Radar attack method and device for autonomous vehicle, storage medium and electronic equipment

Abstract

The application provides a radar attack method and device for an autonomous vehicle, a storage medium and an electronic device, and relates to the technical field of autonomous driving safety. The method comprises the following steps: obtaining radar data information of the autonomous vehicle when driving on a target road section; determining an attack purpose according to the radar data information, and determining a target frequency of laser emission of a plurality of laser emitters based on the attack purpose; finally, controlling the plurality of laser emitters to emit laser light according to the target frequency until the state information of the autonomous vehicle meets a preset condition. The radar attack method and device for the autonomous vehicle, the storage medium and the electronic device provided by the application can emit laser light of a specific frequency to the radar sensor, simultaneously modify the point cloud diagram of the autonomous vehicle in multiple ways, so as to induce the autonomous vehicle to fail to perceive the surrounding environment and make abnormal or unsafe behaviors, and thus promote the development of defense means and the update iteration of the radar system by relevant researchers.

Description

TECHNICAL FIELD

[0001] The application relates to the technical field of automatic driving safety, in particular to a radar attack method and device for an automatic driving vehicle, a storage medium and an electronic device. BACKGROUND

[0002] Automatic driving technology has become an important part of building a smart city, which plays a key role in improving traffic efficiency and improving travel experience. Automatic driving vehicles rely on a combination of various sensors (such as cameras, radars, and laser radars) and artificial intelligence technology to achieve real-time perception of the environment, path planning, and decision control.

[0003] As one of the core components of the automatic driving perception system, radar is widely used due to its all-weather working ability and high-precision environment detection, but it is also vulnerable to attacks based on signal interference or data deception. For example, by simulating or tampering with radar point cloud data, attackers can fake non-existent obstacles, hide real objects, and even change the positions of objects in the scene, causing automatic driving vehicles to make incorrect path planning and decision execution. Such attacks not only may cause a single automatic driving vehicle to make a mistake, but also may have a chain reaction on the coordinated behavior of the entire automatic driving vehicle fleet, causing greater traffic safety hazards.

[0004] Therefore, there is an urgent need for a radar attack method for an automatic driving vehicle to improve the defense means of the automatic driving vehicle against attacks and the update iteration of the radar system. SUMMARY

[0005] The purpose of the application is to provide a radar attack method and device for an automatic driving vehicle, a storage medium and an electronic device, which can modify the point cloud map of the automatic driving vehicle by emitting laser of a specific frequency to the radar sensor, so as to induce the vehicle to lose perception of the surrounding environment and make abnormal or unsafe behavior, thereby promoting the development of defense means and the update iteration of the radar system by related researchers.

[0006] The application provides a radar attack method for an automatic driving vehicle, comprising:

[0007] Radar data information of an autonomous vehicle driving on a target road section is acquired; a plurality of laser emitters are arranged on the target road section, and coverage of the plurality of laser emitters on the target road section is greater than a preset threshold; an attack purpose is determined according to the radar data information, and a target frequency of laser emission of the plurality of laser emitters is determined based on the attack purpose; the plurality of laser emitters are controlled to emit laser light at the target frequency until state information of the autonomous vehicle meets a preset condition; wherein the preset condition includes any one of the following: the autonomous vehicle drives out of the coverage of the plurality of laser emitters; the autonomous vehicle is induced to an abnormal behavior by laser light emitted by a laser radar.

[0008] Optionally, the attack purpose is determined according to the radar data information, and the target frequency of laser emission of the plurality of laser emitters is determined based on the attack purpose, including: in a case where the radar data information indicates that point cloud data collected by the autonomous vehicle meets a first preset condition, determining that the attack purpose is a first purpose, and taking a laser emission frequency corresponding to the first purpose as the target frequency; wherein the first preset condition includes that there is no point cloud data affecting the behavior of the autonomous vehicle in the point cloud data collected by the autonomous vehicle.

[0009] Optionally, the plurality of laser emitters are controlled to emit laser light at the target frequency until the state information of the autonomous vehicle meets the preset condition, including: the plurality of laser emitters are controlled to emit laser light at the target frequency until the autonomous vehicle is induced to a first abnormal behavior by laser light emitted by a laser radar; wherein the first abnormal behavior includes: creating new point cloud data in the point cloud data collected by the autonomous vehicle, and the new point cloud data is located in front of the driving direction of the autonomous vehicle.

[0010] Optionally, the attack purpose is determined according to the radar data information, and the target frequency of laser emission of the plurality of laser emitters is determined based on the attack purpose, including: in a case where the radar data information indicates that point cloud data collected by the autonomous vehicle meets a second preset condition, determining that the attack purpose is a second purpose, and taking a laser emission frequency corresponding to the second purpose as the target frequency; wherein the second preset condition includes that there is point cloud data affecting the behavior of the autonomous vehicle and causing the vehicle to slow down or brake in the point cloud data collected by the autonomous vehicle.

