WO2022027353A1 - 一种智巴车队控制方法、系统和计算机可读存储介质 - Google Patents

一种智巴车队控制方法、系统和计算机可读存储介质 Download PDF

Info

Publication number
WO2022027353A1
WO2022027353A1 PCT/CN2020/107195 CN2020107195W WO2022027353A1 WO 2022027353 A1 WO2022027353 A1 WO 2022027353A1 CN 2020107195 W CN2020107195 W CN 2020107195W WO 2022027353 A1 WO2022027353 A1 WO 2022027353A1
Authority
WO
WIPO (PCT)
Prior art keywords
vehicle
fleet
target value
target
smart
Prior art date
Application number
PCT/CN2020/107195
Other languages
English (en)
French (fr)
Inventor
于欣佳
程涛
Original Assignee
深圳技术大学
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by 深圳技术大学 filed Critical 深圳技术大学
Priority to PCT/CN2020/107195 priority Critical patent/WO2022027353A1/zh
Publication of WO2022027353A1 publication Critical patent/WO2022027353A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/09—Arrangements for giving variable traffic instructions
    • G08G1/0962—Arrangements for giving variable traffic instructions having an indicator mounted inside the vehicle, e.g. giving voice messages
    • G08G1/0968—Systems involving transmission of navigation instructions to the vehicle

