CN113188556A - Intelligent network-connected automobile trajectory planning method and device based on driving safety field - Google Patents
Intelligent network-connected automobile trajectory planning method and device based on driving safety field Download PDFInfo
- Publication number
- CN113188556A CN113188556A CN202110459321.8A CN202110459321A CN113188556A CN 113188556 A CN113188556 A CN 113188556A CN 202110459321 A CN202110459321 A CN 202110459321A CN 113188556 A CN113188556 A CN 113188556A
- Authority
- CN
- China
- Prior art keywords
- automobile
- planning
- track
- speed
- vehicle
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 73
- 238000005457 optimization Methods 0.000 claims abstract description 19
- 230000006855 networking Effects 0.000 claims abstract description 16
- 238000007670 refining Methods 0.000 claims abstract description 13
- 238000005381 potential energy Methods 0.000 claims description 13
- 238000004364 calculation method Methods 0.000 claims description 12
- 238000011478 gradient descent method Methods 0.000 claims description 8
- 238000005070 sampling Methods 0.000 claims description 7
- 238000004088 simulation Methods 0.000 claims description 7
- 230000006399 behavior Effects 0.000 description 15
- 238000004422 calculation algorithm Methods 0.000 description 13
- 238000010586 diagram Methods 0.000 description 6
- 230000008569 process Effects 0.000 description 6
- 230000006870 function Effects 0.000 description 5
- 238000013528 artificial neural network Methods 0.000 description 3
- 238000010801 machine learning Methods 0.000 description 3
- 230000001133 acceleration Effects 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 238000010845 search algorithm Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
- G01C21/34—Route searching; Route guidance
- G01C21/3446—Details of route searching algorithms, e.g. Dijkstra, A*, arc-flags, using precalculated routes
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Abstract
The application discloses an intelligent networking automobile track planning method and device based on a driving safety field, wherein the method comprises the following steps: calculating the risk of the traffic environment to the intelligent networked automobile on the basis of the driving safety field; generating a sparse searchable area according to the surrounding road traffic environment of the automobile, the speed of the automobile and the prediction time domain of the automobile; and generating a lane selection track in the searchable area based on the risk, refining the sparse search area on the basis of the lane selection track to obtain an initial planned path and a planned speed, and finally deducing in a prediction time domain to solve the track tracking optimization problem and obtain a final planned track of the intelligent networked automobile in the prediction time domain. The trajectory planning method provided by the embodiment of the application can improve the accuracy, effectiveness and instantaneity of trajectory planning, effectively ensures driving safety and is more intelligent.
Description
Technical Field
The application relates to the technical field of driving safety, in particular to an intelligent networked automobile trajectory planning method and device based on a driving safety field.
Background
At present, key technologies of the intelligent networked automobile comprise autonomous positioning, environment perception, behavior decision, trajectory planning, motion control, networked communication and the like, wherein the trajectory planning is an essential part and determines what trajectory the intelligent networked automobile is going to travel. However, in the face of complex traffic environment, how to make safe, efficient and complex traffic adaptive trajectory planning still faces serious challenges.
In the related art, a commonly used trajectory planning method mainly includes: 1) graph search based methods, 2) optimization based methods, 3) machine learning based methods and 4) artificial potential energy field based methods.
In particular, the graph search based method is a very common method, and the method is applicable to various fields for searching an optimal track from a point a to a point B. The method firstly needs to express the areas used for planning into a state space by using an occupied grid, and objects in each area are expressed by using the occupied grid. Then searching out the optimal track by adopting search algorithms such as an A-star algorithm, a Dijkstra algorithm, a fast expansion random tree and the like; the optimization-based method is that a track planning problem is expressed into an optimization problem, and a solution which enables a cost function to be minimum is solved under a series of constraints by adopting a numerical solving mode aiming at the optimization problem, so that a planned track is obtained; the machine learning-based method is to train a neural network by learning the driving results of a human driver to obtain training results. In the process of the track planning, the environment information is used as input and transmitted to the neural network, and then the structure of the track planning can be output; the method based on artificial potential energy fields is an advanced method. The method adopts an artificial potential energy field to model obstacles, road structures, lane lines, destinations and the like in the traffic environment, and then adopts a gradient descent method to find the optimal path.
