WO2023098238A1 - 车辆控制方法、装置、设备、介质及计算机程序产品 - Google Patents

车辆控制方法、装置、设备、介质及计算机程序产品 Download PDF

Info

Publication number
WO2023098238A1
WO2023098238A1 PCT/CN2022/119827 CN2022119827W WO2023098238A1 WO 2023098238 A1 WO2023098238 A1 WO 2023098238A1 CN 2022119827 W CN2022119827 W CN 2022119827W WO 2023098238 A1 WO2023098238 A1 WO 2023098238A1
Authority
WO
WIPO (PCT)
Prior art keywords
vehicle
lane
score
current state
dimension
Prior art date
Application number
PCT/CN2022/119827
Other languages
English (en)
French (fr)
Inventor
杜海宁
Original Assignee
腾讯科技（深圳）有限公司
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 腾讯科技（深圳）有限公司 filed Critical 腾讯科技（深圳）有限公司
Publication of WO2023098238A1 publication Critical patent/WO2023098238A1/zh

Links

Images

Classifications

    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W30/00—Purposes of road vehicle drive control systems not related to the control of a particular sub-unit, e.g. of systems using conjoint control of vehicle sub-units
    • B60W30/18—Propelling the vehicle
    • B60W30/18009—Propelling the vehicle related to particular drive situations
    • B60W30/18163—Lane change; Overtaking manoeuvres