[0011] Optionally, the controlling the plurality of laser emitters to emit laser light at the target frequency until the state information of the autonomous vehicle meets the preset condition comprises: controlling the plurality of laser emitters to emit laser light at the target frequency until the autonomous vehicle is induced to exhibit a second abnormal behavior by laser light emitted by the laser radar; and wherein the second abnormal behavior comprises: part of the point cloud data collected by the autonomous vehicle being hidden.

[0012] Optionally, the determining the attack purpose according to the radar data information and determining the target frequency at which the plurality of laser emitters emit laser light based on the attack purpose comprises: in a case where the radar data information indicates that the point cloud data collected by the autonomous vehicle meets a third preset condition, determining that the attack purpose is a third purpose, and taking a laser emission frequency corresponding to the third purpose as the target frequency; and wherein the third preset condition comprises: there being point cloud data in the point cloud data collected by the autonomous vehicle that affects the behavior of the autonomous vehicle but is not in the direction of travel of the vehicle.

[0013] Optionally, the controlling the plurality of laser emitters to emit laser light at the target frequency until the state information of the autonomous vehicle meets the preset condition comprises: controlling the plurality of laser emitters to emit laser light at the target frequency until the autonomous vehicle is induced to exhibit a third abnormal behavior by laser light emitted by the laser radar; and wherein the third abnormal behavior comprises: the point cloud data collected by the autonomous vehicle being positionally offset.

[0014] The application also provides a radar attack device for an autonomous vehicle, comprising:

[0015] An information acquisition module is configured to acquire radar data information of an autonomous vehicle when the autonomous vehicle travels on a target road section; the target road section is provided with a plurality of laser emitters, and a coverage range of the plurality of laser emitters on the target road section is greater than a preset threshold. A determination module is configured to determine an attack purpose according to the radar data information and determine a target frequency at which the plurality of laser emitters emit laser light based on the attack purpose. A control module is configured to control the plurality of laser emitters to emit laser light at the target frequency until state information of the autonomous vehicle meets a preset condition; and wherein the preset condition comprises any one of the following: the autonomous vehicle travels out of the coverage range of the plurality of laser emitters; and the autonomous vehicle is induced to exhibit an abnormal behavior by laser light emitted by a laser radar.

[0016] Optionally, the determining module is specifically configured to determine that the attack purpose is a first purpose and take a laser emission frequency corresponding to the first purpose as the target frequency, in a case where the radar data information indicates that the point cloud data collected by the autonomous vehicle meets a first preset condition; and the first preset condition includes that there is no point cloud data affecting the behavior of the autonomous vehicle in the point cloud data collected by the autonomous vehicle.

[0017] Optionally, the control module is specifically configured to control the plurality of laser emitters to emit laser light according to the target frequency until the autonomous vehicle is induced to have a first abnormal behavior by the laser light emitted by the laser radar; and the first abnormal behavior includes creating new point cloud data in the point cloud data collected by the autonomous vehicle, and the new point cloud data is located in front of the driving direction of the autonomous vehicle.

[0018] Optionally, the determining module is specifically configured to determine that the attack purpose is a second purpose and take a laser emission frequency corresponding to the second purpose as the target frequency, in a case where the radar data information indicates that the point cloud data collected by the autonomous vehicle meets a second preset condition; and the second preset condition includes that there is point cloud data affecting the behavior of the autonomous vehicle and causing the vehicle to slow down or brake in the point cloud data collected by the autonomous vehicle.

[0019] Optionally, the control module is specifically configured to control the plurality of laser emitters to emit laser light according to the target frequency until the autonomous vehicle is induced to have a second abnormal behavior by the laser light emitted by the laser radar; and the second abnormal behavior includes that part of the point cloud data collected by the autonomous vehicle is hidden.

[0020] Optionally, the determining module is specifically configured to determine that the attack purpose is a third purpose and take a laser emission frequency corresponding to the third purpose as the target frequency, in a case where the radar data information indicates that the point cloud data collected by the autonomous vehicle meets a third preset condition; and the third preset condition includes that there is point cloud data affecting the behavior of the autonomous vehicle but not in the driving direction of the vehicle in the point cloud data collected by the autonomous vehicle.

[0021] Optionally, the control module is specifically configured to control the plurality of laser emitters to emit laser light according to the target frequency until the autonomous vehicle is induced to have a third abnormal behavior by the laser light emitted by the laser radar; and the third abnormal behavior includes that the position of the point cloud data collected by the autonomous vehicle is offset.

[0022] The application also provides a computer program product comprising computer programs / instructions which, when executed by a processor, implement the steps of any of the radar attack methods for an autonomous vehicle described above.