However, the related art has certain disadvantages, such as that the trajectory planning result obtained by the map search-based method may not be a smooth curve, and the planned trajectory and the actual driving trajectory of the vehicle may not be consistent because the vehicle dynamics are not considered, resulting in that the motion of the vehicle is not smooth enough. And as the trajectory obtained by the optimization-based method can ensure the optimality, the problem of excessive computational complexity is often faced because the actual traffic environment is complex and the modeling and solving of the optimization problem are difficult. As with the machine learning based method, the neural network is still difficult to be adopted in practical applications because it cannot be located when it is problematic due to its inexplicability. Finally, the existing methods based on artificial potential energy fields are generally difficult to comprehensively consider various risks in traffic environments, including vehicle behaviors, complex road conditions and mutual influences among traffic participants, and are also lack of application in complex scenes, and only applied to simple scenes, such as lane keeping, vehicle following, lane changing and the like. Therefore, the related art still remains to be improved.
Content of application
The application provides an intelligent networking automobile track planning method and device based on a driving safety field, and aims to solve the problem that the consistency of the intelligent networking automobile planning track and an actual track is poor.
An embodiment of a first aspect of the application provides an intelligent networking automobile track planning method based on a driving safety field, which comprises the following steps: calculating the risk of the traffic environment to the intelligent networked automobile on the basis of the driving safety field; generating a sparse searchable area according to the traffic environment of the road around the automobile, the speed of the automobile and the prediction time domain of the automobile; generating a lane selection track in the searchable area based on the risk, refining the sparse search area on the basis of the lane selection track to obtain an initial planned path and a planned speed, deducing in the prediction time domain to solve the track tracking optimization problem and obtain a final planned track of the intelligent networked automobile in the prediction time domain.
Optionally, in an embodiment of the present application, the calculating the risk caused by the traffic environment to the intelligent networked automobile self based on the driving safety field includes: calculating the risk by utilizing a model obtained by modeling traffic environment elements by a driving safety field, wherein the risk calculation formula is as follows:
ED=EP+EK+EB,
wherein ,ED、EP、EK and EBThe field intensities are respectively corresponding to a traffic safety field, a potential energy field, a kinetic energy field and a behavior field.
Optionally, in an embodiment of the present application, the refining the sparse search region on the basis of the lane selection trajectory to obtain an initial planned path and a planned speed includes: thinning the sparse search area around a reference track; and (3) obtaining an optimal path by using a gradient descent method, and simultaneously, carrying out speed planning by using a self-adaptive car following method to plan a speed target so as to obtain the initial planned path and the planned speed.
Optionally, in an embodiment of the present application, the generated model of the planning speed is:
wherein ,amaxIs the maximum speed of the vehicle, vdIs a target vehicle speed, d is a distance between the own vehicle and the preceding vehicle, d*The target minimum vehicle distance.
Optionally, in an embodiment of the present application, the deriving in the prediction time domain to solve the trajectory tracking optimization problem to obtain a final planned trajectory of the intelligent networked automobile in the prediction time domain includes: and performing dynamics simulation on the prediction time domain at each sampling moment by using a closed-loop dynamics method, and performing deduction by using a controller and a vehicle model which are the same as an actual vehicle control module to obtain a final planned track of the intelligent networked automobile in the prediction time domain.
The embodiment of the second aspect of this application provides an intelligence networking car orbit planning device based on driving safety field, includes: the calculation module is used for calculating risks caused by the traffic environment to the intelligent networked automobile on the basis of the driving safety field; the generating module is used for generating a sparse searchable area according to the surrounding road traffic environment of the automobile, the speed of the automobile and the prediction time domain of the automobile; and the planning module is used for generating a lane selection track in the searchable area based on the risk, refining the sparse search area on the basis of the lane selection track to obtain an initial planned path and a planning speed, deducing in the prediction time domain to solve the track tracking optimization problem and obtain a final planned track of the intelligent internet vehicle in the prediction time domain.
