CN111324130B - Intelligent vehicle formation cooperative self-adaptive cruise control switching method imitating pigeon flock - Google Patents
Intelligent vehicle formation cooperative self-adaptive cruise control switching method imitating pigeon flock Download PDFInfo
- Publication number
- CN111324130B CN111324130B CN202010234627.9A CN202010234627A CN111324130B CN 111324130 B CN111324130 B CN 111324130B CN 202010234627 A CN202010234627 A CN 202010234627A CN 111324130 B CN111324130 B CN 111324130B
- Authority
- CN
- China
- Prior art keywords
- vehicle
- individual
- control
- obstacle
- vehicles
- 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.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course or altitude of land, water, air, or space vehicles, e.g. automatic pilot
- G05D1/0088—Control of position, course or altitude of land, water, air, or space vehicles, e.g. automatic pilot characterized by the autonomous decision making process, e.g. artificial intelligence, predefined behaviours
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course or altitude of land, water, air, or space vehicles, e.g. automatic pilot
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0287—Control of position or course in two dimensions specially adapted to land vehicles involving a plurality of land vehicles, e.g. fleet or convoy travelling
- G05D1/0291—Fleet control
- G05D1/0293—Convoy travelling
Abstract
The invention discloses an intelligent vehicle formation cooperative adaptive cruise control switching method imitating a pigeon flock i Are all bigAt a congestion degree threshold delta max Then the fleet enters into a hierarchical control mode h (ii) a Otherwise, the motorcade enters an equal interaction mode e (ii) a Then, under the current state, each individual vehicle i in the fleet marks the neighbor vehicle j within a distance with lower communication delay so as to obtain a neighbor vehicle set
Or
Then, control input is carried out, wherein the control input comprises formation control gain, target point control gain and following control gain, and potential field functions are added to the three to maintain the function value within a reasonable range; finally, the safety is judged, each individual vehicle judges whether the direction of the control input vector is in the obstacle angle theta or not by calculating the obstacle angle occupied by all obstacle vehicles in the sensible range avoi Within the range, the safety of the driving behavior is predicted.
Description
Technical Field
The invention belongs to the field of intelligent vehicle formation control, and particularly relates to a pigeon group-simulated intelligent vehicle formation cooperative self-adaptive cruise control switching method.
Background
With technological progress and increasing human needs, smart cars are increasingly coming into view of people. At present, the intelligent vehicle team cooperative control technology has become a significant subject in the field. In 1986, the Burkeley division of the university of California, USA, established the PATH (Partners for Advanced Transit and Highways) agency, which motivated the hot tide of the research work on fleet cooperative control. Two coordinated Driving challenges (GCDC) have been held in europe in 2011 and 2016 to promote the development of Coordinated Adaptive Cruise Control (CACC) and alleviate current world traffic problems. The current team cooperative control research gradually has three major branches: the first is the research direction of longitudinal cooperative Control, and the research focus is Adaptive Cruise Control (ACC); the second is the lateral cooperative control research direction, the research focus of which is Lane changing and Lane Keeping (LKA); and thirdly, the comprehensive cooperative control research direction, wherein the research focus is the vehicle obstacle avoidance direction and the like. The cooperative self-adaptive cruise control belongs to a longitudinal coordination control technology, has very important significance for guaranteeing the safety of a large-flow traffic flow in the future, but is novel in field, and has a plurality of urgent researches because relevant theories and methods are not mature.
Pigeon swarm intelligence is a new concept in the field of swarm intelligence, and is proposed and developed rapidly by professor on the shore in the country. For example, the optimization algorithm of the pigeon flock is proposed by the enlightenment of the pigeon flock homing mode of the seashore and the like, and two different operator models are built in: a map, compass operator and landmark operator creatively broaden the new direction of group intelligent research; boyi CHEN and the like propose a quantum mixing-based pigeon swarm optimization algorithm, and improve the multi-peak problem and the non-convex problem under high dimension in the original algorithm by using a small sample size.
