Automatic driving fleet attack method and device based on ghost vehicle, storage medium and electronic equipment

Abstract

The invention provides an automatic driving motorcade attack method and device based on a ghost vehicle, a storage medium and electronic equipment, and relates to the technical field of automatic driving automobile safety, and the method comprises the steps: firstly, obtaining the driving position information and the driving state information of an attacked motorcade; and then, projecting a ghost vehicle in an adjacent lane of the attacked motorcade based on the driving position information, gradually adjusting the projection position of the ghost vehicle based on the driving lane information, and fusing the ghost vehicle into the attacked motorcade until the attacked motorcade is influenced by the ghost vehicle to generate an abnormal behavior. According to the automatic driving motorcade attack method based on the ghost vehicle provided by the invention, the motorcade behavior is influenced under the environment that the attacked motorcade is not directly contacted and the real vehicle is not used, even the abnormal behavior of the real vehicle is extended, and the development of related defense means and the vehicle abnormal behavior monitoring technology is promoted.

Description

Technical Field

[0001] This application relates to the technical field of autonomous vehicle safety, and particularly to an attack method, device, storage medium and electronic device for an autonomous vehicle fleet based on a ghost vehicle. Background Art

[0002] The development of smart cities enables more efficient and safer social operations by leveraging emerging technologies. Autonomous vehicles, as one of the key areas, provide important support for intelligent transportation and environmentally friendly travel. With the rapid advancement of technology, autonomous vehicles have introduced complex fleet management systems (such as platooning, adaptive cruise, and formation driving) in group collaboration and efficient operation. These fleet systems achieve efficient cooperation between vehicles through vehicle-to-vehicle communication technology and vehicle-to-road communication technology, aiming to reduce the accident rate, optimize energy consumption, and improve traffic efficiency.

[0003] However, autonomous vehicle fleets face a series of severe security challenges during collaborative operation. In particular, autonomous driving systems that rely on perception modules and behavior planning algorithms are vulnerable to forged information and communication network attacks, such as false message injection, positioning interference, and vision deception attacks. In addition, the high degree of collaborative dependence in the fleet allows errors at one node to spread to the entire system, leading to chain reaction failures or potential security risks.

[0004] Based on this, there is an urgent need for an attack method for autonomous vehicle fleets to improve the improvement of defense means for autonomous vehicle fleets and the development of vehicle abnormal behavior monitoring technology. Summary of the Invention

[0005] The purpose of this application is to provide an attack method, device, storage medium and electronic device for an autonomous vehicle fleet based on a ghost vehicle, which is used to affect the behavior of the fleet without directly contacting the attacked fleet and without using real vehicles, and even extend to abnormal behaviors of real vehicles, promoting the development of relevant defense means and vehicle abnormal behavior monitoring technology.

[0006] This application provides an attack method for an autonomous vehicle fleet based on a ghost vehicle, including: Obtain the driving position information and driving status information of the attacked fleet; the driving position information includes: the driving road where the attacked fleet is located and the driving lane information; the driving status information includes: the position of each vehicle in the fleet, the driving speed, queue spacing, and queue turning angle of each vehicle; project a ghost vehicle in the adjacent lane of the attacked fleet based on the driving position information, and gradually adjust the projection position of the ghost vehicle based on the driving lane information, and integrate the ghost vehicle into the attacked fleet until the attacked fleet exhibits abnormal behavior under the influence of the ghost vehicle.

[0007] Optionally, projecting a ghost vehicle in an adjacent lane of the attacked vehicle fleet based on the driving position information includes: determining the adjacent lane based on the driving road where the attacked vehicle fleet is located and the driving lane information; the adjacent lane is: in the driving road where the attacked vehicle fleet is located, a lane adjacent to the driving road of the attacked vehicle fleet; projecting the ghost vehicle in the adjacent lane and controlling the movement of the ghost vehicle according to the physical laws of the vehicle; wherein, the moving direction of the ghost vehicle is the same as the driving direction of the attacked vehicle fleet.

