CN111290400A - Separation control method for motorcade cooperative driving - Google Patents
Separation control method for motorcade cooperative driving Download PDFInfo
- Publication number
- CN111290400A CN111290400A CN202010190094.9A CN202010190094A CN111290400A CN 111290400 A CN111290400 A CN 111290400A CN 202010190094 A CN202010190094 A CN 202010190094A CN 111290400 A CN111290400 A CN 111290400A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- automatic driving
- fleet
- splitting
- driving 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 35
- 238000000926 separation method Methods 0.000 title claims abstract description 15
- 230000009471 action Effects 0.000 claims abstract description 11
- 230000001960 triggered effect Effects 0.000 claims abstract description 5
- 230000006399 behavior Effects 0.000 claims description 56
- 230000007613 environmental effect Effects 0.000 claims description 18
- 238000004891 communication Methods 0.000 claims description 17
- 230000001133 acceleration Effects 0.000 claims description 11
- 230000000694 effects Effects 0.000 abstract description 2
- 102100024633 Carbonic anhydrase 2 Human genes 0.000 description 4
- 101000760643 Homo sapiens Carbonic anhydrase 2 Proteins 0.000 description 4
- 230000008859 change Effects 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 102100024650 Carbonic anhydrase 3 Human genes 0.000 description 3
- 101000760630 Homo sapiens Carbonic anhydrase 3 Proteins 0.000 description 3
- 238000001514 detection method Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- GHASVSINZRGABV-UHFFFAOYSA-N Fluorouracil Chemical compound FC1=CNC(=O)NC1=O GHASVSINZRGABV-UHFFFAOYSA-N 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 210000004556 brain Anatomy 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 229940001981 carac Drugs 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- 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
- G05D1/0231—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means
- G05D1/0246—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means using a video camera in combination with image processing means
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- 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
- G05D1/0212—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory
- G05D1/0223—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory involving speed control of the vehicle
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- 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
- G05D1/0276—Control of position or course in two dimensions specially adapted to land vehicles using signals provided by a source external to the vehicle
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- 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
-
- 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
- Y02T10/80—Technologies aiming to reduce greenhouse gasses emissions common to all road transportation technologies
- Y02T10/84—Data processing systems or methods, management, administration
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Aviation & Aerospace Engineering (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Multimedia (AREA)
- Electromagnetism (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention relates to a motorcade cooperative driving split control method, which comprises the steps of establishing a motorcade split behavior rule base in a controller of an automatic driving vehicle in advance; when the automatic driving vehicle team cruises and encounters a trigger reason of a motorcade splitting event, and the controller judges that the distance between the automatic driving vehicle and a front vehicle in the cruising motorcade meets the separation distance, the motorcade splitting event is triggered, and the controller of the automatic driving vehicle controls the automatic driving vehicle to execute a motorcade splitting driving behavior; when the motorcade split driving behavior is executed, the controller of the automatic driving vehicle obtains the pose information of the automatic driving vehicle and predicts the motion action of the automatic driving vehicle at the next moment; and judging whether the motion action of the automatic driving vehicle at the next moment is matched with the fleet splitting behavior rule base or not, and if so, iteratively updating the fleet splitting driving behavior rule in the fleet splitting behavior rule base by using the pose information of the current automatic driving vehicle. The invention can realize the optimal control effect on the motorcade split.
Description
Technical Field
The invention belongs to the technical field of automatic driving of vehicles, and particularly relates to a separation control method for cooperative driving of a motorcade.
Background
The automatic driving vehicle is not only an important electromechanical product, but also a carrier of high and new technologies such as new energy, new materials and new equipment, and covers basic science and common technical problems of cross fields such as environmental perception, planning decision, information communication and automatic control. The planning and decision-making are responsible for generating safe and reasonable driving behaviors like skilled drivers, so that automatic driving control is performed on the vehicle according to the safe and reasonable driving behaviors.