[0023] The application also provides an electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of any of the radar attack methods for an autonomous vehicle described above when executing the program.

[0024] The application also provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the steps of any of the radar attack methods for an autonomous vehicle described above.

[0025] The radar attack method for an autonomous vehicle provided by the application, the device, the storage medium and the electronic device, first, radar data information of an autonomous vehicle driving on a target section is obtained; a plurality of laser emitters are arranged on the target section, and the coverage range of the plurality of laser emitters on the target section is greater than a preset threshold; then, an attack purpose is determined according to the radar data information, and a target frequency of laser emission of the plurality of laser emitters is determined based on the attack purpose; finally, the plurality of laser emitters emit laser according to the target frequency until the state information of the autonomous vehicle meets a preset condition; wherein the preset condition includes any one of the following: the autonomous vehicle drives out of the coverage range of the plurality of laser emitters; the autonomous vehicle is induced to an abnormal behavior by laser emitted by a laser radar. In this way, by emitting laser of a specific frequency to the radar sensor, the point cloud map of the autonomous vehicle is modified in multiple ways at the same time, so as to induce the vehicle to fail to perceive the surrounding environment and make abnormal or unsafe behavior, thereby promoting the development of defense means and the update iteration of the radar system by relevant researchers. BRIEF DESCRIPTION OF DRAWINGS

[0026] In order to more clearly illustrate the technical solutions in the application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or prior art description. Obviously, the drawings in the following description are some embodiments of the application, and for those skilled in the art, other drawings can also be obtained without creative labor.

[0027] Figure 1 is one of the flowcharts of the radar attack method for an autonomous vehicle provided by the application;

[0028] Figure 2 is another flowchart of the radar attack method for an autonomous vehicle provided by the application;

[0029] Figure 3 is an example diagram of a radar attack workflow provided by the present application;

[0030] Figure 4 is a structural schematic diagram of a radar attack device for an autonomous vehicle provided by the present application;

[0031] Figure 5 is a structural schematic diagram of an electronic device provided by the present application. DETAILED DESCRIPTION

[0032] For the purposes of the present application, the technical solutions and advantages thereof, the technical solutions in the present application will be described in detail below with reference to the drawings in the present application. Obviously, the described embodiments are part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative labor fall within the scope of the present application.

[0033] The terms "first", "second", and the like 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 the data used in this way can 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 a class, and do not limit the number of objects, for example, the first object can be one or more. In addition, "and / or" in the specification and claims means at least one of the connected objects, and the character " / ", generally represents a "or" relationship between the front and rear associated objects.

[0034] In view of the above technical problems existing in the related art, the embodiments of the present application modify the point cloud map of the autonomous vehicle by emitting laser of specific frequency to the radar sensor, so as to induce the vehicle to fail to perceive the surrounding environment and make abnormal or unsafe behavior. The specific principle is: by using a laser emitter to emit laser of specific frequency to the radar sensor to generate a new point cloud map to induce the autonomous vehicle to perceive abnormally. In this way, the diversity of radar attack based on laser emitter also improves the possibility of autonomous vehicle affected by attacked radar cloud point map. On the one hand, it reveals the safety hidden danger of radar cloud point map, and on the other hand, it can promote the development of defense means and the update iteration of radar system by related researchers.

[0035] The radar attack method for an autonomous vehicle provided by the embodiments of the present application will be described in detail below with reference to the drawings and specific embodiments and their application scenarios.

[0036] AsFigure 1 As shown in the embodiment of this application, a radar attack method for autonomous vehicles is provided, which may include the following steps 101 to 103:

[0037] Step 101: Obtain radar data information of the autonomous vehicle driving on the target road segment.

[0038] The target road segment is equipped with multiple laser emitters, and the coverage area of ​​the multiple laser emitters on the target road segment is greater than a preset threshold.

[0039] For example, in this embodiment of the application, it may include four parts: setting up multiple laser emitters on a selected target road segment, acquiring radar data information from an autonomous vehicle, analyzing the acquired radar data information, and forging radar point cloud information. Setting up laser emitters on a selected road segment refers to setting up multiple laser emitters on the target road segment traversed by the autonomous vehicle; acquiring radar data information from an autonomous vehicle refers to intruding into the autonomous vehicle's perception module to acquire radar point cloud data; intruding into the autonomous vehicle's perception module refers to separating the radar sensor portion from the autonomous vehicle's perception module; acquiring radar point cloud data information refers to acquiring the surrounding point cloud environment detected by the autonomous vehicle's radar sensor.

[0040] Step 102: Determine the attack target based on the radar data information, and determine the target frequency of the laser emitted by the plurality of laser emitters based on the attack target.