[0008] Optionally, gradually adjusting the projection position of the ghost vehicle based on the driving lane information and integrating the ghost vehicle into the attacked vehicle fleet until the attacked vehicle fleet exhibits abnormal behavior under the influence of the ghost vehicle includes: determining the target position in the attacked vehicle fleet to integrate the ghost vehicle based on the relative position information between the ghost vehicle and the attacked vehicle fleet; controlling the moving speed and turning angle of the ghost vehicle based on the driving speed of each vehicle and the queue turning angle, and controlling the ghost vehicle to maintain the same spacing as the adjacent vehicle in the attacked vehicle fleet based on the position of each vehicle in the vehicle fleet and the queue spacing. Wherein, the target position includes any one of the following: in front of the vehicle fleet, behind the vehicle fleet, and in the middle of the vehicle fleet.

[0009] Optionally, gradually adjusting the projection position of the ghost vehicle based on the driving lane information and integrating the ghost vehicle into the attacked vehicle fleet until the attacked vehicle fleet exhibits abnormal behavior under the influence of the ghost vehicle includes: after integrating the ghost vehicle into the attacked vehicle fleet, controlling the ghost vehicle to perform target actions until the attacked vehicle fleet exhibits abnormal behavior under the influence of the ghost vehicle, and then stopping projecting the ghost vehicle; wherein, the target actions include at least one of the following: accelerating, braking, changing lanes, and overtaking.

[0010] Optionally, the abnormal behavior of the attacked vehicle fleet includes: inducing the vehicles in the attacked vehicle fleet to brake, collide, and change lanes.

[0011] This application also provides an attack device for an autonomous driving vehicle fleet based on a ghost vehicle, including: An acquisition module for acquiring the driving position information and driving status information of the attacked vehicle convoy; the driving position information includes: the driving road where the attacked vehicle convoy is located and the driving lane information; the driving status information includes: the position of each vehicle in the convoy, the driving speed of each vehicle, the queue spacing, and the queue turning angle; an attack module for projecting a ghost vehicle in the adjacent lane of the attacked vehicle convoy based on the driving position information, and gradually adjusting the projection position of the ghost vehicle based on the driving lane information, and integrating the ghost vehicle into the attacked vehicle convoy until the attacked vehicle convoy exhibits abnormal behavior due to the influence of the ghost vehicle.

[0012] Optionally, the attack module is specifically configured to determine the adjacent lane based on the driving road where the attacked vehicle convoy is located and the driving lane information; the adjacent lane is: the lane adjacent to the driving road of the attacked vehicle convoy within the driving road where the attacked vehicle convoy is located; the attack module is further specifically configured to project the ghost vehicle in the adjacent lane and control the movement of the ghost vehicle according to the physical laws of the vehicle; wherein, the moving direction of the ghost vehicle is the same as the driving direction of the attacked vehicle convoy.

[0013] Optionally, the attack module is specifically configured to integrate the ghost vehicle into the target position in the attacked vehicle convoy based on the relative position information between the ghost vehicle and the attacked vehicle convoy; the attack module is further specifically configured to control the moving speed and turning angle of the ghost vehicle based on the driving speed of each vehicle and the queue turning angle, and control the ghost vehicle to maintain the same spacing as the adjacent vehicle in the attacked vehicle convoy based on the position of each vehicle in the convoy and the queue spacing; wherein, the target position includes any one of the following: in front of the convoy, behind the convoy, and in the middle of the convoy.

[0014] Optionally, the attack module is specifically configured to control the ghost vehicle to perform a target action after integrating the ghost vehicle into the attacked vehicle convoy, and stop projecting the ghost vehicle until the attacked vehicle convoy exhibits abnormal behavior due to the influence of the ghost vehicle; wherein, the target action includes at least one of the following: accelerating, braking, changing lanes, and overtaking.

[0015] Optionally, the abnormal behavior of the attacked vehicle convoy includes: inducing the vehicles in the attacked vehicle convoy to brake, collide, and change lanes.

[0016] This application also provides a computer program product, including computer programs / instructions, which when executed by a processor implement the steps of the method for attacking an autonomous driving vehicle convoy based on a ghost vehicle as described in any one of the above.

[0017] The present application further provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the program, the steps of any one of the above-mentioned ghost vehicle-based autonomous driving fleet attack methods are implemented.