With the development of artificial intelligence technologies represented by deep learning and machine learning, an "end-to-end" driving decision method for simulating a driver to directly generate a driving decision instruction by observing the environment is increasingly gaining attention of researchers. Compared with the traditional rule-based driving decision method, the end-to-end driving decision method can be suitable for complex traffic environments with unclear lane lines or missing road scenes and severe and changeable driving environments. However, the off-line training of the method in a real scene needs a sample with a large enough scale, and the provided sample often contains an attention point irrelevant to driving decision, so that the interpretability is poor; meanwhile, the test in the simulation scene cannot be directly used in the actual environment, and the practicability is lacked.
Therefore, there is a need to provide a better driving decision method to achieve automatic control of an autonomous vehicle.
Disclosure of Invention
The invention aims to provide a method for generating rules by simulating the thinking mode of a human driver so as to control the fleet splitting behavior of an automatic driving vehicle.
In order to achieve the purpose, the invention adopts the technical scheme that:
a motorcade collaborative driving split control method is applied to a controller of an automatic driving vehicle and used for controlling the automatic driving vehicle to realize the split of a cruising motorcade, and the motorcade collaborative driving split control method comprises the following steps:
a fleet splitting behavior rule base is established in a controller of the automatic driving vehicle in advance, and the fleet splitting behavior rule base contains fleet splitting driving behavior rules constrained by vehicle dynamics parameters;
when the automatic driving vehicle team cruises and encounters a trigger reason of a fleet splitting event, and the controller judges that the distance between the automatic driving vehicle and a front vehicle in the cruising fleet meets the separation distance, the fleet splitting event is triggered, and the controller of the automatic driving vehicle controls the automatic driving vehicle to execute fleet splitting driving behaviors based on the fleet splitting driving behavior rules in the fleet splitting behavior rule base;
when a fleet split driving behavior is executed, a controller of the automatic driving vehicle obtains pose information of the automatic driving vehicle according to a work cycle, and motion action of the automatic driving vehicle at the next moment is obtained through prediction based on the pose information; and the controller of the automatic driving vehicle judges whether the predicted motion action of the automatic driving vehicle at the next moment is matched with the fleet splitting behavior rule base or not, and if so, iteratively updates the fleet splitting driving behavior rule in the fleet splitting behavior rule base by using the pose information of the current automatic driving vehicle.
Preferably, for the motion error of the automatic driving vehicle, the corresponding fleet split driving behavior rule in the fleet split behavior rule base is iteratively updated by using predictive control over an error feasible region.
Preferably, the pose information of the autonomous vehicle includes own vehicle running state information, obstacle information, and environmental vehicle information of the autonomous vehicle.
Preferably, the vehicle running state information and the obstacle information of the autonomous vehicle are both obtained by a vehicle sensor of the autonomous vehicle, and the environmental vehicle information of the autonomous vehicle is obtained by communication with the other autonomous vehicles.
Preferably, the self running state information of the automatic driving vehicle at least comprises speed, acceleration, position, direction, vehicle number and fleet information; the obstacle information of the autonomous vehicle at least includes a relative direction and a relative distance of an obstacle; the environmental vehicle information of the autonomous vehicle includes at least a speed, an acceleration, a position, a direction, a vehicle number, and a fleet number of other autonomous vehicles within a communication range.
Preferably, the trigger reasons of the fleet split event include a passive reason and an active reason; the passive reasons include: the distance between the automatic driving vehicle and a front vehicle is increased due to the influence of an obstacle, the distance between the automatic driving vehicle and the front vehicle is increased due to the fact that the front vehicle accelerates beyond the acceleration capacity of the automatic driving vehicle, or the communication or sensor information of the automatic driving vehicle is insufficient, so that the automatic driving vehicle and the front vehicle do not meet the following condition; the proactive cause includes the autonomous vehicle differing from a preceding destination or the autonomous vehicle differing from a preceding target speed.
