An obstacle avoidance method and device for an autonomous vehicle

Abstract

The application discloses an obstacle avoidance method and device for an automatic driving vehicle, and the method comprises the following steps: acquiring vehicle radar data at a current moment; acquiring vehicle radar data at a previous moment; acquiring a position relationship of an obstacle relative to a vehicle radar according to the vehicle radar data at the current moment and the vehicle radar data at the previous moment; converting the position relationship of the obstacle relative to the vehicle radar in a vehicle body coordinate system of the vehicle to obtain obstacle position coordinates detected by the vehicle radar at each moment based on the vehicle body coordinate system; acquiring an instantaneous turning center of the vehicle; generating a polar coordinate system containing obstacle position polar coordinates according to the instantaneous turning center and the obstacle position coordinates; and obtaining an obstacle avoidance range of the vehicle according to the polar coordinate system containing the obstacle position coordinates. The application enhances the passing capacity of the automatic driving vehicle on an obstacle road section and improves the obstacle avoidance capability of the automatic driving vehicle.

Description

Technical Field

[0001] This application relates to the field of intelligent driving technology, specifically to an obstacle avoidance method and an obstacle avoidance device for autonomous vehicles. Background Technology

[0002] The rapid development of technology has led to increasing demands for intelligent transportation. Designing safer and more convenient vehicles is a future trend, and obstacle avoidance capability is a key factor reflecting vehicle intelligence. With the popularization of artificial intelligence technology, autonomous vehicles need to gradually achieve 100% passability in navigable areas of parking lots. Achieving complete passability at the vehicle end, and accurately obtaining perception information of the vehicle's surrounding environment, requires improving the vehicle's perception capabilities. Currently, the industry commonly relies on adding sensors to enhance vehicle perception capabilities, such as lidar, cameras, and ultrasonic radar. However, relying solely on sensors to detect obstacles for obstacle avoidance has limitations, including limited detection range, insufficient data points, and inaccurate detection results. This affects the accuracy of vehicle obstacle avoidance control, potentially leading to collisions. Summary of the Invention

[0003] The purpose of this invention is to provide an obstacle avoidance method and an obstacle avoidance device for autonomous vehicles, so as to solve at least one of the above-mentioned technical problems.

[0004] This invention provides the following solution:

[0005] According to one aspect of the present invention, an obstacle avoidance method for an autonomous vehicle is provided, comprising:

[0006] Obtain vehicle radar data at the current moment;

[0007] Obtain vehicle radar data from the previous moment at the current moment;

[0008] The positional relationship of the obstacle relative to the vehicle radar is obtained based on the vehicle radar data at the current moment and the vehicle radar data at the previous moment.

[0009] The positional relationship of the obstacle relative to the vehicle radar is transformed into the vehicle's body coordinate system to obtain the obstacle's position coordinates detected by the vehicle radar at various times based on the vehicle's body coordinate system.

[0010] Obtain the instantaneous turning center of the vehicle;

[0011] A polar coordinate system containing the polar coordinates of the obstacle's position is generated based on the instantaneous turning center and the obstacle's position coordinates;

[0012] The obstacle avoidance range of the vehicle is obtained based on the polar coordinate system containing the location coordinates of the obstacles.

[0013] Optionally, the vehicle radar data at the current moment includes forward ultrasonic radar data at the current moment, angular ultrasonic radar data at the current moment, lateral ultrasonic radar data at the current moment, and the vehicle's movement status relative to the previous moment.

[0014] The vehicle radar data at the current moment and the previous moment includes forward ultrasonic radar data, angular ultrasonic radar data, and lateral ultrasonic radar data.

[0015] Optionally, the vehicle's movement condition at the current moment relative to the previous moment includes longitudinal movement, longitudinal and lateral movement, and longitudinal, lateral, and angular rotation.

[0016] The step of obtaining the positional relationship of the obstacle relative to the vehicle radar based on the vehicle radar data at the current moment and the vehicle radar data at the previous moment includes:

[0017] Based on the described mobile conditions, obtain the corresponding vehicle radar data at the current moment and the vehicle radar data at the previous moment.

[0018] Based on the vehicle radar data at the current moment and the vehicle radar data at the previous moment, the positional relationship between the forward ultrasonic radar, the corner ultrasonic radar, and the lateral ultrasonic radar corresponding to the moving condition and the obstacle is obtained respectively.