Definitions

  • the present application relates to the field of Internet technology, specifically to the field of automatic driving technology, and in particular to a vehicle control method, device, equipment, medium and computer program product.
  • Embodiments of the present application provide a vehicle control method, device, device, medium, and computer program product, which can improve the authenticity of the lane-changing behavior of the vehicle, thereby improving the driving safety of the vehicle.
  • an embodiment of the present application provides a vehicle control method executed by a computer device, the method comprising:
  • controlling the first vehicle to travel on the first lane, the road area where the first lane is located also includes: a second lane and a middle lane between the first lane and the second lane; wherein, the Both the second lane and the middle lane are in the same direction as the first lane;
  • the first vehicle intends to change lanes to the middle lane, control the first vehicle to change lanes to the middle lane; and observe the first vehicle during the lane change of the first vehicle.
  • two lanes If the first vehicle intends to change lanes to the middle lane, control the first vehicle to change lanes to the middle lane; and observe the first vehicle during the lane change of the first vehicle.
  • a target driving action of the first vehicle is determined, and the first vehicle is controlled to execute the target driving action.
  • an embodiment of the present application provides a vehicle control device, the device comprising:
  • a control unit configured to control the first vehicle to travel on the first lane, and the road area where the first lane is located further includes: a second lane and a middle lane between the first lane and the second lane ; Wherein, both the second lane and the middle lane are in the same direction as the first lane;
  • the control unit is further configured to control the first vehicle to change lanes to the middle lane if the first vehicle intends to change lanes to the middle lane;
  • a processing unit configured to observe the second lane during lane changing of the first vehicle
  • the processing unit is further configured to determine the current state information of the first vehicle and the current state information of the second vehicle when observing that there is a second vehicle in the second lane that is changing lanes to the middle lane. current status information;
  • the control unit is further configured to determine the target driving action of the first vehicle according to the current state information of the first vehicle and the current state information of the second vehicle, and control the first vehicle to execute the Target driving action.
  • the embodiment of the present application provides a computer device, the computer device includes a processor and a computer storage medium, wherein the computer storage medium is used to store one or more instructions, when the one or more instructions When the instructions are executed by the processor, the above vehicle control method is realized.
  • an embodiment of the present application provides a computer storage medium, the computer storage medium stores one or more instructions, and the one or more instructions are suitable for being loaded by a processor and executing the above vehicle control method.
  • an embodiment of the present application provides a computer program product, which includes a computer program; when the computer program is executed by a processor, the above-mentioned vehicle control method is implemented.
  • Fig. 1a is a schematic diagram of vehicles in the left and right lanes changing lanes to the middle lane at the same time provided by the embodiment of the present application;
  • Figure 1b is a schematic diagram of a front car and a rear car of any vehicle provided by the embodiment of the present application;
  • Fig. 1c is a schematic diagram of an enlarged field of view for lateral inspection of any vehicle in a lane-changing state provided by an embodiment of the present application;
  • Fig. 1d is a schematic diagram of a vehicle changing lanes according to an embodiment of the present application.
  • Fig. 2 is a schematic flow chart of a vehicle control method provided by an embodiment of the present application
  • Fig. 3a is a schematic diagram of the position of a first cross-lane detection line provided by an embodiment of the present application.
  • Fig. 3b is a schematic diagram of a head angle closest to the middle lane among the head angles of a first vehicle provided by an embodiment of the present application;
  • Fig. 3c is a schematic diagram of the positional relationship between the reference point of the first vehicle and the first cross-lane detection line provided by the embodiment of the present application;
  • Fig. 4 is a schematic flowchart of a vehicle control method provided by another embodiment of the present application.
  • Fig. 5a is a schematic diagram of a first vehicle performing a target driving action according to an embodiment of the present application
  • Fig. 5b is a schematic diagram of another first vehicle performing a target driving action according to an embodiment of the present application.
  • Fig. 5c is a schematic diagram of yet another first vehicle performing a target driving action according to an embodiment of the present application.
  • Fig. 6a is an application scene diagram of a vehicle control method provided by an embodiment of the present application.
  • Fig. 6b is a schematic flowchart of a decision logic for a vehicle to perform lane-changing behavior provided by an embodiment of the present application
  • Fig. 7 is a schematic structural diagram of a vehicle control device provided by an embodiment of the present application.
  • Fig. 8 is a schematic structural diagram of a computer device provided by an embodiment of the present application.
  • Artificial Intelligence is a theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.
  • artificial intelligence is a comprehensive technique of computer science that attempts to understand the nature of intelligence and produce a new kind of intelligent machine that can respond in a similar way to human intelligence.
  • Artificial intelligence is to study the design principles and implementation methods of various intelligent machines, so that the machines have the functions of perception, reasoning and decision-making.
  • Artificial intelligence technology is a comprehensive subject that involves a wide range of fields, including both hardware-level technology and software-level technology.
  • Artificial intelligence basic technologies generally include technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing technology, operation/interaction systems, and mechatronics.
  • automatic driving technology usually includes technologies such as high-precision maps, environmental perception, behavior decision-making, path planning, and motion control.
  • Autonomous driving technology usually includes traffic simulation and real vehicle testing (that is, controlling the vehicle to drive on the actual lane), and traffic simulation, as a zero-risk, fast iterative, reproducible test method, has laid a solid foundation for autonomous driving technology to go on the road. Foundation.
  • traffic simulation can also be called road traffic simulation, which is an important tool for studying complex traffic problems; especially when a system is too complex to be described by a simple and abstract mathematical model, the role of traffic simulation is even more prominent. Traffic simulation can clearly assist in the analysis and prediction of the location and cause of traffic congestion, compare and evaluate the relevant schemes of urban planning, traffic engineering and traffic management, and try to avoid or prepare for the problem before it becomes a reality.
  • traffic simulation technology is a simulation model technology that uses simulation hardware and simulation software to reflect system behavior or process through simulation experiments, with the help of certain numerical calculations and problem solving.
  • FIG. 1a Suppose there are three lanes indicating the same driving direction, respectively lane A, lane B, and lane C from left to right, then there may be a vehicle 11 in lane A and a vehicle 12 in lane C When changing lanes to the middle lane B at the same time.
  • the vehicle in the left lane should let the vehicle in the right lane go first.
  • vehicles in the right lane may also choose to avoid vehicles in the left lane when changing lanes under appropriate circumstances.
  • the left lane refers to the lane located on the left side of the middle lane, such as lane A in Figure 1a; the right lane refers to the lane located on the right side of the middle lane, such as lane C in Figure 1a.
  • the embodiment of the present application proposes a vehicle control method , the vehicle control method can safely and flexibly control the driving behavior of each vehicle by considering the driving behavior of each vehicle changing lanes to the middle lane when the vehicles on the left and right lanes change lanes to the middle lane at the same time, and improve The authenticity of vehicle lane-changing behavior and the safety of vehicle driving.
  • any vehicle In the process of executing the vehicle control method, any vehicle first needs to decide whether to change lanes to the side target lane according to the rule-based lane changing principle.
  • the rule-based lane-changing principle refers to the principle that vehicles need to judge whether they can change lanes based on rules such as lane-changing willingness and safety conditions; it can be seen that vehicles need to judge based on rules such as lane-changing willingness and safety conditions. to initiate and complete a lane change sequence.
  • the safety conditions that need to be considered usually include but are not limited to: the distance G TP between the vehicle and the vehicle in front TP in the target lane must be greater than the preset safety distance G of the vehicle in front SP , and the distance G TR between the self-vehicle and the rear vehicle TR in the target lane must be greater than the preset rear vehicle safety distance G SR ; that is, the safety principle may include: G TP > front vehicle safety distance G SP , and G TR is greater than the rear vehicle safety distance G SR .
  • the front vehicle TP refers to: along the driving direction indicated by the target lane, a vehicle in the target lane that is longitudinally in front of the vehicle and is closest to the vehicle;
  • the following vehicle TR refers to: along the driving direction indicated by the target lane, a vehicle in the target lane that is longitudinally behind the own vehicle and is closest to the own vehicle.
  • the direction parallel to the target lane may be called the longitudinal direction
  • the direction perpendicular to the target lane that is, the direction where the lane normal of the target lane is located
  • any vehicle when any vehicle makes a lane-changing decision, it needs to judge the distance/speed of the front vehicle and the rear vehicle in the target lane on the side, so as to meet the lane-changing willingness and safety conditions. Lateral movement to the target lane can be initiated. After moving laterally for a certain distance, any vehicle in the lane-changing state can expand the field of vision for lateral inspection to ensure that it is aware of the roads involved in the lane-changing path trajectory and the other lane on the other side of the target lane, such as Figure 1c shows.
  • any vehicle detects that there is a vehicle X in the other lane that is also in the state of changing lanes to the target lane, it can make different driving actions according to the state information such as the position and speed of the vehicle X. Judgment, so that any vehicle executes the corresponding driving action. For example, referring to Figure 1d, if the A car in the left lane and the B car in the right lane are changing lanes to the middle lane (i.e. the aforementioned target lane), then the A car and the B car In the process of changing lanes, not only the state information such as the position and speed of the front car C and the rear car D in the middle lane must be considered, but also the relationship between the other lane and its own lane-changing competition should be considered.
  • the state information of the vehicle so as to perform corresponding driving actions according to each state information.
  • the lane on the other side is the right lane in Figure 1d
  • the relevant vehicle that has a lane-changing competition relationship with car A is car B
  • the lane on the other side is In the left lane in Figure 1d
  • the relevant vehicle that has a lane-changing competition relationship with vehicle B is vehicle A.
  • the vehicle control method proposed in the embodiment of the present application can be executed by a computer device, which can be a terminal or a server; or, the vehicle control method proposed in the embodiment of the present application can also be executed jointly by the terminal and the server, which is not limited .
  • a computer device which can be a terminal or a server
  • the vehicle control method proposed in the embodiment of the present application can also be executed jointly by the terminal and the server, which is not limited .
  • the following descriptions will be made by taking the computer equipment to execute the vehicle control method as an example.
  • the terminals mentioned here may include but are not limited to: smart phones, tablet computers, notebook computers, desktop computers, smart watches, smart TVs, smart vehicle terminals, etc.; the server may be an independent physical server, or multiple A server cluster or distributed system composed of several physical servers can also provide cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content distribution networks (Content Delivery Network, CDN), and cloud servers for basic cloud computing services such as big data and artificial intelligence platforms, etc.
  • CDN Content Delivery Network
  • the vehicle control method proposed in the embodiment of the present application can be applied in the actual vehicle test process of automatic driving, so that the vehicle can be controlled by the vehicle control method to safely and flexibly perform lane changing behavior in the process of automatic driving.
  • the vehicle control method can also be used in the traffic simulation process of automatic driving; in this case, the computer equipment can at least include simulation software.
  • the simulation software mentioned here can be a kind of micro-traffic simulation software (TAD Sim), and this micro-traffic simulation software can include but not limited to the simulation software that needs networking or the simulation software that does not need networking; it can be understood that traffic Simulation is divided into macro simulation, meso simulation and micro simulation according to the accuracy and scope of simulation.
  • TAD Sim micro-traffic simulation software
  • Micro traffic simulation takes the behavior of individual vehicles as the research object and describes the simulation of the state of each vehicle in the traffic system.
  • the logic algorithm involved in the vehicle control method can be embedded in the simulation software, so as to be used for the lane-changing behavior performed when the vehicles in the left and right lanes simultaneously change lanes to the middle lane Carry out simulation; that is to say, when any vehicle needs to change lanes from the two lanes to the middle lane, the logic algorithm involved in the vehicle control method proposed in the embodiment of the present application can be used to simulate its lane changing behavior, so as to Simulate the complex interaction between vehicles to simulate more realistic driving behavior, improve the authenticity of the simulation results and the degree of conformity between the simulation results and the actual situation.
  • the logic algorithm involved in the vehicle control method can be exited.
  • the vehicle control method proposed in the embodiment of the present application will be further elaborated below in conjunction with the schematic flowchart shown in FIG. 2 .
  • the vehicle control method can be executed by the computer device shown in FIG. 8, including the following steps S201-S205:
  • the road area where the first lane is located also includes: a second lane and a middle lane between the first lane and the second lane. And, both the second lane and the middle lane are in the same direction as the first lane; that is to say, the driving directions indicated by the first lane, the second lane and the middle lane are the same. It should be noted that, viewed along the driving direction indicated by the middle lane, the first lane may be located on the left side of the middle lane or on the right side of the middle lane, which is not limited.
  • the second lane can be the lane on the right side of the middle lane; when the second lane is the lane on the left side of the middle lane, the first lane can be on the right side of the middle lane side driveway.
  • the first vehicle may be any simulated vehicle in the traffic simulation process, or any vehicle in an automatic driving state during the actual vehicle test process, which is not limited.
  • controlling the first vehicle to travel on the first lane specifically, it may be to control the first vehicle to travel along the lane centerline of the first lane (hereinafter referred to as the first lane centerline); or, to control the first vehicle to travel in the first lane driving in places other than the centerline of the first lane, etc.
  • the lane centerline refers to a line located in the middle of the lane, that is, the distance between the lane centerline and the left boundary of the lane is equal to the distance between the lane centerline and the right boundary of the lane.
  • the computer device may select the vehicle that is longitudinally in front of the first vehicle and closest to the first vehicle from all the vehicles in the middle lane as the vehicle of the first vehicle.
  • the target front vehicle and, selecting the vehicle that is longitudinally behind the first vehicle and closest to the first vehicle as the target rear vehicle of the first vehicle.
  • the first vehicle may be controlled to change lanes in the middle lane; if it is determined that the first vehicle does not meet the safety conditions, the first vehicle may be controlled to continue driving in the first lane.
  • the lane-changing behavior of the vehicle is mainly determined by the longitudinal driving behavior and the lateral driving behavior, which can be considered separately; wherein, the longitudinal driving behavior can be determined by the car-following (car-following) algorithm, and the lateral driving behavior can be determined by A rule-based lane-changing algorithm is described. Based on this, when the computer device controls the first vehicle to change lanes to the middle lane, it can use the car-following (car-following) algorithm to calculate the longitudinal direction of the first vehicle in the middle lane according to the target vehicle in the longitudinal direction.
  • longitudinal driving parameters can include maximum driving speed and minimum safe distance between vehicles; the so-called maximum driving speed is used to indicate the maximum speed that the vehicle cannot exceed during driving (such as road speed limit), and the minimum safe distance between vehicles is used to represent The minimum inter-vehicle distance to be maintained at all times while driving.
  • the computer device can also use the initial state and the final state in the lateral direction to plan the lateral driving parameters of the first vehicle in the process of driving to the middle lane. track etc. After calculating the longitudinal driving parameters and corresponding lateral driving parameters of the first vehicle in the process of driving to the middle lane, the computer device can control the first vehicle to change to the middle lane according to the calculated longitudinal driving parameters and corresponding lateral driving parameters. drive.
  • the lateral driving parameters can be calculated by computer equipment by adopting a quintic polynomial solution; that is, the initial state (0, 0, 0) and the end state (H, 0, 0) are given, and the computer equipment can be The coefficients of the quintic polynomial are calculated according to the initial state and the final state, so as to deduce the lateral speed and moving trajectory of the first vehicle during the process of the first vehicle changing lanes to the middle lane.
  • the parameters of the initial state (0, 0, 0) describe in turn the initial moment when the first vehicle moves to the middle lane, the position, velocity and acceleration of the first vehicle in the lateral direction; the final state (H, 0, 0) To describe in turn the end moment of the first vehicle moving to the middle lane (that is, the moment when the first vehicle changes lanes to the middle lane), the position, velocity and acceleration of the first vehicle in the lateral direction, H is equal to the first vehicle at The lateral distance between the position before the lane change and the lane centerline of the middle lane (may be referred to as the centerline of the middle lane).
  • the computer device may start to observe the second lane when the first vehicle starts to enter the lane-changing process (that is, when the moving speed of the first vehicle in the lateral direction starts to be greater than 0).
  • the computer device may also start to observe the second lane in real time or periodically during the lane-changing driving process of the first vehicle after entering the lane-changing process for a certain period of time.
  • the computer device may also determine the first lane-crossing detection line in the first lane during the lane-changing driving process of the first vehicle.
  • the first cross-lane detection line mentioned here refers to the cross-lane detection line located in the first lane.
  • the so-called cross-lane detection line refers to a virtual line parallel to the lane and used to trigger the observation of the other lane.
  • a virtual line is a line that is virtualized in the lane and does not exist in the real world.
  • the first cross-lane awareness line may be located between the first lane dividing line and the target driving line.
  • the so-called first lane dividing line refers to the lane dividing line between the first lane and the middle lane (that is, used to separate different lane markings).
  • the so-called target driving line refers to the line along which the first vehicle travels in the first lane before starting to change lanes; for example, the first vehicle travels along the centerline of the first lane before starting to change lanes, then The target driving line may be the center line of the first lane.
  • the schematic diagram of the position of the first lane-crossing detection line can be referred to in FIG. 3a.
  • the second cross-lane detection line in FIG. 3 a refers to the cross-lane detection line located in the second lane
  • the second lane centerline refers to the lane centerline of the second lane.
  • the embodiment of the present application does not limit the manner of determining the distance Do between the first lane-crossing detection line and the first lane separation line.
  • the distance Do between the first lane-crossing detection line and the first lane dividing line can be randomly and dynamically determined, as long as the distance is smaller than the distance between the target driving line and the first lane dividing line.
  • the computer equipment can introduce the aggressiveness of the vehicle, so as to determine the distance between the cross-lane detection line and the lane dividing line through a function related to the aggressiveness; wherein, the aggressiveness of the vehicle can use a (0, 1) to represent the floating point number A, 0 represents the most conservative type, 1 represents the most aggressive type.
  • the first lane-crossing detection line may be determined according to the aggressiveness of the first vehicle; and as the aggressiveness of the first vehicle is higher, the distance between the first lane-crossing detection line and the first lane separation line is Small.
  • the embodiment of the present application does not limit the setting method of the aggressiveness of the vehicle. For example, for the simulated vehicle in the simulation software, the simulated vehicle can be given a random fixed aggressiveness parameter at the beginning of the simulation. , to indicate the aggressiveness of the simulated vehicle; and, the aggressiveness of different simulated vehicles can be set separately according to the driving behavior in the simulated area they require.
  • the computer device may detect a positional relationship between the first vehicle and the first lane-crossing awareness line. If it is detected that the first vehicle does not travel to the first cross-lane awareness line, the first vehicle can be controlled to continue to change lanes to the middle lane; if it is detected that the first vehicle travels to the first cross-lane detection line, or the When a vehicle passes the first lane-crossing detection line, it starts to observe the second lane. In one embodiment, the computer device can detect the positional relationship between the entire vehicle body on the first vehicle and the first lane-crossing detection line to determine whether the first vehicle has driven to or passed the first lane-crossing detection line.