Preferably, when the automatic driving vehicle team patrols and encounters a trigger reason of a fleet splitting event, the controller controls the automatic driving vehicle to adjust the distance between the automatic driving vehicle and a front vehicle; and when the distance between the automatic driving vehicle and a front vehicle in the cruising fleet meets the separation distance, triggering a fleet splitting event.
Preferably, the controller updates the state information of the cruising fleet simultaneously with triggering a fleet split event.
Due to the application of the technical scheme, compared with the prior art, the invention has the following advantages: the invention establishes the motorcade splitting behavior rule base by referring to the thinking process of human drivers, thereby realizing the automatic control of the motorcade splitting of the automatic driving vehicles, and can gradually realize the optimal control effect by the iterative update of the motorcade splitting behavior rule base.
Drawings
FIG. 1 is a flow chart of a fleet collaborative driving split control method of the present invention.
Fig. 2 is a schematic diagram of sensor information of a vehicle in the method for controlling separation of fleet collaborative driving according to the present invention.
Fig. 3 is a schematic diagram of the vehicle code of the fleet splitting status change rule.
Detailed Description
The invention will be further described with reference to examples of embodiments shown in the drawings to which the invention is attached.
The first embodiment is as follows: a motorcade cooperative driving split control method is applied to a controller of an automatic driving vehicle and is used for controlling the automatic driving vehicle to split a cruising motorcade. The fleet formed by automatic driving vehicles cruising in a team comprises a pilot vehicle and a plurality of follow-up vehicles which sequentially run.
The separation control method for the team collaborative driving comprises the following steps:
1. fleet split behavior rule base design
A fleet split behavior rule base is established in a controller of an automatic driving vehicle in advance, and the fleet split behavior rule base contains fleet split driving behavior rules constrained by vehicle dynamics parameters.
It is also necessary to preset the relevant rules of the subsequently required autonomous vehicle pose information, as follows: the pose information of the autonomous vehicle comprises the autonomous running state information, the obstacle information and the environmental vehicle information of the autonomous vehicle, wherein the obstacle information and the environmental vehicle information belong to the surrounding environment data. Depending on the confidence acquisition route, the pose information of the autonomous vehicle is mainly classified into two types, one is information obtained by an own vehicle sensor of the autonomous vehicle, and the other is information obtained by communication with other autonomous vehicles. The running state information of the own vehicle obtained by the own vehicle sensor includes at least speed, (longitudinal and lateral) acceleration, position, direction, vehicle number, fleet information, and the like. The obstacle information obtained by the own vehicle sensor includes at least the relative direction, relative distance, and the like of the obstacle. The road information can be obtained through the vehicle sensor, and poor road marking lines (lane lines) and the like can be obtained. The environmental vehicle information obtained by the communication means includes at least the speed, acceleration, position, direction, vehicle number, fleet number, and the like of other autonomous vehicles within the communication range. The pose information of the autonomous vehicle is specifically shown in table 1.
TABLE 1 vehicle System Driving information Table
For convenience of description, format definitions may be made:
CarState＝[ID，Position，Dir，Speed，Acc，PltnEn，PlatoonID，PltnNum，LeaderID，PltnLength，intraDis]
the method comprises the steps that CarState is an event type and represents the running state of a vehicle, ID is the number of the vehicle, Position is the Position of the vehicle, Dir is the heading angle of the vehicle, Speed is the Speed of the vehicle, Acc is the acceleration of the vehicle, and PltnEn is a team forming enabling mark, when PltnEn is 1, the vehicle can execute a team forming cruise strategy, and when PltnEn is0, the vehicle only executes a free cruise strategy. The PlatonID is the serial number of the motorcade, the PlatonID is the ID of the own vehicle in the free cruising state, and the PlatonID is the ID of the piloting vehicle in the motorcade cruising state. PltnNum is the position of the vehicle in the fleet, and is 1 if the vehicle is free-wheeling. The leader ID is a front following vehicle when the vehicle executes the team cruise strategy, and the leader ID is a vehicle ID when the vehicle is free cruising or piloted. PltnLength is the total number of vehicles in the fleet where the vehicles are located, and is 1 if the vehicles freely cruise by one vehicle. IntraDis is a set value of inter-vehicle distance in a fleet when vehicles execute a fleet cruise strategy. And the current cooperation state of the vehicle can be judged according to the values of different state quantities of the vehicle, and the specific corresponding relation is shown in table 2.