Definitions

  • the present application relates to the field of intelligent driving, and in particular, to a method, system and computer-readable storage medium for controlling a fleet of smart buses.
  • Embodiments of the present application provide a method, system, and computer-readable storage medium for controlling a fleet of smart buses, so as to solve various problems existing in existing urban public transportation.
  • the technical solution is as follows:
  • a method for controlling a fleet of smart buses comprising:
  • the driving decision of the smart bus fleet is determined, and the driving decision includes at least one of an aggregation behavior strategy, a follow-up behavior strategy, a route change behavior strategy, and a follow-up behavior strategy;
  • the Zhiba fleet is controlled.
  • a smart bus fleet control system includes:
  • the information acquisition module is used to acquire the path information of the Zhiba fleet
  • a strategy determination module configured to determine the driving decision of the Zhiba fleet according to the path information passed by the Zhiba fleet, and the driving decision includes an aggregation behavior strategy, a follow-up behavior strategy, a route change behavior strategy, and a follow-up behavior strategy at least one of;
  • the fleet control module is used for controlling the Zhiba fleet according to the determined driving decision.
  • a smart bus comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program code being executed by the one or more processors Load and execute to implement the operations performed by this smart bus fleet control method.
  • a computer-readable storage medium stores a computer program that is loaded and executed by a processor to implement operations performed by the method for controlling a fleet of smart buses.
  • the vehicles in the Zhiba fleet can obtain the path information passed by the Zhiba fleet, and then determine the driving decision of the Zhiba fleet according to the path information.
  • the vehicles in the Zhiba fleet can make different driving decisions based on different path information, which is conducive to the better driving of the vehicles in the driving decision and ensures the entire driving.
  • Safety and synergy in decision-making on the other hand, a fleet of smart buses with a certain level of safety and synergy has the advantages of flexible transportation, low cost, economical benefits, high network density, good accessibility and accessibility, and occupation of the right of way. The advantages of flexibility, etc., have well solved many problems existing in traditional buses, subways and cloud/air rails in the city.
  • FIG. 1 is a flowchart of a method for controlling a fleet of smart buses provided by an embodiment of the present application
  • FIG. 2 is a schematic structural diagram of a smart bus fleet control system provided by an embodiment of the present application.
  • FIG. 3 is a schematic functional structure diagram of a smart bus provided by an embodiment of the present application.
  • FIG. 1 it is a method for controlling a fleet of smart buses provided by an embodiment of the present application.
  • the method mainly includes the following steps S101 to S103, which are described in detail as follows:
  • Step S101 Obtain the route information of the Zhiba fleet.
  • the smart bus fleet refers to a fleet composed of smart buses.
  • the vehicle that is, the smart bus itself, can obtain the path information of the smart bus fleet in real time through sensors, such as GPS, radar, camera, etc., such as vehicle location information, surrounding environment information, vehicle speed information, etc. Obtain the path information of other vehicles, and the information can be interacted with each other.
  • Step S102 Determine the driving decision of the smart bus fleet according to the path information passed by the smart bus fleet, wherein the driving decision includes at least one of the aggregation behavior strategy, the follow-up behavior strategy, the route change behavior strategy, and the follow-up behavior strategy.
  • Step S103 Control the Zhiba fleet according to the determined driving decision.
  • a command vehicle in the Zhiba fleet there may be a command vehicle in the Zhiba fleet, and other vehicles in the Zhiba fleet can transmit their own driving status to the command vehicle in real time, and the command vehicle can control the driving situation of the entire fleet, such as controlling The starting point and the end point, etc., and each vehicle can be controlled by sending commands.
  • the vehicle in the present application may be a command vehicle in the Zhiba fleet, or may be other vehicles in the Zhiba fleet, which is not limited in the embodiment of the present application.
  • the vehicle can determine the driving decision of the Zhiba fleet according to the path information passed by the Zhiba fleet, and the driving decision can include aggregation At least one of a behavioral strategy, a follow-up behavioral strategy, an en route change behavioral strategy, and a follow-up behavioral strategy. Each behavior is described below.
  • the Zhiba team naturally gathers in groups to ensure the overall driving efficiency and individual vehicle avoidance risks.
  • the vehicle group follows the following three rules:
  • the gathering rule that is, try to move to the center of the adjacent vehicle.
  • Route change behavior that is, under normal circumstances, the vehicle runs at a uniform speed along the lane.
  • Route change behavior that is, under normal circumstances, the vehicle runs at a uniform speed along the lane.
  • it will drive to a better road environment position by accelerating, decelerating, and changing lanes.
  • Follow-up behavior that is, a behavior in which the vehicle randomly selects the driving state, is to randomly select a state in the field of view of the vehicle, and then move in this direction.
  • follow-up behavior is a default behavior of route change behavior.
  • determining the driving decision of the Zhiba convoy according to the path information passed by the Zhiba convoy may be: according to the preset maximum function and the path information passed by the Zhiba convoy, determine the current state of the vehicles in the Zhiba convoy The target value of the position, according to the target value of the current position of the vehicle, to determine the driving decision of the vehicle in the Zhiba fleet.
  • the maximum value function is the maximum target according to the driving speed of the surrounding vehicles, the maximum safe driving distance target and the surrounding vehicles. The quantity minimizes at least one of the determined functions of the objective.
  • the driving environment optimization problem is a multi-objective optimization problem, and at least one of the following three objectives can be used as the objective function.
  • the present disclosure takes the combination of the following three objectives to obtain the overall objective function as an example.
  • L 1 is a function of the average traveling speed of the surrounding sensing vehicles
  • m is the number of surrounding sensing vehicles
  • V( xi ) represents the speed value of the vehicle at the position xi within the sensing range.
  • L 2 is a function of the safety distance
  • x f is the position of the preceding vehicle.
  • an objective function for maximizing the safe driving distance can also be obtained by comprehensively considering the safe driving distance with the side-by-side vehicle or the rear vehicle, which is not limited in this embodiment of the present application.
  • L 3 is a function of the number of surrounding sensed vehicles
  • M( xi ) represents the number of vehicles within the sensing range of the vehicle at position xi .
  • the expected target value is the objective function value of each objective function in an ideal state, such as vehicle exclusive access to road resources, maintaining the best safe driving distance with other vehicles and driving under the maximum speed limit, where v max represents the road speed limit, then in, 3.2 in is the safety distance coefficient given by experience, and can also be other values. Since the unit of v max is km/h, the unit is converted to m/s by multiplying by 1/3.6;
  • the target value of the position when calculating the target value of the position, directly pass the formula Just calculate.
  • the units of the values obtained under each target may be different, for example, the units of the number of vehicles and the driving speed are different, the de-dimensioning process will be performed first when calculating.
  • the smaller the target value of a position the better the condition of the position.
  • Constraints can be set:
  • V(x i ) ⁇ v max which means that the vehicle cannot overspeed, It means that the distance from the vehicle in front is greater than or equal to the safety distance.
  • the driving decision to determine the vehicle in the Zhiba fleet may be: detecting whether there are other vehicles in the Zhiba fleet within the sensing range of the vehicle; When there are other vehicles in the Zhiba fleet within the range, determine the center position of other vehicles; if the target value of the center position of other vehicles is smaller than the target value of the current position of the vehicle, and the aggregation degree of the center positions of other vehicles is less than the first preset If the aggregation degree threshold is set, the driving decision of the vehicle in the Zhiba fleet is determined as the aggregation behavior strategy for the central position of other vehicles.
  • the priority value of the group behavior strategy can be the highest.
  • Vehicle groups need to follow two rules when traveling: one is to try to move toward the center of the adjacent fleet of vehicles, and the other is to avoid excessive aggregation.
  • the vehicle senses the number of vehicles in the smart bus fleet in the current neighborhood, calculates the center position of the vehicle, and then compares the newly obtained target value of the center position with the target value of the current position. If the target value of the central position is smaller than the target value of the current position and it is not very aggregated, it can move from the current position to the central position to perform the aggregation behavior, otherwise other behavioral strategies are executed.
  • the current position of the vehicle is xi
  • the number of vehicles in the Benzhiba fleet in its visible area is n f , forming a set K:
  • d visual represents the sensing distance of the vehicle and is defined as the maximum distance supported by the communication between vehicles.
  • K is not an empty set, it means that there is a vehicle in the field of view, that is, n f ⁇ 1, then the state of the center position x c is sensed according to the following formula:
  • the value of x c represents the state of the center position x c .
  • ⁇ represent the aggregation degree factor, that is, ⁇ is the first preset aggregation degree threshold, if the central position aggregation degree ⁇ r, (0 ⁇ 1), and the target value of the central position is smaller than the target value of the current position, that is, L c ⁇ L i , it indicates that the driving environment at the center location is better and less crowded, then the vehicle drives to the center location x c , otherwise other behaviors are performed.
  • the formula is expressed as follows:
  • x j represents the position of the vehicle after moving
  • st represents the step size of the vehicle moving
  • Rand(st) represents a random number between [0, st]
  • x ci is the unit vector of x c -xi .
  • the driving decision of the vehicle in the Zhiba fleet may also be: if the target value of the center position of other vehicles is greater than or equal to the target value of the current position of the vehicle, and/ or the aggregation degree at the center position of other vehicles is greater than or equal to the first preset aggregation degree threshold, then according to the maximum value function, among other vehicles in the Zhiba fleet included in the sensing range, determine the target vehicle with the smallest target value; if If the target value of the location of the target vehicle is less than the target value of the current location of the vehicle, and the aggregation degree of the location of the target vehicle is less than the second preset aggregation degree threshold, it is determined that the driving decision of the vehicle in the Zhiba fleet is the follow-up behavior strategy , and the target vehicle is determined as the vehicle's immediate object.
  • the vehicle When the vehicle senses that there are vehicles in the Benzhiba convoy around, but the condition of the center of the Benzhiba fleet is worse than the current situation, it may not be able to perform grouping behavior.
  • the follow-up behavior policy can be set to the second priority policy lower than the aggregation behavior policy. If the condition of the aggregation behavior is executed, then it can continue to judge whether the vehicle meets the condition of following the behavior policy.
  • the current state of the vehicle be x i , and sense the optimal state of the Benzhiba fleet vehicle state x max in its neighborhood.
  • the target value at x max is less than the target value of the current position of the vehicle, that is, L max ⁇ L i , and x max
  • the aggregation degree of vehicles in the neighborhood of r ⁇ , (0 ⁇ 1, where ⁇ represents the second preset aggregation degree threshold, which can be set to the same value as the first preset aggregation degree threshold, or can also be set to set to different values) indicating that there is a better driving environment near x max and it is less crowded, the vehicle will drive to the position of x max , otherwise other behavioral strategies will be implemented.
  • x j represents the position of the vehicle after moving
  • st represents the step size of the vehicle moving
  • Rand(st) represents a random number between [0, st]
  • x mi is the unit vector of x max - x i .
  • the driving decision to determine the vehicle in the smart bus fleet may also be: if the target value of the position of the target vehicle is greater than or equal to the target value of the current position of the vehicle, and/ Or the aggregation degree of the position where the target vehicle is located is greater than or equal to the second preset aggregation degree threshold, then randomly determine a target position within the sensing range; detect whether the target value of the target position is less than the target value of the current position of the vehicle; if the target position The target value of , is less than the target value of the current position of the vehicle, and the driving decision of the vehicle in the Zhiba fleet is determined as the route change behavior strategy for the target position.
  • the vehicle does not detect other vehicles in the Benzhiba team within the sensing range, it means that the vehicle may have fallen behind, so the vehicle can first find a good position within its own sensing range, and change the route.
  • the vehicle will periodically detect whether there are vehicles in the Benzhiba convoy, so as to be able to keep up with the convoy, and if there are other vehicles in the convoy within the sensing range of the vehicle, but it does not meet the judgment of the aggregation behavior strategy condition, and does not meet the judgment condition of closely following the behavior strategy, then it means that the vehicle is temporarily unable to keep up with other vehicles in the team, then you can first find a good position within the sensing range, and change the route.
  • the en-route change behavior strategy may be set as a strategy lower than the third priority immediately following the behavior strategy.
  • the route change behavior includes acceleration, deceleration, lane change, and other behaviors to drive to a specific location.
  • x j represents the position of the vehicle after moving
  • st represents the step size of the vehicle moving
  • Rand(st) represents a random number between [0, st]
  • x ji is the unit vector of x j -xi .
  • the driving decision of the vehicle in the Zhiba fleet can also be determined as follows: if the target value of the target position is greater than or equal to the target value of the current position of the vehicle, then within the sensing range Randomly re-determine another target position within the next step, and perform the step of detecting whether the target value of the target position is smaller than the target value of the current position of the vehicle again; if the target value of the target position randomly determined for N consecutive times is not less than the target value of the current position of the vehicle , to determine the driving decision of the vehicle in the Zhiba fleet as the follow-up behavior strategy.
  • the follow-up behavior can be a default behavior of the route change behavior.
  • the vehicle can be controlled.