  • the computer device can define a reference point (or referred to as a reference point) for the first vehicle, so as to determine the positional relationship between the reference point of the first vehicle and the first cross-lane detection line. Whether the first vehicle travels to or passes the first cross-lane detection line. That is, in this embodiment, the first vehicle traveling to the first cross-lane detection line may include: the reference point of the first vehicle is located on the first cross-lane detection line; or, the first vehicle passing the first cross-lane detection line includes : The reference point of the first vehicle faces the direction of the middle lane and crosses the first lane-crossing detection line.
  • the reference point of the first vehicle crosses (that is, crosses) the first cross-lane awareness line, it starts to observe the other side lane (ie, the second lane) of the middle lane; Before the reference point of the first vehicle crosses the first cross-lane detection line, it may be considered that the first vehicle is not aware of the need to observe the other side lane of the middle lane.
  • the reference point of the first vehicle may include: the center of mass of the first vehicle, or the head angle of the first vehicle that is closest to the middle lane among the head angles of the first vehicle. See the left and right sides of Fig. 3b: when the first lane where the first vehicle is located is located on the left side of the middle lane, since the front of the first vehicle needs to turn to the right to change lanes to the middle lane, the first vehicle The right head angle of the first vehicle is closest to the middle lane, then the reference point of the first vehicle in this case may include the right head angle of the first vehicle; when the first lane where the first vehicle is located is on the right side of the middle lane, since the The front of a vehicle needs to turn to the left to change lanes to the middle lane, so that the left head angle of the first vehicle is closest to the middle lane.
  • the reference point of the first vehicle may include the left head angle of the first vehicle. Based on this, taking the reference point of the first vehicle including the right head angle of the first vehicle as an example, the reference point of the first vehicle is located in the schematic diagram of the first cross-lane detection line and the reference point of the first vehicle crosses the first cross-lane detection line The schematic diagrams on the line can be respectively shown in the left and right diagrams in Fig. 3c.
  • the current state information of the first vehicle refers to the state information of the first vehicle when the second vehicle is observed in the second lane; similarly, the current state information of the second vehicle refers to: when the second vehicle is observed When the second vehicle exists in the second lane, the status information of the second vehicle.
  • any current state information may include state data obtained under one or more state dimensions, and the one or more state dimensions may be set according to actual needs or experience values, such as one or more state dimensions may include position and orientation dimensions , the longitudinal distance dimension, the transverse distance dimension, the relative velocity dimension, and so on.
  • the first state data may include: the position and orientation of the first lane where the first vehicle is located relative to the middle lane (such as a left orientation or a right orientation);
  • the second status data includes: the position and orientation of the second lane where the second vehicle is located relative to the middle lane.
  • the first state data may include: the longitudinal distance between the current position of the first vehicle and a reference point in the road area;
  • the second state data may include: the current position of the second vehicle The longitudinal distance between the position and the reference point.
  • the current position of the first vehicle (or the second vehicle) refers to: when the second vehicle is observed in the second lane, the specified point (such as the center of mass, the head, the rear of the vehicle) of the first vehicle (or the second vehicle) etc.) in the road area;
  • the reference point can be a point set in the road area according to actual needs, for example, the reference point can be a point located behind the first vehicle and the second vehicle, specifically, for example, in the road area
  • the reference point is the point behind the first vehicle and the second vehicle as an example.
  • the first state data may include: the lateral distance between the current position of the first vehicle and the lane centerline of the middle lane; the second state data may include: the current position of the second vehicle The lateral distance between the location and the lane centerline of the middle lane.
  • both the first state data and the second state data may include: a relative speed between the current speed of the first vehicle and the current speed of the second vehicle; wherein the relative speed It may be calculated based on the current speed of the first vehicle, or may be calculated based on the current speed of the second vehicle, which is not limited.
  • the computer device can introduce the scoring system into the interactive decision-making process between vehicles in the state of changing lanes in the lanes on both sides, so as to simulate the complex interaction between vehicles, so that the final determined target driving action is closer to the Real, that is, to improve the accuracy and authenticity of the target driving action.
  • the computer device may first score the lane-changing priority of the first vehicle and the second vehicle according to the current state information of the first vehicle and the current state information of the second vehicle, and obtain the lane-changing priority score and The lane change priority score for the second vehicle. Then, by comparing the magnitude relationship between the lane-changing priority score of the first vehicle and the lane-changing priority score of the second vehicle, the target driving behavior of the first vehicle is determined.
  • the lane change priority score of the first vehicle is greater than the lane change priority score of the second vehicle, it can indicate that the first vehicle can change lanes to the middle lane first, that is, the first vehicle is allowed to change lanes to the middle lane before the second vehicle , then the action of continuing to change lanes to the middle lane can be determined as the target driving action of the first vehicle. If the lane change priority score of the first vehicle is less than the lane change priority score of the second vehicle, it can indicate that the second vehicle can change lanes to the middle lane first, that is, the second vehicle is allowed to change lanes to the middle lane before the first vehicle , then canceling the action of changing lanes to the middle lane can be determined as the target driving action of the first vehicle.
  • the lane-changing priority score of the first vehicle is equal to the lane-changing priority score of the second vehicle, it can be further determined whether the position orientation of the first lane where the first vehicle is located relative to the middle lane is the leading orientation; if so, allow The first vehicle changes lanes to the middle lane before the second vehicle, then the action of continuing to change lanes to the middle lane can be determined as the target driving action of the first vehicle; otherwise, cancel the action of changing lanes to the middle lane The action is determined as the target driving action of the first vehicle.
  • the advance orientation mentioned here can be set according to experience or actual needs.
  • the right direction of the middle lane can be determined as the leading direction; If the side vehicle has the right of way, it can determine the left direction of the middle lane as the leading direction along the driving direction.
  • any current state information may include state data obtained under one or more state dimensions; based on this, corresponding dimension priorities may be set in advance for each state dimension . Then, when determining the target driving action of the first vehicle, the computer device can select a state dimension from the unselected state dimensions as the reference state dimension according to the dimension priority of each state dimension in the order of dimension priority from high to low . Secondly, the state data in the reference state dimension is obtained from the current state information of the first vehicle as the reference state data, and the state data in the reference state dimension is obtained from the current state information of the second vehicle as the reference state data. Then, the computer device can select the leading vehicle from the first vehicle and the second vehicle according to the reference state data and the reference state data. in:
  • the reference state dimension is the position and orientation dimension
  • the reference state data is the position and orientation of the first lane where the first vehicle is located relative to the middle lane
  • the reference state data is the position and orientation of the second lane where the second vehicle is located relative to the middle lane. location orientation.
  • the way of selecting the leading vehicle can be: if the position and orientation of the first lane where the first vehicle is located relative to the middle lane is the leading direction, then select the first vehicle as the leading vehicle; otherwise, select the second vehicle as the leading vehicle.
  • the reference state dimension is the longitudinal distance dimension
  • the reference state data is the longitudinal distance between the current position of the first vehicle and the reference point in the road area
  • the reference state data is the distance between the current position of the second vehicle and the reference point vertical distance.
  • the reference state data is the lateral distance between the current position of the first vehicle and the lane centerline of the middle lane, and the reference state data is the current position of the second vehicle and the lane center of the middle lane The lateral distance between lines.
  • the way to select the leading vehicle can be: if the reference state data is equal to the reference state data, it is determined that the selection of the leading vehicle fails; if the reference state data is smaller than the reference state data, it indicates that the first vehicle is closer to the middle lane, so the first vehicle can be selected The vehicle is used as the leading vehicle; if the reference state data is greater than the reference state data, it indicates that the second vehicle is closer to the middle lane, so the second vehicle can be selected as the leading vehicle.
  • both the reference state data and the reference state data are relative speeds between the current speed of the first vehicle and the current speed of the second vehicle. Then the way to select the leading vehicle can be: if the relative speed is equal to 0, it means that the first vehicle and the second vehicle have the same speed, and at this time it can be determined that the selection of the leading vehicle has failed. If the relative speed is not equal to 0, a vehicle with a higher speed is selected from the first vehicle and the second vehicle based on the relative speed as the preceding vehicle.
  • the computer device selects the preceding vehicle from the first vehicle and the second vehicle according to the reference state data and the reference state data, it may successfully select the preceding vehicle, or it may fail to select the preceding vehicle.
  • the computer equipment can further judge whether the first vehicle is the leading vehicle; when the first vehicle is the leading vehicle, the action of continuing to change lanes in the middle lane can be determined as the first The target driving action of the vehicle; when the first vehicle is not the preceding vehicle, canceling the action of changing lanes to the middle lane may be determined as the target driving action of the first vehicle.
  • the computer device can again execute according to the dimension priority of each state dimension, and select a state dimension from the unselected state dimensions as the reference state dimension in the order of dimension priority from high to low. step to reselect the preceding vehicle.
  • the embodiment of the present application also proposes a vehicle control method as shown in Figure 4; illustrate.
  • the vehicle control method may include the following steps S401-S407:
  • Control the first vehicle to travel on the first lane, where the road area where the first lane is located further includes: a second lane and a middle lane between the first lane and the second lane.
  • a lane change detection speed Vo can be introduced to assist in judging whether there is a second vehicle in the second lane that is changing lanes to the middle lane. Specifically, first observe whether there is a vehicle in the second lane; in the case of observing that there is a vehicle in the second lane, the lateral velocity of the existing vehicle can be further determined, and the size between the lateral velocity and the lane change detection speed can be judged relation.
  • the existing vehicle is in the state of changing lanes to the middle lane, and the existing vehicle is determined to be the second vehicle in the second lane to change lanes to the middle lane; if If the lateral speed is less than or equal to the lane change detection speed, it is determined that the existing vehicle does not change lanes to the middle lane, and it is determined that there is no second vehicle in the second lane that changes lanes to the middle lane.
  • the lane-changing detection speed refers to a speed used to measure whether the vehicle is in a lane-changing state, and the embodiment of the present application does not limit the determination method of the lane-changing detection speed.
  • the detection speed of changing lanes can be pre-set according to experience values.
  • the computer device can introduce the aggressiveness of the vehicle, so as to determine the lane-changing awareness speed corresponding to the corresponding vehicle through a function related to the aggressiveness. In this way, each vehicle may have a different lane-changing awareness speed.
  • the lane change awareness speed corresponding to the first vehicle may be determined according to the aggressiveness of the first vehicle, and the lane change awareness speed is proportional to the aggressiveness of the first vehicle. That is to say, the more aggressive the first vehicle is, the greater the lane-changing detection speed is, and when the lateral speed of the second vehicle is greater than the lane-changing detection speed, the second vehicle is considered to be changing lanes.
  • the computer device may not judge whether there is a second vehicle in the second lane changing lanes to the middle lane based on the detection speed of the lane change, but may judge based on the state of the turn signal of the vehicle. Specifically, when the computer device observes that there is a vehicle in the second lane, it can acquire the state of the target turn signal of the existing vehicle approaching the middle lane.
  • the state of the target turning signal is turned on, it is determined that the existing vehicle is in the state of changing lanes to the middle lane, and the existing vehicle is determined as the second vehicle in the second lane to change lanes to the middle lane; If the state of the target turn signal is off, it is determined that the existing vehicle does not change lanes to the middle lane, and it is determined that there is no second vehicle that changes lanes to the middle lane in the second lane.
  • any current state information includes: state data under one or more state dimensions; correspondingly, the specific implementation manner of step S405 may be: s11, traversing each of the current state information of the first vehicle
  • the state data under the state dimension determines the first state data currently traversed, and the state dimension where the first state data is located is the current state dimension.
  • s12 The state data in the current state dimension in the current state information of the second vehicle may be used as the second state data.
  • s13 according to the lane-changing priority scoring strategy corresponding to the current state dimension, according to the first state data and the second state data, score the score of the first vehicle in the current state dimension, and the score of the second vehicle in the current state dimension under the score.
  • the lane change priority score of the first vehicle may be determined based on the scores of the first vehicle in each state dimension; and, A lane-changing priority score of the second vehicle is determined based on the scores of the second vehicle in each state dimension.
  • weighted summation or weighted average may be performed on the scores of any vehicle (ie, the first vehicle or the second vehicle) in each state dimension to obtain the lane-changing priority score of any vehicle. It can be seen that the scoring results obtained through this embodiment include: the lane-changing priority score of the first vehicle and the lane-changing priority score of the second vehicle.
  • the specific implementation manner of step s12 may be: if the position orientation in the first state data is the leading orientation, then determine the first score as the score of the first vehicle in the current state dimension, and determine the second score as the first Second, the score of the vehicle in the current state dimension. Wherein, the first score is greater than the second score; for example, the first score is 1 and the second score is 0, or the first score is 2 and the second score is 0, etc.
  • the position orientation in the second state data is the leading orientation
  • the second score is determined as the score of the first vehicle in the current state dimension
  • the first score is determined as the score of the second vehicle in the current state dimension.
  • the first state data includes: the longitudinal distance between the current position of the first vehicle and the reference point in the road area; the second state data includes: the current position of the second vehicle and Vertical distance between datum points.
  • a specific implementation manner of step s12 may be: performing a difference operation on the longitudinal distance in the first state data and the longitudinal distance in the second state data to obtain a difference in the longitudinal distance. If the longitudinal distance difference is greater than the longitudinal difference threshold (such as a value of 0, a value of 0.5, etc.), the third score can be determined as the score of the first vehicle in the current state dimension, and the fourth score can be determined as the score of the second vehicle in the current state dimension. Score under the current state dimension.
  • the third score is greater than the fourth score; for example, the third score is 1 and the fourth score is 0, or the third score is 3 and the fourth score is 1, etc.
  • the fourth score can be determined as the score of the first vehicle in the current state dimension
  • the third score can be determined as the score of the second vehicle in the current state dimension .
  • the longitudinal distance difference is equal to the longitudinal difference threshold, it can be further judged whether the position orientation of the first lane relative to the middle lane is the leading orientation; if so, the third score is determined as the score of the first vehicle in the current state dimension, And the fourth score is determined as the score of the second vehicle in the current state dimension; if not, the fourth score is determined as the score of the first vehicle in the current state dimension, and the third score is determined as the score of the second vehicle in Score under the current state dimension.
  • step s12 may also be: comparing the vertical distance in the first state data with the vertical distance in the second state data. If the longitudinal distance in the first state data is greater than the longitudinal distance in the second state data, it indicates that the first vehicle is ahead in the longitudinal direction than the second vehicle, that is, the head of the first vehicle is ahead of the head of the second vehicle, so it can be The third score is determined as the first vehicle's score in the current state dimension, and the fourth score is determined as the second vehicle's score in the current state dimension.
  • a fourth score is determined as the first vehicle's score in the current state dimension, and a third score is determined as the second vehicle's score in the current state dimension.
  • the longitudinal distance in the first state data is equal to the longitudinal distance in the second state data, it can be further judged whether the position orientation of the first lane relative to the middle lane is the leading orientation; if so, then the third score is determined as the first vehicle score in the current state dimension, and determine the fourth score as the score of the second vehicle in the current state dimension; if not, determine the fourth score as the score of the first vehicle in the current state dimension, and set the fourth score A score of three is determined as the score of the second vehicle in the current state dimension.
  • the specific implementation manner of step s12 may be: performing difference calculation on the lateral distance in the first state data and the lateral distance in the second state data to obtain the lateral distance difference (such as numerical value 0, numerical value 0.5, etc.); if If the lateral distance difference is greater than the lateral difference threshold, the fifth score is determined as the score of the first vehicle in the current state dimension, and the sixth score is determined as the score of the second vehicle in the current state dimension.
  • the fifth score is smaller than the sixth score; for example, the fifth score is 0, the sixth score is 1, and so on.
  • the sixth score is determined as the score of the first vehicle in the current state dimension
  • the fifth score is determined as the score of the second vehicle in the current state dimension.
  • the lateral distance difference is equal to the lateral difference threshold, it can be further judged whether the position orientation of the first lane relative to the middle lane is the leading orientation; if so, the sixth score is determined as the score of the first vehicle in the current state dimension, And the fifth score is determined as the score of the second vehicle in the current state dimension; if not, the fifth score is determined as the score of the first vehicle in the current state dimension, and the sixth score is determined as the score of the second vehicle in Score under the current state dimension.
  • step s12 may also be: comparing the lateral distance in the first state data with the horizontal distance in the second state data. If the lateral distance in the first state data is greater than the lateral distance in the second state data, it indicates that the second vehicle is closer to the middle lane than the first vehicle, so the fifth score can be determined as the first vehicle's current state dimension score, and determine the sixth score as the score of the second vehicle in the current state dimension.
  • the sixth score can be determined as the first vehicle’s current state dimension score, and determine the fifth score as the score of the second vehicle in the current state dimension.
  • the lateral distance in the first state data is equal to the lateral distance in the second state data, it can be further judged whether the position orientation of the first lane relative to the middle lane is the leading orientation; if so, then the sixth score is determined as the first vehicle score in the current state dimension, and determine the fifth score as the score of the second vehicle in the current state dimension; if not, determine the fifth score as the score of the first vehicle in the current state dimension, and set the fifth score A score of six is determined as the score of the second vehicle in the current state dimension.
  • step S406 may be: according to the lane-changing priority score of the first vehicle and the lane-changing priority score of the second vehicle, select the lane-changing priority score from the first vehicle and the second vehicle to be greater than
  • the vehicle with the score threshold is regarded as the vehicle with the right of way to change lanes to the middle lane.
  • step S406 may be: according to the lane-changing priority score of the first vehicle and the lane-changing priority score of the second vehicle, select a larger lane-changing priority from the first vehicle and the second vehicle
  • the vehicle corresponding to the score is regarded as the vehicle having the right of way to change lanes to the middle lane.
  • S407. Determine the target driving action of the first vehicle according to the selection result, and control the first vehicle to execute the target driving action.
  • the computer device during the process of determining the target driving action of the first vehicle according to the selection result, if the selection result includes the first vehicle, the computer device will continue to change lanes to the middle lane and determine it as the target driving action of the first vehicle. The target driving action; if the selection result includes the second vehicle, the action of changing lanes to the middle lane will be canceled and determined as the target driving action of the first vehicle.
