1-4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110590796.0A CN113232674A (en) | 2021-05-28 | 2021-05-28 | Vehicle control method and device based on decision tree and Bayesian network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110590796.0A CN113232674A (en) | 2021-05-28 | 2021-05-28 | Vehicle control method and device based on decision tree and Bayesian network |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113232674A true CN113232674A (en) | 2021-08-10 |
Family
ID=77135580
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110590796.0A Pending CN113232674A (en) | 2021-05-28 | 2021-05-28 | Vehicle control method and device based on decision tree and Bayesian network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113232674A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113687991A (en) * | 2021-08-25 | 2021-11-23 | 北京赛目科技有限公司 | Vehicle defect recommendation method and device |
| CN114162144A (en) * | 2022-01-06 | 2022-03-11 | 苏州挚途科技有限公司 | Automatic driving decision method and device and electronic equipment |
| CN114399659A (en) * | 2021-12-28 | 2022-04-26 | 禾多科技（北京）有限公司 | Vehicle control information generation method, device, equipment and computer readable medium |
| CN116385965A (en) * | 2023-03-17 | 2023-07-04 | 深圳市明源云科技有限公司 | Method, apparatus and computer readable storage medium for identifying a wandering animal |
| WO2023151499A1 (en) * | 2022-02-09 | 2023-08-17 | 武汉路特斯汽车有限公司 | Empty space identification method, vehicle, and readable storage medium |
| CN116620271A (en) * | 2023-07-19 | 2023-08-22 | 之江实验室 | Intelligent driving pedestrian avoiding method and system based on short-time memory and behavior tree |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7272587B1 (en) * | 2005-01-28 | 2007-09-18 | Hrl Laboratories, Llc | Generation of decision trees by means of a probabilistic model |
| US20150211867A1 (en) * | 2012-10-09 | 2015-07-30 | Bayerische Motoren Werke Aktiengesellschaft | Estimating a Street Type Using Sensor-Based Surroundings Data |
| CN107977670A (en) * | 2017-10-09 | 2018-05-01 | 中国电子科技集团公司第二十八研究所 | Accident classification stage division, the apparatus and system of decision tree and bayesian algorithm |
| CN108475057A (en) * | 2016-12-21 | 2018-08-31 | 百度（美国）有限责任公司 | The method and system of one or more tracks of situation prediction vehicle based on vehicle periphery |
| CN111368465A (en) * | 2019-12-31 | 2020-07-03 | 成都理工大学 | Unmanned decision-making method based on ID3 decision tree |
| CN112818910A (en) * | 2021-02-23 | 2021-05-18 | 腾讯科技（深圳）有限公司 | Vehicle gear control method and device, computer equipment and storage medium |
-
2021
- 2021-05-28 CN CN202110590796.0A patent/CN113232674A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7272587B1 (en) * | 2005-01-28 | 2007-09-18 | Hrl Laboratories, Llc | Generation of decision trees by means of a probabilistic model |
| US20150211867A1 (en) * | 2012-10-09 | 2015-07-30 | Bayerische Motoren Werke Aktiengesellschaft | Estimating a Street Type Using Sensor-Based Surroundings Data |
| CN108475057A (en) * | 2016-12-21 | 2018-08-31 | 百度（美国）有限责任公司 | The method and system of one or more tracks of situation prediction vehicle based on vehicle periphery |
| CN107977670A (en) * | 2017-10-09 | 2018-05-01 | 中国电子科技集团公司第二十八研究所 | Accident classification stage division, the apparatus and system of decision tree and bayesian algorithm |
| CN111368465A (en) * | 2019-12-31 | 2020-07-03 | 成都理工大学 | Unmanned decision-making method based on ID3 decision tree |
| CN112818910A (en) * | 2021-02-23 | 2021-05-18 | 腾讯科技（深圳）有限公司 | Vehicle gear control method and device, computer equipment and storage medium |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113687991A (en) * | 2021-08-25 | 2021-11-23 | 北京赛目科技有限公司 | Vehicle defect recommendation method and device |