  • the vehicles in the smart bus fleet can be unmanned vehicles, that is, smart buses, then the vehicles can be directly controlled to drive according to the behaviors corresponding to the determined driving decisions, or, the vehicles in the fleet are not unmanned vehicles, then for example
  • the prompt information can be output through the vehicle instrument panel, thereby prompting the driver to drive according to the behavior corresponding to the determined driving decision.
  • the vehicle may be controlled by decelerating.
  • the vehicle can also receive the respective status information sent by all vehicles in the Zhiba fleet except the command vehicle; and then detect the driving status of the Zhiba team according to the status information.
  • the convergence conditions include at least one of the speed convergence conditions, the overall connectivity convergence conditions of the Zhiba fleet, and the interference convergence conditions of surrounding vehicles; when the driving state of the Zhiba fleet meets the convergence conditions, the Each vehicle in the bus fleet sends the first notification information to instruct each vehicle to maintain the current driving state; when the driving state of the Zhiba fleet does not meet the convergence condition, it sends the second notification information to each vehicle in the Zhiba fleet to inform Each vehicle is instructed to re-determine the driving strategy.
  • the above convergence conditions may be:
  • D represents the distance between the head and tail vehicles in the Zhiba fleet
  • L represents the length of the vehicle in the Zhiba fleet.
  • the command vehicle can detect whether the driving state of the entire Zhiba fleet meets the convergence conditions according to a set period, for example, every other communication period. If the convergence conditions are met, each vehicle can be notified to maintain the current driving decision-making state, for example, keep the current driving speed at a constant speed; if the convergence conditions are not met, each vehicle can be notified to re-determine the driving strategy. In this way, the entire Zhiba fleet can continue to maintain coordinated and consistent driving.
  • a complete embodiment of the present application can determine the current path of the vehicles in the Zhiba fleet in the order of the aggregation behavior strategy, the follow-up behavior strategy, the route change behavior strategy, and the follow-up behavior strategy from high to low priority. Which behavior the information is suitable for, after the driving decision is determined, the driving can be carried out according to the corresponding behavior. During the driving process, it can be determined whether to maintain the current driving status or to re-determine the driving decision according to whether the current driving status of the entire fleet satisfies the set convergence conditions.
  • the group target value detection can be carried out cyclically according to a certain period, that is, for the command vehicle, the driving status of each vehicle in the Zhiba fleet can be obtained, and then the driving status of the entire Zhiba fleet can be determined. Convergence conditions are met; for non-command vehicles, the driving state of the vehicle can be sent to the command vehicle for detection, and the detection results sent by the command vehicle can be received.
  • the vehicles in the Zhiba convoy can obtain the path information passed by the Zhiba convoy, and then determine the driving decision of the Zhiba convoy according to the path information.
  • the vehicles in the Zhiba fleet can make different driving decisions according to different path information, which is conducive to the better driving of the vehicles in the driving decision-making and ensures the whole
  • the safety and synergy of driving decision-making on the other hand, the fleet of Zhiba with a certain level of safety and synergy has the advantages of flexible transportation, low cost, economical benefits, high line network density, good connectivity and accessibility, and right of way. With the advantages of flexible occupation, it has well solved many problems existing in traditional buses, subways and cloud/air rails in the city.
  • FIG. 2 is a schematic structural diagram of a smart bus fleet control system provided by an embodiment of the present application.
  • the system can be integrated into an unmanned vehicle such as a smart bus, and the system includes an information acquisition module 201 and a strategy determination module 202 and fleet control module 203, where:
  • the information acquisition module 201 is used to acquire the path information of the Zhiba convoy
  • the strategy determination module 202 is used to determine the driving decision of the smart bus fleet according to the path information passed by the smart bus fleet, wherein the driving decision includes at least one of the aggregation behavior strategy, the follow-up behavior strategy, the route change behavior strategy and the follow-up behavior strategy.
  • the driving decision includes at least one of the aggregation behavior strategy, the follow-up behavior strategy, the route change behavior strategy and the follow-up behavior strategy.
  • the fleet control module 203 is configured to control the Zhiba fleet according to the determined driving decision.
  • the policy determination module 202 may include a first determination unit and a second determination unit, wherein:
  • the first determination unit is configured to determine the target value of the current position of the vehicle in the Zhiba fleet according to the preset maximum function and the path information passed by the Zhiba fleet, wherein the maximum function is to maximize the target according to the driving speed of the surrounding vehicles, a function determined by at least one of the objective of maximizing the safe driving distance and the objective of minimizing the number of surrounding vehicles;
  • the second determination unit is configured to determine the driving decision of the vehicle in the Zhiba fleet according to the target value of the current position of the vehicle.
  • the policy determination module 202 may include a detection unit, a third determination unit and a fourth determination unit, wherein:
  • a detection unit used to detect whether there are other vehicles in the Zhiba fleet within the sensing range of the vehicle
  • a third determining unit configured to determine the center position of the other vehicles when it is detected that there are other vehicles in the Zhiba fleet within the sensing range;
  • the fourth determination unit is configured to determine that the vehicle is in the smart bus fleet if the target value of the center position of the other vehicle is smaller than the target value of the current position of the vehicle, and the aggregation degree of the center position of the other vehicle is smaller than the first preset aggregation degree threshold
  • the driving decision is an aggregated behavioral strategy for the central location of other vehicles.
  • the policy determination module 202 may include a fifth determination unit, a sixth determination unit and a seventh determination unit, wherein:
  • a fifth determining unit configured to arbitrarily determine a target position within the sensing range when it is detected that no other vehicle in the Zhiba fleet exists within the sensing range of the vehicle;
  • a sixth determination unit configured to detect whether the target value of the target position is smaller than the target value of the current position of the vehicle
  • the seventh determination unit is configured to determine that the vehicle's driving decision in the smart bus fleet is a route change behavior strategy for the target position if the target value of the target position is smaller than the target value of the current position of the vehicle.
  • the policy determination module 202 may include an eighth determination unit and a ninth determination unit, wherein:
  • the eighth determination unit is configured to, if the target value of the center position of the other vehicle is greater than or equal to the target value of the current position of the vehicle, and/or the aggregation degree of the center position of the other vehicle is greater than or equal to the first preset aggregation degree threshold, according to The maximum value function, which determines the target vehicle with the smallest target value among other vehicles in the Zhiba fleet included in the sensing range;
  • a ninth determination unit configured to determine that the vehicle is in the smart bus fleet if the target value of the location of the target vehicle is less than the target value of the current location of the vehicle, and the aggregation degree of the location of the target vehicle is less than the second preset aggregation degree threshold
  • the driving decision is the follow-up behavior strategy, and the target vehicle is determined as the follow-up object of the vehicle.
  • the policy determination module 202 may include a tenth determination unit, a detection unit and an eleventh determination unit, wherein:
  • the tenth determining unit is configured to, if the target value of the location where the target vehicle is located is greater than or equal to the target value of the current location of the vehicle, and/or the aggregation degree of the location where the target vehicle is located is greater than or equal to the second preset aggregation degree threshold, then Randomly determine a target position within the sensing range;
  • a detection unit for detecting whether the target value of the target position is smaller than the target value of the current position of the vehicle
  • the eleventh determining unit is configured to determine that the vehicle's driving decision in the smart bus fleet is a route change behavior strategy for the target position if the target value of the target position is smaller than the target value of the current position of the vehicle.
  • the policy determination module 202 may include a twelfth determination unit and a thirteenth determination unit, wherein:
  • the twelfth determination unit is configured to randomly re-determine another target position within the sensing range if the target value of the target position is greater than or equal to the target value of the current position of the vehicle, and perform again to detect whether the target value of the target position is smaller than the vehicle The step of the target value of the current position;
  • the thirteenth determination unit is used to determine that the vehicle's driving decision in the smart bus fleet is a follow-up behavior policy if the target value of the target position randomly determined for N consecutive times is not less than the target value of the current position of the vehicle.
  • FIG. 3 shows a schematic structural diagram of the smart bus involved in the embodiment of the present application, specifically:
  • the smart bus may include a processor 301 of one or more processing cores, a memory 302 of one or more computer-readable storage media, a power supply 303 and an input unit 304 and other components.
  • a processor 301 of one or more processing cores may include a processor 301 of one or more processing cores, a memory 302 of one or more computer-readable storage media, a power supply 303 and an input unit 304 and other components.
  • FIG. 3 does not constitute a limitation on the smart bus, and may include more or less components than the one shown, or combine some components, or arrange different components. in:
  • the processor 301 is the control center of the smart bus, using various interfaces and lines to connect various parts of the entire smart bus, by running or executing the software programs and/or modules stored in the memory 302, and calling the software programs stored in the memory 302. Data, perform various functions of the smart bus and process the data, so as to carry out the overall monitoring of the smart bus.
  • the processor 301 may include one or more processing cores; preferably, the processor 301 may integrate an application processor and a modem processor, wherein the application processor mainly processes the operating system, user interface, and application programs, etc. , the modem processor mainly deals with wireless communication. It can be understood that, the above-mentioned modulation and demodulation processor may not be integrated into the processor 301.
  • the memory 302 can be used to store software programs and modules, and the processor 301 executes various functional applications and data processing by running the software programs and modules stored in the memory 302 .
  • the memory 302 may mainly include a stored program area and a stored data area, wherein the stored program area may store an operating system, an application program required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; Data created by the use of smart buses, etc.
  • memory 302 may include high-speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other volatile solid state storage device. Accordingly, memory 302 may also include a memory controller to provide processor 301 access to memory 302 .
  • the smart bus further includes a power supply 303 for supplying power to various components.
  • the power supply 303 can be logically connected to the processor 301 through a power management system, so as to manage charging, discharging, and power consumption management functions through the power management system.
  • the power source 303 may also include one or more DC or AC power sources, recharging systems, power failure detection circuits, power converters or inverters, power status indicators, and any other components.
  • the smart bus may also include an input unit 304, which may be used to receive input numerical or character information and generate keyboard, mouse, joystick, optical or trackball signal input related to user settings and function control.
  • an input unit 304 which may be used to receive input numerical or character information and generate keyboard, mouse, joystick, optical or trackball signal input related to user settings and function control.
  • the smart bus may also include a display unit, etc., which will not be described here.
  • the processor 301 in the smart bus will load the executable files corresponding to the processes of one or more application programs into the memory 302 according to the following instructions, and the processor 301 will run them and store them in the memory 302 .
  • the application program in the memory 302, thereby realizing various functions, as follows: obtaining the route information of the Zhiba convoy; Follow at least one of the behavior strategy, the route change behavior strategy and the follow-up behavior strategy; control the Zhiba fleet according to the determined driving decision.
  • the vehicles in the Zhiba fleet can obtain the path information passed by the Zhiba fleet, and then determine the driving decision of the Zhiba fleet according to the path information.
  • the vehicles in the Zhiba fleet can make different driving decisions according to different path information, which is conducive to the better driving of the vehicles in the driving decision, and ensures the safety and coordination of the entire driving decision.
  • the smart bus fleet with a certain level of safety and synergy has the advantages of flexible transportation, low cost, economic benefits, high network density, good accessibility and accessibility, and flexible occupation of the right of way, which is very good. It solves many problems existing in traditional buses, subways and cloud/air rails in the city.
  • the embodiments of the present application provide a computer-readable storage medium, in which a plurality of instructions are stored, and the instructions can be loaded by a processor to execute any of the methods for controlling a fleet of smart buses provided by the embodiments of the present application.
  • the instruction can perform the following steps: obtain the route information of the Zhiba convoy; determine the driving decision of the Zhiba convoy according to the route information passed by the Zhiba convoy, wherein the driving decision includes the aggregation behavior strategy, the follow-up behavior strategy, the route Change at least one of the behavior strategy and the follow-up behavior strategy; control the Zhiba fleet according to the determined driving decision.
  • the computer-readable storage medium may include: a read-only memory (ROM, Read Only Memory), a random access memory (RAM, Random Access Memory), a magnetic disk or an optical disk, and the like.
  • the instructions stored in the computer-readable storage medium can execute the steps in any of the smart bus fleet control methods provided by the embodiments of the present application, it is possible to implement any of the smart bus fleet control methods provided by the embodiments of the present application.
  • the beneficial effects that can be achieved by the fleet control method can be seen in the previous embodiments, which will not be repeated here.