  • canceling the action of changing lanes to the middle lane may include: changing back to the target driving line of the first vehicle (the line along which the first vehicle travels in the first lane before starting to change lanes); In this case, taking the target driving line as the centerline of the first lane as an example, the schematic diagram of the first vehicle performing the target driving action can be referred to as shown in FIG. 5 a .
  • canceling the action of changing lanes to the middle lane may include: an action of decelerating along the first cross-lane detection line; in this case, the schematic diagram of the first vehicle performing the target driving action can be referred to as shown in FIG. 5b.
  • canceling the action of changing lanes to the middle lane may include: stopping and waiting; in this case, the schematic diagram of the first vehicle performing the target driving action can be referred to as shown in FIG. 5c.
  • a virtual line (cross-lane awareness line) parallel to the lane is proposed, and the lane change awareness speed is introduced to simulate the driver's behavior , and introduce the scoring system into the interactive decision-making process between lane-changing vehicles on both sides to simulate complex interactions between vehicles, which can simulate more realistic driving behaviors, thus making lane-changing behaviors closer to reality.
  • the target driving action can be made safer, In this way, the safety of vehicle driving can be further improved; on the other hand, with the difference of the current state information of the first vehicle and the second vehicle, the determined target driving actions are also different, which can make the first vehicle
  • the method is not limited to one driving action, and can improve the flexibility of the lane changing behavior of the first vehicle, thereby improving the driving safety of the vehicle.
  • car A After car A decides to change lanes to the middle lane, it can start the lane change process; and during the lane change process, it can judge in real time whether the lane change has been completed. If the lane change is not completed, it can be detected whether the reference point of car A crosses the cross-lane awareness line in the left lane. If not, you can continue to change lanes to the middle lane; if you have crossed, you can observe whether there is a vehicle with a lateral speed greater than the lane change detection speed in the other lane (ie, the right lane).
  • car A can determine the lateral speed of car B; in the eyes of car A, only the lateral speed of car B in the other lane is greater than the perceived speed of lane change, then It will be considered that car B is changing lanes. At this time, it can be considered that there is a lane-changing competition between car A and car B in the left and right lanes.
  • the lane-changing priority score of car A and the lane-changing priority score of car B are calculated. Specifically, when the lane change has not started, the lane change priority scores of car A and car B are both 0 points. After the start of the lane change, since the Chinese traffic rules stipulate that the car in the right lane has the right of way in this situation, you can first score 1 point for car B in the right lane, and 0 for car A in the left lane. points to give the vehicle on the right a certain priority advantage. Then, cars A and B can be scored according to other lane-changing priority scoring strategies, as follows:
  • ⁇ Dy can be defined as the distance of the reference point of car A in the direction of the lane (that is, the longitudinal distance between the current position of car A and the reference point in the road area) minus the distance of the reference point of car B in the direction of the lane distance (that is, the longitudinal distance between the current position of car B and the reference point in the road area); then, scoring can be performed according to the following logic:
  • Dxa and Dxb are defined as the distance from the reference point of car A and the reference point of car B to the centerline of the middle lane in the normal direction of the lane, that is, Dxa is the distance between the current position of car A and the centerline of the middle lane.
  • the judgment of the lane-changing vehicle on the other side lane during the lane-changing process is a continuous process, that is, There is a situation where car B finds that car A is changing lanes, and car B thinks it has priority and continues to change lanes.
  • the judgment process is a continuous process, that is, when the car A mentioned here also crosses the cross-lane awareness line (and realizes that the lateral speed of the car B is greater than Vo), it will observe each other with the car B, and apply the above scoring at the same time Logic is used to judge which of the two vehicles has priority.
  • the vehicle control device may be a computer program (including program code) running on a computer device.
  • the vehicle control device can execute the vehicle control methods shown in FIG. 2 and FIG. 4 . Referring to Figure 7, the vehicle control device can operate the following units:
  • the control unit 701 is configured to control the first vehicle to drive on the first lane, and the road area where the first lane is located also includes: a second lane and a vehicle located in the middle between the first lane and the second lane Lane; wherein, both the second lane and the middle lane are in the same direction as the first lane;
  • the control unit 701 is further configured to control the first vehicle to change lanes to the middle lane if the first vehicle intends to change lanes to the middle lane;
  • a processing unit 702 configured to observe the second lane during the lane changing of the first vehicle
  • the processing unit 702 is further configured to determine the current state information of the first vehicle and the second vehicle's current state information of
  • the control unit 701 is further configured to determine the target driving action of the first vehicle according to the current state information of the first vehicle and the current state information of the second vehicle, and control the first vehicle to execute the Describe the target driving behavior.
  • processing unit 702 when used to observe the second lane during the lane-changing driving process of the first vehicle, it may be specifically used to:
  • the first cross-lane awareness line is located between the first lane dividing line and the target driving line;
  • the first lane dividing line refers to the lane dividing line between the first lane and the middle lane, so
  • the target driving line refers to a line along which the first vehicle travels in the first lane before starting to change lanes.
  • processing unit 702 may also be used to:
  • the existing vehicle is in the state of changing lanes to the middle lane, and the existing vehicle is determined to be in the second lane to the middle A second vehicle traveling in a lane change;
  • the lateral speed is less than or equal to the lane change detection speed, then determine that the existing vehicle does not change lanes to the middle lane, and determine that there is no change to the middle lane in the second lane A second vehicle traveling on the road.
  • control unit 701 when used to determine the target driving action of the first vehicle according to the current state information of the first vehicle and the current state information of the second vehicle, it may be specifically used to :
  • the target driving action of the first vehicle is determined according to the selection result.
  • the scoring result includes the lane-changing priority score of the first vehicle and the lane-changing priority score of the second vehicle; correspondingly, the control unit 701 is used to From the first vehicle and the second vehicle, when selecting the vehicle having the right of way to change lanes to the middle lane, it can be specifically used for:
  • the vehicle corresponding to the larger lane-changing priority score from the first vehicle and the second vehicle.
  • a vehicle as a vehicle having the right of way to change lanes to the middle lane.
  • control unit 701 when used to determine the target driving action of the first vehicle according to the selection result, it may be specifically used for:
  • the selection result includes the first vehicle, continue to change lanes to the middle lane, and determine it as the target driving action of the first vehicle;
  • the action of changing lanes to the middle lane will be canceled and determined as the target driving action of the first vehicle.
  • any current state information includes: state data in one or more state dimensions; the scoring results include: the lane-changing priority score of the first vehicle and the lane-changing priority score of the second vehicle. channel priority score;
  • control unit 701 is configured to perform lane-changing priority scores on the first vehicle and the second vehicle according to the current state information of the first vehicle and the current state information of the second vehicle, and obtain When scoring results, it can be used specifically for:
  • the scores of the first vehicle in the current state dimension are obtained by scoring, and the score of the second vehicle in the current state dimension;
  • the current state dimension includes a position and orientation dimension
  • the first state data includes: the position and orientation of the first lane where the first vehicle is located relative to the middle lane
  • the second The status data includes: the position and orientation of the second lane where the second vehicle is located relative to the middle lane
  • control unit 701 is used to obtain the lane change priority scoring strategy corresponding to the current state dimension according to the first state data and the second state data to obtain the score of the first vehicle in the current state.
  • the score under the state dimension, and the score of the second vehicle under the current state dimension can be specifically used for:
  • the position orientation in the first state data is the leading orientation, then determine the first score as the score of the first vehicle in the current state dimension, and determine the second score as the score of the second vehicle in the current state dimension. A score under the current state dimension; wherein, the first score is greater than the second score;
  • the current state dimension includes a longitudinal distance dimension;
  • the first state data includes: the longitudinal distance between the current position of the first vehicle and a reference point in the road area;
  • the The second state data includes: the longitudinal distance between the current position of the second vehicle and the reference point;
  • control unit 701 is used to obtain the lane change priority scoring strategy corresponding to the current state dimension according to the first state data and the second state data to obtain the score of the first vehicle in the current state.
  • the score under the state dimension, and the score of the second vehicle under the current state dimension can be specifically used for:
  • the third score is determined as the score of the first vehicle in the current state dimension
  • the fourth score is determined as the score of the second vehicle in the A score under the current state dimension; wherein, the third score is greater than the fourth score
  • the fourth score is determined as the score of the first vehicle in the current state dimension, and the third score is determined as the A score of the second vehicle in the current state dimension.
  • the current state dimension includes a lateral distance dimension
  • the first state data includes: the lateral distance between the current position of the first vehicle and the lane centerline of the middle lane
  • the The second status data includes: the lateral distance between the current position of the second vehicle and the lane centerline of the middle lane
  • control unit 701 is used to obtain the lane change priority scoring strategy corresponding to the current state dimension according to the first state data and the second state data to obtain the score of the first vehicle in the current state.
  • the score under the state dimension, and the score of the second vehicle under the current state dimension can be specifically used for:
  • the fifth score is determined as the score of the first vehicle in the current state dimension
  • the sixth score is determined as the score of the second vehicle in the A score under the current state dimension; wherein, the fifth score is smaller than the sixth score
  • the sixth score is determined as the score of the first vehicle in the current state dimension, and the fifth score is determined as the A score of the second vehicle in the current state dimension.
  • each step involved in the methods shown in FIG. 2 and FIG. 4 may be executed by each unit in the vehicle control device shown in FIG. 7 .
  • steps S201-S202 shown in FIG. 2 can be executed by the control unit 701 shown in FIG. 7
  • steps S203-S204 can be executed by the processing unit 702 shown in FIG. 7
  • step S205 can be executed by the shown in the control unit 701
  • step S401 and step S402 shown in FIG. Both can be executed by the control unit 701 shown in FIG. 7
  • the "determining the first cross-lane detection line in the first lane" in step S402 and steps S403-S404 can be performed by
  • the processing unit 702 shown in FIG. 7 is executed
  • steps S405-S407 can be executed by the control unit 701 shown in FIG. 7 , and so on.
  • each unit in the vehicle control device shown in FIG. A plurality of functionally smaller units can achieve the same operation without affecting the realization of the technical effects of the embodiments of the present application.
  • the above-mentioned units are divided based on logical functions.
  • the functions of one unit may also be realized by multiple units, or the functions of multiple units may be realized by one unit.
  • the vehicle-based control device may also include other units.
  • these functions may also be implemented with the assistance of other units, and may be implemented cooperatively by multiple units.
  • a general-purpose computing device such as a computer that includes processing elements such as a central processing unit (CPU), a random access storage medium (RAM), and a read-only storage medium (ROM) and storage elements
  • CPU central processing unit
  • RAM random access storage medium
  • ROM read-only storage medium
  • the computer program can be recorded in, for example, a computer-readable recording medium, loaded into the above-mentioned computing device through the computer-readable recording medium, and executed therein.
  • the computer device includes at least a processor 801 and a computer storage medium 804 .
  • the computer device may further include an input interface 802 and an output interface 803 .
  • the processor 801, the input interface 802, the output interface 803 and the computer storage medium 804 in the computer device can be connected through a bus or in other ways.
  • the computer storage medium 804 may be stored in the memory of the computer device, the computer storage medium 804 is used to store computer programs, the computer programs include program instructions, and the processor 801 is used to execute the programs stored in the computer storage medium 804 instruction.
  • Processor 801 (or called CPU (Central Processing Unit, central processing unit)) is the calculation core and control core of computer equipment, which is suitable for implementing one or more instructions, specifically for loading and executing one or more instructions to realize Corresponding method flow or corresponding function.
  • the processor 801 described in the embodiment of the present application can be used to perform a series of vehicle controls, specifically including: controlling the first vehicle to drive on the first lane, and the road area where the first lane is located Also includes: a second lane and a middle lane between the first lane and the second lane; wherein, both the second lane and the middle lane are in the same direction as the first lane; if the When the first vehicle intends to change lanes to the middle lane, control the first vehicle to change lanes to the middle lane; and observe the second lane during the lane change of the first vehicle; When it is observed that there is a second vehicle in the second lane that is changing lanes to the middle lane, determining the current state information of the first vehicle and the current state information of the second vehicle; according to the second vehicle The current state information of a vehicle and the current state information of the second vehicle determine a target driving action of the first vehicle, and control the first vehicle to perform the target driving action, and so on.
  • the embodiment of the present application also provides a computer storage medium (Memory).
  • the computer storage medium is a memory device in a computer device and is used to store programs and data. It can be understood that the computer storage medium here may include a built-in storage medium in the computer device, and of course may also include an extended storage medium supported by the computer device.
  • a computer storage medium provides a storage space that stores an operating system of a computer device. Moreover, one or more instructions suitable for being loaded and executed by the processor 801 are also stored in the storage space, and these instructions may be one or more computer programs (including program codes).
  • the computer storage medium here can be a high-speed RAM memory, or a non-volatile memory (non-transitory memory), such as at least one disk memory; it can also be at least one computer storage medium located away from the aforementioned processor. medium.
  • one or more instructions stored in the computer storage medium can be loaded and executed by the processor, so as to realize the corresponding steps of the above method in the embodiment of the vehicle control method shown in FIG. 2 or FIG. 4; specific implementation Among them, one or more instructions in the computer storage medium are loaded by the processor and execute the following steps:
  • controlling the first vehicle to travel on the first lane, the road area where the first lane is located also includes: a second lane and a middle lane between the first lane and the second lane; wherein, the Both the second lane and the middle lane are in the same direction as the first lane;
  • the first vehicle intends to change lanes to the middle lane, control the first vehicle to change lanes to the middle lane; and observe the first vehicle during the lane change of the first vehicle.
  • two lanes If the first vehicle intends to change lanes to the middle lane, control the first vehicle to change lanes to the middle lane; and observe the first vehicle during the lane change of the first vehicle.
  • a target driving action of the first vehicle is determined, and the first vehicle is controlled to execute the target driving action.
  • the one or more instructions may be loaded by a processor and specifically executed:
  • the first cross-lane awareness line is located between the first lane dividing line and the target driving line;
  • the first lane dividing line refers to the lane dividing line between the first lane and the middle lane, so
  • the target driving line refers to a line along which the first vehicle travels in the first lane before starting to change lanes.
  • the one or more instructions may also be loaded and specifically executed by the processor:
  • the existing vehicle is in the state of changing lanes to the middle lane, and the existing vehicle is determined to be in the second lane to the middle A second vehicle traveling in a lane change;
  • the lateral speed is less than or equal to the lane change detection speed, then determine that the existing vehicle does not change lanes to the middle lane, and determine that there is no change to the middle lane in the second lane A second vehicle traveling on the road.
  • the one or more instructions may be processed by The loader is loaded and specifically executed:
  • the target driving action of the first vehicle is determined according to the selection result.
  • the scoring result includes the lane-changing priority score of the first vehicle and the lane-changing priority score of the second vehicle;
  • the one or more instructions may be loaded by the processor and specifically executed:
  • the vehicle corresponding to the larger lane-changing priority score from the first vehicle and the second vehicle.
  • a vehicle as a vehicle having the right of way to change lanes to the middle lane.
  • the one or more instructions may be loaded by the processor and specifically executed:
  • the selection result includes the first vehicle, continue to change lanes to the middle lane, and determine it as the target driving action of the first vehicle;
  • the action of changing lanes to the middle lane will be canceled and determined as the target driving action of the first vehicle.
  • any current state information includes: state data in one or more state dimensions; the scoring results include: the lane-changing priority score of the first vehicle and the lane-changing priority score of the second vehicle. channel priority score;
  • the lane-changing priority scores are performed on the first vehicle and the second vehicle, and when scoring results are obtained, the One or more of the above instructions can be loaded and specifically executed by the processor:
  • the scores of the first vehicle in the current state dimension are obtained by scoring, and the score of the second vehicle in the current state dimension;
  • the current state dimension includes a position and orientation dimension
  • the first state data includes: the position and orientation of the first lane where the first vehicle is located relative to the middle lane
  • the second The status data includes: the position and orientation of the second lane where the second vehicle is located relative to the middle lane
  • the one or more instructions can be loaded by the processor and specifically executed:
  • the position orientation in the first state data is the leading orientation, then determine the first score as the score of the first vehicle in the current state dimension, and determine the second score as the score of the second vehicle in the current state dimension. A score under the current state dimension; wherein, the first score is greater than the second score;
  • the current state dimension includes a longitudinal distance dimension;
  • the first state data includes: the longitudinal distance between the current position of the first vehicle and a reference point in the road area;
  • the The second state data includes: the longitudinal distance between the current position of the second vehicle and the reference point;
  • the one or more instructions can be loaded by the processor and specifically executed:
  • the third score is determined as the score of the first vehicle in the current state dimension
  • the fourth score is determined as the score of the second vehicle in the A score under the current state dimension; wherein, the third score is greater than the fourth score
  • the fourth score is determined as the score of the first vehicle in the current state dimension, and the third score is determined as the A score of the second vehicle in the current state dimension.
  • the current state dimension includes a lateral distance dimension
  • the first state data includes: the lateral distance between the current position of the first vehicle and the lane centerline of the middle lane
  • the The second status data includes: the lateral distance between the current position of the second vehicle and the lane centerline of the middle lane
  • the one or more instructions can be loaded by the processor and specifically executed:
  • the fifth score is determined as the score of the first vehicle in the current state dimension
  • the sixth score is determined as the score of the second vehicle in the A score under the current state dimension; wherein, the fifth score is smaller than the sixth score
  • the sixth score is determined as the score of the first vehicle in the current state dimension, and the fifth score is determined as the A score of the second vehicle in the current state dimension.
  • the target driving action of the first vehicle can be determined according to the current state information of the first vehicle and the current state information of the second vehicle, and the first vehicle can be controlled to execute the target. driving action.
  • the target driving action can be made safer, thereby further improving the safety of the vehicle; on the other hand, it can realize As the current state information of the first vehicle and the second vehicle are different, the determined target driving actions are also different, so that the first vehicle is not limited to one driving action during the lane change process, and the driving behavior of the first vehicle can be improved.
  • the flexibility of lane-changing behavior improves the safety of vehicles.
  • a computer program product or computer program where the computer program product or computer program includes computer instructions, and the computer instructions are stored in a computer-readable storage medium.
  • the processor of the computer device reads the computer instruction from the computer-readable storage medium, and the processor executes the computer instruction, so that the computer device executes the vehicle control method shown in FIG. 2 or FIG. Methods.