TABLE 2 vehicle cooperative state correspondence table
In general, the vehicle-mounted sensor mainly includes two types, i.e., an image processing type and a distance sensor type, in order to sense an external obstacle, the vehicle-mounted sensor needs to measure the surrounding road environment and obstacle information in addition to the state information of the vehicle itself. In any way, most of the finally obtained obstacle information can be converted into the coordinate system of the vehicle. For convenience of description, the obstacle information event is described herein in the following format:
Obs＝[ObID，ObAng，ObDis，ObPosition]
the Obs is an event type and represents an obstacle obtained by the sensor, the ObID is an obstacle number, the ObAng is an azimuth angle between the obstacle and the controlled vehicle, the ObDis is a distance between the obstacle and the controlled vehicle, and the ObPosition is coordinates of the obstacle in a world coordinate system.
Specifically, as shown in fig. 2, on a three-lane road where the controlled vehicle is located, there are three environmental vehicles Car1, Car2, and Car3 on the road ahead, but two cars can be detected within the detection range of the sensor, Car1 and Car3 are numbered Ob01 and Ob02 respectively according to the detection sequence of the sensor, the advancing direction of the vehicle body of the controlled vehicle is taken as the x-axis, a reference coordinate system is established, the positions of the two cars and the y-axis have included angles of ObAng01 and ObAng02 respectively, and the distances between the two cars and the controlled vehicle are ObDis01 and ObDis02 respectively. After the direction and the distance of the obstacle are obtained according to the sensor, the coordinate ObPosition corresponding to the obstacle can be easily calculated according to the position of the vehicle and the geometric corresponding relation. In this scenario, two environmental events can be obtained by the controlled vehicle through the sensor, which are:
Obs＝[Ob01，ObAng01，ObDis01，ObPosition01]
Obs＝[Ob02，ObAng02，ObDis02，ObPosition02]
the environmental vehicle information acquired through the communication mode may be defined in a manner similar to that of the sensor obstacle information, it should be noted that more pieces of vehicle information may also be acquired through the communication means as needed, and herein, only part of the core information is used as an event to describe the method, and the specific format is as follows:
Com＝[CarID，CarPosition，CarDir，CarSpeed，CarAcc，PlatoonID]
wherein Com is an event type, representing data information obtained by communication, CarID is a unique vehicle number, carpotion is vehicle position information, CarDir is vehicle course angle information, carpeed is vehicle speed, carac is vehicle acceleration, and platonon id is a vehicle fleet number where the communication is located. Still in the above three-lane scenario, assuming that Car1 and Car2 can communicate with the controlled vehicle, and Car3 cannot communicate, the controlled vehicle may also get two environmental events:
Com＝[Car1，Car1Position，Car1Dir，Car1Speed，Car1Acc，Car1PlatoonID]
Com＝[Car2，Car2Position，Car2Dir，Car2Speed，Car2Acc，Car2PlatoonID]
i.e., environmental events that the vehicle may generally obtain are shown in the table below.