Abstract

一种智巴车队控制方法、系统和计算机可读存储介质。智巴车队控制方法包括：获取智巴车队途经的路径信息（S101）；根据智巴车队途经的路径信息，确定智巴车队的行车决策，其中，行车决策包括聚集行为策略、紧跟行为策略、航路改变行为策略以及随动行为策略中的至少一种（S102）；根据确定出的行车决策，对智巴车队进行控制（S103）。智巴车队中的车辆可以根据不同的路径信息制定不同的行车决策，有利于车辆在行车决策中较好的行驶，保证整个行车决策的安全性、协同性，能够很好地解决现在城市中传统公共汽车、地铁和云轨/空轨存在的诸多问题。

Description

一种智巴车队控制方法、系统和计算机可读存储介质 技术领域
本申请涉及智能驾驶领域，特别涉及一种智巴车队控制方法、系统和计算机可读存储介质。
背景技术
随着城市化的飞速发展和城市规模的急剧膨胀，各种“城市病”也越发严重，其中，公共交通就是其中的典型例子。
城市公共交通的问题包括传统公共汽车的运载量小、拥堵、时速慢、站点密集和长距离乘坐耗时多等问题。针对传统公共汽车的上述问题，发展地铁和云轨/空轨貌似能够解决，然而，地铁在建设难度大、周期长、投资大、投入/产出比小、运营成本高、路网结构不易调整、对交通变化适应性较差、对环境安全影响较大等方面也是问题突出，而云轨/空轨在运量、线网覆盖密度、乘客上乘便捷性、城市空间限制、紧急情况处置安全等方面，有轨电车、轻轨等在运载量、运行速度与效率、路权占用、供配电线网建设、路网覆盖性等方面的局限性与不足。
因此，亟需一种方案来解决上述城市公共交通存在的问题。
发明内容
本申请实施例提供了一种智巴车队控制方法、系统和计算机可读存储介质，以解决现有城市共公共交通存在的各种问题。该技术方案如下：
一方面，提供了一种智巴车队控制方法，该方法包括：
获取智巴车队途经的路径信息；
根据所述智巴车队途经的路径信息，确定所述智巴车队的行车决策，所述行车决策包括聚集行为策略、紧跟行为策略、航路改变行为策略以及随动行为策略中的至少一种；
根据确定出的行车决策，对所述智巴车队进行控制。
一方面，提供了一种智巴车队控制系统，，该系统包括：
信息获取模块，用于获取智巴车队途经的路径信息；
策略确定模块，用于根据所述智巴车队途经的路径信息，确定所述智巴车队的行车决策，所述行车决策包括聚集行为策略、紧跟行为策略、航路改变行为策略以及随动行为策略中的至少一种；
车队控制模块，用于根据确定出的行车决策，对所述智巴车队进行控制。
一方面，提供了一种智能巴士，该智能巴士包括存储器、处理器以及存储在所述存储器中并可在所述处理器上运行的计算机程序，该计算机程序代码由该一个或多个处理器加载并执行以实现该智巴车队控制方法所执行的操作。
一方面，提供了一种计算机可读存储介质，该计算机可读存储介质存储有计算机程序由处理器加载并执行以实现该智巴车队控制方法所执行的操作。
从上述本申请提供的技术方案可知，智巴车队中的车辆可以获取智巴车队途经的路径信息，然后根据路径信息来确定智巴车队的行车决策，确定了行车决策后，可以根据确定的行车决策来对智巴车队进行控制，通过这样的方式，一方面，智巴车队中的车辆可以根据不同的路径信息制定不同的行车决策，有利于车辆在行车决策中较好的行驶，保证整个行车决策的安全性、协同性；另一方面，安全性、协同性达到一定程度的智巴车队，具有运载灵活、成本低、经济实惠、线网密度高、四通八达与可达性好、路权占用灵活等优势，很好地解决了现在城市中传统公共汽车、地铁和云轨/空轨存在的诸多问题。
附图说明
为了更清楚地说明本申请实施例中的技术方案，下面将对实施例描述中所需要使用的附图作简单地介绍，显而易见地，下面描述中的附图仅仅是本申请 的一些实施例，对于本领域普通技术人员来讲，在不付出创造性劳动的前提下，还可以根据这些附图获得其他的附图。
图1是本申请实施例提供的智巴车队控制方法的流程图；
图2是本申请实施例提供的智巴车队控制系统的结构示意图；
图3是本申请实施例提供的一种智能巴士的功能结构示意图。
具体实施方式
为使本申请的目的、技术方案和优点更加清楚，下面将结合附图对本申请实施方式作进一步地详细描述。
参见图1，是本申请实施例提供的一种智巴车队控制方法，该方法主要包括以下步骤S101至S103，详细说明如下：
步骤S101：获取智巴车队途经的路径信息。
在本申请实施例中，智巴车队指的是由智能巴士构成的车队。在本申请实施例中，车辆即智能巴士本身可以通过传感器，例如GPS、雷达、摄像等实时获取智巴车队途经的路径信息，例如车辆位置信息、周围环境信息、车速信息等等，还可以按照获取其他车辆的路径信息，信息在各车辆间可以进行交互。
步骤S102：根据智巴车队途经的路径信息，确定智巴车队的行车决策，其中，行车决策包括聚集行为策略、紧跟行为策略、航路改变行为策略以及随动行为策略中的至少一种。
步骤S103：根据确定出的行车决策，对智巴车队进行控制。
在本申请实施例中，智巴车队中可以有一个指挥车辆，智巴车队中的其他车辆可以实时地将自身的行驶状态传送给指挥车辆，指挥车辆从而对整个车队行驶情况进而掌控，例如掌控起点终点等，并且可以通过发送指令来控制各车辆。本申请中的车辆可以是智巴车队中的指挥车辆，也可以是智巴车队中的其他车辆，本申请实施例对此不作限定。
车辆在获取智巴车队途经的路径信息(包括自身的路径信息和车队里其他 车辆的路径信息)后，可以根据智巴车队途经的路径信息来确定智巴车队的行车决策，行车决策可以包括聚集行为策略、紧跟行为策略、航路改变行为策略以及随动行为策略中的至少一种。以下对各行为进行说明。
聚集行为，即在行进过程中，智巴车队为了保证整体行车效率和车辆个体躲避风险而自然地集聚成群，车辆集群遵守如下三条规则：
1、间隔规则，即避免与邻近车辆过于聚集；
2、对齐规则，即与前方邻近车辆的平均方向一致；
3、聚拢规则，即尽量向邻近车辆的中心移动。
紧跟行为，即当车辆发现智巴车队中其他车辆的行车环境更好时，会尾随其快速向此方向移动。
航路改变行为，即一般情况下，车辆沿着车道匀速运行，当发现更优的道路环境时，则会通过加减速、变道来向更优的道路环境位置行驶。
随动行为，即车辆随机选择行驶状态的一种行为，就是在车辆在视野中随机选择一个状态，然后向该方向移动，随动行为它是航路改变行为的一个缺省行为。
作为本申请一个实施例，根据智巴车队途经的路径信息，确定智巴车队的行车决策，可以是：根据预设的最值函数和智巴车队途经的路径信息，确定智巴车队中车辆当前位置的目标值，根据车辆当前位置的目标值，确定该车辆在智巴车队中的行车决策，此处，最值函数为根据周边车辆行驶速度最大化目标、安全驾驶距离最大化目标以及周边车辆数量最小化目标中的至少一种确定的函数。具体地，假设智巴车队中存在n辆车，智巴车队的状态可表示为X＝(x 1，x 2，…，x n)，其中x i(i＝1，2，3，…，n)为欲寻优的变量，即智巴车队中第i个车辆的状态信息，x i代表二维空间内车辆的坐标位置以及速度信息，用向量表示x i＝[xi1，xi2，xi3，xi4]，其中，xi1表示车辆行驶过程中所处的经度，xi2表示车辆行驶过程中所处的纬度，xi3表示车辆行驶过程中的速度，xi4表示 车辆行驶过程中的方向角。车辆当前所在位置的目标函数为L＝G(X)，其中L为目标值。
行车环境最优化问题属于多目标优化问题，可以将以下三个目标中的至少一种来作为目标函数，本公开以综合下述三个目标来得到总的目标函数为例。
1、周边车辆行驶速度最大化目标：
Figure PCTCN2020107195-appb-000001
其中，L 1为周边感测车辆平均行驶速度的函数，m为周边感测车辆的数量，V(x i)表示感测范围内的位置x i处车辆的速度值。
2、安全驾驶距离最大化目标：
max L 2＝G 2(X)＝||x f-x||
其中，L 2为安全距离的函数，x f为前车位置。当然，在实际应用中，还可以综合考虑与并排车辆或者后方车辆之间的安全驾驶距离来得到安全驾驶距离最大化的目标函数，本申请实施例对此不作限定。
3、周边车辆数量最小化目标：
max L 3＝G 3(X)＝M(x i)
其中，L 3为周边感测车辆数量的函数，M(x i)表示车辆在位置x i处的感测范围内车辆数量。
将多目标问题转化成单目标问题，给出各目标的期望值
Figure PCTCN2020107195-appb-000002
和
Figure PCTCN2020107195-appb-000003
目标期望值为各个目标函数在理想状态下的目标函数值，如车辆独享道路资源，与其他车辆保持最佳安全行驶距离以及最高限速下行驶，其中，v max表示道路限速，则
Figure PCTCN2020107195-appb-000004
其中，
Figure PCTCN2020107195-appb-000005
中的3.2为根据经验给出的安全距离系数，也可以是其他值，由于v max单位为km/h，通过乘以1/3.6将单位转化为m/s；
将当前位置得到的各目标的真实值与对应的期望值作差，差值越小说明越接近期望值，那么寻求最优位置实际上是寻求差值最小的位置，因此可以定义 总的目标函数为：
Figure PCTCN2020107195-appb-000006
当然，针对某个位置，在计算该位置的目标值时，直接通过公式
Figure PCTCN2020107195-appb-000007
计算即可。同时，由于各目标下得到的值的单位可能不同，例如车辆数量与行驶速度的单位不同，那么在进行计算时，会先进行去量纲化处理。在本申请实施例中，一个位置的目标值越小，说明该位置的状况越好。
同时，由于车辆不能超速，与前车的距离也必须大于安全距离，可以设定约束条件：
V(x i)≤v max，即表示车辆不能超速，
Figure PCTCN2020107195-appb-000008
即表示与前车距离大于或等于安全距离。