In the pigeon flock in nature, two formation interaction modes exist, namely an equal interaction mode and a hierarchical control mode. When the curvature of the flying curve of the pigeon flock is larger (namely the flying state is not stable), the pigeon flock is more inclined to adopt an equal interaction mode. In this mode, the individual pigeons are influenced by neighboring pigeons within the sensible range, the flight plan of the body is determined according to the flight plans (flight direction, flight speed) of the neighboring pigeons, and the influence degree of each neighboring pigeon in the body decision plan is the same. Therefore, the consistency of the individual distance and the flight speed vector in the flying formation is kept, and the formation form is reasonable. When the curvature of the flight curve of the pigeon flock is small (namely, the flight state is stable), the pigeon flock is more inclined to adopt a hierarchical control mode. In this mode, the flight plan of an individual pigeon is affected by both a neighboring ordinary pigeon and a neighboring dominant pigeon. And in the body flight decision, the influence degree of the neighbor dominant pigeons is larger than that of the neighbor ordinary pigeons. (neighbor dominant pigeons, namely pigeons with superior inherent conditions in a pigeon group, such as pigeons with farther visual field and healthier conditions) are in a flatter interaction mode, the decision efficiency of the hierarchical control mode is higher, and the formation reaction is more sensitive; but the equal interaction mode can greatly ensure the safety of each individual pigeon, and the overall safety degree is improved.
However, the existing pigeon swarm intelligent concept is only used for unmanned aerial vehicle cluster battle and spacecraft formation, and a large research space is still left in other directions such as vehicle formation cooperative control and the like. The longitudinal cooperative control aims at improving the efficiency and the safety of vehicle formation adaptive cruise, but because the road condition in the real environment is extremely complex and the control difficulty of cluster formation is higher, a mature and complete vehicle team cooperative adaptive control strategy does not exist at present.
Disclosure of Invention
In order to solve the problems, the invention provides a pigeon group-simulated vehicle formation cooperative adaptive cruise control switching method, which is used for ensuring that the running speed of a fleet is in an ideal range and the vehicle formation form is kept reasonable under the working conditions of different road congestion degrees, so that the speed of the fleet passing through a congested road section and the safety of single vehicles are improved, and traffic jam and traffic accidents are reduced.
The invention provides a pigeon group imitating intelligent vehicle formation cooperative self-adaptive cruise control switching method, which adopts two cooperative control modes: equal interaction mode (equaliarian mode, noted as mode) e ) And hierarchical control mode (hierarchical mode), denoted as mode h ). The overall control flow chart is shown in fig. 1. First, each individual vehicle calculates the degree of road congestion according to the number of obstacle vehicles within its sensible range. Congestion degree delta calculated for all individual cars i Are all larger than the set road congestion degree threshold delta max Then the fleet enters into a hierarchical control mode h (ii) a The degree of congestion δ calculated if there is any one individual vehicle i Less than the congestion threshold delta max Then the fleet enters into an equal interaction mode e . Then, under the current state, each individual vehicle i in the fleet is required to mark a neighbor vehicle j within a distance with lower communication delay so as to obtain a neighbor vehicle set
(or
) And then, carrying out control input, wherein the control input comprises formation control gain, target point control gain and follow-up control gain. And all three maintain the function value within a reasonable range by adding a potential field function. In the two modes, the following control gain of the equal interaction mode assigns the weight of the influence of all the other neighbor pigeons on the body pigeon to 1; hierarchical control schemeThe following control gain assigns a weight w to the influence of the neighboring dominant pigeons on the body, and the weight assignment of the influence of the neighboring ordinary pigeons on the body is 1. And finally, judging the safety direction, and carrying out secondary check on the rationality of control input. Each individual vehicle judges whether the direction of the control input vector is at the obstacle angle theta or not by calculating the obstacle angle occupied by all obstacle vehicles in the sensible range avoi Within the range, the safety of the driving behavior is predicted.
The invention has the beneficial effects that:
(1) The cooperative control of the motorcade is combined with the characteristics of pigeon group interaction modes for the first time, and through potential field functions and gradient operation, the motorcade can keep a relatively ideal speed to pass through a set road area by formation with high flexibility under working conditions with different crowdedness degrees, so that traffic congestion is relieved, and the safety, high speed and sensitivity of road running of the motorcade are improved.
(2) The formation potential field function is simple in form, complex mathematical operations such as logarithm and index are avoided, and the operation efficiency is improved when the distance between an individual vehicle and a neighbor vehicle is controlled. The dynamic characteristics of the system are improved by following the proportional-differential control formed by the potential field function and the formation potential field function.
(3) The potential field function and the obstacle angle are introduced, the obstacle angle is used as a secondary check of control input rationality, the group accident risk caused by unreasonable group decision is reduced, and the driving safety of the motorcade is improved.