TABLE 3 Environment event types and Format definitions
Therefore, it is defined that, in the above scenario, the controlled vehicle can obtain five pieces of environmental event information in the same control cycle in the current scenario as follows:
CarState＝[SelfID，SelfPosition，SelfDir，SelfSpeed，SelfAcc，SelfPlatoonID，SelfPltnNum，SelfLeaderID，SelfPltnLength，SelfintraDis]
Obs＝[Ob01，ObAng01，ObDis01，ObPosition01]
Obs＝[Ob02，ObAng02，ObDis02，ObPosition02]
Com＝[Car1，Car1Position，Car1Dir，Car1Speed，Car1Acc，Car1PlatoonID]
Com＝[Car2，Car2Position，Car2Dir，Car2Speed，Car2Acc，Car2PlatoonID]
in this scenario, it can be noted that the position information of Car1 is obtained simultaneously from the vehicle's own sensors and the communication information, and it can be found by comparison that Ob01 and Car1 both represent the same vehicle, if a certain environmental vehicle is detected simultaneously with the sensors through communication, it is said that the controlled vehicle and the vehicle realize the "verification" of the cooperation information.
2. Vehicle pose information acquisition, behavior prediction and split rule optimization
When the automatic driving vehicle team cruises and encounters a trigger reason of a motorcade splitting event, and the controller judges that the distance between the automatic driving vehicle and a front vehicle in the cruising motorcade meets the separation distance, the motorcade splitting event is triggered, and the controller of the automatic driving vehicle controls the automatic driving vehicle to execute motorcade splitting driving behaviors based on motorcade splitting driving behavior rules in a motorcade splitting behavior rule base.
The method specifically comprises the following steps: as shown in fig. 1, a controller of an autonomous vehicle first determines whether the autonomous vehicle is in a team cruise state, and if so, then determines whether the current states of the autonomous vehicle and a preceding vehicle meet a follow-up condition, and if so, updates a PltnEn variable in an environmental event.
Then, if the automatic driving vehicle encounters the trigger reason of the motorcade splitting event, the controller controls the automatic driving vehicle to adjust the distance between the automatic driving vehicle and the front vehicle. And when the distance between the automatic driving vehicle and a front vehicle in the cruising fleet meets the preset separation distance, triggering a fleet splitting event.
The team forming state of the vehicle can be interrupted, random conditions for the rule base to enter the splitting event triggering process are more, and the triggering reasons of the team splitting event can be divided into a passive reason and an active reason according to different triggering main bodies. The passive reasons include: the distance between the automatic driving vehicle and the front vehicle is increased under the influence of the obstacle, the distance between the automatic driving vehicle and the front vehicle is increased when the front vehicle is accelerated beyond the acceleration capacity of the automatic driving vehicle, or the communication or sensor information of the automatic driving vehicle is incomplete, so that the automatic driving vehicle and the front vehicle do not meet the following condition; active causes include the autonomous vehicle differing from a preceding destination or the autonomous vehicle differing from a preceding target speed. The details are shown in Table 4.
Table 4 split event trigger cause
When the controller judges that the controlled vehicle meets the separation condition, before the controlled vehicle can enter a separation event, the controller needs to add one step to judge whether the vehicle meets the separation distance, which is mainly because the potential field calculation rule of the vehicle in front changes suddenly at the moment that the team cruise state is switched to the free cruise state, and the data of the rule base possibly shakes, so that distance adjustment and judgment are added, and the shaking of the controller can be effectively avoided.
And simultaneously triggering the motorcade splitting event, updating the state information of the cruising motorcade by the controller. To illustrate the state change rule, the key location vehicle code is shown in fig. 3. The split event state change rule is shown in table 5.
Table 5 split event state change rule table
In the table, L1 is a fleet pilot vehicle, L2 is a split event triggering vehicle, F1 is a L2 following vehicle before splitting, the tail vehicle code of the fleet before splitting is F2, and when the fleet parameters are updated, the split event is triggered.
When the controller of the automatic driving vehicle controls the automatic driving vehicle to execute the fleet split driving behavior based on the fleet split driving behavior rule in the fleet split driving behavior rule base, the controller of the automatic driving vehicle obtains the pose information of the automatic driving vehicle according to the work period, and the motion action of the automatic driving vehicle at the next moment is obtained based on the pose information prediction; and the controller of the automatic driving vehicle judges whether the predicted motion action of the automatic driving vehicle at the next moment is matched with the fleet splitting behavior rule base or not, and if so, the fleet splitting driving behavior rule in the fleet splitting behavior rule base is updated iteratively by using the pose information of the current automatic driving vehicle. Aiming at the motion error of the automatic driving vehicle, the corresponding fleet splitting driving behavior rule in the fleet splitting behavior rule base is iteratively updated by utilizing the predictive control on the error feasible region.