Landscapes

  • Engineering & Computer Science (AREA)
  • Automation & Control Theory (AREA)
  • Transportation (AREA)
  • Mechanical Engineering (AREA)
  • Traffic Control Systems (AREA)
  • Control Of Driving Devices And Active Controlling Of Vehicle (AREA)

Abstract

一种车辆控制方法包括：控制第一车辆在第一车道上行驶，第一车道所在的道路区域中还包括第二车道以及位于第一车道和第二车道之间的中间车道；若第一车辆欲换道至中间车道，则控制第一车辆向中间车道进行换道行驶；在第一车辆的换道行驶过程中，观察第二车道；在观察到第二车道中存在向中间车道进行换道行驶的第二车辆时，确定第一车辆的当前状态信息以及第二车辆的当前状态信息；根据第一车辆的当前状态信息和第二车辆的当前状态信息，确定第一车辆的目标行驶动作，控制第一车辆执行目标行驶动作。该方法可以提升车辆的换道行为的真实性，从而提升车辆行驶的安全性。还提供了车辆控制装置、计算机设备、计算机存储介质和计算机程序产品。

Description

车辆控制方法、装置、设备、介质及计算机程序产品
本申请要求于2021年12月2日提交中国专利局、申请号为202111462561.X、发明名称为“车辆控制方法、装置及计算机程序产品”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。
技术领域
本申请涉及互联网技术领域，具体涉及自动驾驶技术领域，尤其涉及一种车辆控制方法、装置、设备、介质及计算机程序产品。
发明背景
随着人工智能的日益发展，人工智能技术在生活中的应用越来越广泛，例如在自动驾驶技术上的应用。其中，交通仿真是自动驾驶技术落地实施前的重要阶段；通过预先进行交通仿真，可使得自动驾驶技术在实际应用时保持较优的性能。目前，无论是在交通仿真过程中，还是实际的自动驾驶过程中，在车辆从当前车道换道至相邻车道时，通常是通过改变一些换道的参数来实现的，这样的车辆控制方式容易导致车辆行驶的安全性较差。
发明内容
本申请实施例提供了一种车辆控制方法、装置、设备、介质及计算机程序产品，可以提升车辆的换道行为的真实性，从而提升车辆行驶的安全性。
一方面，本申请实施例提供了一种车辆控制方法，由计算机设备执行，所述方法包括：
控制第一车辆在第一车道上行驶，所述第一车道所在的道路区域中还包括：第二车道以及位于所述第一车道和所述第二车道之间的中间车道；其中，所述第二车道和所述中间车道均与所述第一车道同向；
若所述第一车辆欲换道至所述中间车道，则控制所述第一车辆向所述中间车道进行换道行驶；并在所述第一车辆的换道行驶过程中，观察所述第二车道；
在观察到所述第二车道中存在向所述中间车道进行换道行驶的第二车辆时，确定所述第一车辆的当前状态信息以及所述第二车辆的当前状态信息；
根据所述第一车辆的当前状态信息和所述第二车辆的当前状态信息，确定所述第一车辆的目标行驶动作，并控制所述第一车辆执行所述目标行驶动作。
另一方面，本申请实施例提供了一种车辆控制装置，所述装置包括：
控制单元，用于控制第一车辆在第一车道上行驶，所述第一车道所在的道路区域中还包括：第二车道以及位于所述第一车道和所述第二车道之间的中间车道；其中，所述第二车道和所述中间车道均与所述第一车道同向；
所述控制单元，还用于若所述第一车辆欲换道至所述中间车道，则控制所述第一车辆向所述中间车道进行换道行驶；
处理单元，用于在所述第一车辆的换道行驶过程中，观察所述第二车道；
所述处理单元，还用于在观察到所述第二车道中存在向所述中间车道进行换道行驶的第二车辆时，确定所述第一车辆的当前状态信息以及所述第二车辆的当前状态信息；
所述控制单元，还用于根据所述第一车辆的当前状态信息和所述第二车辆的当前状态信息，确定所述第一车辆的目标行驶动作，并控制所述第一车辆执行所述目标行驶动作。
再一方面，本申请实施例提供了一种计算机设备，所述计算机设备包括处理器和计算机存储介质，其中，所述计算机存储介质用于存储一条或多条指令，当所述一条或多条指令被所述处理器执行时，实现上述车辆控制方法。
再一方面，本申请实施例提供了一种计算机存储介质，所述计算机存储介质存储有一条或多条指令，所述一条或多条指令适于由处理器加载并执行上述车辆控制方法。
再一方面，本申请实施例提供了一种计算机程序产品，该计算机程序产品包括计算机程序；所述计算机程序被处理器执行时，实现上述所提及的车辆控制方法。
附图简要说明
为了更清楚地说明本申请实施例技术方案，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1a是本申请实施例提供的一种左右两侧车道的车辆同时向中间车道换道的示意图；
图1b是本申请实施例提供的一种任一车辆的前车和后车的示意图；
图1c是本申请实施例提供的一种处于换道状态的任一车辆扩大侧向检查的视野的示意图；
图1d是本申请实施例提供的一种车辆进行换道行驶的示意图；
图2是本申请实施例提供的一种车辆控制方法的流程示意图；
图3a是本申请实施例提供的一种第一跨车道觉察线的位置示意图；
图3b是本申请实施例提供的一种第一车辆的车头角中距离中间车道最近的车头角的示意图；
图3c是本申请实施例提供的一种第一车辆的参照点和第一跨车道觉察线之间的位置关系的示意图；
图4是本申请另一实施例提供的一种车辆控制方法的流程示意图；
图5a是本申请实施例提供的一种第一车辆执行目标行驶动作的示意图；
图5b是本申请实施例提供的另一种第一车辆执行目标行驶动作的示意图；
图5c是本申请实施例提供的再一种第一车辆执行目标行驶动作的示意图；
图6a是本申请实施例提供的一种车辆控制方法的应用场景图；
图6b是本申请实施例提供的一种车辆执行换道行为的决策逻辑的流程示意图；
图7是本申请实施例提供的一种车辆控制装置的结构示意图；
图8是本申请实施例提供的一种计算机设备的结构示意图。
实施方式
下面将结合本申请实施例中的附图，对本申请实施例中的技术方案进行清楚、完整地描述。
人工智能(Artificial Intelligence，AI)是利用数字计算机或者数字计算机控制的机器模拟、延伸和扩展人的智能，感知环境、获取知识并使用知识获得最佳结果的理论、方法、技术及应用系统。换句话说，人工智能是计算机科学的一个综合技术，它企图了解智能 的实质，并生产出一种新的能以人类智能相似的方式做出反应的智能机器。人工智能也就是研究各种智能机器的设计原理与实现方法，使机器具有感知、推理与决策的功能。人工智能技术是一门综合学科，涉及领域广泛，既有硬件层面的技术也有软件层面的技术。人工智能基础技术一般包括如传感器、专用人工智能芯片、云计算、分布式存储、大数据处理技术、操作/交互系统、机电一体化等技术。
随着人工智能技术研究和进步，人工智能技术在多个领域展开研究和应用，例如：自动驾驶、无人驾驶、常见的智能家居、智能穿戴设备、虚拟助理、智能音箱、智能营销、无人机、机器人、智能医疗、智能客服、智能视频服务，等等。其中，自动驾驶技术通常包括高精地图、环境感知、行为决策、路径规划、运动控制等技术。自动驾驶技术通常可包括交通仿真和实车测试(即控制车辆在实际车道上行驶)，且交通仿真作为一种零风险、快速迭代、可复现的测试方法，为自动驾驶技术上路奠定了坚实的基础。所谓的交通仿真又可称为道路交通仿真，其是研究复杂交通问题的重要工具；尤其是当一个系统过于复杂，无法用简单抽象的数学模型描述时，交通仿真的作用就更为突出。交通仿真可以清晰地辅助分析预测交通堵塞的地段和原因，对城市规划、交通工程和交通管理的有关方案进行比较和评价，在问题成为现实以前，尽量避免，或有所准备。总结而言，交通仿真技术是应用仿真硬件和仿真软件通过仿真实验，借助某些数值计算和问题求解，反映系统行为或过程的仿真模型技术。
无论是在自动驾驶的交通仿真过程中，还是在自动驾驶的实车测试过程中，通常会涉及左右两侧车道的车辆同时向中间车道换道的情况。需要说明的是，本申请实施例所提及的“同时向中间车道换道”的含义是指：两辆及以上的车辆在同一时刻均处于向中间车道换道的状态，这些车辆启动换道过程的开始时刻可可相同或不同，对此不作限定。例如参见图1a所示：设存在指示同一种行驶方向的三条车道，从左到右依次分别是车道A、车道B以及车道C，那么可能存在车道A中的车辆11和车道C中的车辆12同时向中间车道B换道的情况。经研究表明，虽然在交通规则中，分别位于左右两侧车道中的两个车辆向同一车道(即中间车道)进行换道变更时，左侧车道中的车辆应该让右侧车道中的车辆先行；但是在现实世界中，右侧车道中的车辆为了避免发生事故(如剐蹭或碰撞)，可能也会在适当的情况下选择对左侧车道中处于换道状态的车辆进行避让。其中，左侧车道是指位于中间车道左侧的车道，如图1a中的车道A；右侧车道是指位于中间车道右侧的车道，如图1a中的车道C。由此可见，分别位于左右两侧车道中的两个车辆同时向中间车道进行换道时，这两个车辆的行驶行为是多样化的；基于此，本申请实施例提出了一种车辆控制方法，该车辆控制方法可在左右两侧车道的车辆同时向中间车道换道时，通过考虑向中间车道进行换道行驶的各个车辆的行驶行为，来安全且灵活地控制各个车辆的行驶动作，提升车辆换道行为的真实性和车辆行驶的安全性。
在执行该车辆控制方法的过程中，任一车辆首先需按照基于规则的换道原则，决策是否向旁侧的目标车道进行换道。其中，基于规则的换道原则是指：车辆需基于换道意愿和安全性条件等规则，判断是否可以换道的原则；可见，车辆需基于对换道意愿和安全性条件等规则的判断，来启动并完成一个车道变换过程。在本车有换道意愿的前提下，需要考虑的安全性条件通常可包括但不限于：本车与目标车道内的前车TP之间的距离G TP需大于预设的前车安全距离G SP，以及本车与目标车道内的后车TR的距离G TR需大于预设的后车安全距离G SR；也就是说，安全性原则可包括：G TP＞前车安全距离G SP，且G TR大于后车安全距离G SR。参见图1b所示：针对任一车辆而言，前车TP是指：沿着目标车道所指示的行驶方向，目标车道中在纵向上位于本车之前且离本车最近的一辆车辆；相应的，后车TR是指：沿着目标车道所指示的行驶方向，目标车道中在纵向上位于本车之后且离本车最近的一辆车辆。其中，本申请实施例可将与目标车道相平行的方向称为纵向，将与目标车道垂直的方向(即目标车道的车道法线所在的方向) 称为横向。
由此可见，任一车辆在进行换道决策时，需对旁侧的目标车道中的前车和后车距离/速度等进行判断，从而在满足换道意愿和安全性条件的情况下，才可开始向目标车道进行横向移动。在横向移动一定距离后，处于换道状态的任一车辆可扩大侧向检查的视野，以保证对换道路径轨迹所涉及的各条道路以及位于目标车道的另一侧车道处于觉察状态，如图1c所示。若任一车辆觉察到另一侧车道中有车辆X也处于向目标车道进行换道的换道状态，则可根据该车辆X所处的位置、速度等状态信息，做出不同的行驶动作的判断，从而使得任一车辆执行相应的行驶动作。例如参见图1d所示，处于左侧车道中的A车与处于右侧车道中的B车均在向中间车道(即前述所提及的目标车道)进行换道行驶，那么A车和B车在换道行驶过程中，不仅需考虑中间车道中的前车C和后车D这两辆车的位置与速度等状态信息，还需考虑另一侧车道中与自身存在换道竞争关系的相关车辆的状态信息，从而根据各个状态信息来执行相应的行驶动作。其中，对于A车而言，另一侧车道为图1d中的右侧车道，与A车存在换道竞争关系的相关车辆为B车；同理，对于B车而言，另一侧车道为图1d中的左侧车道，与B车存在换道竞争关系的相关车辆为A车。
基于上述描述，针对本申请实施例所提出的车辆控制方法，需要说明以下几点：
①本申请实施例所提出的车辆控制方法可由一个计算机设备执行，该计算机设备可以是终端或服务器；或者，本申请实施例所提出的车辆控制方法也可由终端和服务器共同执行，对此不作限定。为便于阐述，后续均以计算机设备执行该车辆控制方法为例进行说明。其中，此处所提及的终端可以包括但不限于：智能手机、平板电脑、笔记本电脑、台式计算机、智能手表、智能电视、智能车载终端等；服务器可以是独立的物理服务器，也可以是多个物理服务器构成的服务器集群或者分布式系统，还可以是提供云服务、云数据库、云计算、云函数、云存储、网络服务、云通信、中间件服务、域名服务、安全服务、内容分发网络(Content Delivery Network，CDN)、以及大数据和人工智能平台等基础云计算服务的云服务器，等等。
②本申请实施例所提出的车辆控制方法可被运用在自动驾驶的实车测试过程中，以使得可通过该车辆控制方法来控制车辆在自动驾驶的过程中，安全且灵活执行换道行为。或者，该车辆控制方法也可被运用在自动驾驶的交通仿真过程中；在此情况下，计算机设备中可至少包括仿真软件。此处所提及的仿真软件可以是一种微观交通仿真软件(TAD Sim)，该微观交通仿真软件可以包括但不限于需要联网的仿真软件或者不需要联网的仿真软件；可以理解的是，交通仿真按照仿真的精确程度和范围分为宏观仿真、中观仿真和微观仿真，微观交通仿真以个人车辆行为为研究对象，描述交通系统中每个车辆的状态的仿真。当计算机设备包括仿真软件时，该车辆控制方法所涉及到的逻辑算法可以嵌入在该仿真软件中，以用于位于左右两侧车道中的车辆同时换道至中间车道时所执行的换道行为进行模拟仿真；也就是说，当任一车辆需要从两侧车道向中间车道换道时，可采用本申请实施例所提出的车辆控制方法所涉及的逻辑算法对其换道行为进行模拟，以模拟出车辆之间复杂的互动，从而模拟更加真实的驾驶行为，提升仿真结果的真实性以及仿真结果和实际情况之间的符合度。其中，当换道过程完成后，可退出该车辆控制方法所涉及的逻辑算法。
基于上述的描述，下面结合图2所示的流程示意图，对本申请实施例所提出的车辆控制方法作进一步阐述。请参见图2，该车辆控制方法可由图8所示的计算机设备执行，包括以下步骤S201-S205：
S201，控制第一车辆在第一车道上行驶。
其中，第一车道所在的道路区域中还包括：第二车道以及位于第一车道和第二车道之间的中间车道。并且，第二车道和中间车道均与第一车道同向；也就是说，第一车道、第二车道以 及中间车道所指示的行驶方向是相同的。需要说明的是，顺着中间车道所指示的行驶方向来看，第一车道可以位于中间车道左侧，也可以位于中间车道的右侧，对此不作限定。当第一车道是位于中间车道左侧的车道时，第二车道可以是位于中间车道右侧的车道；当第二车道是位于中间车道左侧的车道时，第一车道可以是位于中间车道右侧的车道。
在本申请实施例中，第一车辆可以是交通仿真过程中的任一仿真车辆，也可以是实车测试过程中的处于自动驾驶状态的任一车辆，对此不作限定。在控制第一车辆在第一车道上行驶时，具体可以是控制第一车辆沿着第一车道的车道中心线(后续简称第一车道中心线)行驶；或者，控制第一车辆在第一车道中除第一车道中心线以外的地方行驶，等等。其中，车道中心线是指位于车道中间的线，即车道中心线与所在车道的左侧边界之间的距离，等于车道中心线与所在车道的右侧边界之间的距离。
S202，若第一车辆欲换道至中间车道，则控制第一车辆向中间车道进行换道行驶。
在具体实现中，若第一车辆欲换道至中间车道，则计算机设备可从中间车道中的全部车辆中，选取纵向上位于第一车辆之前且离第一车辆最近的车辆作为第一车辆的目标前车；以及，选取纵向下位于第一车辆之后且离第一车辆最近的车辆作为第一车辆的目标后车。然后，可根据第一车辆与目标前车之间的第一距离以及第一车辆与目标后车之间的第二距离，判断第一车辆是否满足换道所需的安全性条件；或者，在第一距离和第二距离的基础上，进一步结合第一车辆的速度、目标前车的速度和目标后车的速度，来判断第一车辆是否满足换道所需的安全性条件。若判定第一车辆满足安全性条件，则可控制第一车辆向中间车道进行换道行驶；若判定第一车辆不满足安全性条件，则可控制第一车辆继续在第一车道中行驶。
在本申请实施例中，车辆的换道行为主要由纵向驾驶行为和横向驾驶行为决定，可分别予以考虑；其中，纵向驾驶行为是可由车辆跟驰(跟车)算法决定，横向驾驶行为则可基于规则的换道算法进行描述。基于此，计算机设备在控制第一车辆向中间车道进行换道行驶时，可在纵向上根据目标前车，采用车辆跟驰(跟车)算法来计算第一车辆向中间车道行驶过程中的纵向行驶参数，纵向行驶参数可包括最大行驶速度和最小安全车间距；所谓的最大行驶速度用于表示车辆在行驶过程中不能超过的最大速度(如道路限速)，最小安全车间距用于表示车辆在行驶过程中始终需保持的最小车间距。另外，计算机设备还可在横向上以初始状态和终止状态，来规划第一车辆向中间车道行驶过程中的横向行驶参数，横向行驶参数可包括横向速度(即在横向上的行驶速度)和移动轨迹等。在计算出第一车辆向中间车道行驶过程中的纵向行驶参数和相应的横向行驶参数后，计算机设备可按照计算出的纵向行驶参数和相应的横向行驶参数，控制第一车辆向中间车道进行换道行驶。
其中，横向行驶参数可以是由计算机设备通过采用五次多项式求解的方式来计算得到的；即可给定初始状态(0，0，0)和终止状态(H，0，0)，计算机设备可根据该初始状态和终止状态对五次多项式的系数加以计算，从而推算出第一车辆向中间车道进行换道行驶的过程中，第一车辆的横向速度和移动轨迹。其中，初始状态(0，0，0)的各参数来依次描述第一车辆向中间车道移动的初始时刻，第一车辆在横向上的位置、速度和加速度；终止状态(H，0，0)的各参数来依次描述第一车辆完成向中间车道移动的结束时刻(即第一车辆换道至中间车道的时刻)，第一车辆在横向上的位置、速度和加速度，H等于第一车辆在换道前所处的位置与中间车道的车道中心线(可简称中间车道中心线)之间的横向距离。
S203，在第一车辆的换道行驶过程中，观察第二车道。
在步骤S203的一种实施方式中，计算机设备可在第一车辆开始进入换道过程时(即第一车辆在横向上的移动速度开始大于0时)，就开始观察第二车道。
在步骤S203的另一种实施方式中，计算机设备也可在进入换道过程后的一定时长后，开始 在第一车辆的换道行驶过程中，实时或周期性地观察第二车道。
在步骤S203的另一种实施方式中，计算机设备也可在第一车辆的换道行驶过程中，确定第一车道中的第一跨车道觉察线。此处所提及的第一跨车道觉察线是指位于第一车道中的跨车道觉察线，所谓的跨车道觉察线是指平行于车道且用于触发开始观察另一侧车道的虚拟线，虚拟线则是一种在车道中虚拟出的且在现实世界中不存在的线。具体的，第一跨车道觉察线可位于第一车道分隔线和目标行驶线之间，所谓的第一车道分隔线是指第一车道和中间车道之间的车道分隔线(即用于分隔不同车道的标识线)。所谓的目标行驶线是指第一车辆在开始换道前，在第一车道中沿着行驶的线；例如，第一车辆在开始换道前，是沿着第一车道中心线行驶的，则目标行驶线可以是该第一车道中心线，此情况下的第一跨车道觉察线的位置示意图可参见图3a所示。其中，图3a中的第二跨车道觉察线是指位于第二车道中的跨车道觉察线，第二车道中心线是指第二车道的车道中心线。
需要说明的是，本申请实施例对第一跨车道觉察线与第一车道分隔线之间的距离Do的确定方式不作限定。例如，第一跨车道觉察线和第一车道分隔线之间的距离Do可以是随机动态确定的，只需满足此距离小于目标行驶线和第一车道分隔线之间的距离即可。又如，若第一车辆在开始换道之前，是沿着第一车道中心线行驶的，则由于第一车道中心线与第一车道分隔线之间的距离X是固定不变的，且该距离是可以预先确定的，因此可预先设置一个小于距离X的值作为第一跨车道觉察线与第一车道分隔线之间的距离Do。又如，针对任一车辆而言，计算机设备可引入车辆的激进程度，从而通过与激进程度相关的函数确定跨车道觉察线和车道分隔线之间的距离；其中，车辆的激进程度可采用一个(0，1)之间的浮点数A来表示，0代表最保守型，1代表最激进型。在此情况下，车辆越激进，对应的距离就越小，即可越晚对另一侧车道进行观察，并作出反应；通过此方式可使得每辆车辆可能有不同的跨车道觉察线和距离Do。基于此，第一跨车道觉察线可以是根据第一车辆的激进程度确定的；且随着第一车辆的激进程度越高，第一跨车道觉察线和第一车道分隔线之间的距离越小。应理解的是，本申请实施例对车辆的激进程度的设置方法不加限定，例如针对仿真软件中的仿真车辆而言，仿真车辆在仿真开始时，便可被赋予一个随机的固定激进程度参数，以指示该仿真车辆的激进程度；并且，不同仿真车辆的激进程度可根据其所需仿真区域的驾驶行为的不同而分别设置。
在确定第一跨车道觉察线后，计算机设备可检测第一车辆与第一跨车道觉察线之间的位置关系。若检测到第一车辆未行驶至第一跨车道觉察线，则可控制第一车辆继续向中间车道进行换道行驶；若检测到第一车辆行驶至第一跨车道觉察线，或检测到第一车辆驶过第一跨车道觉察线，则开始观察第二车道。在一种实施方式中，计算机设备可检测第一车辆上的整个车身与第一跨车道觉察线之间的位置关系来判断第一车辆是否行驶至或驶过第一跨车道觉察线。另一种实施方式中，计算机设备可为第一车辆定义一个参照点(或称为参考点)，从而通过检测第一车辆的参照点与第一跨车道觉察线之间的位置关系，来判断第一车辆是否行驶至或驶过第一跨车道觉察线。即在此实施方式下，第一车辆行驶至第一跨车道觉察线可包括：第一车辆的参照点位于第一跨车道觉察线上；或者，第一车辆驶过第一跨车道觉察线包括：第一车辆的参照点朝着中间车道的方向，越过第一跨车道觉察线。也就是说，通过此实施方式可实现在第一车辆的参照点越过(即跨过)第一跨车道觉察线时，开始对中间车道的另一侧车道(即第二车道)进行观察；当第一车辆的参照点跨过第一跨车道觉察线之前，可认为第一车辆未意识到需对中间车道的另一侧车道进行观察。
其中，第一车辆的参照点可包括：第一车辆的质心，或者第一车辆的车头角中距离中间车道最近的车头角。参见图3b的左右两侧所示：当第一车辆所处的第一车道位于中间车道的左侧时，由于第一车辆的车头需向右侧转向以换道至中间车道，使得第一车辆的右车头角离中间车 道最近，那么此情况下的第一车辆的参照点可包括第一车辆的右车头角；当第一车辆所处的第一车道位于中间车道的右侧时，由于第一车辆的车头需向左侧转向以换道至中间车道，使得第一车辆的左车头角离中间车道最近，那么此情况下的第一车辆的参照点可包括第一车辆的左车头角。基于此，以第一车辆的参照点包括第一车辆的右车头角为例，第一车辆的参照点位于第一跨车道觉察线的示意图以及第一车辆的参照点跨过第一跨车道觉察线上的示意图可分别参见图3c中的左侧图和右侧图所示。