[0041] For example, in the embodiments of this application, analyzing the acquired radar data refers to analyzing the acquired radar point cloud data in order to determine whether there is point cloud data in front and around that affects the future behavior of the autonomous vehicle; forging fused radar point cloud information refers to emitting lasers of a specific frequency to forge radar point cloud information; emitting lasers of a specific frequency to forge radar point cloud information refers to emitting lasers of a specific frequency to create new point clouds, hide existing point clouds, move existing point clouds, or change existing point clouds based on the analysis of existing radar point cloud data.

[0042] For example, such as Figure 2 The flowchart shown is a process required for radar attack provided in the embodiment of this application. In this embodiment, the point cloud map of the autonomous vehicle is divided into the following three categories: (1) there is no point cloud data that affects the behavior of the target vehicle; (2) there is point cloud data that affects the behavior of the target vehicle and is likely to cause the target vehicle to decelerate or brake; (3) there is point cloud data that affects the behavior of the target vehicle but is not in the direction of the target vehicle's travel.

[0043] Specifically, for the first type of point cloud map mentioned above, step 102 may further include the following step 102a:

[0044] Step 102a, in a case where the radar data information indicates that the point cloud data collected by the autonomous vehicle satisfies a first preset condition, determining that the attack purpose is a first purpose, and taking the laser emission frequency corresponding to the first purpose as the target frequency.

[0045] The first preset condition includes that there is no point cloud data affecting the behavior of the autonomous vehicle in the point cloud data collected by the autonomous vehicle.

[0046] Specifically, for the second point cloud graph, the step 102 can further include the following step 102b.

[0047] Step 102b, in a case where the radar data information indicates that the point cloud data collected by the autonomous vehicle satisfies a second preset condition, determining that the attack purpose is a second purpose, and taking the laser emission frequency corresponding to the second purpose as the target frequency.

[0048] The second preset condition includes that there is point cloud data affecting the behavior of the autonomous vehicle and causing the vehicle to slow down or brake in the point cloud data collected by the autonomous vehicle.

[0049] Specifically, for the third point cloud graph, the step 102 can further include the following step 102c.

[0050] Step 102c, in a case where the radar data information indicates that the point cloud data collected by the autonomous vehicle satisfies a third preset condition, determining that the attack purpose is a third purpose, and taking the laser emission frequency corresponding to the third purpose as the target frequency.

[0051] The third preset condition includes that there is point cloud data affecting the behavior of the autonomous vehicle but not in the driving direction of the vehicle in the point cloud data collected by the autonomous vehicle.

[0052] Exemplarily, by obtaining the point cloud data collected by the autonomous vehicle, the type of the point cloud graph of the autonomous vehicle can be determined, and then the corresponding attack purpose is determined, and the laser frequency matched with the attack purpose is determined. Finally, the laser emitter is controlled to emit laser of the frequency to attack the radar of the autonomous vehicle.

[0053] Step 103, controlling the plurality of laser emitters to emit laser according to the target frequency until the state information of the autonomous vehicle satisfies a preset condition.

[0054] The preset condition includes any of the following: the autonomous vehicle drives out of the coverage range of the plurality of laser emitters; the autonomous vehicle is induced to abnormal behavior by the laser emitted by the laser radar.

[0055] Exemplarily, as shown in Figure 2 The three different types of point cloud maps can be attacked by different attack methods. That is, according to the three types of point cloud maps, different laser emission frequencies are selected to achieve different effects. When the point cloud map is the first type of point cloud map, the emitted laser of a specific frequency should be able to create a new point cloud data in the existing point cloud map, which should be located in front of or side of the target vehicle driving direction, and the data should be similar to the vehicle data or pedestrian data, etc. which can easily cause the target vehicle to reflect abnormally. When the point cloud map is the second type of point cloud map, the emitted laser of a specific frequency should be able to hide the existing point cloud, so that the target vehicle cannot correctly detect the front obstacle in the radar sensor; the emitted laser of a specific frequency can also change the existing point cloud to mislead the target vehicle to identify the front obstacle as an object that has no effect on driving. When the point cloud map is the third type of point cloud map, the emitted laser of a specific frequency should be able to cause the existing point cloud to shift, that is, to move the existing point cloud to a position close to the driving direction of the target vehicle as much as possible, so as to affect the behavior of the target vehicle.

[0056] Specifically, for the first type of point cloud map, the step 103 can further include the following step 103a:

[0057] Step 103a, controlling the plurality of laser emitters to emit laser according to the target frequency until the autonomous vehicle is induced to the first abnormal behavior by the laser emitted by the laser radar.

[0058] The first abnormal behavior includes creating new point cloud data in the point cloud data collected by the autonomous vehicle, and the new point cloud data is located in front of the driving direction of the autonomous vehicle.