[0019] The positional relationship of the obstacle relative to the vehicle's radar is obtained based on the positional relationship between the vehicle's forward ultrasonic radar and the obstacle, the positional relationship between the corner ultrasonic radar and the obstacle, and the positional relationship between the side ultrasonic radar and the obstacle.

[0020] Optionally, obtaining the positional relationships between the forward ultrasonic radar, angular ultrasonic radar, and lateral ultrasonic radar corresponding to the movement condition and the obstacle based on the vehicle radar data at the current moment and the vehicle radar data at the previous moment includes:

[0021] The angles between the obstacle and the centerlines of each ultrasonic radar at the current moment and the obstacle at the previous moment are obtained by using the vehicle radar data at the current moment, the distances between each ultrasonic radar and the obstacle at the previous moment, and the movement data of each ultrasonic radar at the current moment.

[0022] The angles between the obstacle and the center lines of each ultrasonic radar at the current moment, and the angles between the obstacle and the center lines of each ultrasonic radar at the previous moment, are calculated using the following formulas.

[0023] X radar =x n ·cos(α n +β r )-x n+1 ·cos(α n+1 +β r +α r )

[0024] Y radar =x n ·sin(α n +β r )-x n+1 ·sin(α n+1 +β r +α r ),

[0025] From the above formula,

[0026]

[0027]

[0028] Among them, X radar Y represents the longitudinal movement distance of the radar as it moves with the vehicle body. radar α is the lateral movement distance of the radar as the vehicle body moves. r β is the change in the heading angle of the vehicle. r x represents the angle between the initial position of the angular ultrasonic radar and the lateral ultrasonic radar and the vehicle body. n+1 x represents the distance between the ultrasonic radar and the obstacle at the current moment. n α represents the distance between the ultrasonic radar and the obstacle at the current moment and the previous moment. n+1 Let α be the angle between the obstacle and the centerline of the ultrasonic radar at the current moment. n The angle between the obstacle and the centerline of the ultrasonic radar at the current moment and the previous moment.

[0029] The positional relationship between each ultrasonic radar and the obstacle at each moment is obtained based on the distance between each ultrasonic radar and the obstacle at each moment and the angle between the obstacle and the centerline of the ultrasonic radar.

[0030] Optionally, the step of converting the positional relationship of the obstacle relative to the vehicle radar into the vehicle's body coordinate system includes:

[0031] Based on the positional relationship between the vehicle's ultrasonic radar and the obstacle at each moment, the position coordinates of the obstacle detected by the vehicle's ultrasonic radar at each moment are obtained based on the vehicle coordinate system.

[0032] Transform the position coordinates of the obstacle at each moment into the vehicle coordinate system.

[0033] Optionally, generating a polar coordinate system containing the polar coordinates of the obstacle's position based on the instantaneous turning center and the obstacle's position coordinates includes:

[0034] A polar coordinate system is generated based on the instantaneous turning center of the vehicle as the pole;

[0035] The position coordinates of the obstacle are transformed into the polar coordinate system with the instantaneous turning center of the vehicle as the pole to obtain the polar coordinates of the obstacle.

[0036] Optionally, obtaining the obstacle avoidance range of the vehicle based on the polar coordinate system containing the obstacle's position coordinates includes:

[0037] Obtain the radius of the instantaneous turning center of the vehicle;

[0038] Obtain the deceleration and obstacle avoidance range of the vehicle in the polar coordinate system;

[0039] Obtain the vehicle's real-time driving path;

[0040] Based on the vehicle's real-time driving path, determine whether the vehicle has exceeded the deceleration and obstacle avoidance range. If so, then...

[0041] An obstacle avoidance signal is generated and sent to the vehicle braking system so that the vehicle braking system performs obstacle avoidance braking according to the obstacle avoidance signal.

[0042] Optionally, the deceleration and obstacle avoidance range includes the deceleration and obstacle avoidance distance range and the deceleration and obstacle avoidance angle range;

[0043] The process of obtaining the vehicle's deceleration and obstacle avoidance range in the polar coordinate system includes:

[0044] Obtain the first distance between the vehicle body and the instantaneous turning center;

[0045] Obtain the second distance between the vehicle body and the instantaneous turning center;

[0046] Obtain the lateral warning distance of the vehicle;

[0047] The minimum deceleration and obstacle avoidance distance of the vehicle in the polar coordinate system is obtained by subtracting the lateral warning distance from the first distance between the vehicle body and the instantaneous turning center.