(4) The pigeon team intelligent concept is introduced into the motorcade cooperative control field for the first time, so that the application of group intelligence in the motorcade cooperative field is widened, and the problems of road blockage and road safety in the driving of the motorcade in a crowded traffic environment are solved.
Drawings
FIG. 1 is a schematic control flow diagram of an intelligent vehicle formation cooperative adaptive cruise control switching method of an imitation pigeon flock
Detailed Description
The invention will be further described with reference to the accompanying drawings.
As shown in fig. 1, the implementation of the present invention comprises the following steps:
step 1 road congestion degree judgment
When the vehicles are formed to run in a certain road area, each individual vehicle can automatically calculate the perceptible area R of the individual vehicle vision Degree of congestion of the inner road. If the calculated congestion degree of all the individual vehicles is less than the congestion degree threshold value delta max Then the group enters the hierarchical control mode h (ii) a Otherwise, entering an equal interaction mode e . Considering that the vehicle formation has N vehicles, the dynamic model of each individual vehicle i is
Wherein x i ，v i ，P i Respectively, the position vector, velocity vector and control input, m, of the individual vehicle i i Is the mass of the individual vehicle i. At R vision Degree of congestion δ detected by individual vehicle i i Is composed of
Where α is the visual blur factor, N di Is at R vision The number of detected obstacle vehicles. Congestion degree threshold δ max Is composed of
K is a switching mode safety coefficient set manually and needs to be selected according to actual conditions. When the vehicle formation runs on an open road and the formation is loose, K can be 3; k is 1 when the formation is very tight on a non-open road; otherwise K is taken to be 2. When delta i >δ max At time (i =1,2, \8230; N), the vehicle fleet enters mode using a hierarchical control mode h (ii) a When there is any one individual vehicle delta i <δ max In the time, the vehicle formation adopts an equal interaction mode and enters a mode e 。
Step 2 neighbor vehicle determination
When the fleet needs to determine the neighbor vehicle set within the sensing range of the fleet in real time. The following definitions can be made according to the two control modes.
(1) And judging the neighbor vehicles in the equal interaction mode. For defining neighbor set of individual vehicle i in equal interaction mode
Is shown as
Wherein, the first and the second end of the pipe are connected with each other,
the communication distance is the communication distance with lower communication delay of the individual vehicle in the equal interaction mode; j =1,2, \8230wheren is the individual vehicle in the formation of the obstacle removed vehicle within this communication distance. x is the number of ij Is the position vector between the vehicle individual i and the "neighbor" vehicle individual j.
(2) And judging neighbor vehicles in the hierarchical interaction mode. For defining neighbour sets of individual vehicles i in hierarchical control mode
Expressed as:
wherein the content of the first and second substances,
is a communication distance of lower communication delay of the individual vehicle in the hierarchical control mode; j =1,2, \8230andN is the individual vehicle in the formation of the obstacle-removing vehicle in the communication distance.
Step 3 input control
The individual vehicle determines the driving elements of the body according to the driving information of the neighbor vehicle: the individual vehicle performs potential function gradient calculation on a displacement difference vector, a speed difference vector and the like of the neighbor vehicle relative to the body of the individual vehicle, and input control of the body is obtained. . Under the equal interaction state, the influence weights of the neighbor vehicles on the decision of the body vehicle are the same and are all assigned to 1. In the hierarchical control mode, the influence weight of the neighbor dominant vehicle on the body vehicle decision is w, and the influence weight of the neighbor ordinary vehicle on the body vehicle decision is 1.
(1) In the equal interaction mode, control is input
Is defined as:
wherein Pro is a dominant vehicle cluster, and the dominant vehicle individual i belongs to Pro. K f >0 is the formation control gain, K t >0. Is the target point controlling the gain, K v >0 is the follow-up control gain; x is the number of t Is the target center point position vector, v ij ＝v i -v j Is the velocity difference vector between the vehicle individual i and the "neighbor" vehicle individual j.
Formation potential field function
Is composed of
Wherein R is exp Is the desired distance between individuals, R min Is the minimum safe distance between individuals, R max The maximum safe distance between individuals.
In order to achieve the above-mentioned safety range,
in order to achieve the lower safety range,
target potential field function
Is composed of
Wherein R is t Is the target area radius.
Following potential field function
Comprises the following steps:
wherein v is exp Desired speed, v, for individual vehicles min Is the individual vehicle minimum speed, v max Is the individual vehicle maximum speed.