[0059] Specifically, for the second type of point cloud map, the step 103 can further include the following step 103b:

[0060] Step 103b, controlling the plurality of laser emitters to emit laser according to the target frequency until the autonomous vehicle is induced to the second abnormal behavior by the laser emitted by the laser radar.

[0061] The second abnormal behavior includes that part of the point cloud data collected by the autonomous vehicle is hidden.

[0062] Specifically, for the third type of point cloud map, the step 103 can further include the following step 103c:

[0063] Step 103c, controlling the plurality of laser emitters to emit laser light according to the target frequency until the autonomous vehicle is induced to exhibit a third abnormal behavior by the laser light emitted by the laser radar.

[0064] The third abnormal behavior includes that the point cloud data collected by the autonomous vehicle is positionally offset.

[0065] It should be noted that the radar data collected by the autonomous vehicle can contain one or more of the above three point cloud maps, and therefore one or more of the above attack methods can be used for attack to induce the target vehicle to exhibit abnormal behavior to the greatest extent.

[0066] Exemplarily, as shown in Figure 3 The flowchart of the radar attack method for the autonomous vehicle provided by the embodiment of the present application is shown in the figure, which specifically includes: ①, a target vehicle (i.e. the autonomous vehicle) is selected in advance to pass through a road section, and a laser emitter covering a certain range is set up on the roadside of the road section. ②, the target vehicle perception module is invaded in advance to be ready to obtain real-time data at any time. ③, after the target vehicle enters the coverage range of the laser emitter, the radar sensor data is separated from the target vehicle perception module. ④, the real-time captured radar sensor point cloud data is analyzed to determine whether there is point cloud information affecting the future behavior of the target vehicle. ⑤, according to the analysis result of the point cloud data, the laser of a specific frequency is emitted to the radar sensor of the target vehicle. ⑥, the emitted laser of a specific frequency should achieve at least one of creating new point cloud, hiding existing point cloud, moving existing point cloud and changing existing point cloud. ⑦, the above steps ④ to ⑥ are repeated until the target vehicle drives out of the coverage range of the laser emitter or exhibits an abnormal behavior.

[0067] The radar attack method for an autonomous vehicle provided in the embodiment of the present application first acquires radar data information of the autonomous vehicle when driving on a target road section; the target road section is provided with a plurality of laser emitters, and the coverage range of the plurality of laser emitters on the target road section is greater than a preset threshold; then, an attack purpose is determined according to the radar data information, and a target frequency of laser emission of the plurality of laser emitters is determined based on the attack purpose; finally, the plurality of laser emitters emit laser according to the target frequency until the state information of the autonomous vehicle meets a preset condition; wherein the preset condition includes any one of the following: the autonomous vehicle drives out of the coverage range of the plurality of laser emitters; the autonomous vehicle is induced to an abnormal behavior by the laser emitted by the laser radar. In this way, by emitting laser of a specific frequency to the radar sensor, the point cloud map of the autonomous vehicle is simultaneously modified in multiple ways to induce the vehicle to fail to perceive the surrounding environment and to make abnormal or unsafe behaviors, thereby promoting the development of defense means by relevant researchers and the update iteration of the radar system.

[0068] It should be noted that the radar attack method for an autonomous vehicle provided in the embodiment of the present application can be a radar attack device for an autonomous vehicle, or a control module in the radar attack device for an autonomous vehicle for executing the radar attack method for an autonomous vehicle. In the embodiment of the present application, the radar attack device for an autonomous vehicle executes the radar attack method for an autonomous vehicle as an example, and the radar attack device for an autonomous vehicle provided in the embodiment of the present application is described.

[0069] It should be noted that in the embodiment of the present application, the radar attack method for an autonomous vehicle shown in each of the above methods is described by taking one of the drawings in the embodiment of the present application as an example. In specific implementation, the radar attack method for an autonomous vehicle shown in each of the above methods can also be implemented in combination with any other drawings that can be combined as described in the above embodiments, which will not be described here.

[0070] The radar attack device for an autonomous vehicle provided in the present application is described below, and the radar attack device for an autonomous vehicle described below can be correspondingly referred to the radar attack method for an autonomous vehicle described above.

[0071] Figure 4 The structure diagram of the radar attack device for an autonomous vehicle provided in the embodiment of the present application is shown in FIG. 1, and specifically includes: Figure 4

[0072] ​The information acquisition module 401 is configured to acquire radar data information of an autonomous vehicle driving on a target road section; the target road section is provided with a plurality of laser emitters, and coverage ranges of the plurality of laser emitters on the target road section are greater than a preset threshold; the determination module 402 is configured to determine an attack purpose according to the radar data information, and determine a target frequency of laser emission of the plurality of laser emitters based on the attack purpose; the control module 403 is configured to control the plurality of laser emitters to emit laser light at the target frequency until state information of the autonomous vehicle meets a preset condition; wherein the preset condition includes any one of the following: the autonomous vehicle drives out of the coverage range of the plurality of laser emitters; the autonomous vehicle is induced to an abnormal behavior by laser light emitted by a laser radar.