[0048] The maximum deceleration and obstacle avoidance distance of the vehicle in the polar coordinate system is obtained by adding the second distance between the vehicle body and the instantaneous turning center to the lateral warning distance.

[0049] The deceleration and obstacle avoidance distance range of the vehicle in the polar coordinate system is obtained based on the minimum and maximum deceleration and obstacle avoidance distances.

[0050] Optionally, obtaining the vehicle's deceleration and obstacle avoidance range in the polar coordinate system includes:

[0051] Obtain the first angle at which the vehicle moves in the heading direction;

[0052] Obtain the second angle of the vehicle's movement in the heading direction;

[0053] The deceleration and obstacle avoidance angle of the vehicle in the polar coordinate system is obtained based on the first angle of movement of the vehicle in the heading direction and the second angle of movement of the vehicle in the heading direction.

[0054] The present invention also provides an obstacle avoidance device for autonomous vehicles, comprising:

[0055] The current-time vehicle radar data acquisition module is used to acquire the current-time vehicle radar data.

[0056] The current moment previous moment vehicle radar data acquisition module is used to acquire the current moment previous moment vehicle radar data.

[0057] A positional relationship acquisition module is used to acquire the positional relationship of an obstacle relative to the vehicle radar based on the vehicle radar data at the current moment and the vehicle radar data at the previous moment.

[0058] A position coordinate acquisition module is used to transform the positional relationship of the obstacle relative to the vehicle radar into the vehicle body coordinate system, and obtain the obstacle position coordinates detected by the vehicle radar at various times based on the vehicle body coordinate system.

[0059] Instantaneous turning center acquisition module, the instantaneous turning center acquisition module is used to acquire the instantaneous turning center of the vehicle;

[0060] A polar coordinate system generation module is used to generate a polar coordinate system containing the polar coordinates of the obstacle position based on the instantaneous turning center and the obstacle position coordinates.

[0061] An obstacle avoidance range acquisition module is used to obtain the obstacle avoidance range of the vehicle based on the polar coordinate system containing the position coordinates of the obstacles.

[0062] Compared with the prior art, the present invention has the following advantages:

[0063] This invention uses ultrasonic radar to obtain obstacle distances, calculates obstacle coordinates relative to the vehicle's coordinate system, and determines the obstacle avoidance range based on the vehicle's instantaneous turning center. By using only ultrasonic radar around the vehicle, it improves the vehicle's ability to pass through and avoid obstacles on obstacle-prone road sections, while significantly reducing the reliance on lidar and cameras during driving. It is innovative and groundbreaking in terms of algorithm capabilities. The obstacle avoidance method for autonomous vehicles is simple, efficient, and stable, greatly reducing the cost of obstacle avoidance. Attached Figure Description

[0064] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0065] Figure 1 This is a flowchart illustrating an obstacle avoidance method for an autonomous vehicle according to an embodiment of the present invention.

[0066] Figure 2 This is a radar position diagram of an obstacle avoidance method for autonomous vehicles according to an embodiment of the present invention.

[0067] Figure 3 This is a schematic diagram of the obstacle avoidance area in an obstacle avoidance method for an autonomous vehicle according to an embodiment of the present invention.

[0068] Figure 4 This is a schematic diagram of the structure of an obstacle avoidance device for an autonomous vehicle according to an embodiment of the present invention;

[0069] Figure 5 This is a structural diagram of an electronic device that can implement the obstacle avoidance method for autonomous vehicles according to the present invention. Detailed Implementation

[0070] The technical solution of the present invention will now be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0071] Figure 1 This is a flowchart illustrating an obstacle avoidance method for an autonomous vehicle according to an embodiment of the present invention.

[0072] like Figure 1 As shown, an obstacle avoidance method for autonomous vehicles includes:

[0073] Step 1: Obtain vehicle radar data at the current moment;

[0074] Step 2: Obtain vehicle radar data from the previous moment;

[0075] Step 3: Obtain the positional relationship of the obstacle relative to the vehicle radar based on the vehicle radar data at the current moment and the vehicle radar data at the previous moment;

[0076] Step 4: Transform the positional relationship of the obstacle relative to the vehicle radar into the vehicle's body coordinate system to obtain the obstacle position coordinates detected by the vehicle radar at various times based on the vehicle's body coordinate system.