S204，在观察到第二车道中存在向中间车道进行换道行驶的第二车辆时，确定第一车辆的当前状态信息以及第二车辆的当前状态信息。
其中，第一车辆的当前状态信息是指：在观察到第二车道中存在第二车辆时，第一车辆所具有的状态信息；同理，第二车辆的当前状态信息是指：在观察到第二车道中存在第二车辆时，第二车辆所具有的状态信息。进一步的，任一当前状态信息可包括一个或多个状态维度下得到的状态数据，该一个或多个状态维度可根据实际需求或经验值设置，如一个或多个状态维度可包括位置方位维度、纵向距离维度、横向距离维度、相对速度维度，等等。
相应的，当一个或多个状态维度包括位置方位维度时，第一状态数据可包括：第一车辆所处的第一车道相对于中间车道的位置方位(如左侧方位或右侧方位)；第二状态数据包括：第二车辆所处的第二车道相对于中间车道的位置方位。当一个或多个状态维度包括纵向距离维度时，第一状态数据可包括：第一车辆的当前位置与道路区域中的基准点之间的纵向距离；第二状态数据包括：第二车辆的当前位置与基准点之间的纵向距离。其中，第一车辆(或第二车辆)的当前位置是指：在观察到第二车道中存在第二车辆时，第一车辆(或第二车辆)的指定点(如质心、车头、车尾等)在道路区域中所处的位置；基准点可以是根据实际需求在道路区域中设置的点，例如基准点可以是位于第一车辆和第二车辆之后的点，具体可以例如是道路区域中的车道起始点，或者道路区域中行驶在最后的车辆所处的位置点；或者，基准点可以是位于第一车辆和第二车辆之前的点，具体可以例如是道路区域中的车道结束点等；为便于阐述，后续均以基准点是位于第一车辆和第二车辆之后的点为例进行说明。当一个或多个状态维度包括横向距离维度时，第一状态数据可包括：第一车辆的当前位置与中间车道的车道中心线之间的横向距离；第二状态数据包括：第二车辆的当前位置与中间车道的车道中心线之间的横向距离。当一个或多个状态维度包括相对速度维度时，第一状态数据和第二状态数据均可包括：第一车辆的当前速度和第二车辆的当前速度之间的相对速度；其中，该相对速度可以是以第一车辆的当前速度为基准计算得到的，也可以是以第二车辆的当前速度为基准计算得到的，对此不作限定。
S205，根据第一车辆的当前状态信息和第二车辆的当前状态信息，确定第一车辆的目标行驶动作，并控制第一车辆执行目标行驶动作。
在一种具体实现中，计算机设备可将评分系统引入两侧车道中处于换道状态的车辆之间的互动决策过程，以模拟车辆之间复杂的互动，使得最终确定出的目标行驶动作更加贴近真实，即提升目标行驶动作的准确性和真实性。具体的，计算机设备可先根据第一车辆的当前状态信息和第二车辆的当前状态信息，对第一车辆和第二车辆进行换道优先级评分，得到第一车辆的换道优先级分数和第二车辆的换道优先级分数。然后，通过比较第一车辆的换道优先级分数和第二车辆的换道优先级分数之间的大小关系，来确定第一车辆的目标行驶动作。
若第一车辆的换道优先级分数大于第二车辆的换道优先级分数，则可表明第一车辆可优先换道至中间车道，即允许第一车辆先于第二车辆换道至中间车道，那么可将继续向中间车道进行换道行驶的动作，确定为第一车辆的目标行驶动作。若第一车辆的换道优先级分数小于第二车辆的换道优先级分数，则可表明第二车辆可优先换道至中间车道，即允许第二车辆先于第一车辆换道至中间车道，那么可将取消向中间车道进行换道行驶的动作，确定为第一车辆的目标 行驶动作。若第一车辆的换道优先级分数等于第二车辆的换道优先级分数，则可进一步确定第一车辆所处的第一车道相对于中间车道的位置方位是否为先行方位；若是，则允许第一车辆先于第二车辆换道至中间车道，那么可将继续向中间车道进行换道行驶的动作，确定为第一车辆的目标行驶动作；否则，则取消向中间车道进行换道行驶的动作，确定为第一车辆的目标行驶动作。其中，此处所提及的先行方位可根据经验或者实际需求设置。例如，若交通法规规定沿着行驶方向的右侧车辆具有先行权，则可沿着行驶方向，将中间车道的右侧方位确定为先行方位；又如，若交通法规规定沿着行驶方向的左侧车辆具有先行权，则可沿着行驶方向，将中间车道的左侧方位确定为先行方位。
另一种具体实现中，由前述步骤S204的相关描述可知，任一当前状态信息可包括一个或多个状态维度下得到的状态数据；基于此，可预先为各个状态维度设置相应的维度优先级。那么在确定第一车辆的目标行驶动作时，计算机设备可根据各个状态维度的维度优先级，按照维度优先级从高到低的顺序从未被选取的状态维度中选取一个状态维度作为基准状态维度。其次，从第一车辆的当前状态信息中获取基准状态维度下的状态数据作为基准状态数据，以及从第二车辆的当前状态信息中获取基准状态维度下的状态数据作为参考状态数据。然后，计算机设备可根据基准状态数据和参考状态数据，从第一车辆和第二车辆中选取先行车辆。其中：
①当基准状态维度为位置方位维度时，基准状态数据为第一车辆所处的第一车道相对于中间车道的位置方位，参考状态数据为第二车辆所处的第二车道相对于中间车道的位置方位。那么先行车辆的选取方式可以是：若第一车辆所处的第一车道相对于中间车道的位置方位为先行方位，则选取第一车辆作为先行车辆；否则，则选取第二车辆作为先行车辆。
②当基准状态维度为纵向距离维度时，基准状态数据为第一车辆的当前位置与道路区域中的基准点之间的纵向距离，参考状态数据为第二车辆的当前位置与基准点之间的纵向距离。那么先行车辆的选取方式可以是：若基准状态数据等于参考状态数据，则确定选取先行车辆失败；若基准状态数据大于参考状态数据，则表明第一车辆比第二车辆在纵向上靠前，因此可选取第一车辆作为先行车辆；若基准状态数据小于参考状态数据，则表明第二车辆比第一车辆在纵向上靠前，因此可选取第二车辆作为先行车辆。
③当基准状态维度为横向距离维度时，基准状态数据为第一车辆的当前位置与中间车道的车道中心线之间的横向距离，参考状态数据为第二车辆的当前位置与中间车道的车道中心线之间的横向距离。那么先行车辆的选取方式可以是：若基准状态数据等于参考状态数据，则确定选取先行车辆失败；若基准状态数据小于参考状态数据，则表明第一车辆离中间车道更近，因此可选取第一车辆作为先行车辆；若基准状态数据大于参考状态数据，则表明第二车辆离中间车道更近，因此可选取第二车辆作为先行车辆。
④当基准状态维度为相对速度维度时，基准状态数据和参考状态数据均为第一车辆的当前速度和第二车辆的当前速度之间的相对速度。那么先行车辆的选取方式可以是：若该相对速度等于0，则表明第一车辆和第二车辆拥有相同的速度，此时可确定选取先行车辆失败。若该相对速度不等于0，则基于相对速度从第一车辆和第二车辆中选取速度较大的车辆作为先行车辆。
基于上述描述可知，计算机设备在根据基准状态数据和参考状态数据，从第一车辆和第二车辆中选取先行车辆时，可能会成功选取出先行车辆，也可能选取先行车辆失败。基于此，若成功选取出先行车辆，则计算机设备可进一步判断第一车辆是否为先行车辆；当第一车辆是先行车辆时，可将继续向中间车道进行换道行驶的动作，确定为第一车辆的目标行驶动作；当第一车辆不是先行车辆时，则可将取消向中间车道进行换道行驶的动作，确定为第一车辆的目标行驶动作。若未成功选取出先行车辆，则计算机设备可再次执行根据各个状态维度的维度优先级，按照维度优先级从高到低的顺序从未被选取的状态维度中选取一个状态维度作为基准状态 维度的步骤，以重新选取先行车辆。
基于上述图2所示的方法实施例的相关描述，本申请实施例还提出了如图4所示的车辆控制方法；在本申请实施例中，仍以计算机设备执行该车辆控制方法为例进行说明。参见图4所示，该车辆控制方法可包括以下步骤S401-S407：
S401，控制第一车辆在第一车道上行驶，第一车道所在的道路区域中还包括：第二车道以及位于第一车道和所述第二车道之间的中间车道。
S402，若第一车辆欲换道至所述中间车道，则控制第一车辆向中间车道进行换道行驶；并在第一车辆的换道行驶过程中，确定第一车道中的第一跨车道觉察线。
S403，若检测到第一车辆行驶至第一跨车道觉察线，或检测到第一车辆驶过第一跨车道觉察线，则开始观察第二车道。
在观察第二车道的过程中，可引入一个换道觉察速度Vo来辅助判断第二车道中是否存在向中间车道进行换道行驶的第二车辆。具体的，可先观察第二车道中是否存在车辆；在观察到第二车道中存在车辆的情况下，可进一步确定存在的车辆的横向速度，并判断横向速度和换道觉察速度之间的大小关系。若横向速度大于换道觉察速度，则可确定存在的车辆处于向中间车道进行换道行驶的状态，并将存在的车辆确定为第二车道中向中间车道进行换道行驶的第二车辆；若横向速度小于或等于换道觉察速度，则确定存在的车辆未向中间车道进行换道行驶，并确定第二车道中不存在向中间车道进行换道行驶的第二车辆。
其中，换道觉察速度是指用于衡量车辆是否处于换道状态的速度，本申请实施例对换道觉察速度的确定方式不作限定。例如，换道觉察速度是可以预先根据经验值设置的。又如，计算机设备可引入车辆的激进程度，从而通过与激进程度相关的函数确定相应车辆所对应的换道觉察速度，通过此方式可使得每辆车辆可能有不同的换道觉察速度。基于此，第一车辆对应的换道觉察速度可以是根据第一车辆的激进程度确定的，且换道觉察速度与第一车辆的激进程度成正比。也就是说，第一车辆越激进，换道觉察速度越大，且当第二车辆的横向速度大于该换道觉察速度，第二车辆才会被认为是正在换道。
在其他实施方式中，计算机设备也可不通过换道觉察速度来判断第二车道中是否存在向中间车道进行换道行驶的第二车辆，而是通过车辆的转向灯的状态来进行判断。具体的，计算机设备在观察到第二车道中存在车辆的情况下，可获取存在的车辆靠近中间车道的目标转向灯的状态。若该目标转向灯的状态为开启状态，则确定存在的车辆处于向中间车道进行换道行驶的状态，并将存在的车辆确定为第二车道中向中间车道进行换道行驶的第二车辆；若目标转向灯的状态为关闭状态，则确定存在的车辆未向中间车道进行换道行驶，并确定第二车道中不存在向中间车道进行换道行驶的第二车辆。
S404，在观察到第二车道中存在向中间车道进行换道行驶的第二车辆时，确定第一车辆的当前状态信息以及第二车辆的当前状态信息。
S405，根据第一车辆的当前状态信息和第二车辆的当前状态信息，对第一车辆和第二车辆进行换道优先级评分，得到评分结果。
在本申请实施例中，任一当前状态信息包括：一个或多个状态维度下的状态数据；相应的，步骤S405的具体实施方式可以是：s11，遍历第一车辆的当前状态信息中的各状态维度下的状态数据，确定当前遍历的第一状态数据，第一状态数据所处的状态维度为当前状态维度。s12，可将第二车辆的当前状态信息中处于当前状态维度下的状态数据，作为第二状态数据。s13，可按照当前状态维度对应的换道优先级评分策略，根据第一状态数据和第二状态数据，评分得到第一车辆在当前状态维度下的分数，以及第二车辆在所述当前状态维度下的分数。s14，在第一车辆的当前状态信息中的各状态维度下的状态数据均被遍历后，可基于第一车辆在各状态维度 下的分数，确定第一车辆的换道优先级分数；以及，基于第二车辆在各状态维度下的分数，确定第二车辆的换道优先级分数。具体的，可对任一车辆(即第一车辆或第二车辆)在各个状态维度下的分数进行加权求和或加权平均，得到任一车辆的换道优先级分数。可见，通过此实施方式所得到的评分结果包括：第一车辆的换道优先级分数和第二车辆的换道优先级分数。
其中，若当前状态维度包括位置方位维度，则第一状态数据包括：第一车辆所处的第一车道相对于中间车道的位置方位，第二状态数据包括：第二车辆所处的第二车道相对于中间车道的位置方位。那么，步骤s12的具体实施方式可以是：若第一状态数据中的位置方位为先行方位，则将第一分数确定为第一车辆在当前状态维度下的分数，并将第二分数确定为第二车辆在当前状态维度下的分数。其中，第一分数大于第二分数；例如，第一分数为1，第二分数为0，或者第一分数为2，第二分数为0等。相应的，若第二状态数据中的位置方位为先行方位，则将第二分数确定为第一车辆在当前状态维度下的分数，并将第一分数确定为第二车辆在当前状态维度下的分数。
其中，若当前状态维度包括纵向距离维度，则第一状态数据包括：第一车辆的当前位置与道路区域中的基准点之间的纵向距离；第二状态数据包括：第二车辆的当前位置与基准点之间的纵向距离。那么，步骤s12的具体实施方式可以是：对第一状态数据中的纵向距离和第二状态数据中的纵向距离进行差值运算，得到纵向距离差值。若纵向距离差值大于纵向差值阈值(例如数值0、数值0.5等)，则可将第三分数确定为第一车辆在当前状态维度下的分数，并将第四分数确定为第二车辆在当前状态维度下的分数。其中，第三分数大于第四分数；例如，第三分数为1，第四分数为0，或者第三分数为3，第四分数为1等。相应的，若纵向距离差值小于纵向差值阈值，则可将第四分数确定为第一车辆在当前状态维度下的分数，并将第三分数确定为第二车辆在当前状态维度下的分数。若纵向距离差值等于纵向差值阈值，则可进一步判断第一车道相对于中间车道的位置方位是否为先行方位；若是，则将第三分数确定为第一车辆在当前状态维度下的分数，并将第四分数确定为第二车辆在当前状态维度下的分数；若不是，则将第四分数确定为第一车辆在当前状态维度下的分数，并将第三分数确定为第二车辆在当前状态维度下的分数。
若当前状态维度包括纵向距离维度，则步骤s12的具体实施方式还可以是：比较第一状态数据中的纵向距离和第二状态数据中的纵向距离之间的大小。若第一状态数据中的纵向距离大于第二状态数据中的纵向距离，则表明第一车辆比第二车辆在纵向上靠前，即第一车辆的车头比第二车辆的车头领先，因此可将第三分数确定为第一车辆在当前状态维度下的分数，并将第四分数确定为第二车辆在当前状态维度下的分数。若第一状态数据中的纵向距离小于第二状态数据中的纵向距离，则表明第二车辆比第一车辆在纵向上靠前，即第二车辆的车头比第一车辆的车头领先，因此可将第四分数确定为第一车辆在当前状态维度下的分数，并将第三分数确定为第二车辆在当前状态维度下的分数。若第一状态数据中的纵向距离等于第二状态数据中的纵向距离，则可进一步判断第一车道相对于中间车道的位置方位是否为先行方位；若是，则将第三分数确定为第一车辆在当前状态维度下的分数，并将第四分数确定为第二车辆在当前状态维度下的分数；若不是，则将第四分数确定为第一车辆在当前状态维度下的分数，并将第三分数确定为第二车辆在当前状态维度下的分数。
其中，若当前状态维度包括横向距离维度，则第一状态数据包括：第一车辆的当前位置与中间车道的车道中心线之间的横向距离；第二状态数据包括：第二车辆的当前位置与中间车道的车道中心线之间的横向距离。那么，步骤s12的具体实施方式可以是：对第一状态数据中的横向距离和第二状态数据中的横向距离进行差值运算，得到横向距离差值(例如数值0、数值0.5等)；若横向距离差值大于横向差值阈值，则将第五分数确定为第一车辆在当前状态维度下 的分数，并将第六分数确定为第二车辆在当前状态维度下的分数。其中，第五分数小于第六分数；例如，第五分数为0，第六分数为1等。相应的，若横向距离差值小于横向差值阈值，则将第六分数确定为第一车辆在当前状态维度下的分数，并将第五分数确定为第二车辆在当前状态维度下的分数。若横向距离差值等于横向差值阈值，则可进一步判断第一车道相对于中间车道的位置方位是否为先行方位；若是，则将第六分数确定为第一车辆在当前状态维度下的分数，并将第五分数确定为第二车辆在当前状态维度下的分数；若不是，则将第五分数确定为第一车辆在当前状态维度下的分数，并将第六分数确定为第二车辆在当前状态维度下的分数。
若当前状态维度包括横向距离维度，则步骤s12的具体实施方式还可以是：比较第一状态数据中的横向距离和第二状态数据中的横向距离之间的大小。若第一状态数据中的横向距离大于第二状态数据中的横向距离，则表明第二车辆比第一车辆更靠近中间车道，因此可将第五分数确定为第一车辆在当前状态维度下的分数，并将第六分数确定为第二车辆在当前状态维度下的分数。若第一状态数据中的横向距离小于第二状态数据中的横向距离，则表明第一车辆比第二车辆更靠近中间车道，因此可将第六分数确定为第一车辆在当前状态维度下的分数，并将第五分数确定为第二车辆在当前状态维度下的分数。若第一状态数据中的横向距离等于第二状态数据中的横向距离，则可进一步判断第一车道相对于中间车道的位置方位是否为先行方位；若是，则将第六分数确定为第一车辆在当前状态维度下的分数，并将第五分数确定为第二车辆在当前状态维度下的分数；若不是，则将第五分数确定为第一车辆在当前状态维度下的分数，并将第六分数确定为第二车辆在当前状态维度下的分数。
S406，基于评分结果从第一车辆和第二车辆中，选取拥有向中间车道换道的先行权的车辆。
由步骤S405的相关描述可知，评分结果包括第一车辆的换道优先级分数和第二车辆的换道优先级分数。基于此，步骤S406的一种实施方式可以是：根据第一车辆的换道优先级分数和第二车辆的换道优先级分数，从第一车辆和第二车辆中选取换道优先级分数大于分数阈值的车辆，作为拥有向中间车道换道的先行权的车辆。或者，步骤S406的另一种实施方式可以是：根据第一车辆的换道优先级分数和第二车辆的换道优先级分数，从第一车辆和第二车辆中选取较大换道优先级分数对应的车辆，作为拥有向中间车道换道的先行权的车辆。
S407，根据选取结果确定第一车辆的目标行驶动作，并控制第一车辆执行目标行驶动作。
在具体实现中，计算机设备在根据选取结果确定第一车辆的目标行驶动作的过程中，若选取结果包括第一车辆，则将继续向中间车道进行换道行驶的动作，确定为第一车辆的目标行驶动作；若选取结果包括第二车辆，则将取消向中间车道进行换道行驶的动作，确定为第一车辆的目标行驶动作。其中，取消向中间车道进行换道行驶的动作可包括：换回至第一车辆的目标行驶线(第一车辆在开始换道前，在第一车道中沿着行驶的线)的动作；此情况下，以目标行驶线为第一车道中心线为例，第一车辆执行目标行驶动作的示意图可参见图5a所示。或者，取消向中间车道进行换道行驶的动作可包括：沿着第一跨车道觉察线减速行驶的动作；此情况下，第一车辆执行目标行驶动作的示意图可参见图5b所示。又或者，取消向中间车道进行换道行驶的动作可包括：停车等待的动作；此情况下，第一车辆执行目标行驶动作的示意图可参见图5c所示。
本申请实施例在考虑到左右两侧车道中的车辆同时向中间车道换道的情况下，通过提出平行于车道的虚拟线(跨车道觉察线)，引入换道觉察速度对驾驶员行为进行模拟，并将评分系统引入两侧换道车辆之间的互动决策过程，来模拟车辆之间复杂的互动，可以模拟更加真实的驾驶行为，从而使得换道行为更加贴近真实。并且，在观察到第二车道中存在第二车辆时，通过考虑第一车辆和第二车辆的当前状态信息来确定第一车辆的目标行驶动作，一方面可使得目标行驶动作是较为安全的，从而进一步提升车辆行驶的安全性；另一方面，可实现随着第一车 辆和第二车辆的当前状态信息的不同，确定出的目标行驶动作也不同，这样可使得第一车辆在换道过程中不局限于一种行驶动作，可提升第一车辆的换道行为的灵活性，进而提升车辆行驶的安全性。
在实际应用中，上述所提及的图2或图4所示的车辆控制方法可运用于图6a所示的场景中；下面以图6a所示的场景中的A车为例，结合图6b所示的流程图，对车辆执行换道行为的决策逻辑作进一步阐述：
A车在决定换道至中间车道后，可启动换道过程；并在换道行驶过程中，可实时判断是否已换道完成。若未换道完成，则可检测A车的参照点是否跨过左侧车道中的跨车道觉察线。若未跨过，则可继续向中间车道进行换道行驶；若已跨过，则可观察另一侧车道(即右侧车道)中是否存在横向速度大于换道觉察速度的车辆。参见图6a所示，另一侧车道中存在B车，因此A车可确定B车的横向速度；在A车眼中，只有另一侧车道中的B车的横向速度大于换道觉察速度，则会认为B车正在换道，此时可认为左右两侧车道中的A车和B车存在换道竞争关系。基于此，假设B车的横向速度大于换道觉察速度，即假设观察到另一侧车道中存在横向速度大于换道觉察速度的B车，那么可通过对两车在横向和纵向上的相对位置进行比较，从而计算出A车的换道优先级分数，以及B车的换道优先级分数。具体的，在换道未开始时，A车和B车的换道优先级分数均为0分。在换道开始后，由于中国交通规则规定这种情形下右侧车道的车拥有先行权，因此首先可给位于右侧车道的B车评1分，给位于左侧车道中的A车评0分，以给予右侧车辆一定的优先权优势。然后，可按照其他的换道优先级评分策略对A车和B车进行评分，具体如下：
①如果A车比B车在纵向(车道方向)上靠前，即A车头比B车头领先，则A车得一分，B车得0分，定义A车为纵向位置占优，反之亦然。基于此，可定义ΔDy为A车的参照点在车道方向上的距离(即A车的当前位置与道路区域中的基准点之间的纵向距离)减去B车的参照点在车道方向上的距离(即B车的当前位置与道路区域中的基准点之间的纵向距离)；那么，可按照如下逻辑进行评分：
当ΔDy>0时，A车得1分，B车得0分；
当ΔDy<＝0时，A车得0分，B车得1分(此处所提及的“＝”的意思是纵向距离相同时，B占优)。
②如果A车比B车在横向(车道法线方向)上更加靠近中间车道的车道中心线，则A车得一分，B车得0分，定义A车为横向位置占优，反之亦然。基于此，定义Dxa和Dxb分别为A车的参照点和B车的参照点在车道法线方向上到中间车道中心线的距离，即Dxa为A车的当前位置与中间车道的车道中心线之间的横向距离，Dxb为B车的当前位置与中间车道的车道中心线之间的横向距离。设ΔDx＝Dxa-Dxb，那么，可按照如下逻辑进行评分：
当ΔDx>＝0时，B车离中间车道更近，A车得0分，B车得1分(此处所提及的“＝”的意思是距离相同时，B占优)
当ΔDx<0时，A车离目标车道更近，A车得1分，B车得0分。
通过上述逻辑，可知最终得到的A车和B车的换道优先级分数中，必然会存在一个换道优先级分数大于或等于2，另一个换道优先级分数则小于2。基于此，可判断A车的换道优先级分数是否大于或等于2；若是，则可继续向中间车道进行换道行驶；若否，则取消换道行驶，并换回至第一车道中心线上进行行驶。由此可见，在A车和B车中，得到2分及以上的车辆可拥有向目标车道换道的优先权，可以继续换道过程；如果得到1分或者0分则将选择避让，即取消换道。并且，通过上述评分逻辑可知，对于右侧车道中的车辆来说，只要其在横向或者纵向位置中的一项占优，就认为它拥有了换道的优先权；而对于位于左侧车道中的车辆来说，只有当 横向和纵向位置同时占优，才拥有换道的优先权。