[0073] Optionally, the determination module 402 is specifically configured to, in a case where the radar data information indicates that point cloud data collected by the autonomous vehicle meets a first preset condition, determine that the attack purpose is a first purpose, and take a laser emission frequency corresponding to the first purpose as the target frequency; wherein the first preset condition includes that there is no point cloud data affecting the behavior of the autonomous vehicle in the point cloud data collected by the autonomous vehicle.

[0074] Optionally, the control module 403 is specifically configured to control the plurality of laser emitters to emit laser light at the target frequency until the autonomous vehicle is induced to a first abnormal behavior by laser light emitted by a laser radar; wherein the first abnormal behavior includes creating new point cloud data in the point cloud data collected by the autonomous vehicle, and the new point cloud data is located in front of the driving direction of the autonomous vehicle.

[0075] Optionally, the determination module 402 is specifically configured to, in a case where the radar data information indicates that point cloud data collected by the autonomous vehicle meets a second preset condition, determine that the attack purpose is a second purpose, and take a laser emission frequency corresponding to the second purpose as the target frequency; wherein the second preset condition includes that there is point cloud data affecting the behavior of the autonomous vehicle and causing the vehicle to slow down or brake in the point cloud data collected by the autonomous vehicle.

[0076] Optionally, the control module 403 is specifically configured to control the plurality of laser emitters to emit laser light at the target frequency until the autonomous vehicle is induced to a second abnormal behavior by laser light emitted by a laser radar; wherein the second abnormal behavior includes that part of the point cloud data in the point cloud data collected by the autonomous vehicle is hidden.

[0077] Optionally, the determining module 402 is specifically configured to determine that the attack purpose is a third purpose and take the laser emission frequency corresponding to the third purpose as the target frequency in a case where the radar data information indicates that the point cloud data collected by the autonomous vehicle meets a third preset condition; wherein the third preset condition includes that there is point cloud data in the point cloud data collected by the autonomous vehicle that affects the behavior of the autonomous vehicle but is not in the driving direction of the vehicle.

[0078] Optionally, the control module 403 is specifically configured to control the plurality of laser emitters to emit laser according to the target frequency until the autonomous vehicle is induced to have a third abnormal behavior by the laser emitted by the laser radar; wherein the third abnormal behavior includes that the position of the point cloud data collected by the autonomous vehicle is offset.

[0079] The radar attack device for an autonomous vehicle provided in the present application first acquires radar data information of an autonomous vehicle driving on a target road section; the target road section is provided with a plurality of laser emitters, and the coverage range of the plurality of laser emitters on the target road section is greater than a preset threshold; then, an attack purpose is determined according to the radar data information, and a target frequency of laser emission of the plurality of laser emitters is determined based on the attack purpose; finally, the plurality of laser emitters are controlled to emit laser according to the target frequency until the state information of the autonomous vehicle meets a preset condition; wherein the preset condition includes any one of the following: the autonomous vehicle drives out of the coverage range of the plurality of laser emitters; the autonomous vehicle is induced to have an abnormal behavior by the laser emitted by the laser radar. In this way, by emitting laser of a specific frequency to the radar sensor, the point cloud map of the autonomous vehicle is simultaneously modified in multiple ways to induce the vehicle to fail to perceive the surrounding environment and to make abnormal or unsafe behavior, thereby promoting the development of defense means by relevant researchers and the update iteration of the radar system.

[0080] Figure 5 An example of an entity structure diagram of an electronic device is shown in Figure 5As shown, the electronic device can include a processor 510, a communications interface 520, a memory 530, and a communications bus 540, wherein the processor 510, the communications interface 520, and the memory 530 communicate with each other through the communications bus 540. The processor 510 can invoke the logic instructions in the memory 530 to execute the radar attack method for an autonomous vehicle, which includes: first, obtaining radar data information of the autonomous vehicle when driving on a target section; the target section is provided with a plurality of laser emitters, and the coverage range of the plurality of laser emitters on the target section is greater than a preset threshold; then, determining an attack purpose according to the radar data information, and determining a target frequency of laser emission of the plurality of laser emitters based on the attack purpose; finally, controlling the plurality of laser emitters to emit laser according to the target frequency until the state information of the autonomous vehicle meets a preset condition; wherein the preset condition includes any one of the following: the autonomous vehicle drives out of the coverage range of the plurality of laser emitters; the autonomous vehicle is induced to an abnormal behavior by the laser emitted by the laser radar. In this way, by emitting laser of a specific frequency to the radar sensor, the point cloud map of the autonomous vehicle is modified in multiple ways at the same time, so as to induce the vehicle to perceive the surrounding environment and make abnormal or unsafe behavior, thereby promoting the development of defense means and the update iteration of the radar system by relevant researchers.