[0018] The present application further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of any one of the above-mentioned ghost vehicle-based autonomous driving fleet attack methods are implemented.

[0019] For the ghost vehicle-based autonomous driving fleet attack method, device, storage medium, and electronic device provided by the present application, first, the driving position information and driving status information of the attacked fleet are obtained; the driving position information includes: the driving road where the attacked fleet is located and the driving lane information; the driving status information includes: the position of each vehicle in the fleet, the driving speed, queue spacing, and queue turning angle of each vehicle; then, based on the driving position information, ghost vehicles are projected into the adjacent lanes of the attacked fleet, and based on the driving lane information, the projection positions of the ghost vehicles are gradually adjusted to integrate the ghost vehicles into the attacked fleet until the attacked fleet exhibits abnormal behavior under the influence of the ghost vehicles. In this way, the behavior of the fleet can be affected without directly contacting the attacked fleet and without using real vehicles, and even extended to the abnormal behavior of real vehicles, promoting the development of relevant defense means and vehicle abnormal behavior monitoring technologies. Description of the Drawings

[0020] In order to more clearly illustrate the technical solutions in the present application or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0021] Figure 1 is one of the flow diagrams of the ghost vehicle-based autonomous driving fleet attack method provided by the present application; Figure 2 is another flow diagram of the ghost vehicle-based autonomous driving fleet attack method provided by the present application; Figure 3 is a schematic diagram of using ghost vehicles to attack an autonomous driving fleet provided by the present application; Figure 4 is a schematic structural diagram of the ghost vehicle-based autonomous driving fleet attack device provided by the present application; Figure 5 is a schematic structural diagram of the electronic device provided by the present application. Detailed implementation manners

[0022] To make the objectives, technical solutions and advantages of the present application clearer, the technical solutions in the present application will be clearly and completely described below with reference to the accompanying drawings in the present application. Apparently, the described embodiments are some but not all of the embodiments of the present application. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in the present application without making creative efforts shall fall within the protection scope of the present application.

[0023] The terms "first", "second", etc. in the specification and claims of the present application are used to distinguish similar objects and are not used to describe a specific order or sequence. It should be understood that such used data may be interchanged under appropriate circumstances so that the embodiments of the present application can be implemented in an order other than those illustrated or described herein, and the objects distinguished by "first", "second", etc. are generally of the same category and do not limit the number of objects. For example, the first object may be one or multiple. In addition, "and / or" in the specification and claims means at least one of the connected objects, and the character " / " generally indicates an "or" relationship between the associated objects before and after.

[0024] To reveal the safety blind spots existing in the autonomous driving fleet, and at the same time provide an important direction for the improvement of future defense technologies and the optimization of the intelligent transportation ecosystem, the embodiments of the present application provide an attack method for an autonomous driving fleet based on ghost vehicles. This method can affect the behavior of the fleet without directly contacting the attacked fleet and without using real vehicles in the environment, and even extend to the abnormal behavior of physical vehicles. Specifically, it includes: ① By projecting a ghost vehicle, a normally driving fleet is made to think that there is a real vehicle, and by inserting a ghost vehicle into the middle of the fleet, the behavior logic of the fleet is changed, and finally the fleet is affected to make abnormal or even dangerous behaviors; ② This method proposes an attack strategy with almost no economic loss. On the one hand, it points out the blindness of current autonomous driving vehicles in visual recognition, and on the other hand, it can promote relevant researchers to improve defense means and develop vehicle abnormal behavior monitoring technologies.

[0025] The following will, with reference to the accompanying drawings, through specific embodiments and their application scenarios, detail the attack method for an autonomous driving fleet based on ghost vehicles provided by the embodiments of the present application.

[0026] As Figure 1 shown, an attack method for an autonomous driving fleet based on ghost vehicles provided by the embodiments of the present application may include the following steps 101 and 102: Step 101: Obtain the driving position information and driving status information of the attacked fleet.

[0027] Among them, the driving position information includes: the driving road where the attacked convoy is located and the driving lane information; the driving state information includes: the position of each vehicle in the convoy, the driving speed, queue spacing, and queue rotation angle of each vehicle.