Optionally, in an embodiment of the present application, the calculating module is specifically configured to calculate the risk by using a model obtained by modeling traffic environment elements by a driving safety field, where a calculation formula of the risk is:
ED=EP+EK+EB,
wherein ,ED、EP、EK and EBThe field intensities are respectively corresponding to a traffic safety field, a potential energy field, a kinetic energy field and a behavior field.
Optionally, in an embodiment of the present application, the planning module includes: the thinning unit is used for thinning the sparse search area at the periphery of a reference track; and the planning unit is used for planning the speed by using a self-adaptive car following method while obtaining the optimal path by using a gradient descent method, and planning a speed target so as to obtain the initial planned path and the planned speed.
Optionally, in an embodiment of the present application, the generated model of the planning speed is:
wherein ,amaxIs the maximum speed of the vehicle, vdIs a target vehicle speed, d is a distance between the own vehicle and the preceding vehicle, d*The target minimum vehicle distance.
Optionally, in an embodiment of the application, the planning module is specifically configured to perform dynamics simulation in the prediction time domain at each sampling time by using a closed-loop dynamics method, and perform deduction by using a controller and a vehicle model that are the same as those of an actual vehicle control module to obtain a final planned trajectory of the intelligent internet vehicle in the prediction time domain.
The method has the advantages that the influence of different traffic participants, road structures, behavior prediction and other factors in the traffic scene on the intelligent networked automobile is subjected to unified quantitative modeling, so that a foundation is provided for the safety and the real-time performance of a trajectory planning algorithm, the trajectory planning of the intelligent networked automobile is carried out on the basis, a layered framework is adopted, the optimal lane selection trajectory is obtained on a macroscopic planning layer, the movement trajectory is obtained through refining on a microscopic planning layer, the accuracy, the effectiveness and the real-time performance of trajectory planning are improved, the driving safety is effectively guaranteed, and the method is more intelligent.
Additional aspects and advantages of the present 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 present application.
Drawings
The foregoing and/or additional aspects and advantages of the present application will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings of which:
fig. 1 is a flowchart of an intelligent networked automobile trajectory planning method based on a driving safety field according to an embodiment of the present application;
FIG. 2 is a schematic top view of a typical scene driving safety scene according to an embodiment of the present application;
FIG. 3 is a schematic diagram of a method for hierarchical trajectory planning for a vehicle according to an embodiment of the present application;
FIG. 4 is a schematic diagram of search area generation according to one embodiment of the present application;
FIG. 5 is a schematic diagram of lane selection path generation according to one embodiment of the present application;
FIG. 6 is a schematic diagram of generating a trajectory according to one embodiment of the present application;
fig. 7 is an exemplary diagram of an intelligent networked automobile trajectory planning device based on a driving safety field according to an embodiment of the application.
Detailed Description
Reference will now be made in detail to embodiments of the present application, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below with reference to the drawings are exemplary and intended to be used for explaining the present application and should not be construed as limiting the present application.
The following describes an intelligent networking automobile trajectory planning method and device based on a driving safety field according to an embodiment of the application with reference to the accompanying drawings. The method is characterized in that the influence of different traffic participants, road structures, behavior prediction and other factors in a traffic scene on the intelligent networked automobile is unified and quantized to model, so that a basis is provided for the safety and the real-time performance of a track planning algorithm, the track planning of the intelligent networked automobile is carried out on the basis, a layered architecture is adopted, an optimal lane selection track is obtained on a macroscopic planning layer, a motion track is obtained by refining on a microscopic planning layer, the accuracy, the effectiveness and the real-time performance of the track planning are improved, the driving safety is effectively guaranteed, and the method is more intelligent. Therefore, the problem that the consistency of the intelligent networked automobile planning track and the actual track is poor is solved.
Specifically, fig. 1 is a schematic flow chart of an intelligent networked automobile trajectory planning method based on a driving safety field according to an embodiment of the present application.
As shown in fig. 1, the intelligent networked automobile trajectory planning method based on the driving safety field comprises the following steps:
in step S101, risk of the traffic environment to the intelligent networked automobile is calculated based on the driving safety field.