[0077] Step 5: Obtain the instantaneous turning center of the vehicle;

[0078] Step 6: Generate a polar coordinate system containing the polar coordinates of the obstacle's position based on the instantaneous turning center and the obstacle's position coordinates;

[0079] Step 7: Obtain the vehicle's obstacle avoidance range using a polar coordinate system that includes the location coordinates of obstacles.

[0080] This invention uses ultrasonic radar to obtain obstacle distances, calculates obstacle coordinates relative to the vehicle's coordinate system, and determines the obstacle avoidance range based on the vehicle's instantaneous turning center. By using only ultrasonic radar around the vehicle, it improves the vehicle's ability to pass through and avoid obstacles on obstacle-prone road sections, while significantly reducing the reliance on lidar and cameras during driving. It is innovative and groundbreaking in terms of algorithm capabilities. The obstacle avoidance method for autonomous vehicles is simple, efficient, and stable, greatly reducing the cost of obstacle avoidance.

[0081] In this embodiment, the vehicle radar data at the current moment includes the forward ultrasonic radar data at the current moment, the angular ultrasonic radar data at the current moment, the lateral ultrasonic radar data at the current moment, and the vehicle's movement condition relative to the previous moment. The vehicle's movement condition relative to the previous moment is obtained by the distance the vehicle has moved relative to the previous moment and the change in the vehicle's heading angle.

[0082] The vehicle radar data at the current moment and the previous moment includes the forward ultrasonic radar data at the current moment and the previous moment, the angular ultrasonic radar data at the current moment and the previous moment, and the lateral ultrasonic radar data at the current moment and the previous moment.

[0083] In this embodiment, the movement conditions of the vehicle at the current moment relative to the previous moment include longitudinal movement conditions, longitudinal and lateral movement conditions, and longitudinal and lateral movement and angular rotation conditions.

[0084] The positional relationship of the obstacle relative to the vehicle radar is obtained based on the vehicle radar data at the current moment and the vehicle radar data at the previous moment, including:

[0085] Based on the current vehicle radar data and the vehicle radar data of the previous moment, the corresponding vehicle radar data at the current moment is obtained;

[0086] Based on the vehicle radar data at the current moment and the vehicle radar data at the previous moment, the positional relationship between the forward ultrasonic radar, the corner ultrasonic radar, and the side ultrasonic radar corresponding to the moving condition and the obstacle is obtained respectively.

[0087] The positional relationship of the obstacle relative to the vehicle's radar is obtained based on the positional relationship between the vehicle's forward ultrasonic radar, the angle ultrasonic radar, and the obstacle.

[0088] In this embodiment, the positional relationships between the forward ultrasonic radar, corner ultrasonic radar, and lateral ultrasonic radar and the obstacle are obtained based on the vehicle radar data at the current moment and the vehicle radar data at the previous moment, respectively, corresponding to the moving condition.

[0089] The angles between the obstacle and the centerlines of each ultrasonic radar at the current moment and the obstacle at the previous moment are obtained by using the vehicle radar data at the current moment, the distances between each ultrasonic radar and the obstacle at the previous moment, and the movement data of each ultrasonic radar at the current moment.

[0090] The angles between the obstacle and the center lines of each ultrasonic radar at the current moment, and the angles between the obstacle and the center lines of each ultrasonic radar at the previous moment, are calculated using the following formulas.

[0091] X radar =x n ·cos(α n +β r )-x n+1 ·cos(α n+1 +β r +α r )

[0092] Y radar =x n ·sin(α n +β r )-x n+1·sin(α n+1 +β r +α r ),

[0093] From the above formula,

[0094]

[0095]

[0096] Among them, X radar Y represents the longitudinal movement distance of the radar as it moves with the vehicle body. radar α represents the lateral movement distance of the radar as it moves with the vehicle body. r β represents the change in the vehicle's heading angle. r x represents the angle between the initial position of the angular ultrasonic radar and the lateral ultrasonic radar and the vehicle body. n+1 x represents the distance between the ultrasonic radar and the obstacle at the current moment. n α represents the distance between the ultrasonic radar and the obstacle at the current moment and the previous moment. n+1 Let α be the angle between the obstacle and the centerline of the ultrasonic radar at the current moment. n The angle between the obstacle and the centerline of the ultrasonic radar at the current moment and the previous moment.