[0028] Exemplarily, the driving position information and driving state information of the above-mentioned attacked convoy are mainly for facilitating the projection of the ghost vehicle in subsequent steps. By using this ghost vehicle to attack the autonomous driving convoy, it is possible to affect the convoy behavior without directly contacting the attacked convoy and without using real vehicles, and even extend to abnormal behaviors of real vehicles, promoting the development of relevant defense means and vehicle abnormal behavior monitoring technologies.

[0029] Step 102: Project a ghost vehicle in the adjacent lane of the attacked convoy based on the driving position information, and gradually adjust the projection position of the ghost vehicle based on the driving lane information, and integrate the ghost vehicle into the attacked convoy until the attacked convoy exhibits abnormal behavior under the influence of the ghost vehicle.

[0030] Exemplarily, as Figure 2 shown, for the method for attacking an autonomous driving convoy based on a ghost vehicle provided in an embodiment of the present application, it is first necessary to locate the convoy and lane information, that is, determine the driving position information of the attacked convoy through Global Positioning System (GPS) positioning, and determine the driving lane information of the attacked convoy based on the lane information. Then, project a ghost vehicle (i.e., the above-mentioned ghost vehicle) on the adjacent road of the queue, and gradually move the ghost vehicle to the same road as the convoy. Finally, adjust the behavior of the ghost vehicle and insert it into the convoy to imitate the behavior of the convoy vehicles, and perform abnormal behaviors (such as braking, accelerating, lane changing, overtaking, etc.) to induce the convoy vehicles to have collisions or other abnormal behaviors. In this way, an attack on the autonomous driving convoy is achieved.

[0031] Specifically, the above step 102 may further include the following steps 102a1 and 102a2: Step 102a1: Determine the adjacent lane based on the driving road where the attacked convoy is located and the driving lane information.

[0032] Among them, the adjacent lane is: in the driving road where the attacked convoy is located, the lane adjacent to the driving road of the attacked convoy.

[0033] Step 102a2: Project the ghost vehicle in the adjacent lane and control the movement of the ghost vehicle according to the physical laws of vehicles.

[0034] Among them, the moving direction of the ghost vehicle is the same as the driving direction of the attacked convoy.

[0035] Exemplarily, in order to attack an autonomous driving fleet using a ghost vehicle, the attacker first needs to determine the location information of the autonomous driving fleet (i.e., the attacked fleet mentioned above), that is, the driving location information mentioned above. At the same time, it is also necessary to obtain information such as the position, speed, queue spacing, and turning angle of the vehicles in the fleet (i.e., the driving state information mentioned above). Then, based on the driving location information of the fleet, find the road adjacent to the fleet and project the ghost vehicle on the road. Finally, imitate the physical laws of normal vehicle movement, control the projection of the moving ghost vehicle on the road, and gradually move this projection in the same direction as the target road of the fleet. When the ghost vehicle and the fleet are in adjacent lanes on the same road, adjust the projection position of the ghost vehicle according to the relative position of the ghost vehicle and the fleet, and wait for an opportunity to insert it as a leader in front of the fleet, as a follower behind the fleet, or in the middle of the fleet.

[0036] Specifically, step 102 above may further include the following steps 102b1 and 102b2: Step 102b1, based on the relative position information between the ghost vehicle and the attacked fleet, integrate the ghost vehicle into the target position in the attacked fleet.

[0037] Wherein, the target position includes any one of the following: in front of the fleet, behind the fleet, and in the middle of the fleet.

[0038] Exemplarily, the way for the above ghost vehicle to integrate into the fleet includes: when the ghost vehicle moves to the same road as the fleet, if the ghost vehicle is close to the first vehicle in the fleet, insert it in front of the fleet; if the ghost vehicle is close to the last vehicle in the fleet, insert it behind the fleet; otherwise, insert it in the middle of the fleet.

[0039] Step 102b2, control the moving speed and turning angle of the ghost vehicle based on the driving speed of each vehicle and the queue turning angle, and control the ghost vehicle to maintain the same spacing as the adjacent vehicle in the attacked fleet based on the position of each vehicle in the fleet and the queue spacing.