作为本申请一个实施例，根据车辆当前位置的目标值，确定车辆在智巴车队中的行车决策可以是：检测车辆的感测范围内是否存在智巴车队中的其他车辆；在检测到感测范围内存在智巴车队中的其他车辆时，确定其他车辆的中心位置；若其他车辆的中心位置的目标值小于车辆当前位置的目标值，且其他车辆的中心位置的聚集度小于第一预设聚集度阈值，则确定车辆在智巴车队中的行车决策为针对其他车辆的中心位置的聚集行为策略。车辆在感测到周围有本智巴车队的车辆时，说明车辆没有掉队，那么需要尽量向着本智巴车队车辆的中心靠拢，进而能够更好地同本车队车辆一同前行。因此为了保证车队整体的协同性，可以将聚群行为策略的优先级值为最高，在获取智巴车队途经的路径信息后，可以首先判定车辆当前是否满足聚集行为策略的条件。车辆群体在行进中需要遵守两条规则：一是尽量向邻近车队车辆的中心移动，二是避免过分聚集。车辆感测当前邻域内智巴车队的车辆数量，并计算车辆的中心位置，然后将新得到的中心位置的目标值与当前位置的目标值相比较。若中心位置的目标值小于当前位置的目标值并且不是很聚集，则可以从当前位置向中心位置移动，执行聚集行为，否则执行其他行为策略。
拥挤度定义：
Figure PCTCN2020107195-appb-000009
其中，
Figure PCTCN2020107195-appb-000010
表示车队所有车辆周边感测车辆去重后的集合。
车辆当前位置为x i，设其可见区域内的本智巴车队车辆个数为n f，形成集合K：
K＝{x j|x j-x i≤d visual}i，j＝1，2，3，…，n
d visual表示车辆的感测距离，定义为车辆之间通信支持的最大距离。
如果K不是空集的话，表明在视野范围内有车辆存在，即n f≥1，那么就按如下公式感测中心位置x c的状态：
Figure PCTCN2020107195-appb-000011
x c的值即表示中心位置x c的状态。令λ表示聚集度因子，即λ为第一预设聚集度阈值，如果中心位置聚集度λ<r，(0<λ<1)，并且中心位置的目标值小于当前位置的目标值，即L c<L i，则表明中心位置行车环境较好并且不太聚集，则车辆向中心位置x c行驶，否则执行其他行为。公式表述如下：
if(r<λ，L c<L i)，then x j＝x i+Rand(st)×x ci；
其中，x j表示车辆移动后所处的位置，st表示车辆移动的步长，Rand(st)表示[0，st]之间的随机数字，x ci为x c-x i的单位向量。
作为本申请一个实施例，根据车辆当前位置的目标值，确定车辆在智巴车队中的行车决策还可以是：若其他车辆的中心位置的目标值大于或等于车辆当前位置的目标值，和/或其他车辆的中心位置的聚集度大于或等于第一预设聚集度阈值，则根据最值函数，在感测范围内包括的智巴车队的其他车辆中，确定目标值最小的目标车辆；若目标车辆所处位置的目标值小于车辆当前位置的目标值，且目标车辆所处位置的聚集度小于第二预设聚集度阈值，则确定车辆在 智巴车队中的行车决策为紧跟行为策略，且将目标车辆确定为车辆的紧跟对象。车辆在感测到周边有本智巴车队的车辆，但得出本智巴车队车辆中心位置的状况比当前状况差时，可能无法进行聚群行为，而为了让车辆尽可能地不掉队，能够继续跟着本智巴车队的车辆走，可以进一步检测车辆是否满足紧跟行为策略的条件，即，可以将跟车行为策略设置为低于聚集行为策略的第二优先级策略，如果车辆当前不符合执行聚集行为的条件，那么可以继续判断车辆是否满足紧跟行为策略的条件。设车辆当前状态为x i，感测其邻域内状态最优的本智巴车队车辆状态x max若x max处的目标值小于车辆当前位置的目标值，即L max<L i，并且x max的邻域内车辆的聚集度r<λ，(0<λ<1，此处，λ表示第二预设聚集度阈值，可以设置为与第一预设聚集度阈值相同的值，或者也可以设定为不同的值)，表明x max的附近有更优的行车环境并且不太拥挤，车辆则向x max的位置行驶，否则执行其他行为策略。
公式描述如下：(r<λ，L max<L i)
if(r<λ，L max<L i)，thenx j＝x i+Rand(st)×x mi
其中，x j表示车辆移动后所处的位置，st表示车辆移动的步长，Rand(st)表示[0，st]之间的随机数字，x mi为x max-x i的单位向量。在检测是否满足紧跟行为策略的条件时，由于车辆只能前进这一特性，跟车也只能是跟前方的车辆，因此可以只检测车辆前方一定范围内的本智巴车队车辆的目标值是否小于车辆当前位置的目标值。比如，检测范围可以是车辆左右45度正前方的范围，等等。
作为本申请一个实施例，根据车辆当前位置的目标值，确定车辆在智巴车队中的行车决策还可以是：若目标车辆所处位置的目标值大于或等于车辆当前位置的目标值，和/或目标车辆所处位置的聚集度大于或等于第二预设聚集度阈值，则在感测范围内随机确定一目标位置；检测目标位置的目标值是否小于车辆当前位置的目标值；若目标位置的目标值小于车辆当前位置的目标值，确定车辆在智巴车队中的行车决策为针对目标位置的航路改变行为策略。车辆如果 在感测范围内没有检测到本智巴车队的其他车辆，那么说明车辆可能已经掉队了，那么可以让车辆先在自身的感测范围内找寻状况好的位置，进行航路改变行为，同时车辆在行进过程中，会周期性地探测周边是否存在本智巴车队的车，以便能够跟上车队，而若车辆感测范围内有本车队的其他车辆，但既不满足聚集行为策略的判定条件，也不满足紧跟行为策略的判定条件，那么说明车辆暂时无法跟上本车队的其他车，那么可以先在感测范围内找寻状况好的位置，进行航路改变行为，同时在行进过程中，周期性地检测是否满足聚集行为策略的判定条件或者紧跟行为策略的判定条件，以便能够较好地跟上本智巴车队的其他车辆。航路改变行为策略可以设定为低于紧跟行为策略的第三优先级的策略。在车辆感测到周边感测范围内有本智巴车队的其他车辆，会先判定是否满足聚集行为策略及紧跟行为策略的条件，如果都不满足，会继续判定是否满足航路改变行为策略的条件；或者，在车辆检测到周边感测范围内不存在本车队的其他车辆时，可以直接判定是否满足航路改变行为策略的条件。航路改变行为包含加速、减速、变道、等驶向特定地点的行为，设车辆当前状态为x i，在其视野范围内随机选择一个状态x j，若L j<L i，则选择状态x j继续行驶；反之，再重新随机选择状态x j，判断是否满足前进条件。
公式表述如下：
if(L j<L i)，then x j＝x i+Rand(st)×x ji
其中，x j表示车辆移动后所处的位置，st表示车辆移动的步长，Rand(st)表示[0，st]之间的随机数字，x ji为x j-x i的单位向量。
作为本申请一个实施例，根据车辆当前位置的目标值，确定车辆在智巴车队中的行车决策还可以是：若目标位置的目标值大于或等于车辆当前位置的目标值，则在感测范围内随机重新确定另一目标位置，并再次执行检测目标位置的目标值是否小于车辆当前位置的目标值的步骤；若连续N次随机确定的目标位置的目标值均不小于车辆当前位置的目标值，确定车辆在智巴车队中的行车决策为随动行为策略。随动行为可以是航路改变行为的一个缺省行为，在判断 航路改变行为过程中，如果试探N次后，如果仍不满足航路改变行为的条件，则可以执行随动行为或维持航路改变行为。随动行为指车辆在视野内随意移动，x i处的车辆随意移动一步，到达一个新的状态：x j＝x i+Rand(st)，其中，步长st是车辆在一次通信控制周期内行驶的距离，st＝V(x i)×t，式中t为车辆之间通信控制周期。
在确定车辆的行车决策之后，可以对车辆进行控制。例如，智巴车队里的车辆可以是无人驾驶的车辆即智能巴士，那么可以直接控制车辆按照确定的行车决策对应的行为进行驾驶，或者，车队里的车辆不是无人驾驶的车辆，那么比如可以通过车辆仪表盘输出提示信息，进而提示驾驶员按照确定的行车决策对应的行为进行驾驶。
当然，由于车辆行驶的特性，位于前方的车辆检测到需要向后方车辆集群时，控制车辆的方式可以是减速。
通过以上方式，可以较好地确定车辆当前采用何种行车决策行驶能够在车队里更加协同、安全地行驶，保证车辆群体的移动的整体性、一致性，有助于最大化利用道路空间资源，节省智巴车队整体能耗以及减小交通风险。
可选的，如果车辆是智巴车队中的指挥车辆，那么还可以接收智巴车队中除指挥车辆外的全部车辆发送的各自的状态信息；然后根据状态信息，检测车智巴队的行驶状态是否满足设定的收敛条件，收敛条件包括速度收敛条件、智巴车队整体连接性收敛条件以及周围车辆干扰性收敛条件中的至少一种；在智巴车队的行驶状态满足收敛条件时，向智巴车队中的各车辆发送第一通知信息，以指示各车辆维持当前的行驶状态；在智巴车队的行驶状态不满足收敛条件时，向智巴车队中的各车辆发送第二通知信息，以指示各车辆重新确定行驶策略。
作为本申请一个实施例，上述收敛条件可以是：
Figure PCTCN2020107195-appb-000012
Figure PCTCN2020107195-appb-000013
Figure PCTCN2020107195-appb-000014
其中，D表示智巴车队中头尾车辆的距离，L表示智巴车队中车辆车身长度。最优终止条件为三个收敛条件的任意权重组合，即φ＝ηφ 1∪μφ 2∪ωφ 3，其中，φ 1体现速度优先原则，φ 2体现整个智巴车队连贯原则，φ 3体现智巴车队中各车辆互不干扰原则，权值η、μ和ω可以根据智巴车队的属性和业务需求的侧重面来确定具体的值，例如，对智巴车队整体连贯性要求较高的业务，可以将权重μ设置得更高，等等。指挥车辆可以按照设定的周期来检测整个智巴车队的行驶状态是否满足收敛条件，例如，每隔一个通信周期检测一次。若满足收敛条件，则可以通知各车辆维持当前的行车决策状态，例如，保持当前行驶速度匀速行驶；若不满足收敛条件，则可以通知各车辆重新确定行驶策略。这样，可以让整个智巴车队持续地保持协同、一致地行驶。
本申请一个完整的实施例是可以按照优先级从高到低依次为聚集行为策略、紧跟行为策略、航路改变行为策略以及随动行为策略的顺序，来判定智巴车队中的车辆当前的路径信息适应于哪一种行为，行车决策确定后，可以按照对应的行为进行行驶。在行驶过程中，可以根据整个车队当前的行驶状态是否满足设定的收敛条件，来确定是保持当前的行驶状态，还是需要重新确定行车决策。同时在行进过程中，可以按照一定的周期循环地进行群体目标值的检测，即，对于指挥车辆而言，可以获取智巴车队中各个车辆的行驶状态，进而确定整个智巴车队的行驶状态是否满足收敛条件；对于非指挥车辆而言，可以将自身的行驶状态发送给指挥车辆进行检测，并接收指挥车辆发送的检测结果。