| CN113687991B (en) * | 2021-08-25 | 2023-08-22 | 北京赛目科技股份有限公司 | Vehicle defect recommending method and device |
| CN114399659A (en) * | 2021-12-28 | 2022-04-26 | 禾多科技（北京）有限公司 | Vehicle control information generation method, device, equipment and computer readable medium |
| CN114162144A (en) * | 2022-01-06 | 2022-03-11 | 苏州挚途科技有限公司 | Automatic driving decision method and device and electronic equipment |
| CN114162144B (en) * | 2022-01-06 | 2024-02-02 | 苏州挚途科技有限公司 | Automatic driving decision method and device and electronic equipment |
| WO2023151499A1 (en) * | 2022-02-09 | 2023-08-17 | 武汉路特斯汽车有限公司 | Empty space identification method, vehicle, and readable storage medium |
| CN116385965A (en) * | 2023-03-17 | 2023-07-04 | 深圳市明源云科技有限公司 | Method, apparatus and computer readable storage medium for identifying a wandering animal |
| CN116620271A (en) * | 2023-07-19 | 2023-08-22 | 之江实验室 | Intelligent driving pedestrian avoiding method and system based on short-time memory and behavior tree |
| CN116620271B (en) * | 2023-07-19 | 2023-11-03 | 之江实验室 | Intelligent driving pedestrian avoiding method and system based on short-time memory and behavior tree |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113232674A (en) | Vehicle control method and device based on decision tree and Bayesian network | |
| CN108256577B (en) | Obstacle clustering method based on multi-line laser radar | |
| CN112099496B (en) | Automatic driving training method, device, equipment and medium | |
| US7523079B2 (en) | Situation dependent operation of a semantic network machine | |
| CN112347993B (en) | Expressway vehicle behavior and track prediction method based on vehicle-unmanned aerial vehicle cooperation | |
| CN110503743B (en) | Abnormity detection method, device and equipment for automatic driving vehicle | |
| Díaz-Álvarez et al. | Modelling the human lane-change execution behaviour through multilayer perceptrons and convolutional neural networks | |
| Deshpande et al. | Deep reinforcement learning based vehicle navigation amongst pedestrians using a grid-based state representation | |
| CN112149618B (en) | Pedestrian abnormal behavior detection method and device suitable for inspection vehicle | |
| CN113742163A (en) | Fault early warning method, device, equipment and storage medium | |
| Marengoni et al. | Decision making and uncertainty management in a 3D reconstruction system | |
| CN111507499B (en) | Method, device and system for constructing model for prediction and testing method | |
| Lee et al. | Extendable navigation network based reinforcement learning for indoor robot exploration | |
| US20220076129A1 (en) | Method of training a deep neural network to classify data | |
| CN114104005B (en) | Decision-making method, device and equipment of automatic driving equipment and readable storage medium | |
| Jain et al. | A machine learning pipeline for fuel-economical driving model | |
| Chang et al. | Interaction-Based Driving Scenario Classification and Labeling | |
| CN112100836B (en) | Method and device for acquiring vehicle boundary parameters | |
| CN115496131B (en) | Equipment health state classification method based on multiple pre-training neural networks | |
| Luo et al. | Gaussian successive fuzzy integral for sequential multi-decision making | |
| Roberts | Intelligent mechatronics | |
| CN117593890B (en) | Detection method and device for road spilled objects, electronic equipment and storage medium | |
| US20230245554A1 (en) | Method and computer program for characterizing future trajectories of traffic participants | |
| Shkuropat et al. | Intelligence system of artificial vision for unmanned aerial vehicle | |
| Oliveira et al. | A History-based Framework for Online Continuous Action Ensembles in Deep Reinforcement Learning. |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210810 |