[0040] Exemplarily, as Figure 3 shown, when initially generating the ghost vehicle, use the proportional, integral, and derivative PID algorithm to adjust the speed and turning angle of the ghost vehicle until the ghost vehicle and the attacked fleet appear on the same road. First, according to the relative position between the ghost vehicle and the fleet, determine the position where the ghost vehicle inserts into the fleet, gradually adjust the projection position of the ghost vehicle to be close to the insertion position, and imitate a normal vehicle changing lanes and inserting into the middle of the fleet.

[0041] After that, continuously adjust the transformation frequency and direction of the projection position of the ghost vehicle so that the distance between the projected ghost vehicle and the vehicles in the adjacent vehicle fleet is approximately the same as the distance between other vehicles in the vehicle fleet, and imitate the forward speed and turning angle of the vehicle fleet to change the projection frequency and direction of the ghost vehicle.

[0042] Finally, after the ghost vehicle is stably in the vehicle fleet, change the projection position of the ghost vehicle according to the strategy that may affect the normal behavior of the vehicle fleet, such as slowing down the projection speed or changing the projection direction, etc., forcing the vehicle fleet to make abnormal feedback after noticing the above behaviors.

[0043] Specifically, step 102 above may further include the following step 102c: Step 102c, after integrating the ghost vehicle into the attacked vehicle fleet, control the ghost vehicle to perform target actions until abnormal behaviors occur in the attacked vehicle fleet due to the influence of the ghost vehicle, and then stop projecting the ghost vehicle.

[0044] Wherein, the target actions include at least one of the following: accelerating, braking, changing lanes, and overtaking.

[0045] Exemplarily, the attacker moves the projected ghost vehicle by imitating the average driving speed and turning angle of the vehicle fleet and keeps the same queue distance from the vehicles in the adjacent vehicle fleet; after the ghost vehicle is basically consistent with the vehicle fleet behavior, perform actions such as accelerating, braking, changing lanes, and overtaking without affecting the stable projection of the ghost vehicle; after abnormal or unsafe behaviors such as braking and collision occur in the vehicle fleet due to the influence of the ghost vehicle, stop projecting the ghost vehicle, otherwise return to the previous step and change the behavior strategy of the ghost vehicle until abnormal behaviors occur in the vehicle fleet due to the influence of the ghost vehicle.

[0046] Exemplarily, in the embodiments of the present application, the abnormal behaviors of the attacked vehicle fleet include: inducing the vehicles in the attacked vehicle fleet to brake, collide, and change lanes.

[0047] The autonomous driving fleet attack method based on a ghost vehicle provided by an embodiment of this application first obtains the driving position information and driving status information of the attacked fleet; the driving position information includes: the driving road where the attacked fleet is located and the driving lane information; the driving status information includes: the position of each vehicle in the fleet, the driving speed, queue spacing, and queue rotation angle of each vehicle; then, projects a ghost vehicle in the adjacent lane of the attacked fleet based on the driving position information, and gradually adjusts the projection position of the ghost vehicle based on the driving lane information, and integrates the ghost vehicle into the attacked fleet until the attacked fleet exhibits abnormal behavior due to the influence of the ghost vehicle. In this way, the behavior of the fleet can be affected without directly contacting the attacked fleet and without using real vehicles, and even extended to the abnormal behavior of real vehicles, promoting the development of relevant defense means and vehicle abnormal behavior monitoring technologies.

[0048] It should be noted that for the autonomous driving fleet attack method based on a ghost vehicle provided by an embodiment of this application, the execution entity can be an autonomous driving fleet attack device based on a ghost vehicle, or a control module in the autonomous driving fleet attack device based on a ghost vehicle for executing the autonomous driving fleet attack method based on a ghost vehicle. In an embodiment of this application, the autonomous driving fleet attack device based on a ghost vehicle is taken as an example for executing the autonomous driving fleet attack method based on a ghost vehicle to illustrate the autonomous driving fleet attack device based on a ghost vehicle provided by an embodiment of this application.