从上述附图1示例的技术方案可知，智巴车队中的车辆可以获取智巴车队途经的路径信息，然后根据路径信息来确定智巴车队的行车决策，确定了行车决策后，可以根据确定的行车决策来对智巴车队进行控制，通过这样的方式，一方面，智巴车队中的车辆可以根据不同的路径信息制定不同的行车决策，有利于车辆在行车决策中较好的行驶，保证整个行车决策的安全性、协同性；另一方面，安全性、协同性达到一定程度的智巴车队，具有运载灵活、成本低、 经济实惠、线网密度高、四通八达与可达性好、路权占用灵活等优势，很好地解决了现在城市中传统公共汽车、地铁和云轨/空轨存在的诸多问题。
请参阅附图2，是本申请实施例提供的一种智巴车队控制系统的结构示意图，该系统可以集成在智能巴士等无人驾驶车辆中，该系统包括信息获取模块201、策略确定模块202和车队控制模块203，其中：
信息获取模块201，用于获取智巴车队途经的路径信息；
策略确定模块202，用于根据智巴车队途经的路径信息，确定智巴车队的行车决策，其中，行车决策包括聚集行为策略、紧跟行为策略、航路改变行为策略以及随动行为策略中的至少一种；
车队控制模块203，用于根据确定出的行车决策，对智巴车队进行控制。
在一种可能实现方式中，策略确定模块202可以包括第一确定单元和第二确定单元，其中：
第一确定单元，用于根据预设的最值函数和智巴车队途经的路径信息，确定智巴车队中车辆当前位置的目标值，其中，最值函数为根据周边车辆行驶速度最大化目标、安全驾驶距离最大化目标以及周边车辆数量最小化目标中的至少一种确定的函数；
第二确定单元，用于根据车辆当前位置的目标值，确定车辆在智巴车队中的行车决策。
在一种可能实现方式中，策略确定模块202可以包括检测单元、第三确定单元和第四确定单元，其中：
检测单元，用于检测车辆的感测范围内是否存在智巴车队中的其他车辆；
第三确定单元，用于在检测到感测范围内存在智巴车队中的其他车辆时，确定其他车辆的中心位置；
第四确定单元，用于若其他车辆的中心位置的目标值小于车辆当前位置的目标值，且其他车辆的中心位置的聚集度小于第一预设聚集度阈值，则确定车辆在智巴车队中的行车决策为针对其他车辆的中心位置的聚集行为策略。
在一种可能实现方式中，策略确定模块202可以包括第五确定单元、第六确定单元和第七确定单元，其中：
第五确定单元，用于在检测到车辆的感测范围内不存在智巴车队中的其他车辆时，在感测范围内随意确定一目标位置；
第六确定单元，用于检测目标位置的目标值是否小于车辆当前位置的目标值；
第七确定单元，用于若目标位置的目标值小于车辆当前位置的目标值，确定车辆在智巴车队中的行车决策为针对目标位置的航路改变行为策略。
在一种可能实现方式中，策略确定模块202可以包括第八确定单元和第九确定单元，其中：
第八确定单元，用于若其他车辆的中心位置的目标值大于或等于车辆当前位置的目标值，和/或其他车辆的中心位置的聚集度大于或等于第一预设聚集度阈值，则根据最值函数，在感测范围内包括的智巴车队的其他车辆中确定目标值最小的目标车辆；
第九确定单元，用于若目标车辆所处位置的目标值小于车辆当前位置的目标值，且目标车辆所处位置的聚集度小于第二预设聚集度阈值，则确定车辆在智巴车队中的行车决策为紧跟行为策略，且将目标车辆确定为车辆的紧跟对象。
在一种可能实现方式中，策略确定模块202可以包括第十确定单元、检测单元和第十一确定单元，其中：
第十确定单元，用于若目标车辆所处位置的目标值大于或等于车辆当前位置的目标值，和/或目标车辆所处位置的聚集度大于或等于第二预设聚集度阈值，则在感测范围内随机确定一目标位置；
检测单元，用于检测目标位置的目标值是否小于车辆当前位置的目标值；
第十一确定单元，用于若目标位置的目标值小于车辆当前位置的目标值，确定车辆在智巴车队中的行车决策为针对目标位置的航路改变行为策略。
在一种可能实现方式中，策略确定模块202可以包括第十二确定单元和第十三确定单元，其中：
第十二确定单元，用于若目标位置的目标值大于或等于车辆当前位置的目标值，则在感测范围内随机重新确定另一目标位置，并再次执行检测目标位置的目标值是否小于车辆当前位置的目标值的步骤；
第十三确定单元，用于若连续N次随机确定的目标位置的目标值均不小于车辆当前位置的目标值，确定车辆在智巴车队中的行车决策为随动行为策。
需要说明的是，上述实施例提供的智巴车队控制系统在控制智巴车队时，仅以上述各功能模块的划分进行举例说明，实际应用中，可以根据需要而将上述功能分配由不同的功能模块完成，即将系统的内部结构划分成不同的功能模块，以完成以上描述的全部或者部分功能。另外，上述实施例提供的智巴车队控制系统与智巴车队控制方法实施例属于同一构思，其具体实现过程以及技术效果详见方法实施例，此处不再赘述。
本申请实施例还提供一种智能巴士，该智能巴士如图3所示，其示出了本申请实施例所涉及的智能巴士的结构示意图，具体来讲：
该智能巴士可以包括一个或者一个以上处理核心的处理器301、一个或一个以上计算机可读存储介质的存储器302、电源303和输入单元304等部件。本领域技术人员可以理解，图3中示出的智能巴士结构并不构成对智能巴士的限定，可以包括比图示更多或更少的部件，或者组合某些部件，或者不同的部件布置。其中：
处理器301是该智能巴士的控制中心，利用各种接口和线路连接整个智能巴士的各个部分，通过运行或执行存储在存储器302内的软件程序和/或模块，以及调用存储在存储器302内的数据，执行智能巴士的各种功能和处理数据，从而对智能巴士进行整体监控。可选的，处理器301可包括一个或多个处理核心；优选的，处理器301可集成应用处理器和调制解调处理器，其中，应用处理器主要处理操作系统、用户界面和应用程序等，调制解调处理器主要处理无 线通信。可以理解的是，上述调制解调处理器也可以不集成到处理器301中。
存储器302可用于存储软件程序以及模块，处理器301通过运行存储在存储器302的软件程序以及模块，从而执行各种功能应用以及数据处理。存储器302可主要包括存储程序区和存储数据区，其中，存储程序区可存储操作系统、至少一个功能所需的应用程序(比如声音播放功能、图像播放功能等)等；存储数据区可存储根据智能巴士的使用所创建的数据等。此外，存储器302可以包括高速随机存取存储器，还可以包括非易失性存储器，例如至少一个磁盘存储器件、闪存器件、或其他易失性固态存储器件。相应地，存储器302还可以包括存储器控制器，以提供处理器301对存储器302的访问。
智能巴士还包括给各个部件供电的电源303，可选地，电源303可以通过电源管理系统与处理器301逻辑相连，从而通过电源管理系统实现管理充电、放电、以及功耗管理等功能。电源303还可以包括一个或一个以上的直流或交流电源、再充电系统、电源故障检测电路、电源转换器或者逆变器、电源状态指示器等任意组件。
该智能巴士还可包括输入单元304，该输入单元304可用于接收输入的数字或字符信息，以及产生与用户设置以及功能控制有关的键盘、鼠标、操作杆、光学或者轨迹球信号输入。
尽管未示出，智能巴士还可以包括显示单元等，在此不再赘述。具体在本实施例中，智能巴士中的处理器301会按照如下的指令，将一个或一个以上的应用程序的进程对应的可执行文件加载到存储器302中，并由处理器301来运行存储在存储器302中的应用程序，从而实现各种功能，如下：获取智巴车队途经的路径信息；根据智巴车队途经的路径信息，确定智巴车队的行车决策，其中，行车决策包括聚集行为策略、紧跟行为策略、航路改变行为策略以及随动行为策略中的至少一种；根据确定出的行车决策，对智巴车队进行控制。
以上个操作的具体实施例可参见前面的实施例，在此不再赘述。
由以上可知，智巴车队中的车辆可以获取智巴车队途经的路径信息，然后 根据路径信息来确定智巴车队的行车决策，确定了行车决策后，可以根据确定的行车决策来对智巴车队进行控制，通过这样的方式，一方面，智巴车队中的车辆可以根据不同的路径信息制定不同的行车决策，有利于车辆在行车决策中较好的行驶，保证整个行车决策的安全性、协同性；另一方面，安全性、协同性达到一定程度的智巴车队，具有运载灵活、成本低、经济实惠、线网密度高、四通八达与可达性好、路权占用灵活等优势，很好地解决了现在城市中传统公共汽车、地铁和云轨/空轨存在的诸多问题。
本领域普通技术人员可以理解，上述实施例的各种方法中的全部或部分步骤可以通过指令来完成，或通过指令控制相关的硬件来完成，该指令可以存储于一计算机可读存储介质中，并由处理器进行加载和执行。
为此，本申请实施例提供一种计算机可读存储介质，其中存储有多条指令，该指令能够被处理器进行加载，以执行本申请实施例所提供的任一种智巴车队控制方法中的步骤。例如，该指令可以执行如下步骤：获取智巴车队途经的路径信息；根据智巴车队途经的路径信息，确定智巴车队的行车决策，其中，行车决策包括聚集行为策略、紧跟行为策略、航路改变行为策略以及随动行为策略中的至少一种；根据确定出的行车决策，对智巴车队进行控制。
以上各个操作的具体实施方式可参见前面的实施例，在此不再赘述。
其中，该计算机可读存储介质可以包括：只读存储器(ROM，Read Only Memory)、随机存取记忆体(RAM，Random Access Memory)、磁盘或光盘等。
由于该计算机可读存储介质中所存储的指令，可以执行本申请实施例所提供的任一种智巴车队控制方法中的步骤，因此，可以实现本申请实施例所提供的任一种智巴车队控制方法所能实现的有益效果，详见前面的实施例，在此不再赘述。
以上对本申请实施例所提供的一种智巴车队控制方法、设备和计算机可读存储介质进行了详细介绍，本文中应用了具体个例对本申请的原理及实施方式 进行了阐述，以上实施例的说明只是用于帮助理解本申请的方法及其核心思想；同时，对于本领域的技术人员，依据本申请的思想，在具体实施方式及应用范围上均会有改变之处，综上，本说明书内容不应理解为对本申请的限制。