(2) In a hierarchical control mode, control is input
Is defined as follows:
the definition of the formation potential field function, the target point potential field function and the following potential field function is the same as the definition of the formation potential field function, the target point potential field function and the following potential field function. w is the follow-up control weight, which must be calibrated according to the actual road conditions.
Step 4 safe direction judgment
The individual vehicles need to check the rationality of the control input after obtaining the control input, avoiding the decision of groupAnd the safety of the individual is reduced. The following definitions are made: after the individual vehicle i is input and controlled, a real-time obstacle avoidance angle can be calculated according to surrounding obstacle vehicles. If the direction of the speed v of the input control is in the range of the obstacle angle space set, keeping the current vehicle speed and other states, and giving up the previous step of input control; if the direction of the velocity v is outside the range of the obstacle angle space set, the input control may be performed. For an individual vehicle i, at its perceivable distance R vision In-vehicle detected obstacle vehicle N d Barrier angle θ of avoi Is composed of
Wherein R is obsi Is the distance, θ, from the individual vehicle i to the obstacle vehicle obsi The angle between the speed direction of the individual vehicle i and a connecting line between the vehicle i and the barrier vehicle is included, and alpha is a safety angle coefficient and needs to be calibrated according to the actual road condition.
The above-listed series of detailed descriptions are merely specific illustrations of possible embodiments of the present invention, and they are not intended to limit the scope of the present invention, and all equivalent means or modifications that do not depart from the technical spirit of the present invention are intended to be included within the scope of the present invention.
Claims (4)
1. A pigeon swarm-imitating intelligent vehicle formation cooperative self-adaptive cruise control switching method is characterized in that firstly, each individual vehicle calculates the road congestion degree according to the number of obstacle vehicles in a perception range, and if all the individual vehicles calculate the congestion degree delta i Are all larger than the set road congestion degree threshold delta max Then the fleet enters into a hierarchical control mode h (ii) a The degree of congestion δ calculated if there is any one individual vehicle i Less than a congestion threshold delta max Then the fleet enters into an equal interaction mode e (ii) a Then, under the current state, each individual vehicle i in the fleet marks the neighbor vehicle j within a distance with lower communication delay so as to obtain a neighbor vehicle set
Or
Then, control input is carried out, wherein the control input comprises formation control gain, target point control gain and following control gain, and the function values of the three are maintained in a reasonable range by adding a potential field function; in the two modes, the following control gain of the equal interaction mode assigns the weight of the influence of all the other neighbor pigeons on the body pigeon to 1; the following control gain of the hierarchical control mode assigns a weight w to the influence of the neighboring dominant pigeon on the main body, and the influence weight of the neighboring common pigeon on the main body is assigned to be 1; finally, judging the safe direction, carrying out secondary check on the rationality of the control input, and judging whether the direction of the control input vector is at an obstacle angle theta or not by calculating the obstacle angle occupied by all obstacle vehicles in a sensible range by each individual vehicle avoi Within the range, the safety of the driving behavior is predicted;
the method comprises the following steps:
step 1, judging the road congestion degree, and selecting to enter a corresponding formation mode according to the congestion degree;
step 2, judging neighbor vehicles, and dividing different neighbor sets according to different control modes;
step 3, setting input control;
step 4, judging the safety direction;
the step 1 is specifically as follows:
when vehicles are arranged to form a vehicle formation to drive in a certain road area, each individual vehicle can automatically calculate the perceptible area R of the individual vehicle vision The congestion degree of the inner road, the congestion degree delta calculated if all the individual vehicles i Are all less than the congestion degree threshold delta max Then the group enters the hierarchical control mode h (ii) a Otherwise, entering an equal interaction mode e ；
The method for calculating the congestion degree and the congestion degree threshold in the step 1 is as follows:
the vehicle formation is provided with N vehicles, and the dynamic model of each individual vehicle i is
Wherein x i ，v i ，P i Respectively, the position vector, velocity vector and control input, m, of the individual vehicle i i Is the mass of the individual vehicle i;