需要说明的是，由于左右两侧车道的车辆相应跨车道觉察线的位置和换道觉察速度可能不同，因此在换道过程中对另一侧车道换道车辆的判断是一个持续的过程，即存在B车发现A车正在换道，而且B车认为自己有优先权，继续换道，而与此同时，A车还未跨越觉察线而并未觉察B车从而继续换道的情况，所以这个判断过程是持续进行的过程，即当这里提到的A车也跨越跨车道觉察线后(并意识到B车横向速度大于Vo)，会和B车互相观察到，从而同时应用上文的评分逻辑来对两车谁拥有优先权进行判断。
基于上述车辆控制方法实施例的描述，本申请实施例还公开了一种车辆控制装置，所述车辆控制装置可以是运行于计算机设备中的一个计算机程序(包括程序代码)。该车辆控制装置可以执行图2以及图4所示的车辆控制方法。请参见图7，所述车辆控制装置可以运行如下单元：
控制单元701，用于控制第一车辆在第一车道上行驶，所述第一车道所在的道路区域中还包括：第二车道以及位于所述第一车道和所述第二车道之间的中间车道；其中，所述第二车道和所述中间车道均与所述第一车道同向；
所述控制单元701，还用于若所述第一车辆欲换道至所述中间车道，则控制所述第一车辆向所述中间车道进行换道行驶；
处理单元702，用于在所述第一车辆的换道行驶过程中，观察所述第二车道；
所述处理单元702，还用于在观察到所述第二车道中存在向所述中间车道进行换道行驶的第二车辆时，确定所述第一车辆的当前状态信息以及所述第二车辆的当前状态信息；
所述控制单元701，还用于根据所述第一车辆的当前状态信息和所述第二车辆的当前状态信息，确定所述第一车辆的目标行驶动作，并控制所述第一车辆执行所述目标行驶动作。
在一种实施方式中，处理单元702在用于在所述第一车辆的换道行驶过程中，观察所述第二车道时，可具体用于：
在所述第一车辆的换道行驶过程中，确定所述第一车道中的第一跨车道觉察线；
若检测到所述第一车辆行驶至所述第一跨车道觉察线，或检测到所述第一车辆驶过所述第一跨车道觉察线，则开始观察所述第二车道；
其中，所述第一跨车道觉察线位于第一车道分隔线和目标行驶线之间；所述第一车道分隔线是指所述第一车道和所述中间车道之间的车道分隔线，所述目标行驶线是指所述第一车辆在开始换道前，在所述第一车道中沿着行驶的线。
另一种实施方式中，处理单元702还可用于：
在观察所述第二车道的过程中，在观察到所述第二车道中存在车辆的情况下，确定存在的车辆的横向速度；
若所述横向速度大于换道觉察速度，则确定所述存在的车辆处于向所述中间车道进行换道行驶的状态，并将所述存在的车辆确定为所述第二车道中向所述中间车道进行换道行驶的第二车辆；
若所述横向速度小于或等于所述换道觉察速度，则确定所述存在的车辆未向所述中间车道进行换道行驶，并确定所述第二车道中不存在向所述中间车道进行换道行驶的第二车辆。
另一种实施方式中，控制单元701在用于根据所述第一车辆的当前状态信息和所述第二车辆的当前状态信息，确定所述第一车辆的目标行驶动作时，可具体用于：
根据所述第一车辆的当前状态信息和所述第二车辆的当前状态信息，对所述第一车辆和所述第二车辆进行换道优先级评分，得到评分结果；
基于所述评分结果从所述第一车辆和所述第二车辆中，选取拥有向所述中间车道换道的先行权的车辆；
根据选取结果确定所述第一车辆的目标行驶动作。
另一种实施方式中，所述评分结果包括所述第一车辆的换道优先级分数和所述第二车辆的换道优先级分数；相应的，控制单元701在用于基于所述评分结果从所述第一车辆和所述第二车辆中，选取拥有向所述中间车道换道的先行权的车辆时，可具体用于：
根据所述第一车辆的换道优先级分数和所述第二车辆的换道优先级分数，从所述第一车辆和所述第二车辆中选取换道优先级分数大于分数阈值的车辆，作为拥有向所述中间车道换道的先行权的车辆；
或者，根据所述第一车辆的换道优先级分数和所述第二车辆的换道优先级分数，从所述第一车辆和所述第二车辆中选取较大换道优先级分数对应的车辆，作为拥有向所述中间车道换道的先行权的车辆。
另一种实施方式中，控制单元701在用于根据选取结果确定所述第一车辆的目标行驶动作时，可具体用于：
若所述选取结果包括所述第一车辆，则将继续向所述中间车道进行换道行驶的动作，确定为所述第一车辆的目标行驶动作；
若所述选取结果包括所述第二车辆，则将取消向所述中间车道进行换道行驶的动作，确定为所述第一车辆的目标行驶动作。
另一种实施方式中，任一当前状态信息包括：一个或多个状态维度下的状态数据；所述评分结果包括：所述第一车辆的换道优先级分数和所述第二车辆的换道优先级分数；
相应的，控制单元701在用于根据所述第一车辆的当前状态信息和所述第二车辆的当前状态信息，对所述第一车辆和所述第二车辆进行换道优先级评分，得到评分结果时，可具体用于：
遍历所述第一车辆的当前状态信息中的各状态维度下的状态数据，确定当前遍历的第一状态数据，所述第一状态数据所处的状态维度为当前状态维度；
将所述第二车辆的当前状态信息中处于所述当前状态维度下的状态数据，作为第二状态数据；
按照所述当前状态维度对应的换道优先级评分策略，根据所述第一状态数据和所述第二状态数据，评分得到所述第一车辆在所述当前状态维度下的分数，以及所述第二车辆在所述当前状态维度下的分数；
在所述第一车辆的当前状态信息中的各状态维度下的状态数据均被遍历后，基于所述第一车辆在所述各状态维度下的分数，确定所述第一车辆的换道优先级分数；以及，基于所述第二车辆在所述各状态维度下的分数，确定所述第二车辆的换道优先级分数。
另一种实施方式中，所述当前状态维度包括位置方位维度；所述第一状态数据包括：所述第一车辆所处的第一车道相对于所述中间车道的位置方位；所述第二状态数据包括：所述第二车辆所处的第二车道相对于所述中间车道的位置方位；
相应的，控制单元701在用于按照所述当前状态维度对应的换道优先级评分策略，根据所述第一状态数据和所述第二状态数据，评分得到所述第一车辆在所述当前状态维度下的分数，以及所述第二车辆在所述当前状态维度下的分数时，可具体用于：
若所述第一状态数据中的位置方位为先行方位，则将第一分数确定为所述第一车辆在所述当前状态维度下的分数，并将第二分数确定为所述第二车辆在所述当前状态维度下的分数；其中，所述第一分数大于所述第二分数；
若所述第二状态数据中的位置方位为先行方位，则将所述第二分数确定为所述第一车辆在所述当前状态维度下的分数，并将所述第一分数确定为所述第二车辆在所述当前状态维度下的分数。
另一种实施方式中，所述当前状态维度包括纵向距离维度；所述第一状态数据包括：所述第一车辆的当前位置与所述道路区域中的基准点之间的纵向距离；所述第二状态数据包括：所述第二车辆的当前位置与所述基准点之间的纵向距离；
相应的，控制单元701在用于按照所述当前状态维度对应的换道优先级评分策略，根据所述第一状态数据和所述第二状态数据，评分得到所述第一车辆在所述当前状态维度下的分数，以及所述第二车辆在所述当前状态维度下的分数时，可具体用于：
对所述第一状态数据中的纵向距离和所述第二状态数据中的纵向距离进行差值运算，得到纵向距离差值；
若所述纵向距离差值大于纵向差值阈值，则将第三分数确定为所述第一车辆在所述当前状态维度下的分数，并将第四分数确定为所述第二车辆在所述当前状态维度下的分数；其中，所述第三分数大于所述第四分数；
若所述纵向距离差值小于所述纵向差值阈值，则将所述第四分数确定为所述第一车辆在所述当前状态维度下的分数，并将所述第三分数确定为所述第二车辆在所述当前状态维度下的分数。
另一种实施方式中，所述当前状态维度包括横向距离维度；所述第一状态数据包括：所述第一车辆的当前位置与所述中间车道的车道中心线之间的横向距离；所述第二状态数据包括：所述第二车辆的当前位置与所述中间车道的车道中心线之间的横向距离；
相应的，控制单元701在用于按照所述当前状态维度对应的换道优先级评分策略，根据所述第一状态数据和所述第二状态数据，评分得到所述第一车辆在所述当前状态维度下的分数，以及所述第二车辆在所述当前状态维度下的分数时，可具体用于：
对所述第一状态数据中的横向距离和所述第二状态数据中的横向距离进行差值运算，得到横向距离差值；
若所述横向距离差值大于横向差值阈值，则将第五分数确定为所述第一车辆在所述当前状态维度下的分数，并将第六分数确定为所述第二车辆在所述当前状态维度下的分数；其中，所述第五分数小于所述第六分数；
若所述横向距离差值小于所述横向差值阈值，则将所述第六分数确定为所述第一车辆在所述当前状态维度下的分数，并将所述第五分数确定为所述第二车辆在所述当前状态维度下的分数。
根据本申请的一个实施例，图2以及图4所示的方法所涉及的各个步骤均可以是由图7所示的车辆控制装置中的各个单元来执行的。例如，图2中所示的步骤S201-S202均可由图7中所示的控制单元701来执行，步骤S203-S204均可由图7中所示的处理单元702来执行，步骤S205可由图7中所示的控制单元701来执行；又如，图4中所示的步骤S401以及步骤S402中的“若第一车辆欲换道至中间车道，则控制第一车辆向中间车道进行换道行驶”均可由图7中所示的控制单元701来执行，步骤S402中的“在第一车辆的换道行驶过程中，确定第一车道中的第一跨车道觉察线”以及步骤S403-S404均可由图7中所示的处理单元702来执行，步骤S405-S407均可由图7中所示的控制单元701来执行，等等。
根据本申请的另一个实施例，图7所示的车辆控制装置中的各个单元可以分别或全部合并为一个或若干个另外的单元，或者其中的某个(些)单元还可以再拆分为功能上更小的多个单元，这可以实现同样的操作，而不影响本申请的实施例的技术效果的实现。上述单元是基于逻辑功能划分的，在实际应用中，一个单元的功能也可以由多个单元来实现，或者多个单元的功能由一个单元实现。在本申请的其它实施例中，基于车辆控制装置也可以包括其它单元，在实际应用中，这些功能也可以由其它单元协助实现，并且可以由多个单元协作实现。
根据本申请的另一个实施例，可以通过在包括中央处理单元(CPU)、随机存取存储介质(RAM)、只读存储介质(ROM)等处理元件和存储元件的例如计算机的通用计算设备上运行能够执行如图2或图4中所示的相应方法所涉及的各步骤的计算机程序(包括程序代码)，来构造如图7中所示的车辆控制装置，以及来实现本申请实施例的车辆控制方法。所述计算机程序可以记载于例如计算机可读记录介质上，并通过计算机可读记录介质装载于上述计算设备中，并在其中运行。
基于上述方法实施例以及装置实施例的描述，本申请实施例还提供一种计算机设备。请参见图8，该计算机设备至少包括处理器801以及计算机存储介质804。其中，该计算机设备还可以进一步包括输入接口802和输出接口803。计算机设备内的处理器801、输入接口802、输出接口803以及计算机存储介质804可通过总线或其他方式连接。计算机存储介质804可以存储在计算机设备的存储器中，所述计算机存储介质804用于存储计算机程序，所述计算机程序包括程序指令，所述处理器801用于执行所述计算机存储介质804存储的程序指令。处理器801(或称CPU(Central Processing Unit，中央处理器))是计算机设备的计算核心以及控制核心，其适于实现一条或多条指令，具体适于加载并执行一条或多条指令从而实现相应方法流程或相应功能。
在一个实施例中，本申请实施例所述的处理器801可以用于进行一系列的车辆控制，具体包括：控制第一车辆在第一车道上行驶，所述第一车道所在的道路区域中还包括：第二车道以及位于所述第一车道和所述第二车道之间的中间车道；其中，所述第二车道和所述中间车道均与所述第一车道同向；若所述第一车辆欲换道至所述中间车道，则控制所述第一车辆向所述中间车道进行换道行驶；并在所述第一车辆的换道行驶过程中，观察所述第二车道；在观察到所述第二车道中存在向所述中间车道进行换道行驶的第二车辆时，确定所述第一车辆的当前状态信息以及所述第二车辆的当前状态信息；根据所述第一车辆的当前状态信息和所述第二车辆的当前状态信息，确定所述第一车辆的目标行驶动作，并控制所述第一车辆执行所述目标行驶动作，等等。
本申请实施例还提供了一种计算机存储介质(Memory)，所述计算机存储介质是计算机设备中的记忆设备，用于存放程序和数据。可以理解的是，此处的计算机存储介质既可以包括计算机设备中的内置存储介质，当然也可以包括计算机设备所支持的扩展存储介质。计算机存储介质提供存储空间，该存储空间存储了计算机设备的操作系统。并且，在该存储空间中还存放了适于被处理器801加载并执行的一条或多条的指令，这些指令可以是一个或一个以上的计算机程序(包括程序代码)。需要说明的是，此处的计算机存储介质可以是高速RAM存储器，也可以是非易失性存储器(non-transitory memory)，例如至少一个磁盘存储器；还可以是至少一个位于远离前述处理器的计算机存储介质。
在一个实施例中，可由处理器加载并执行计算机存储介质中存放的一条或多条指令，以实现上述有关图2或图4所示的车辆控制方法实施例中的方法的相应步骤；具体实现中，计算机存储介质中的一条或多条指令由处理器加载并执行如下步骤：
控制第一车辆在第一车道上行驶，所述第一车道所在的道路区域中还包括：第二车道以及位于所述第一车道和所述第二车道之间的中间车道；其中，所述第二车道和所述中间车道均与所述第一车道同向；
若所述第一车辆欲换道至所述中间车道，则控制所述第一车辆向所述中间车道进行换道行驶；并在所述第一车辆的换道行驶过程中，观察所述第二车道；
在观察到所述第二车道中存在向所述中间车道进行换道行驶的第二车辆时，确定所述第一车辆的当前状态信息以及所述第二车辆的当前状态信息；
根据所述第一车辆的当前状态信息和所述第二车辆的当前状态信息，确定所述第一车辆的目标行驶动作，并控制所述第一车辆执行所述目标行驶动作。
在一种实施方式中，在所述第一车辆的换道行驶过程中，观察所述第二车道时，所述一条或多条指令可由处理器加载并具体执行：
在所述第一车辆的换道行驶过程中，确定所述第一车道中的第一跨车道觉察线；
若检测到所述第一车辆行驶至所述第一跨车道觉察线，或检测到所述第一车辆驶过所述第一跨车道觉察线，则开始观察所述第二车道；
其中，所述第一跨车道觉察线位于第一车道分隔线和目标行驶线之间；所述第一车道分隔线是指所述第一车道和所述中间车道之间的车道分隔线，所述目标行驶线是指所述第一车辆在开始换道前，在所述第一车道中沿着行驶的线。
另一种实施方式中，所述一条或多条指令还可以由处理器加载并具体执行：
在观察所述第二车道的过程中，在观察到所述第二车道中存在车辆的情况下，确定存在的车辆的横向速度；
若所述横向速度大于换道觉察速度，则确定所述存在的车辆处于向所述中间车道进行换道行驶的状态，并将所述存在的车辆确定为所述第二车道中向所述中间车道进行换道行驶的第二车辆；
若所述横向速度小于或等于所述换道觉察速度，则确定所述存在的车辆未向所述中间车道进行换道行驶，并确定所述第二车道中不存在向所述中间车道进行换道行驶的第二车辆。
另一种实施方式中，在根据所述第一车辆的当前状态信息和所述第二车辆的当前状态信息，确定所述第一车辆的目标行驶动作时，所述一条或多条指令可由处理器加载并具体执行：
根据所述第一车辆的当前状态信息和所述第二车辆的当前状态信息，对所述第一车辆和所述第二车辆进行换道优先级评分，得到评分结果；
基于所述评分结果从所述第一车辆和所述第二车辆中，选取拥有向所述中间车道换道的先行权的车辆；
根据选取结果确定所述第一车辆的目标行驶动作。
另一种实施方式中，所述评分结果包括所述第一车辆的换道优先级分数和所述第二车辆的换道优先级分数；相应的，在基于所述评分结果从所述第一车辆和所述第二车辆中，选取拥有向所述中间车道换道的先行权的车辆时，所述一条或多条指令可由处理器加载并具体执行：
根据所述第一车辆的换道优先级分数和所述第二车辆的换道优先级分数，从所述第一车辆和所述第二车辆中选取换道优先级分数大于分数阈值的车辆，作为拥有向所述中间车道换道的先行权的车辆；
或者，根据所述第一车辆的换道优先级分数和所述第二车辆的换道优先级分数，从所述第一车辆和所述第二车辆中选取较大换道优先级分数对应的车辆，作为拥有向所述中间车道换道的先行权的车辆。
另一种实施方式中，在根据选取结果确定所述第一车辆的目标行驶动作时，所述一条或多条指令可由处理器加载并具体执行：
若所述选取结果包括所述第一车辆，则将继续向所述中间车道进行换道行驶的动作，确定为所述第一车辆的目标行驶动作；
若所述选取结果包括所述第二车辆，则将取消向所述中间车道进行换道行驶的动作，确定为所述第一车辆的目标行驶动作。
另一种实施方式中，任一当前状态信息包括：一个或多个状态维度下的状态数据；所述评分结果包括：所述第一车辆的换道优先级分数和所述第二车辆的换道优先级分数；
相应的，在根据所述第一车辆的当前状态信息和所述第二车辆的当前状态信息，对所述第一车辆和所述第二车辆进行换道优先级评分，得到评分结果时，所述一条或多条指令可由处理器加载并具体执行：
遍历所述第一车辆的当前状态信息中的各状态维度下的状态数据，确定当前遍历的第一状态数据，所述第一状态数据所处的状态维度为当前状态维度；
将所述第二车辆的当前状态信息中处于所述当前状态维度下的状态数据，作为第二状态数据；
按照所述当前状态维度对应的换道优先级评分策略，根据所述第一状态数据和所述第二状态数据，评分得到所述第一车辆在所述当前状态维度下的分数，以及所述第二车辆在所述当前状态维度下的分数；
在所述第一车辆的当前状态信息中的各状态维度下的状态数据均被遍历后，基于所述第一车辆在所述各状态维度下的分数，确定所述第一车辆的换道优先级分数；以及，基于所述第二车辆在所述各状态维度下的分数，确定所述第二车辆的换道优先级分数。
另一种实施方式中，所述当前状态维度包括位置方位维度；所述第一状态数据包括：所述第一车辆所处的第一车道相对于所述中间车道的位置方位；所述第二状态数据包括：所述第二车辆所处的第二车道相对于所述中间车道的位置方位；
相应的，在按照所述当前状态维度对应的换道优先级评分策略，根据所述第一状态数据和所述第二状态数据，评分得到所述第一车辆在所述当前状态维度下的分数，以及所述第二车辆在所述当前状态维度下的分数时，所述一条或多条指令可由处理器加载并具体执行：
若所述第一状态数据中的位置方位为先行方位，则将第一分数确定为所述第一车辆在所述当前状态维度下的分数，并将第二分数确定为所述第二车辆在所述当前状态维度下的分数；其中，所述第一分数大于所述第二分数；
若所述第二状态数据中的位置方位为先行方位，则将所述第二分数确定为所述第一车辆在所述当前状态维度下的分数，并将所述第一分数确定为所述第二车辆在所述当前状态维度下的分数。
另一种实施方式中，所述当前状态维度包括纵向距离维度；所述第一状态数据包括：所述第一车辆的当前位置与所述道路区域中的基准点之间的纵向距离；所述第二状态数据包括：所述第二车辆的当前位置与所述基准点之间的纵向距离；
相应的，在按照所述当前状态维度对应的换道优先级评分策略，根据所述第一状态数据和所述第二状态数据，评分得到所述第一车辆在所述当前状态维度下的分数，以及所述第二车辆在所述当前状态维度下的分数时，所述一条或多条指令可由处理器加载并具体执行：
对所述第一状态数据中的纵向距离和所述第二状态数据中的纵向距离进行差值运算，得到纵向距离差值；
若所述纵向距离差值大于纵向差值阈值，则将第三分数确定为所述第一车辆在所述当前状态维度下的分数，并将第四分数确定为所述第二车辆在所述当前状态维度下的分数；其中，所述第三分数大于所述第四分数；
若所述纵向距离差值小于所述纵向差值阈值，则将所述第四分数确定为所述第一车辆在所述当前状态维度下的分数，并将所述第三分数确定为所述第二车辆在所述当前状态维度下的分数。
另一种实施方式中，所述当前状态维度包括横向距离维度；所述第一状态数据包括：所述第一车辆的当前位置与所述中间车道的车道中心线之间的横向距离；所述第二状态数据包括：所述第二车辆的当前位置与所述中间车道的车道中心线之间的横向距离；
相应的，在按照所述当前状态维度对应的换道优先级评分策略，根据所述第一状态数据和所述第二状态数据，评分得到所述第一车辆在所述当前状态维度下的分数，以及所述第二车辆在所述当前状态维度下的分数时，所述一条或多条指令可由处理器加载并具体执行：
对所述第一状态数据中的横向距离和所述第二状态数据中的横向距离进行差值运算，得到横向距离差值；
若所述横向距离差值大于横向差值阈值，则将第五分数确定为所述第一车辆在所述当前状态维度下的分数，并将第六分数确定为所述第二车辆在所述当前状态维度下的分数；其中，所述第五分数小于所述第六分数；
若所述横向距离差值小于所述横向差值阈值，则将所述第六分数确定为所述第一车辆在所述当前状态维度下的分数，并将所述第五分数确定为所述第二车辆在所述当前状态维度下的分数。
本申请实施例在考虑到左右两侧车道中的车辆同时向中间车道换道的情况下，可在第一车辆从第一车道向中间车道进行换道行驶的过程中，观察位于中间车道的另一侧的第二车道中是否存在向中间车道进行换道行驶的第二车辆，这样可有效提升车辆的换道行为的真实性，从而提升车辆行驶的安全性。进一步的，若观察第二车道存在该第二车辆，则可根据第一车辆的当前状态信息和第二车辆的当前状态信息，确定第一车辆的目标行驶动作，并控制第一车辆执行该目标行驶动作。通过考虑第一车辆和第二车辆的当前状态信息来确定第一车辆的目标行驶动作，一方面可使得目标行驶动作是较为安全的，从而进一步提升车辆行驶的安全性；另一方面，可实现随着第一车辆和第二车辆的当前状态信息的不同，确定出的目标行驶动作也不同，这样可使得第一车辆在换道过程中不局限于一种行驶动作，可提升第一车辆的换道行为的灵活性，进而提升车辆行驶的安全性。
需要说明的是，根据本申请实施例的一个方面，还提供了一种计算机程序产品或计算机程序，该计算机程序产品或计算机程序包括计算机指令，该计算机指令存储在计算机可读存储介质中。计算机设备的处理器从计算机可读存储介质读取该计算机指令，处理器执行该计算机指令，使得该计算机设备执行上述图2或图4所示的车辆控制方法实施例方面的各种方式中提供的方法。
并且，应理解的是，以上所揭露的仅为本申请较佳实施例而已，当然不能以此来限定本申请之权利范围，因此依本申请权利要求所作的等同变化，仍属本申请所涵盖的范围。