Claims (10)

  1. 一种智巴车队控制方法，其特征在于，所述方法包括：
    获取智巴车队途经的路径信息；
    根据所述智巴车队途经的路径信息，确定所述智巴车队的行车决策，所述行车决策包括聚集行为策略、紧跟行为策略、航路改变行为策略以及随动行为策略中的至少一种；
    根据确定出的行车决策，对所述智巴车队进行控制。
  2. 如权利要求1所述的智巴车队控制方法，其特征在于，所述根据所述智巴车队途经的路径信息，确定所述智巴车队的行车决策，包括：
    根据预设的最值函数和所述智巴车队途经的路径信息，确定所述智巴车队中车辆当前位置的目标值，所述最值函数为根据周边车辆行驶速度最大化目标、安全驾驶距离最大化目标以及周边车辆数量最小化目标中的至少一种确定的函数；
    根据所述车辆当前位置的目标值，确定所述车辆在所述智巴车队中的行车决策。
  3. 根据权利要求2所述的智巴车队控制方法，其特征在于，所述根据所述车辆当前位置的目标值，确定所述车辆在所述智巴车队中的行车决策，包括：
    检测所述车辆的感测范围内是否存在所述智巴车队中的其他车辆；
    在检测到所述感测范围内存在所述智巴车队中的其他车辆时，确定所述其他车辆的中心位置；
    若所述中心位置的目标值小于所述车辆当前位置的目标值，且所述中心位置的聚集度小于第一预设聚集度阈值，则确定所述车辆在所述智巴车队中的行车决策为针对所述中心位置的聚集行为策略。
  4. 根据权利要求3所述的智巴车队控制方法，其特征在于，所述根据所述车辆当前位置的目标值，确定所述车辆在所述智巴车队中的行车决策，包括：
    在检测到所述车辆的感测范围内不存在所述智巴车队中的其他车辆时，在所述感测范围内随意确定一目标位置；
    检测所述目标位置的目标值是否小于所述车辆当前位置的目标值；
    若所述目标位置的目标值小于所述车辆当前位置的目标值，确定所述车辆在所述智巴车队中的行车决策为针对所述目标位置的航路改变行为策略。
  5. 根据权利要求3所述的智巴车队控制方法，其特征在于，所述根据所述车辆当前位置的目标值，确定所述车辆在所述智巴车队中的行车决策，包括：
    若所述中心位置的目标值大于或等于所述车辆当前位置的目标值，和/或所述中心位置的聚集度大于或等于所述第一预设聚集度阈值，则根据所述最值函数，在所述感测范围内包括的所述智巴车队的其他车辆中，确定目标值最小的目标车辆；
    若所述目标车辆所处位置的目标值小于所述车辆当前位置的目标值，且所述目标车辆所处位置的聚集度小于第二预设聚集度阈值，则确定所述车辆在所述智巴车队中的行车决策为紧跟行为策略，且将所述目标车辆确定为所述车辆的紧跟对象。
  6. 根据权利要求5所述的智巴车队控制方法，其特征在于，所述根据所述车辆当前位置的目标值，确定所述车辆在所述智巴车队中的行车决策，包括：
    若所述目标车辆所处位置的目标值大于或等于所述车辆当前位置的目标值，和/或所述目标车辆所处位置的聚集度大于或等于所述第二预设聚集度阈值，则在所述感测范围内随机确定一目标位置；
    检测所述目标位置的目标值是否小于所述车辆当前位置的目标值；
    若所述目标位置的目标值小于所述车辆当前位置的目标值，确定所述车辆在所述智巴车队中的行车决策为针对所述目标位置的航路改变行为策略。
  7. 根据权利要求4或6所述的智巴车队控制方法，其特征在于，所述根据所述车辆当前位置的目标值，确定所述车辆在所述智巴车队中的行车决策，包括：
    若所述目标位置的目标值大于或等于所述车辆当前位置的目标值，则在所述感测范围内随机重新确定另一目标位置，并再次执行所述检测所述目标位置的目标值是否小于所述车辆当前位置的目标值的步骤；
    若连续N次随机确定的目标位置的目标值均不小于所述车辆当前位置的目标值，确定所述车辆在所述智巴车队中的行车决策为随动行为策略。
  8. 一种智巴车队控制系统，其特征在于，系统包括：
    信息获取模块，用于获取智巴车队途经的路径信息；
    策略确定模块，用于根据所述智巴车队途经的路径信息，确定所述智巴车队的行车决策，所述行车决策包括聚集行为策略、紧跟行为策略、航路改变行为策略以及随动行为策略中的至少一种；
    车队控制模块，用于根据确定出的行车决策，对所述智巴车队进行控制。
  9. 一种智能巴士，包括存储器、处理器以及存储在所述存储器中并可在所述处理器上运行的计算机程序，其特征在于，所述处理器执行所述计算机程序时实现如权利要求1至8任意一项所述方法的步骤。
  10. 一种计算机可读存储介质，所述计算机可读存储介质存储有计算机程序，其特征在于，所述计算机程序被处理器执行时实现如权利要求1至8任意一项所述方法的步骤。
PCT/CN2020/107195 2020-08-05 2020-08-05 一种智巴车队控制方法、系统和计算机可读存储介质 WO2022027353A1 (zh)