at R vision Degree of congestion δ detected by individual vehicle i i Is composed of
Where α is the visual blur factor, N di Is at R vision The number of detected obstacle vehicles;
congestion degree threshold δ max Is composed of
K is a switching mode safety coefficient set manually;
the step 2 is specifically realized as follows:
the fleet determines in real time a set of neighbour vehicles within its sensible range, said set of neighbour vehicles being defined according to two control modes as follows:
(1) And (3) judging neighbor vehicles in an equal interaction mode: for defining neighbor set of individual vehicle i in equal interaction mode
Is shown as
Wherein the content of the first and second substances,
is the communication distance of the individual vehicle with lower communication delay in the equal interaction mode; j =1,2, \8230, N is the individual vehicle in the formation of the obstacle-removing vehicle in the communication distance, x ij Is the position vector between the vehicle individual i and the "neighbor" vehicle individual j;
(2) Judging neighbor vehicles in a hierarchical interaction mode: for defining neighbour sets of individual vehicles i in hierarchical control mode
Expressed as:
wherein the content of the first and second substances,
is a communication distance of lower communication delay of the individual vehicle in the hierarchical control mode; j =1,2, \8230, N is the individual vehicle in the formation of the obstacle-removing vehicle in the communication distance;
the concrete implementation of the step 3 comprises the following steps:
in the equal interaction mode, control is input
Is defined as:
wherein Pro is a dominant vehicle cluster, and a dominant vehicle individual i belongs to Pro and K f > 0 is the formation control gain, K t Target point control gain, K > 0 v If > 0, following control gain; x is the number of t Is the target center point position vector, v ij ＝v i -v j Between vehicle individual i and "neighbor" vehicle individual jA velocity difference vector of (a);
formation potential field function
Is composed of
Wherein R is exp Is the desired distance between individuals, R min Is the minimum safe distance between individuals, R max Is the maximum safe distance between individuals and is,
in order to achieve the above-mentioned safety range,
in order to achieve the lower safety range,
target potential field function
Is composed of
Wherein R is t Is the target area radius;
following potential field function
Comprises the following steps:
wherein v is exp For individual vehicle desired speed, v min Is the individual vehicle minimum speed, v max Is the individual vehicle maximum speed.
2. The pigeon flock-imitated intelligent vehicle formation cooperative adaptive cruise control switching method according to claim 1, wherein the specific implementation of the step 3 further comprises the following steps:
in a hierarchical control mode, control inputs
Is defined as:
3. the pigeon-swarm-imitated intelligent vehicle formation cooperative adaptive cruise control switching method according to claim 2, characterized in that in an equal interaction state, influence weights of neighbor vehicles on a body vehicle decision are the same and are all assigned to 1; in a hierarchical control mode, the influence weight of the neighbor dominant vehicle on the decision of the body vehicle is w, and the influence weight of the neighbor common vehicle on the decision of the body vehicle is 1.
4. The pigeon flock-imitating intelligent vehicle formation cooperative adaptive cruise control switching method according to claim 1, wherein the step 4 is specifically as follows:
after the individual vehicle i is input and controlled, calculating a real-time obstacle avoidance angle according to surrounding obstacle vehicles; if the direction of the speed v of the input control is within the obstacle angle space set range, keeping the current speed state, and giving up the previous step of input control; if the direction of the speed v is outside the obstacle angle space set range, performing input control;
for the individual vehicle i, the vehicle i,at its sensible distance R vision In-vehicle detected obstacle vehicle N d Angle of obstacle theta thereof avoi Is composed of
Wherein R is obsi Is the distance, θ, from the individual vehicle i to the obstacle vehicle obsi The angle between the speed direction of the individual vehicle i and a connecting line between the vehicle i and the barrier vehicle is included, and alpha is a safety angle coefficient and needs to be calibrated according to the actual road condition.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010234627.9A CN111324130B (en) | 2020-03-30 | 2020-03-30 | Intelligent vehicle formation cooperative self-adaptive cruise control switching method imitating pigeon flock |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010234627.9A CN111324130B (en) | 2020-03-30 | 2020-03-30 | Intelligent vehicle formation cooperative self-adaptive cruise control switching method imitating pigeon flock |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111324130A CN111324130A (en) | 2020-06-23 |
| CN111324130B true CN111324130B (en) | 2022-11-18 |
Family
ID=71167922