Claims (21)

  1. 一种车辆控制方法，由计算机设备执行，其特征在于，包括：
    控制第一车辆在第一车道上行驶，所述第一车道所在的道路区域中还包括：第二车道以及位于所述第一车道和所述第二车道之间的中间车道；其中，所述第二车道和所述中间车道均与所述第一车道同向；
    若所述第一车辆欲换道至所述中间车道，则控制所述第一车辆向所述中间车道进行换道行驶；并在所述第一车辆的换道行驶过程中，观察所述第二车道；
    在观察到所述第二车道中存在向所述中间车道进行换道行驶的第二车辆时，确定所述第一车辆的当前状态信息以及所述第二车辆的当前状态信息；
    根据所述第一车辆的当前状态信息和所述第二车辆的当前状态信息，确定所述第一车辆的目标行驶动作，并控制所述第一车辆执行所述目标行驶动作。
  2. 如权利要求1所述的方法，其特征在于，所述在所述第一车辆的换道行驶过程中，观察所述第二车道，包括：
    在所述第一车辆的换道行驶过程中，确定所述第一车道中的第一跨车道觉察线；
    若检测到所述第一车辆行驶至所述第一跨车道觉察线，或检测到所述第一车辆驶过所述第一跨车道觉察线，则开始观察所述第二车道；
    其中，所述第一跨车道觉察线位于第一车道分隔线和目标行驶线之间；所述第一车道分隔线是指所述第一车道和所述中间车道之间的车道分隔线，所述目标行驶线是指所述第一车辆在开始换道前，在所述第一车道中沿着行驶的线。
  3. 如权利要求2所述的方法，其特征在于，所述第一跨车道觉察线是根据所述第一车辆的激进程度确定的；
    随着所述第一车辆的激进程度越高，所述第一跨车道觉察线和所述第一车道分隔线之间的距离越小。
  4. 如权利要求2或3所述的方法，其特征在于，所述第一车辆行驶至所述第一跨车道觉察线包括：所述第一车辆的参照点位于所述第一跨车道觉察线上；
    所述第一车辆驶过所述第一跨车道觉察线包括：所述第一车辆的参照点朝着所述中间车道的方向，越过所述第一跨车道觉察线；
    其中，所述第一车辆的参照点包括：所述第一车辆的质心，或者所述第一车辆的车头角中距离所述中间车道最近的车头角。
  5. 如权利要求1所述的方法，其特征在于，所述方法还包括：
    在观察所述第二车道的过程中，在观察到所述第二车道中存在车辆的情况下，确定存在的车辆的横向速度；
    若所述横向速度大于换道觉察速度，则确定所述存在的车辆处于向所述中间车道进行换道行驶的状态，并将所述存在的车辆确定为所述第二车道中向所述中间车道进行换道行驶的第二车辆；
    若所述横向速度小于或等于所述换道觉察速度，则确定所述存在的车辆未向所述中间车道进行换道行驶，并确定所述第二车道中不存在向所述中间车道进行换道行驶的第二车辆。
  6. 如权利要求5所述的方法，其特征在于，所述换道觉察速度是根据所述第一车辆的激进程度确定的，且所述换道觉察速度与所述第一车辆的激进程度成正比。
  7. 如权利要求1所述的方法，其特征在于，所述根据所述第一车辆的当前状态信息和所述 第二车辆的当前状态信息，确定所述第一车辆的目标行驶动作，包括：
    根据所述第一车辆的当前状态信息和所述第二车辆的当前状态信息，对所述第一车辆和所述第二车辆进行换道优先级评分，得到评分结果；
    基于所述评分结果从所述第一车辆和所述第二车辆中，选取拥有向所述中间车道换道的先行权的车辆；
    根据选取结果确定所述第一车辆的目标行驶动作。
  8. 如权利要求7所述的方法，其特征在于，所述评分结果包括所述第一车辆的换道优先级分数和所述第二车辆的换道优先级分数；所述基于所述评分结果从所述第一车辆和所述第二车辆中，选取拥有向所述中间车道换道的先行权的车辆，包括：
    根据所述第一车辆的换道优先级分数和所述第二车辆的换道优先级分数，从所述第一车辆和所述第二车辆中选取换道优先级分数大于分数阈值的车辆，作为拥有向所述中间车道换道的先行权的车辆；
    或者，根据所述第一车辆的换道优先级分数和所述第二车辆的换道优先级分数，从所述第一车辆和所述第二车辆中选取较大换道优先级分数对应的车辆，作为拥有向所述中间车道换道的先行权的车辆。
  9. 如权利要求7所述的方法，其特征在于，所述根据选取结果确定所述第一车辆的目标行驶动作，包括：
    若所述选取结果包括所述第一车辆，则将继续向所述中间车道进行换道行驶的动作，确定为所述第一车辆的目标行驶动作；
    若所述选取结果包括所述第二车辆，则将取消向所述中间车道进行换道行驶的动作，确定为所述第一车辆的目标行驶动作。
  10. 如权利要求7-9任一项所述的方法，其特征在于，任一当前状态信息包括：一个或多个状态维度下的状态数据；所述评分结果包括：所述第一车辆的换道优先级分数和所述第二车辆的换道优先级分数；
    所述根据所述第一车辆的当前状态信息和所述第二车辆的当前状态信息，对所述第一车辆和所述第二车辆进行换道优先级评分，得到评分结果，包括：
    遍历所述第一车辆的当前状态信息中的各状态维度下的状态数据，确定当前遍历的第一状态数据，所述第一状态数据所处的状态维度为当前状态维度；
    将所述第二车辆的当前状态信息中处于所述当前状态维度下的状态数据，作为第二状态数据；
    按照所述当前状态维度对应的换道优先级评分策略，根据所述第一状态数据和所述第二状态数据，评分得到所述第一车辆在所述当前状态维度下的分数，以及所述第二车辆在所述当前状态维度下的分数；
    在所述第一车辆的当前状态信息中的各状态维度下的状态数据均被遍历后，基于所述第一车辆在所述各状态维度下的分数，确定所述第一车辆的换道优先级分数；以及，基于所述第二车辆在所述各状态维度下的分数，确定所述第二车辆的换道优先级分数。
  11. 如权利要求10所述的方法，其特征在于，所述当前状态维度包括位置方位维度；所述第一状态数据包括：所述第一车辆所处的第一车道相对于所述中间车道的位置方位；所述第二状态数据包括：所述第二车辆所处的第二车道相对于所述中间车道的位置方位；
    所述按照所述当前状态维度对应的换道优先级评分策略，根据所述第一状态数据和所述第二状态数据，评分得到所述第一车辆在所述当前状态维度下的分数，以及所述第二车辆在所述当前状态维度下的分数，包括：
    若所述第一状态数据中的位置方位为先行方位，则将第一分数确定为所述第一车辆在所述当前状态维度下的分数，并将第二分数确定为所述第二车辆在所述当前状态维度下的分数；其中，所述第一分数大于所述第二分数；
    若所述第二状态数据中的位置方位为先行方位，则将所述第二分数确定为所述第一车辆在所述当前状态维度下的分数，并将所述第一分数确定为所述第二车辆在所述当前状态维度下的分数。
  12. 如权利要求10所述的方法，其特征在于，所述当前状态维度包括纵向距离维度；所述第一状态数据包括：所述第一车辆的当前位置与所述道路区域中的基准点之间的纵向距离；所述第二状态数据包括：所述第二车辆的当前位置与所述基准点之间的纵向距离；
    所述按照所述当前状态维度对应的换道优先级评分策略，根据所述第一状态数据和所述第二状态数据，评分得到所述第一车辆在所述当前状态维度下的分数，以及所述第二车辆在所述当前状态维度下的分数，包括：
    对所述第一状态数据中的纵向距离和所述第二状态数据中的纵向距离进行差值运算，得到纵向距离差值；
    若所述纵向距离差值大于纵向差值阈值，则将第三分数确定为所述第一车辆在所述当前状态维度下的分数，并将第四分数确定为所述第二车辆在所述当前状态维度下的分数；其中，所述第三分数大于所述第四分数；
    若所述纵向距离差值小于所述纵向差值阈值，则将所述第四分数确定为所述第一车辆在所述当前状态维度下的分数，并将所述第三分数确定为所述第二车辆在所述当前状态维度下的分数。
  13. 如权利要求10所述的方法，其特征在于，所述当前状态维度包括横向距离维度；所述第一状态数据包括：所述第一车辆的当前位置与所述中间车道的车道中心线之间的横向距离；所述第二状态数据包括：所述第二车辆的当前位置与所述中间车道的车道中心线之间的横向距离；
    所述按照所述当前状态维度对应的换道优先级评分策略，根据所述第一状态数据和所述第二状态数据，评分得到所述第一车辆在所述当前状态维度下的分数，以及所述第二车辆在所述当前状态维度下的分数，包括：
    对所述第一状态数据中的横向距离和所述第二状态数据中的横向距离进行差值运算，得到横向距离差值；
    若所述横向距离差值大于横向差值阈值，则将第五分数确定为所述第一车辆在所述当前状态维度下的分数，并将第六分数确定为所述第二车辆在所述当前状态维度下的分数；其中，所述第五分数小于所述第六分数；
    若所述横向距离差值小于所述横向差值阈值，则将所述第六分数确定为所述第一车辆在所述当前状态维度下的分数，并将所述第五分数确定为所述第二车辆在所述当前状态维度下的分数。
  14. 一种车辆控制装置，其特征在于，包括：
    控制单元，用于控制第一车辆在第一车道上行驶，所述第一车道所在的道路区域中还包括：第二车道以及位于所述第一车道和所述第二车道之间的中间车道；其中，所述第二车道和所述中间车道均与所述第一车道同向；
    所述控制单元，还用于若所述第一车辆欲换道至所述中间车道，则控制所述第一车辆向所述中间车道进行换道行驶；
    处理单元，用于在所述第一车辆的换道行驶过程中，观察所述第二车道；
    所述处理单元，还用于在观察到所述第二车道中存在向所述中间车道进行换道行驶的第二车辆时，确定所述第一车辆的当前状态信息以及所述第二车辆的当前状态信息；
    所述控制单元，还用于根据所述第一车辆的当前状态信息和所述第二车辆的当前状态信息，确定所述第一车辆的目标行驶动作，并控制所述第一车辆执行所述目标行驶动作。
  15. 如权利要求14所述的装置，其特征在于，所述处理单元进一步用于：
    在所述第一车辆的换道行驶过程中，确定所述第一车道中的第一跨车道觉察线；
    若检测到所述第一车辆行驶至所述第一跨车道觉察线，或检测到所述第一车辆驶过所述第一跨车道觉察线，则开始观察所述第二车道；
    其中，所述第一跨车道觉察线位于第一车道分隔线和目标行驶线之间；所述第一车道分隔线是指所述第一车道和所述中间车道之间的车道分隔线，所述目标行驶线是指所述第一车辆在开始换道前，在所述第一车道中沿着行驶的线。
  16. 如权利要求14所述的装置，其特征在于，所述处理单元进一步用于：
    在观察所述第二车道的过程中，在观察到所述第二车道中存在车辆的情况下，确定存在的车辆的横向速度；
    若所述横向速度大于换道觉察速度，则确定所述存在的车辆处于向所述中间车道进行换道行驶的状态，并将所述存在的车辆确定为所述第二车道中向所述中间车道进行换道行驶的第二车辆；
    若所述横向速度小于或等于所述换道觉察速度，则确定所述存在的车辆未向所述中间车道进行换道行驶，并确定所述第二车道中不存在向所述中间车道进行换道行驶的第二车辆。
  17. 如权利要求14所述的装置，其特征在于，所述控制单元进一步用于：
    根据所述第一车辆的当前状态信息和所述第二车辆的当前状态信息，对所述第一车辆和所述第二车辆进行换道优先级评分，得到评分结果；
    基于所述评分结果从所述第一车辆和所述第二车辆中，选取拥有向所述中间车道换道的先行权的车辆；
    根据选取结果确定所述第一车辆的目标行驶动作。
  18. 如权利要求17所述的装置，其特征在于，所述评分结果包括所述第一车辆的换道优先级分数和所述第二车辆的换道优先级分数；所述控制单元进一步用于：
    根据所述第一车辆的换道优先级分数和所述第二车辆的换道优先级分数，从所述第一车辆和所述第二车辆中选取换道优先级分数大于分数阈值的车辆，作为拥有向所述中间车道换道的先行权的车辆；
    或者，根据所述第一车辆的换道优先级分数和所述第二车辆的换道优先级分数，从所述第一车辆和所述第二车辆中选取较大换道优先级分数对应的车辆，作为拥有向所述中间车道换道的先行权的车辆。
  19. 一种计算机设备，其特征在于，包括处理器和计算机存储介质，所述计算机存储介质用于存储一条或多条指令，当所述一条或多条指令被所述处理器执行时，实现如权利要求1-13任一项所述的车辆控制方法。
  20. 一种计算机存储介质，其特征在于，所述计算机存储介质存储有一条或多条指令，所述一条或多条指令适于由处理器加载并执行上述权1-13任一项所述的车辆控制方法。
  21. 一种计算机程序产品，包括计算机程序，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1-13任一项所述的车辆控制方法。
PCT/CN2022/119827 2021-12-02 2022-09-20 车辆控制方法、装置、设备、介质及计算机程序产品 WO2023098238A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202111462561.X 2021-12-02
CN202111462561.XA CN114103956B (zh) 2021-12-02 2021-12-02 车辆控制方法、装置及计算机程序产品

Publications (1)

Publication Number Publication Date
WO2023098238A1 true WO2023098238A1 (zh) 2023-06-08

Family

ID=80366218

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2022/119827 WO2023098238A1 (zh) 2021-12-02 2022-09-20 车辆控制方法、装置、设备、介质及计算机程序产品

Country Status (2)

Country Link
CN (1) CN114103956B (zh)
WO (1) WO2023098238A1 (zh)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114103956B (zh) * 2021-12-02 2023-11-24 腾讯科技（深圳）有限公司 车辆控制方法、装置及计算机程序产品

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112634627A (zh) * 2019-10-08 2021-04-09 宁波吉利汽车研究开发有限公司 一种高速巡航状态下的换道方法、装置及汽车
US20210206378A1 (en) * 2020-09-24 2021-07-08 Beijing Baidu Netcom Science Technology Co., Ltd. Vehicle control method, apparatus, vehicle, electronic device and storage medium
CN113158349A (zh) * 2021-05-24 2021-07-23 腾讯科技（深圳）有限公司 车辆换道仿真方法、装置、电子设备及存储介质
CN114103956A (zh) * 2021-12-02 2022-03-01 腾讯科技（深圳）有限公司 车辆控制方法、装置及计算机程序产品

Family Cites Families (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP6497284B2 (ja) * 2015-09-15 2019-04-10 株式会社デンソー 車両制御装置、及び車両制御方法
JP6740970B2 (ja) * 2017-07-11 2020-08-19 株式会社デンソー 走行支援装置
CN109035862B (zh) * 2018-08-06 2020-04-14 清华大学 一种基于车车通信的多车协同换道控制方法
CN112298200B (zh) * 2019-07-26 2022-12-23 魔门塔(苏州)科技有限公司 一种车辆的换道方法和装置
CN110780602B (zh) * 2019-09-09 2022-02-18 腾讯科技（深圳）有限公司 一种仿真车辆换道轨迹的构建方法、装置及设备
CN111717199B (zh) * 2020-06-24 2021-09-17 中国第一汽车股份有限公司 自动换道避撞控制方法、装置、车辆及存储介质
CN111798699B (zh) * 2020-06-29 2021-12-07 广州小鹏自动驾驶科技有限公司 车辆驾驶方法、装置、车载计算机、车辆以及存储介质
CN112863249B (zh) * 2021-01-11 2022-08-16 广州小鹏自动驾驶科技有限公司 一种车辆的变道预警方法、装置、车辆和可读存储介质

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112634627A (zh) * 2019-10-08 2021-04-09 宁波吉利汽车研究开发有限公司 一种高速巡航状态下的换道方法、装置及汽车
US20210206378A1 (en) * 2020-09-24 2021-07-08 Beijing Baidu Netcom Science Technology Co., Ltd. Vehicle control method, apparatus, vehicle, electronic device and storage medium
CN113158349A (zh) * 2021-05-24 2021-07-23 腾讯科技（深圳）有限公司 车辆换道仿真方法、装置、电子设备及存储介质
CN114103956A (zh) * 2021-12-02 2022-03-01 腾讯科技（深圳）有限公司 车辆控制方法、装置及计算机程序产品

Also Published As

Publication number Publication date
CN114103956A (zh) 2022-03-01
CN114103956B (zh) 2023-11-24

Similar Documents

Publication Publication Date Title
WO2022105579A1 (zh) 一种基于自动驾驶的控制方法、装置、车辆以及相关设备
US20200262448A1 (en) Decision method, device, equipment in a lane changing process and storage medium
WO2022052406A1 (zh) 一种自动驾驶训练方法、装置、设备及介质
CN113071520B (zh) 车辆行驶控制方法及装置
CN111898211A (zh) 基于深度强化学习的智能车速度决策方法及其仿真方法
CN113682318B (zh) 车辆行驶控制方法及装置
US8849625B2 (en) Distributed process simulator
KR102166811B1 (ko) 심층강화학습과 운전자보조시스템을 이용한 자율주행차량의 제어 방법 및 장치
WO2023098238A1 (zh) 车辆控制方法、装置、设备、介质及计算机程序产品
US11529951B2 (en) Safety system, automated driving system, and methods thereof
CN112829747A (zh) 一种驾驶行为决策方法、装置及存储介质
CN113158349A (zh) 车辆换道仿真方法、装置、电子设备及存储介质
CN111967163B (zh) 车辆仿真控制方法、装置、计算机设备及存储介质
CN114212110A (zh) 障碍物轨迹预测方法、装置、电子设备及存储介质
CN113788028B (zh) 车辆控制方法、装置及计算机程序产品
CN113788029B (zh) 车辆控制方法、装置及计算机程序产品
CN113276860B (zh) 车辆控制方法、装置、电子设备以及存储介质
CN115062202A (zh) 驾驶行为意图及轨迹的预测方法、装置、设备及存储介质
Yang et al. Decision-making in autonomous driving by reinforcement learning combined with planning & control
CN116279450B (zh) 车辆控制方法、装置及电子设备、存储介质
Wang et al. Driving Behavior Model for Multi-Vehicle Interaction at Uncontrolled Intersections Based on Risk Field Considering Drivers' Visual Field Characteristics
CN117232531B (zh) 机器人导航规划方法及存储介质和终端设备
WO2023087157A1 (zh) 一种智能驾驶方法及应用该方法的车辆
CN116611533A (zh) 一种面向高速公路开放场景的自动驾驶汽车控制方法
CN116244649A (zh) 面向自动驾驶博弈的交通弱势参与群体自动分流方法及系统

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: 22900046

Country of ref document: EP

Kind code of ref document: A1