Optionally, in an embodiment of the present application, calculating a risk caused by the traffic environment to the intelligent networked automobile self based on the driving safety field includes: calculating risks by using a model obtained by modeling traffic environment elements by a driving safety field, wherein the risk calculation formula is as follows:
ED=EP+EK+EB,
wherein ,ED、EP、EK and EBThe field intensities are respectively corresponding to a traffic safety field, a potential energy field, a kinetic energy field and a behavior field.
It can be understood that, firstly, traffic environment elements are modeled by adopting a driving safety field method to represent the risk of each element of a human-vehicle-road to the intelligent automobile in the driving environment of the automobile:
ED=EP+EK+EB, (1)
in the formula ,ED、EP、EK and EBThe field intensities are respectively corresponding to a traffic safety field, a potential energy field, a kinetic energy field and a behavior field.
As shown in fig. 2, the potential energy field is used to represent the influence degree of the stationary object on the road on the driving risk of the intelligent vehicle, and may be specifically divided into two categories. The first type is an object which can actually collide, such as a stopped vehicle, an obstacle and the like, and the object can generate the risk field intensity relative to the own vehicle for each position in a traffic scene; the second category of potential energy fields is objects which cannot actually collide but play an important role in driving safety, such as lane lines, traffic signs and the like. The dynamic energy field is used for representing the degree of influence of moving objects on the road on the driving risk of the vehicle, and the moving objects on the road can generate the risk field intensity relative to the vehicle on each position in the traffic scene. The behavior field is used for representing the influence degree of the behavior characteristics of the intelligent automobile on the driving risk, and the risk generated by the intelligent automobile with the mature stable algorithm is much smaller than that generated by the intelligent automobile in the testing stage.
In the embodiment of the application, the influence of different traffic participants, road structures, behavior prediction and other factors on the intelligent automobile in the traffic scene is subjected to unified quantitative modeling, so that the problem of high complexity of a decision planning algorithm caused by a plurality of traffic environment elements is solved, and a basis is provided for the effectiveness and the real-time performance of the decision planning algorithm.
In step S102, a sparse searchable area is generated based on the road traffic environment around the vehicle, the vehicle speed of the vehicle, and the prediction time domain.
As shown in fig. 3, in the embodiment of the application, the intelligent internet vehicle trajectory planning is divided into two layers, namely macro planning and micro planning, wherein in the macro planning layer, the intelligent internet vehicle trajectory planning is simulated by a human driver, a lane on which the intelligent internet vehicle is to run is obtained firstly, and then in the micro planning layer, the trajectory on which the intelligent vehicle runs is refined.
It can be understood that, in the macro planning layer, a searchable area is generated on the basis of the road traffic environment around the intelligent networked automobile, and a sparse search range is generated on the basis of the speed of the automobile and the prediction time domain. As shown in fig. 4, the nodes in the search area may be equally spaced on the horizontal axis and one for each lane on the vertical axis.
Further, an optimal road selection track is calculated in the search area by adopting a dynamic planning method and is output to the microscopic planning as a reference value of the final track planning, and the optimization target is to seek the minimum field intensity of a dynamic driving safety field on a path and avoid frequent lane change of the vehicle at the same time, and the following formula is adopted:
in the formula ,ωDIs a time-varying weight coefficient that increases with increasing k, ωCIs a constant weight coefficient, PCTo penalize lane changes to avoid excessive unnecessary lane changes. The lane selection path is generated as shown in fig. 5, and the path describes where the smart car should be located in which lane.
In step S103, a lane selection trajectory is generated in the searchable area based on the risk, and the sparse search area is refined on the basis of the lane selection trajectory to obtain an initial planned path and a planned speed, and a deduction is performed in a prediction time domain to solve the trajectory tracking optimization problem and obtain a final planned trajectory of the intelligent internet vehicle in the prediction time domain.
Optionally, in an embodiment of the present application, refining the sparse search region on the basis of the lane selection trajectory to obtain an initial planned path and a planned speed includes: thinning the sparse search area at the periphery of the reference track; and (3) obtaining an optimal path by using a gradient descent method, and simultaneously, carrying out speed planning by using a self-adaptive car following method to plan a speed target so as to obtain an initial planned path and a planned speed.