In conclusion, the scheme provides a method for quickly generating a cooperative driving motorcade splitting behavior rule base and a method for controlling motorcade splitting based on the rule base by taking the process that the most reasonable driving behavior is determined after the current road traffic environment information is comprehensively analyzed by a human driver according to the past driving experience and traffic rules stored in a brain memory area. The method for quickly generating the split behavior rule base comprises the steps that a vehicle-mounted integrated navigation system acquires the current running pose information of a vehicle and predicts the motion action of the vehicle at the next moment by combining vehicle dynamics and kinematic parameters; meanwhile, the predicted action conditions are matched with the established split behavior rule base, and if the matching conditions are met, the corresponding split driving behaviors in the rule base are updated by using the current vehicle pose information; if not, the autonomous vehicle continues to travel until the new predicted action is re-matched to the rule base. The generated splitting behavior rule base is extracted by a characteristic function capable of representing common driving behaviors of the automatic driving vehicle, and constraint is carried out by utilizing vehicle dynamics parameters. On the basis, the corresponding split behavior rules are iteratively updated according to the motion errors generated by the automatic driving vehicle in the driving process by utilizing the predictive control on the error feasible region, so that the optimal split driving behavior rules are generated. The fleet split behavior of autonomous vehicles can be better controlled based on the optimal split driving behavior rules.
The above embodiments are merely illustrative of the technical ideas and features of the present invention, and the purpose thereof is to enable those skilled in the art to understand the contents of the present invention and implement the present invention, and not to limit the protection scope of the present invention. All equivalent changes and modifications made according to the spirit of the present invention should be covered within the protection scope of the present invention.
Claims (8)
1. A motorcade collaborative driving split control method is applied to a controller of an automatic driving vehicle and is used for controlling the automatic driving vehicle to realize the split of a cruising motorcade, and is characterized in that: the motorcade cooperative driving split control method comprises the following steps:
a fleet splitting behavior rule base is established in a controller of the automatic driving vehicle in advance, and the fleet splitting behavior rule base contains fleet splitting driving behavior rules constrained by vehicle dynamics parameters;
when the automatic driving vehicle team cruises and encounters a trigger reason of a fleet splitting event, and the controller judges that the distance between the automatic driving vehicle and a front vehicle in the cruising fleet meets the separation distance, the fleet splitting event is triggered, and the controller of the automatic driving vehicle controls the automatic driving vehicle to execute fleet splitting driving behaviors based on the fleet splitting driving behavior rules in the fleet splitting behavior rule base;
when a fleet split driving behavior is executed, a controller of the automatic driving vehicle obtains pose information of the automatic driving vehicle according to a work cycle, and motion action of the automatic driving vehicle at the next moment is obtained through prediction based on the pose information; and the controller of the automatic driving vehicle judges whether the predicted motion action of the automatic driving vehicle at the next moment is matched with the fleet splitting behavior rule base or not, and if so, iteratively updates the fleet splitting driving behavior rule in the fleet splitting behavior rule base by using the pose information of the current automatic driving vehicle.
2. The split control method for team cooperative driving according to claim 1, wherein: and aiming at the motion error of the automatic driving vehicle, carrying out iterative updating on the corresponding fleet split driving behavior rule in the fleet split behavior rule base by utilizing predictive control on an error feasible region.
3. The split control method for team cooperative driving according to claim 1, wherein: the pose information of the autonomous vehicle includes the self-running state information, the obstacle information, and the environmental vehicle information of the autonomous vehicle.