[0081] In addition, the logic instructions in the memory 530 described above can be implemented in the form of a software function unit and sold or used as an independent product, which can be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the present application essentially or the part that contributes to the prior art or part of the technical solutions can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a plurality of instructions to make a computer device (which can be a personal computer, a server, or a network device, etc.) execute all or part of the steps of the method described in various embodiments of the present application. The foregoing storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a magnetic disk or an optical disk, and various media that can store program codes.

[0082] In another aspect, the present application also provides a computer program product, which comprises a computer program stored on a computer readable storage medium, and the computer program comprises program instructions, when the program instructions are executed by a computer, the computer can execute the radar attack method for an autonomous vehicle provided by the above method, which comprises the following steps: first, obtaining radar data information of the autonomous vehicle when driving on a target road section; a plurality of laser emitters are arranged on the target road section, and the coverage range of the plurality of laser emitters on the target road section is greater than a preset threshold; then, determining an attack purpose according to the radar data information, and determining a target frequency of laser emission of the plurality of laser emitters based on the attack purpose; finally, controlling the plurality of laser emitters to emit laser according to the target frequency until the state information of the autonomous vehicle meets a preset condition; wherein the preset condition comprises any one of the following: the autonomous vehicle drives out of the coverage range of the plurality of laser emitters; the autonomous vehicle is induced to an abnormal behavior by the laser emitted by the laser radar. In this way, by emitting laser of a specific frequency to the radar sensor, the point cloud map of the autonomous vehicle is simultaneously modified in multiple ways to induce the vehicle to fail to perceive the surrounding environment and to make abnormal or unsafe behaviors, thereby promoting the development of defense means by relevant researchers and the update iteration of the radar system.

[0083] In another aspect, the present application also provides a computer readable storage medium, which stores a computer program, and the computer program is executed by a processor to implement the radar attack method for an autonomous vehicle provided by the above method, which comprises the following steps: first, obtaining radar data information of the autonomous vehicle when driving on a target road section; a plurality of laser emitters are arranged on the target road section, and the coverage range of the plurality of laser emitters on the target road section is greater than a preset threshold; then, determining an attack purpose according to the radar data information, and determining a target frequency of laser emission of the plurality of laser emitters based on the attack purpose; finally, controlling the plurality of laser emitters to emit laser according to the target frequency until the state information of the autonomous vehicle meets a preset condition; wherein the preset condition comprises any one of the following: the autonomous vehicle drives out of the coverage range of the plurality of laser emitters; the autonomous vehicle is induced to an abnormal behavior by the laser emitted by the laser radar. In this way, by emitting laser of a specific frequency to the radar sensor, the point cloud map of the autonomous vehicle is simultaneously modified in multiple ways to induce the vehicle to fail to perceive the surrounding environment and to make abnormal or unsafe behaviors, thereby promoting the development of defense means by relevant researchers and the update iteration of the radar system.

[0084] The device embodiments described above are merely illustrative, wherein the units described as separate components can or can not be physically separate, and the components displayed as units can or can not be physical units, i.e., can be located in one place, or can be distributed to multiple network units. Part or all of the modules can be selected to achieve the purposes of the embodiments according to actual needs. Those skilled in the art can understand and implement without creative labor.

[0085] Through the description of the above embodiments, those skilled in the art can clearly understand that the embodiments can be realized by means of software and the necessary general hardware platform, and of course can also be realized by hardware. Based on such understanding, the above technical solutions can be embodied in the form of software products, and the computer software products can be stored in a computer readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and include a plurality of instructions to make a computer device (which can be a personal computer, a server, or a network device, etc.) execute the methods described in each embodiment or some parts of the embodiments.

[0086] Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present application, and not to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: it can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacement for part 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 radar attack method for an autonomous vehicle, to improve the defense means of the autonomous vehicle against attacks and the update iteration of the radar system, characterized in that, The method comprises: acquiring radar data information of an automatic driving vehicle driving on a target section; a plurality of laser emitters are arranged on the target section, and coverage of the plurality of laser emitters on the target section is greater than a preset threshold; determining an attack purpose according to the radar data information, and determining a target frequency of laser emission of the plurality of laser emitters based on the attack purpose; controlling the plurality of laser emitters to emit laser light at the target frequency until state information of the automatic driving vehicle meets a preset condition; wherein the preset condition comprises any one of the following: the automatic driving vehicle drives out of the coverage of the plurality of laser emitters; the automatic driving vehicle is induced to an abnormal behavior by laser light emitted by a laser radar; the method further comprises: analyzing the acquired radar data, which means analyzing acquired radar point cloud data to determine whether there is point cloud data in front and around that affects future behavior of the automatic driving vehicle; faking and fusing radar point cloud information means emitting laser light of a specific frequency to fake radar point cloud information; emitting laser light of a specific frequency to fake radar point cloud information means creating new point clouds, hiding existing point clouds, moving existing point clouds, or changing existing point clouds according to analysis of existing radar point cloud data.