[0049] It should be noted that in an embodiment of this application, the autonomous driving fleet attack method based on a ghost vehicle shown in each of the above method drawings is exemplarily described by taking one drawing in an embodiment of this application as an example. Specifically, when implemented, the autonomous driving fleet attack method based on a ghost vehicle shown in each of the above method drawings can also be implemented in combination with any other combinable drawings schemed in the above embodiments, which will not be elaborated here.

[0050] The autonomous driving fleet attack device based on a ghost vehicle provided by this application is described below, and the following description can be mutually referred to corresponding to the autonomous driving fleet attack method based on a ghost vehicle described above.

[0051] Figure 4 is a schematic structural diagram of the autonomous driving fleet attack device based on a ghost vehicle provided by an embodiment of this application, as Figure 4 shown, and specifically includes: An acquisition module 401 is configured to acquire the driving position information and driving status information of the attacked convoy; the driving position information includes: the driving road where the attacked convoy is located and the driving lane information; the driving status information includes: the position of each vehicle in the convoy, the driving speed, queue spacing, and queue rotation angle of each vehicle; An attack module 402 is configured to project a ghost vehicle in the adjacent lane of the attacked convoy based on the driving position information, and gradually adjust the projection position of the ghost vehicle based on the driving lane information, and integrate the ghost vehicle into the attacked convoy until the attacked convoy is affected by the ghost vehicle and exhibits abnormal behavior.

[0052] Optionally, the attack module 402 is specifically configured to determine the adjacent lane based on the driving road where the attacked convoy is located and the driving lane information; the adjacent lane is: the lane adjacent to the driving road of the attacked convoy within the driving road where the attacked convoy is located; the attack module 402 is further specifically configured to project the ghost vehicle in the adjacent lane and control the movement of the ghost vehicle according to the physical laws of vehicles; wherein, the moving direction of the ghost vehicle is the same as the driving direction of the attacked convoy.

[0053] Optionally, the attack module 402 is specifically configured to integrate the ghost vehicle into the target position in the attacked convoy based on the relative position information between the ghost vehicle and the attacked convoy; the attack module 402 is further specifically configured to control the moving speed and rotation angle of the ghost vehicle based on the driving speed of each vehicle and the queue rotation angle, and control the ghost vehicle to maintain the same spacing as the adjacent vehicle in the attacked convoy based on the position of each vehicle in the convoy and the queue spacing; wherein, the target position includes any one of the following: in front of the convoy, behind the convoy, and in the middle of the convoy.

[0054] Optionally, the attack module 402 is specifically configured to, after integrating the ghost vehicle into the attacked convoy, control the ghost vehicle to perform target actions until the attacked convoy is affected by the ghost vehicle and exhibits abnormal behavior, and then stop projecting the ghost vehicle; wherein, the target actions include at least one of the following: accelerating, braking, changing lanes, and overtaking.

[0055] Optionally, the abnormal behavior of the attacked convoy includes: inducing the vehicles in the attacked convoy to brake, collide, and change lanes.

[0056] The automatic driving fleet attack device based on a ghost vehicle provided by this application first obtains the driving position information and driving status information of the attacked fleet; the driving position information includes: the driving road where the attacked fleet is located and the driving lane information; the driving status information includes: the position of each vehicle in the fleet, the driving speed of each vehicle, the queue spacing, and the queue turning angle; then, based on the driving position information, a ghost vehicle is projected into the adjacent lane of the attacked fleet, and based on the driving lane information, the projected position of the ghost vehicle is gradually adjusted to integrate the ghost vehicle into the attacked fleet until the attacked fleet exhibits abnormal behavior under the influence of the ghost vehicle. In this way, the behavior of the fleet can be affected without directly contacting the attacked fleet and without using real vehicles, and even extended to the abnormal behavior of real vehicles, promoting the development of relevant defense means and vehicle abnormal behavior monitoring technologies.