Priority Applications (1)

Application Number Priority Date Filing Date Title
PCT/CN2020/107195 WO2022027353A1 (zh) 2020-08-05 2020-08-05 一种智巴车队控制方法、系统和计算机可读存储介质

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2020/107195 WO2022027353A1 (zh) 2020-08-05 2020-08-05 一种智巴车队控制方法、系统和计算机可读存储介质

Publications (1)

Publication Number Publication Date
WO2022027353A1 true WO2022027353A1 (zh) 2022-02-10

Family

ID=80118753

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2020/107195 WO2022027353A1 (zh) 2020-08-05 2020-08-05 一种智巴车队控制方法、系统和计算机可读存储介质

Country Status (1)

Country Link
WO (1) WO2022027353A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115131955A (zh) * 2022-05-24 2022-09-30 江西五十铃汽车有限公司 一种车队管理方法、系统、可读存储介质及设备

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6496774B1 (en) * 2001-05-24 2002-12-17 Prc Inc. Automatic vehicle routing and recommendation system
CN103956045A (zh) * 2014-05-13 2014-07-30 中国人民解放军军事交通学院 利用半实物仿真技术手段实现车队协同驾驶的方法
CN106114507A (zh) * 2016-06-21 2016-11-16 百度在线网络技术（北京）有限公司 用于智能车辆的局部轨迹规划方法和装置
CN108216236A (zh) * 2017-12-25 2018-06-29 东软集团股份有限公司 车辆控制方法、装置、车辆及存储介质
CN111433700A (zh) * 2017-12-08 2020-07-17 克诺尔商用车制动系统有限公司 用于基于配属于车队的可预给定的整体运行策略的车队的运动的方法
CN111445690A (zh) * 2020-03-03 2020-07-24 北京汽车集团有限公司 车辆组队行驶方法、车辆及系统
CN111487975A (zh) * 2020-04-30 2020-08-04 畅加风行(苏州)智能科技有限公司 一种基于智能网联系统的港口卡车自动编队方法及系统

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6496774B1 (en) * 2001-05-24 2002-12-17 Prc Inc. Automatic vehicle routing and recommendation system
CN103956045A (zh) * 2014-05-13 2014-07-30 中国人民解放军军事交通学院 利用半实物仿真技术手段实现车队协同驾驶的方法
CN106114507A (zh) * 2016-06-21 2016-11-16 百度在线网络技术（北京）有限公司 用于智能车辆的局部轨迹规划方法和装置
CN111433700A (zh) * 2017-12-08 2020-07-17 克诺尔商用车制动系统有限公司 用于基于配属于车队的可预给定的整体运行策略的车队的运动的方法
CN108216236A (zh) * 2017-12-25 2018-06-29 东软集团股份有限公司 车辆控制方法、装置、车辆及存储介质
CN111445690A (zh) * 2020-03-03 2020-07-24 北京汽车集团有限公司 车辆组队行驶方法、车辆及系统
CN111487975A (zh) * 2020-04-30 2020-08-04 畅加风行(苏州)智能科技有限公司 一种基于智能网联系统的港口卡车自动编队方法及系统

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115131955A (zh) * 2022-05-24 2022-09-30 江西五十铃汽车有限公司 一种车队管理方法、系统、可读存储介质及设备
CN115131955B (zh) * 2022-05-24 2024-01-26 江西五十铃汽车有限公司 一种车队管理方法、系统、可读存储介质及设备

Similar Documents

Publication Publication Date Title
WO2021136130A1 (zh) 一种轨迹规划方法及装置
CN111867911A (zh) 车辆控制方法和设备
CN112967514B (zh) 一种无信号灯交叉口下智能车辆高效行驶的分布式控制方法及系统
WO2022127150A1 (zh) 无人搬运车的调度方法和装置
CN108216236B (zh) 车辆控制方法、装置、车辆及存储介质
CN112634606A (zh) 货车编队运输调度方法、调度系统、介质及数据处理终端
CN107507430A (zh) 一种城市路口交通控制方法及系统
WO2022016901A1 (zh) 一种规划车辆行驶路线的方法以及智能汽车
CN109523807B (zh) 一种交通路网车辆分布式控制方法
WO2022027353A1 (zh) 一种智巴车队控制方法、系统和计算机可读存储介质
CN112037502A (zh) 一种智巴车队控制方法、系统和计算机可读存储介质
CN109511150B (zh) 一种基于单对多充电技术的移动充电车路径规划方法
CN104021664A (zh) 汽车协同编队行驶的动态路径规划方法
CN105109478A (zh) 一种车辆节能减排编组系统
Gao et al. Multi-lane convoy control for autonomous vehicles based on distributed graph and potential field
CN113147841A (zh) 一种轨道车辆的能力管理及节能辅助驾驶方法及相关装置
Farooqi et al. Railway collaborative ecodrive via dissension based switching nonlinear model predictive control
Long et al. MPC-based eco-platooning for homogeneous connected trucks under different communication topologies
CN110751360B (zh) 一种无人船区域调度方法
Wang et al. Towards higher efficiency and less consumption: Control Strategy and Simulation for CAV platooning
CN115593440B (zh) 车辆控制方法、装置、设备及计算机可读存储介质
CN115331461B (zh) 一种无信号交叉口混合交通通行控制方法、装置及车辆
Xia et al. Lane scheduling around crossroads for edge computing based autonomous driving
LU101992B1 (en) Intelligent bus fleet control method and system as well as computer readable storage medium
WO2022032443A1 (zh) 多智能主体编队搬运方法、系统和计算机可读存储介质

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 20948358

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 20948358

Country of ref document: EP

Kind code of ref document: A1