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010234627.9A Active CN111324130B (en) | 2020-03-30 | 2020-03-30 | Intelligent vehicle formation cooperative self-adaptive cruise control switching method imitating pigeon flock |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111324130B (en) |
Families Citing this family (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113148227A (en) * | 2020-12-11 | 2021-07-23 | 中国空间技术研究院 | Satellite cluster distributed control method and device |
| CN113110494B (en) * | 2021-05-07 | 2022-08-30 | 清华大学 | Cooperative adaptive cruise control fault-tolerant design system based on expected functional safety |
| CN113147764B (en) * | 2021-06-01 | 2022-08-16 | 吉林大学 | Vehicle control method based on hybrid potential function of cooperative adaptive cruise system |
| CN113359852B (en) * | 2021-07-09 | 2022-11-18 | 北京航空航天大学 | Unmanned aerial vehicle cluster cooperative control method capable of simulating individual attribute intelligent behaviors of pigeon |
| CN115311866B (en) * | 2022-09-05 | 2024-04-16 | 阿维塔科技(重庆)有限公司 | Vehicle linkage method and device |
| CN115454099B (en) * | 2022-10-11 | 2024-04-30 | 北京航空航天大学 | Unmanned ship course active disturbance rejection control method based on variable weight self-adaptive pigeon group parameter fitting |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108549407B (en) * | 2018-05-23 | 2020-11-13 | 哈尔滨工业大学（威海） | Control algorithm for multi-unmanned aerial vehicle cooperative formation obstacle avoidance |
| CN108829131B (en) * | 2018-06-12 | 2020-02-14 | 北京航空航天大学 | Unmanned aerial vehicle cluster obstacle avoidance method based on multi-target adaptive variation pigeon swarm optimization |
| CN110096073A (en) * | 2019-04-18 | 2019-08-06 | 北京航空航天大学 | The ultra-large unmanned plane cluster control system and method for imitative homing pigeon intelligent behavior |
| CN110069075B (en) * | 2019-04-19 | 2020-06-09 | 北京航空航天大学 | Cluster super-mobile obstacle avoidance method imitating pigeon group emergency obstacle avoidance mechanism |
| CN110930766A (en) * | 2019-12-02 | 2020-03-27 | 武汉理工大学 | Unmanned vehicle multi-lane convoy formation method based on graph theory and potential field method |
-
2020
- 2020-03-30 CN CN202010234627.9A patent/CN111324130B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN111324130A (en) | 2020-06-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111324130B (en) | Intelligent vehicle formation cooperative self-adaptive cruise control switching method imitating pigeon flock | |
| CN110908373B (en) | Intelligent vehicle track planning method based on improved artificial potential field | |
| CN111222630B (en) | Autonomous driving rule learning method based on deep reinforcement learning | |
| Liu et al. | An efficient on-ramp merging strategy for connected and automated vehicles in multi-lane traffic | |
| CN108583578A (en) | The track decision-making technique based on multiobjective decision-making matrix for automatic driving vehicle | |
| CN109987092A (en) | A kind of determination method on vehicle obstacle-avoidance lane-change opportunity and the control method of avoidance lane-change | |
| CN107719369A (en) | The longitudinally controlled method, apparatus of automatic Pilot and there is its automatic driving vehicle | |
| CN114013443B (en) | Automatic driving vehicle lane change decision control method based on hierarchical reinforcement learning | |
| CN110716562A (en) | Decision-making method for multi-lane driving of unmanned vehicle based on reinforcement learning | |
| CN109754626B (en) | Unmanned autonomous lane change strategy | |
| CN112249008B (en) | Unmanned automobile early warning method aiming at complex dynamic environment | |
| CN111028504A (en) | Urban expressway intelligent traffic control method and system | |
| CN112101120B (en) | Map model based on automatic driving application scene and application method thereof | |
| CN106843210A (en) | One kind is based on bionic automatic driving vehicle progress control method | |
| CN115344052B (en) | Vehicle path control method and control system based on improved group optimization algorithm | |
| CN116118780A (en) | Vehicle obstacle avoidance track planning method, system, vehicle and storage medium | |
| Pan et al. | Research on the behavior decision of connected and autonomous vehicle at the unsignalized intersection | |
| CN109765801A (en) | The implementation method of car networking desin speed adjustment based on VISSIM emulation | |
| Guo et al. | Toward human-like behavior generation in urban environment based on Markov decision process with hybrid potential maps | |
| CN112896185A (en) | Intelligent driving behavior decision planning method and system for vehicle-road cooperation | |
| CN116564095A (en) | CPS-based key vehicle expressway tunnel prediction cruising cloud control method | |
| CN112477846A (en) | Intelligent networking electric automobile queue control method giving consideration to stability and energy conservation | |
| CN105644566A (en) | Tracking method for electric automobile auxiliary lane changing trajectory based on Internet of Vehicles | |
| CN111554081A (en) | Multi-level leader pigeon group theory-based fleet intersection obstacle avoidance control method | |
| CN112937584B (en) | Automatic lane changing control method and device and automobile |
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 |