In other words, in the micro planning layer, a sparse search range is firstly thinned around a reference trajectory to obtain a better trajectory, and then an optimal path is obtained according to a gradient descent method. Meanwhile, speed planning is carried out according to a self-adaptive car following method, and a speed target is planned on the premise of ensuring safety.
In an embodiment of the present application, the generation model of the planning speed is:
wherein ,amaxIs the maximum speed of the vehicle, vdIs a target vehicle speed, d is a distance between the own vehicle and the preceding vehicle, d*The target minimum vehicle distance.
It is understood that the embodiment of the application can adopt an auto-cruising model, an intelligent driver model, to generate the speed track. The intelligent driver model is shown as follows:
in the formula ,amaxIs the maximum speed of the vehicle, vdIs a target vehicle speed, d is a distance between the own vehicle and the preceding vehicle, d*Is a target minimum vehicle distance, which is defined as:
in the formula ,d0For congested inter-vehicle distance, TgFor a safety event interval, Δ v is the difference between the speeds of the host and the lead vehicles, aminThe minimum acceleration of the bicycle.
Optionally, in an embodiment of the present application, the deriving is performed in a prediction time domain to solve a trajectory tracking optimization problem, and the obtaining of the final planned trajectory of the intelligent internet vehicle in the prediction time domain includes: and performing dynamics simulation on the prediction time domain at each sampling moment by using a closed-loop dynamics method, and performing deduction by using a controller and a vehicle model which are the same as an actual vehicle control module to obtain a final planned track of the intelligent networked automobile in the prediction time domain.
In the actual implementation process, the finally obtained planned trajectory is not smooth enough, and the planned trajectory is inconsistent with the actual path of the vehicle due to the fact that the planned trajectory cannot be completely tracked in the actual running process of the vehicle, so a closed-loop dynamics method can be adopted here, dynamics simulation is performed in a prediction time domain at each sampling moment, a controller which is the same as an actual vehicle control module is used for performing deduction with a vehicle model, the motion planned trajectory in the prediction time domain is obtained, and the optimization problem to be solved in the prediction time domain can be described as follows:
solving the optimization problem, the planned motion trajectory of the intelligent automobile in the prediction time domain can be obtained, as shown in fig. 6.
According to the embodiment of the application, the influence of different traffic participants, road structures, behavior prediction and other factors in a traffic scene on the intelligent networked automobile is subjected to unified quantitative modeling, the problem of high complexity of a decision planning algorithm caused by a plurality of traffic environment elements is solved, and a basis is provided for the effectiveness and the real-time performance of the decision planning algorithm.
In addition, the problem that the consistency of the planned path of the intelligent automobile and the actual track is poor is solved, the intelligent internet automobile track planning with higher safety, real-time performance and acceptability is realized, the intelligent internet automobile track planning method can adapt to complex traffic flow, and meanwhile, the method has good computing efficiency.
In conclusion, the problem of high complexity of a decision planning algorithm caused by a plurality of traffic environment elements can be solved by implementing the routine vehicle safety field, a basis is provided for the effectiveness and the real-time performance of the decision planning algorithm, the optimal lane selection track is obtained on a macroscopic planning layer, the motion track is obtained by refining on a microscopic planning layer, the method is small in calculated amount and good in planning effect, the safe, efficient and real-time planning track suitable for complex traffic can be obtained, the driving decision process of a human driver is simulated, and the intelligent internet vehicle track planning is safe and efficient.
According to the intelligent networking automobile track planning method based on the driving safety field, the influence of different traffic participants, road structures, behavior prediction and other factors in a traffic scene on the intelligent networking automobile is subjected to unified quantitative modeling, so that a basis is provided for the safety and the real-time performance of a track planning algorithm, the track planning of the intelligent networking automobile is carried out on the basis, a layered framework is adopted, the optimal lane selection track is obtained on a macroscopic planning layer, the motion track is obtained through refining on a microscopic planning layer, the accuracy, the effectiveness and the real-time performance of the track planning are improved, the driving safety is effectively guaranteed, and the intelligent networking automobile track planning method is more intelligent.