4. The split control method for team cooperative driving according to claim 3, wherein: the vehicle running state information and the obstacle information of the autonomous vehicle are both obtained by a vehicle sensor of the autonomous vehicle, and the environmental vehicle information of the autonomous vehicle is obtained by communication with other autonomous vehicles.
5. The split control method for team cooperative driving according to claim 4, wherein: the self running state information of the automatic driving vehicle at least comprises speed, acceleration, position, direction, vehicle number and fleet information; the obstacle information of the autonomous vehicle at least includes a relative direction and a relative distance of an obstacle; the environmental vehicle information of the autonomous vehicle includes at least a speed, an acceleration, a position, a direction, a vehicle number, and a fleet number of other autonomous vehicles within a communication range.
6. The split control method for team cooperative driving according to claim 1, wherein: the trigger reasons of the fleet splitting event comprise a passive reason and an active reason; the passive reasons include: the distance between the automatic driving vehicle and a front vehicle is increased due to the influence of an obstacle, the distance between the automatic driving vehicle and the front vehicle is increased due to the fact that the front vehicle accelerates beyond the acceleration capacity of the automatic driving vehicle, or the communication or sensor information of the automatic driving vehicle is insufficient, so that the automatic driving vehicle and the front vehicle do not meet the following condition; the proactive cause includes the autonomous vehicle differing from a preceding destination or the autonomous vehicle differing from a preceding target speed.
7. The split control method for team cooperative driving according to claim 1, wherein: when the automatic driving vehicle team patrols and encounters a trigger reason of a fleet splitting event, the controller controls the automatic driving vehicle to adjust the distance between the automatic driving vehicle and a front vehicle; and when the distance between the automatic driving vehicle and a front vehicle in the cruising fleet meets the separation distance, triggering a fleet splitting event.
8. The split control method for team cooperative driving according to claim 1, wherein: and simultaneously triggering a motorcade splitting event, updating the state information of the cruising motorcade by the controller.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010190094.9A CN111290400B (en) | 2020-03-18 | 2020-03-18 | Separation control method for motorcade cooperative driving |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010190094.9A CN111290400B (en) | 2020-03-18 | 2020-03-18 | Separation control method for motorcade cooperative driving |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111290400A true CN111290400A (en) | 2020-06-16 |
| CN111290400B CN111290400B (en) | 2022-05-31 |
Family
ID=71030300
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010190094.9A Active CN111290400B (en) | 2020-03-18 | 2020-03-18 | Separation control method for motorcade cooperative driving |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111290400B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112829767A (en) * | 2021-02-22 | 2021-05-25 | 清华大学苏州汽车研究院（相城） | Automatic driving control system and method based on monitoring misoperation of driver |
| CN113734184A (en) * | 2021-10-18 | 2021-12-03 | 交通运输部公路科学研究所 | On-road team forming method and device for automatically driven vehicles and electronic equipment |
| CN115660301A (en) * | 2022-06-02 | 2023-01-31 | 小米汽车科技有限公司 | Vehicle scheduling method and device, storage medium and chip |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105138044A (en) * | 2015-07-10 | 2015-12-09 | 北京印刷学院 | Fleet formation control device and formation control method based on information physical network |
| CN106338998A (en) * | 2016-10-27 | 2017-01-18 | 吉林大学 | Method to control automobile to drive in cluster type formation |
| CN106708057A (en) * | 2017-02-16 | 2017-05-24 | 北理慧动（常熟）车辆科技有限公司 | Intelligent vehicle formation driving method |