[0057] Figure 5 An entity structure diagram of an electronic device is illustrated, as Figure 5 shown. The electronic device may include: a processor 510, a communication interface 520, a memory 530, and a communication bus 540. Among them, the processor 510, the communication interface 520, and the memory 530 complete communication with each other through the communication bus 540. The processor 510 can call the logical instructions in the memory 530 to execute the automatic driving fleet attack method based on a ghost vehicle. The method includes: first, obtaining the driving position information and driving status information of the attacked fleet; the driving position information includes: the driving road where the attacked fleet is located and the driving lane information; the driving status information includes: the position of each vehicle in the fleet, the driving speed of each vehicle, the queue spacing, and the queue turning angle; then, based on the driving position information, a ghost vehicle is projected into the adjacent lane of the attacked fleet, and based on the driving lane information, the projected position of the ghost vehicle is gradually adjusted to integrate the ghost vehicle into the attacked fleet until the attacked fleet exhibits abnormal behavior under the influence of the ghost vehicle. In this way, the behavior of the fleet can be affected without directly contacting the attacked fleet and without using real vehicles, and even extended to the abnormal behavior of real vehicles, promoting the development of relevant defense means and vehicle abnormal behavior monitoring technologies.

[0058] In addition, when the logical instructions in the above-mentioned memory 530 are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of this application. The aforementioned storage medium includes: various media that can store program codes, such as USB flash drives, mobile hard disks, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), magnetic disks, or optical discs.

[0059] On the other hand, this application also provides a computer program product. The computer program product includes a computer program stored on a computer-readable storage medium. The computer program includes program instructions. When the program instructions are executed by a computer, the computer can execute the autonomous driving fleet attack method based on a ghost vehicle provided by the above-mentioned various methods. The method includes: First, obtain the driving position information and driving status information of the attacked fleet; the driving position information includes: the driving road where the attacked fleet is located and the driving lane information; the driving status information includes: the position of each vehicle in the fleet, the driving speed of each vehicle, the queue spacing, and the queue rotation angle; After that, project a ghost vehicle in the adjacent lane of the attacked fleet based on the driving position information, and gradually adjust the projection position of the ghost vehicle based on the driving lane information, and integrate the ghost vehicle into the attacked fleet until the attacked fleet exhibits abnormal behavior due to the influence of the ghost vehicle. In this way, the behavior of the fleet can be affected without directly contacting the attacked fleet and without using real vehicles, and even extended to the abnormal behavior of real vehicles, promoting the development of relevant defense means and vehicle abnormal behavior monitoring technologies.

[0060] In another aspect, the present application also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, it implements the above-provided autonomous driving fleet attack method based on a phantom vehicle. The method includes: First, obtain the driving position information and driving state information of the attacked fleet; the driving position information includes: the driving road where the attacked fleet is located and the driving lane information; the driving state information includes: the position of each vehicle in the fleet, the driving speed, queue spacing, and queue turning angle of each vehicle; After that, project a phantom vehicle in the adjacent lane of the attacked fleet based on the driving position information, and gradually adjust the projection position of the phantom vehicle based on the driving lane information, and integrate the phantom vehicle into the attacked fleet until the attacked fleet exhibits abnormal behavior due to the influence of the phantom vehicle. In this way, the behavior of the fleet can be affected without directly contacting the attacked fleet and without using real vehicles, and even extend to the abnormal behavior of real vehicles, promoting the development of related defense means and vehicle abnormal behavior monitoring technologies.

[0061] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place, or may be distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art can understand and implement it without creative effort.

[0062] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on such an understanding, the essence of the above technical solution, or the part that contributes to the prior art, can be embodied in the form of a software product. The computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions for causing a computer device (which can be a personal computer, server, or network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0063] Finally, it should be noted that: The above embodiments are only used to illustrate the technical solutions of the present application, and are not intended to limit them; Although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: They can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements on some of the technical features; And these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for attacking an autonomous driving fleet based on ghost vehicles, characterized in that: include: Obtain the driving position information and driving status information of the attacked convoy; The driving position information includes: the driving road and driving lane information of the attacked convoy; the driving state information includes: the position of each vehicle in the convoy, the driving speed of each vehicle, the queue spacing and the queue turning angle; A ghost vehicle is projected in an adjacent lane of the attacked convoy based on the driving position information, and the projection position of the ghost vehicle is gradually adjusted based on the driving lane information to integrate the ghost vehicle into the attacked convoy until the attacked convoy is affected by the ghost vehicle and exhibits abnormal behavior.