The intelligent networked automobile trajectory planning device based on the driving safety field provided by the embodiment of the application is described next with reference to the attached drawings.
Fig. 7 is a block diagram of an intelligent networked automobile trajectory planning device based on a driving safety field according to an embodiment of the present application.
As shown in fig. 7, the intelligent networked automobile trajectory planning device 10 based on the driving safety field includes: a calculation module 100, a generation module 200 and a planning module 300.
Specifically, the calculation module 100 is configured to calculate a risk caused by the traffic environment to the intelligent networked automobile based on the driving safety field.
The generating module 200 is configured to generate a sparse searchable area according to a surrounding road traffic environment of the automobile, a vehicle speed of the automobile and a prediction time domain of the automobile.
The planning module 300 is configured to generate a lane selection track in a searchable area based on the risk, refine a sparse search area on the basis of the lane selection track to obtain an initial planned path and a planning speed, and perform deduction in a prediction time domain to solve a track tracking optimization problem to obtain a final planned track of the intelligent internet automobile in the prediction time domain.
Optionally, in an embodiment of the present application, the calculation module is specifically configured to calculate the risk by using a model obtained by modeling the traffic environment element by a driving safety field, where a calculation formula of the risk is:
ED=EP+EK+EB,
wherein ,ED、EP、EK and EBThe field intensities are respectively corresponding to a traffic safety field, a potential energy field, a kinetic energy field and a behavior field.
Optionally, in an embodiment of the present application, the planning module includes: the thinning unit is used for thinning the sparse search area at the periphery of the reference track; and the planning unit is used for planning the speed by using a self-adaptive car following method while obtaining the optimal path by using a gradient descent method, and planning a speed target so as to obtain an initial planned path and a planned speed.
Optionally, in an embodiment of the present application, the generated model of the planning speed is:
wherein ,amaxIs the maximum speed of the vehicle, vdIs a target vehicle speed, d is a distance between the own vehicle and the preceding vehicle, d*The target minimum vehicle distance.
Optionally, in an embodiment of the present application, the planning module is specifically configured to perform dynamics simulation in the prediction time domain by using a closed-loop dynamics method at each sampling time, and perform deduction by using a controller and a vehicle model that are the same as those of the actual vehicle control module to obtain a final planned trajectory of the intelligent internet vehicle in the prediction time domain.
It should be noted that the explanation of the embodiment of the method for planning a trajectory of an intelligent networked automobile based on a driving safety field is also applicable to the apparatus for planning a trajectory of an intelligent networked automobile based on a driving safety field in this embodiment, and is not repeated here.
According to the intelligent networking automobile track planning device based on the driving safety field, the influence of different traffic participants, road structures, behavior prediction and other factors in a traffic scene on the intelligent networking automobile is subjected to unified quantitative modeling, so that a basis is provided for the safety and the real-time performance of a track planning algorithm, the track planning of the intelligent networking automobile is carried out on the basis, a layered framework is adopted, the optimal lane selection track is obtained on a macroscopic planning layer, the motion track is obtained through refining on a microscopic planning layer, the accuracy, the effectiveness and the real-time performance of the track planning are improved, the driving safety is effectively guaranteed, and the intelligent networking automobile track planning system is more intelligent.
In the description herein, reference to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., means 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 application. 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 N 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.
Furthermore, the terms "first", "second" and "first" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one such feature. In the description of the present application, "N" means at least two, e.g., two, three, etc., unless specifically limited otherwise.
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 N executable instructions for implementing steps of a custom logic function or process, and alternate implementations are included within the scope of the preferred embodiment of the present application 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 implementing the embodiments of the present application.
It should be understood that portions of the present application may be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, the N steps or methods may be implemented in software or firmware stored in a memory and executed by a suitable instruction execution system. 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.
Claims (10)
1. An intelligent networking automobile track planning method based on a driving safety field is characterized by comprising the following steps:
calculating the risk of the traffic environment to the intelligent networked automobile on the basis of the driving safety field;
generating a sparse searchable area according to the traffic environment of the road around the automobile, the speed of the automobile and the prediction time domain of the automobile; and
generating a lane selection track in the searchable area based on the risk, refining the sparse search area on the basis of the lane selection track to obtain an initial planned path and a planned speed, deducing in the prediction time domain to solve the track tracking optimization problem and obtain a final planned track of the intelligent networked automobile in the prediction time domain.