| CN106873589A (en) * | 2017-02-16 | 2017-06-20 | 北理慧动（常熟）车辆科技有限公司 | A kind of autonomous follower method of intelligent vehicle |
| CN108011947A (en) * | 2017-11-30 | 2018-05-08 | 湖北汽车工业学院 | A kind of vehicle cooperative formula formation driving system |
-
2020
- 2020-03-18 CN CN202010190094.9A patent/CN111290400B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105138044A (en) * | 2015-07-10 | 2015-12-09 | 北京印刷学院 | Fleet formation control device and formation control method based on information physical network |
| CN106338998A (en) * | 2016-10-27 | 2017-01-18 | 吉林大学 | Method to control automobile to drive in cluster type formation |
| CN106708057A (en) * | 2017-02-16 | 2017-05-24 | 北理慧动（常熟）车辆科技有限公司 | Intelligent vehicle formation driving method |
| CN106873589A (en) * | 2017-02-16 | 2017-06-20 | 北理慧动（常熟）车辆科技有限公司 | A kind of autonomous follower method of intelligent vehicle |
| CN108011947A (en) * | 2017-11-30 | 2018-05-08 | 湖北汽车工业学院 | A kind of vehicle cooperative formula formation driving system |
Non-Patent Citations (1)
| Title |
|---|
| 马育林等: "基于模型预测控制与环境势场建模的车队协同驾驶方法研究", 《第十一届中国智能交通年会大会论文集》 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112829767A (en) * | 2021-02-22 | 2021-05-25 | 清华大学苏州汽车研究院（相城） | Automatic driving control system and method based on monitoring misoperation of driver |
| CN112829767B (en) * | 2021-02-22 | 2024-05-17 | 清华大学苏州汽车研究院（相城） | Automatic driving control system and method based on monitoring of misoperation of driver |
| CN113734184A (en) * | 2021-10-18 | 2021-12-03 | 交通运输部公路科学研究所 | On-road team forming method and device for automatically driven vehicles and electronic equipment |
| CN115660301A (en) * | 2022-06-02 | 2023-01-31 | 小米汽车科技有限公司 | Vehicle scheduling method and device, storage medium and chip |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111290400B (en) | 2022-05-31 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111290399B (en) | Team cooperative driving team forming control method | |
| US11726477B2 (en) | Methods and systems for trajectory forecasting with recurrent neural networks using inertial behavioral rollout | |
| CN111670468B (en) | Moving body behavior prediction device and moving body behavior prediction method | |
| EP3535636B1 (en) | Method and system for controlling vehicle | |
| Gao et al. | Robust lateral trajectory following control of unmanned vehicle based on model predictive control | |
| CN111290400B (en) | Separation control method for motorcade cooperative driving | |
| Llorca et al. | Autonomous pedestrian collision avoidance using a fuzzy steering controller | |
| Gelbal et al. | Collision avoidance of low speed autonomous shuttles with pedestrians | |
| CN111267852B (en) | Cruise control method for motorcade cooperative driving | |
| CN109426260A (en) | Servomechanism | |
| US11914386B2 (en) | Mobile object control device, mobile object control method, and storage medium | |
| CN110799402B (en) | Vehicle control device | |
| CN108931981A (en) | A kind of paths planning method of automatic driving vehicle | |
| CN113848914B (en) | Method for planning local path by collision coefficient artificial potential field method in dynamic environment | |
| Gu | Improved trajectory planning for on-road self-driving vehicles via combined graph search, optimization & topology analysis | |
| Yoganandhan et al. | Fundamentals and development of self-driving cars | |
| US11429107B2 (en) | Play-forward planning and control system for an autonomous vehicle | |
| Gómez-Huélamo et al. | Train here, drive there: Simulating real-world use cases with fully-autonomous driving architecture in carla simulator | |
| Gao et al. | Cloud model approach for lateral control of intelligent vehicle systems | |
| CN111267858B (en) | Motorcade cooperative driving lane change control method | |
| Souza et al. | Vision-based waypoint following using templates and artificial neural networks | |
| Guo et al. | Self-defensive coordinated maneuvering of an intelligent vehicle platoon in mixed traffic | |
| Siboo et al. | An empirical study of ddpg and ppo-based reinforcement learning algorithms for autonomous driving | |
| Kaur et al. | Scenario-based simulation of intelligent driving functions using neural networks | |
| CN116629114A (en) | Multi-agent model training method, system, computer equipment and storage medium |
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 |