2. The method according to claim 1, characterized in that The projecting of a ghost vehicle in an adjacent lane of the attacked convoy based on the driving position information includes: Based on the driving road and driving lane information of the attacked convoy, the adjacent lane is determined; the adjacent lane is: a lane in the driving road of the attacked convoy that is adjacent to the driving road of the attacked convoy; Projecting the ghost vehicle in the adjacent lane, and controlling the movement of the ghost vehicle according to the physical laws of the vehicle; The moving direction of the ghost vehicle is the same as the moving direction of the attacked convoy.

3. The method according to claim 1 or 2, characterized in that: The step of gradually adjusting the projection position of the ghost vehicle based on the driving lane information to integrate the ghost vehicle into the attacked convoy until the attacked convoy is affected by the ghost vehicle and abnormal behavior occurs, includes: Based on the relative position information between the ghost vehicle and the attacked convoy, integrating the ghost vehicle into a target position in the attacked convoy; Controlling the moving speed and turning angle of the ghost vehicle based on the driving speed of each vehicle and the turning angle of the queue, and controlling the ghost vehicle to maintain the same distance with adjacent vehicles in the attacked convoy based on the position of each vehicle in the convoy and the convoy spacing; The target position includes any one of the following: the front of the convoy, the rear of the convoy, and the middle of the convoy.

4. The method according to claim 3, characterized in that The step of gradually adjusting the projection position of the ghost vehicle based on the driving lane information to integrate the ghost vehicle into the attacked convoy until the attacked convoy is affected by the ghost vehicle and abnormal behavior occurs, includes: After the ghost vehicle is integrated into the attacked convoy, the ghost vehicle is controlled to perform a target action until the attacked convoy is affected by the ghost vehicle and an abnormal behavior occurs, and then the ghost vehicle is stopped from being projected; The target action includes at least one of the following: acceleration, braking, lane changing and overtaking.

5. The method according to claim 1 or 4, characterized in that: The abnormal behavior of the attacked convoy includes: inducing vehicles in the attacked convoy to brake, collide and change lanes.

6. An autonomous driving convoy attack device based on a ghost vehicle, characterized in that: The device comprises: An acquisition module is used to acquire the driving position information and driving state information of the attacked convoy; the driving position information includes: the driving road and driving lane information of the attacked convoy; the driving state information includes: the position of each vehicle in the convoy, the driving speed of each vehicle, the queue spacing and the queue turning angle; The attack module is used to project a ghost vehicle in an adjacent lane of the attacked convoy based on the driving position information, and gradually adjust the projection position of the ghost vehicle based on the driving lane information to integrate the ghost vehicle into the attacked convoy until the attacked convoy is affected by the ghost vehicle and exhibits abnormal behavior.

7. The device according to claim 6, characterized in that The attack module is specifically used to determine the adjacent lane based on the driving road and driving lane information of the attacked convoy; the adjacent lane is: a lane in the driving road of the attacked convoy that is adjacent to the driving road of the attacked convoy; The attack module is further configured to project the ghost vehicle in the adjacent lane and control the movement of the ghost vehicle according to the physical laws of the vehicle; The moving direction of the ghost vehicle is the same as the moving direction of the attacked convoy.

8. The device according to claim 6 or 7, characterized in that The attack module is specifically configured to integrate the ghost vehicle into a target position in the attacked convoy based on the relative position information between the ghost vehicle and the attacked convoy; The attack module is further configured to control the moving speed and turning angle of the ghost vehicle based on the driving speed of each vehicle and the turning angle of the queue, and control the ghost vehicle to maintain the same distance with adjacent vehicles in the attacked convoy based on the position of each vehicle in the convoy and the convoy spacing; The target position includes any one of the following: the front of the convoy, the rear of the convoy, and the middle of the convoy.

9. An electronic device, characterized in that: The invention comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the steps of the ghost vehicle-based autonomous driving fleet attack method as claimed in any one of claims 1 to 5 are implemented.

10. A computer-readable storage medium, characterized in that: A computer program is stored thereon, and when the computer program is executed by a processor, the steps of the ghost vehicle-based autonomous driving fleet attack method as described in any one of claims 1 to 5 are implemented.

Images