2. The method of claim 1, wherein calculating the risk of the traffic environment to the intelligent networked automobile self based on the driving safety field comprises:
calculating the risk by utilizing a model obtained by modeling traffic environment elements by a driving safety field, wherein the risk calculation formula is as follows:
ED=EP+EK+EB,
wherein ,ED、EP、EK and EBThe field intensities are respectively corresponding to a traffic safety field, a potential energy field, a kinetic energy field and a behavior field.
3. The method of claim 1, wherein the refining the sparse search area based on the lane selection trajectory to obtain an initial planned path and a planned speed comprises:
thinning the sparse search area around a reference track;
and (3) obtaining an optimal path by using a gradient descent method, and simultaneously, carrying out speed planning by using a self-adaptive car following method to plan a speed target so as to obtain the initial planned path and the planned speed.
5. The method of claim 1, wherein the deriving in the prediction time domain to solve the trajectory tracking optimization problem to obtain the final planned trajectory of the intelligent networked automobile in the prediction time domain comprises:
and performing dynamics simulation on the prediction time domain at each sampling moment by using a closed-loop dynamics method, and performing deduction by using a controller and a vehicle model which are the same as an actual vehicle control module to obtain a final planned track of the intelligent networked automobile in the prediction time domain.
6. The utility model provides an intelligence networking car orbit planning device based on driving safety field which characterized in that includes:
the calculation module is used for calculating risks caused by the traffic environment to the intelligent networked automobile on the basis of the driving safety field;
the generating module is used for generating a sparse searchable area according to the surrounding road traffic environment of the automobile, the speed of the automobile and the prediction time domain of the automobile; and
and the planning module is used for generating a lane selection track in the searchable area based on the risk, refining the sparse search area on the basis of the lane selection track to obtain an initial planned path and a planning speed, deducing in the prediction time domain to solve the track tracking optimization problem and obtain a final planned track of the intelligent internet vehicle in the prediction time domain.
7. The apparatus according to claim 6, wherein the calculation module is specifically configured to calculate the risk using a model obtained by modeling traffic environment elements by a driving safety field, wherein the calculation formula of the risk is:
ED=EP+EK+EB,
wherein ,ED、EP、EK and EBThe field intensities are respectively corresponding to a traffic safety field, a potential energy field, a kinetic energy field and a behavior field.
8. The apparatus of claim 6, wherein the planning module comprises:
the thinning unit is used for thinning the sparse search area at the periphery of a reference track;
and the planning unit is used for planning the speed by using a self-adaptive car following method while obtaining the optimal path by using a gradient descent method, and planning a speed target so as to obtain the initial planned path and the planned speed.
10. The apparatus of claim 6, wherein the planning module is specifically configured to perform dynamics simulation in the prediction time domain at each sampling time by using a closed-loop dynamics method, and perform deduction using a controller and a vehicle model that are the same as an actual vehicle control module to obtain a final planned trajectory of the intelligent networked automobile in the prediction time domain.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110459321.8A CN113188556B (en) | 2021-04-27 | 2021-04-27 | Intelligent network-connected automobile track planning method and device based on driving safety field |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110459321.8A CN113188556B (en) | 2021-04-27 | 2021-04-27 | Intelligent network-connected automobile track planning method and device based on driving safety field |
Publications (2)
Publication Number | Publication Date |
---|---|
CN113188556A true CN113188556A (en) | 2021-07-30 |
CN113188556B CN113188556B (en) | 2023-06-13 |
Family
ID=76979308