2. The method of claim 1, wherein, the method further comprises: in a case where the radar data information indicates that the point cloud data collected by the automatic driving vehicle meets a first preset condition, determining that the attack purpose is a first purpose, and taking a laser emission frequency corresponding to the first purpose as the target frequency; wherein the first preset condition comprises that there is no point cloud data in the point cloud data collected by the automatic driving vehicle that affects behavior of the automatic driving vehicle.

3. The method of claim 2, wherein, the method further comprises: controlling the plurality of laser emitters to emit laser light at the target frequency until the automatic driving vehicle is induced to a first abnormal behavior by laser light emitted by a laser radar; wherein the first abnormal behavior comprises creating new point cloud data in the point cloud data collected by the automatic driving vehicle, and the new point cloud data is located in front of the driving direction of the automatic driving vehicle.

4. The method of claim 1, wherein, the method further comprises: in a case where the radar data information indicates that the point cloud data collected by the automatic driving vehicle meets a second preset condition, determining that the attack purpose is a second purpose, and taking a laser emission frequency corresponding to the second purpose as the target frequency; The second preset condition includes: the point cloud data collected by the autonomous vehicle exists point cloud data that affects the behavior of the autonomous vehicle and causes the vehicle to slow down or brake.

5. The method of claim 4, wherein, The control of the multiple laser emitters to emit laser light according to the target frequency until the state information of the autonomous vehicle meets the preset condition includes: The control of the multiple laser emitters to emit laser light according to the target frequency until the autonomous vehicle is induced to exhibit a second abnormal behavior by the laser light emitted by the laser radar; The second abnormal behavior includes: part of the point cloud data collected by the autonomous vehicle is hidden.

6. The method of claim 1, wherein, The determination of the attack purpose according to the radar data information and the determination of the target frequency of the multiple laser emitters to emit laser light based on the attack purpose include: In the case that the radar data information indicates that the point cloud data collected by the autonomous vehicle meets a third preset condition, the attack purpose is determined to be a third purpose, and the laser emission frequency corresponding to the third purpose is taken as the target frequency; The third preset condition includes: the point cloud data collected by the autonomous vehicle exists point cloud data that affects the behavior of the autonomous vehicle but is not in the driving direction of the vehicle.

7. The method of claim 6, wherein, The control of the multiple laser emitters to emit laser light according to the target frequency until the state information of the autonomous vehicle meets the preset condition includes: The control of the multiple laser emitters to emit laser light according to the target frequency until the autonomous vehicle is induced to exhibit a third abnormal behavior by the laser light emitted by the laser radar; The third abnormal behavior includes: the position of the point cloud data collected by the autonomous vehicle is offset.

8. A radar attack device for an autonomous vehicle to improve the defensive means of the autonomous vehicle against attacks and the update iteration of the radar system, characterized in that, The device includes: An information acquisition module is configured to acquire radar data information of an autonomous vehicle driving on a target road section; the target road section is provided with multiple laser emitters, and the coverage range of the multiple laser emitters on the target road section is greater than a preset threshold; A determination module is configured to determine an attack purpose according to the radar data information and determine a target frequency of laser light emitted by the multiple laser emitters based on the attack purpose; A control module is configured to control the multiple laser emitters to emit laser light according to the target frequency until the state information of the autonomous vehicle meets a preset condition. The preset condition includes any one of the following: the autonomous vehicle drives out of the coverage range of the multiple laser emitters; the autonomous vehicle is induced to exhibit an abnormal behavior by the laser light emitted by the laser radar; The determination module is specifically configured to analyze the acquired radar data, that is, analyze the acquired radar point cloud data to determine whether there is point cloud data in front and around that affects the future behavior of the autonomous vehicle; the emission of laser light of a specific frequency to fake radar point cloud information means to emit laser light of a specific frequency to create new point cloud, hide existing point cloud, move existing point cloud or change existing point cloud.

9. An electronic device, comprising: A computer program product comprising a memory, a processor and a computer program stored on the memory and loadable on the processor, the processor implementing the steps of the method for radar attack against an autonomous vehicle according to any one of claims 1 to 7 when running the program.

10. A computer-readable storage medium, characterized in that, A computer program product comprising a memory, a processor and a computer program stored on the memory and loadable on the processor, the processor implementing the steps of the method for radar attack against an autonomous vehicle according to any one of claims 1 to 7 when running the program.

Images