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110459321.8A Active CN113188556B (en) | 2021-04-27 | 2021-04-27 | Intelligent network-connected automobile track planning method and device based on driving safety field |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113188556B (en) |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20170364083A1 (en) * | 2016-06-21 | 2017-12-21 | Baidu Online Network Technology (Beijing) Co., Ltd. | Local trajectory planning method and apparatus for smart vehicles |
CN108648447A (en) * | 2018-05-08 | 2018-10-12 | 清华大学 | Vehicular intelligent security decision method based on traffic safety field |
CN111079834A (en) * | 2019-12-16 | 2020-04-28 | 清华大学 | Intelligent vehicle safety situation assessment method considering multi-vehicle interaction |
CN112644498A (en) * | 2021-01-05 | 2021-04-13 | 南京航空航天大学 | Intelligent vehicle safety decision-making method based on novel driving safety field |
-
2021
- 2021-04-27 CN CN202110459321.8A patent/CN113188556B/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20170364083A1 (en) * | 2016-06-21 | 2017-12-21 | Baidu Online Network Technology (Beijing) Co., Ltd. | Local trajectory planning method and apparatus for smart vehicles |
CN108648447A (en) * | 2018-05-08 | 2018-10-12 | 清华大学 | Vehicular intelligent security decision method based on traffic safety field |
CN111079834A (en) * | 2019-12-16 | 2020-04-28 | 清华大学 | Intelligent vehicle safety situation assessment method considering multi-vehicle interaction |
CN112644498A (en) * | 2021-01-05 | 2021-04-13 | 南京航空航天大学 | Intelligent vehicle safety decision-making method based on novel driving safety field |
Non-Patent Citations (1)
Title |
---|
王建强等: "基于人-车-路协同的行车风险场概念、原理及建模", 《中国公路学报》 * |
Also Published As
Publication number | Publication date |
---|---|
CN113188556B (en) | 2023-06-13 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Qu et al. | Jointly dampening traffic oscillations and improving energy consumption with electric, connected and automated vehicles: A reinforcement learning based approach | |
Bai et al. | Hybrid reinforcement learning-based eco-driving strategy for connected and automated vehicles at signalized intersections | |
Wang et al. | An intelligent lane-changing behavior prediction and decision-making strategy for an autonomous vehicle | |
Wang et al. | Hybrid electric vehicle energy management with computer vision and deep reinforcement learning | |
WO2021212728A1 (en) | Unmanned vehicle lane changing decision-making method and system based on adversarial imitation learning | |
US20230124864A1 (en) | Graph Representation Querying of Machine Learning Models for Traffic or Safety Rules | |
CN114495527B (en) | Internet-connected intersection vehicle road collaborative optimization method and system in mixed traffic environment | |
CN111267830B (en) | Hybrid power bus energy management method, device and storage medium | |
CN109991987A (en) | Automatic Pilot decision-making technique and device | |
Zhou et al. | Learning the car-following behavior of drivers using maximum entropy deep inverse reinforcement learning | |
Zhang et al. | Collision avoidance predictive motion planning based on integrated perception and V2V communication | |
Zou et al. | Inverse reinforcement learning via neural network in driver behavior modeling | |
Yang et al. | A hybrid motion planning framework for autonomous driving in mixed traffic flow | |
Gupta et al. | Eco-driving of connected and autonomous vehicles with sequence-to-sequence prediction of target vehicle velocity | |
CN116564095A (en) | CPS-based key vehicle expressway tunnel prediction cruising cloud control method | |
CN116476863A (en) | Automatic driving transverse and longitudinal integrated decision-making method based on deep reinforcement learning | |
Wegener et al. | Longitudinal vehicle motion prediction in urban settings with traffic light interaction | |
CN117032203A (en) | Svo-based intelligent control method for automatic driving | |
Zhang et al. | Multi-modal fusion technology based on vehicle information: A survey | |
Han et al. | Foundation Intelligence for Smart Infrastructure Services in Transportation 5.0 | |
Lodh et al. | Autonomous vehicular overtaking maneuver: A survey and taxonomy | |
Wang et al. | Driver’s lane selection model based on phase-field coupling and multiplayer dynamic game with incomplete information | |
CN113188556A (en) | Intelligent network-connected automobile trajectory planning method and device based on driving safety field | |
Hua et al. | Multi-agent reinforcement learning for connected and automated vehicles control: Recent advancements and future prospects | |
Wu et al. | An optimal longitudinal control strategy of platoons using improved particle swarm optimization |
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 | ||
GR01 | Patent grant | ||
GR01 | Patent grant |