[0097] Figure 2 This is a radar position diagram of an obstacle avoidance method for autonomous vehicles according to an embodiment of the present invention.

[0098] like Figure 2 As shown, when the vehicle's movement is longitudinal, the distance traveled along the Y-axis remains unchanged. radar The value is 0, and the change in the vehicle's heading angle α r If there is no change, then α r The value is 0;

[0099] When the vehicle's movement involves both longitudinal and lateral movement, X radar and Y radar Both can obtain the actual distance value and the vehicle's heading angle change α. r If there is no change, then α r The value is 0;

[0100] When the vehicle's movement conditions include longitudinal movement, lateral movement, and angular rotation, X radar and Y radar The actual distance value can be obtained from both methods. Due to the change in vehicle angle, the change in the vehicle's heading angle α is... r This represents the actual change in angle.

[0101] It is understandable that since the forward-facing ultrasonic radar is positioned at the same angle as the vehicle, β is used when calculating the angle between the obstacle and the forward-facing ultrasonic radar. r The value is 0.

[0102] The positional relationship between each ultrasonic radar and the obstacle at each moment is obtained by calculating the distance between each ultrasonic radar and the obstacle and the angle between the obstacle and the centerline of the ultrasonic radar at each moment.

[0103] In this embodiment, transforming the positional relationship of the obstacle relative to the vehicle radar into the vehicle's body coordinate system includes:

[0104] Based on the positional relationship between the vehicle's ultrasonic radar and the obstacle at each moment, the position coordinates (object_x) of the obstacle detected by the vehicle's ultrasonic radar at each moment are obtained based on the vehicle coordinate system. n ,object_y n );

[0105] The position coordinates of the obstacle at each moment (object_x) n ,object_y n Transform to the vehicle coordinate system.

[0106] In this embodiment, generating a polar coordinate system containing the polar coordinates of the obstacle's position based on the instantaneous turning center and the obstacle's position coordinates includes:

[0107] A polar coordinate system is generated with the instantaneous turning center of the vehicle as the pole;

[0108] The position coordinates of the obstacle (object_x) n ,object_y n Transform the coordinates to a polar coordinate system with the instantaneous turning center of the vehicle as the pole to obtain the polar coordinates of the obstacle (R_object). n ,θ_object n ).

[0109] In this embodiment, the obstacle avoidance range of the vehicle is obtained according to a polar coordinate system that includes the location coordinates of the obstacle, including:

[0110] Obtain the radius of the vehicle's instantaneous turning center;

[0111] Obtain the vehicle's deceleration and obstacle avoidance range in the polar coordinate system;

[0112] Obtain the vehicle's real-time driving path;

[0113] Determine whether the vehicle has exceeded the deceleration and obstacle avoidance range based on its real-time driving path. If so, then...

[0114] An obstacle avoidance signal is generated and sent to the vehicle braking system so that the vehicle braking system can perform obstacle avoidance braking according to the obstacle avoidance signal.

[0115] In this embodiment, the deceleration obstacle avoidance range includes the deceleration obstacle avoidance distance range and the deceleration obstacle avoidance angle range;

[0116] Obtaining the vehicle's deceleration and obstacle avoidance range in the polar coordinate system includes:

[0117] Obtain the first distance between the vehicle body and the instantaneous turning center;

[0118] Obtain the second distance between the vehicle body and the instantaneous turning center;

[0119] Obtain the vehicle's lateral warning distance;

[0120] The minimum distance for vehicle deceleration and obstacle avoidance in the polar coordinate system is obtained by subtracting the lateral warning distance from the first distance between the vehicle body and the instantaneous turning center.

[0121] The maximum deceleration and obstacle avoidance distance of the vehicle in the polar coordinate system is obtained by adding the second distance between the vehicle body and the instantaneous turning center to the lateral warning distance.

[0122] The deceleration and obstacle avoidance distance range of the vehicle in the polar coordinate system is obtained based on the minimum and maximum deceleration and obstacle avoidance distances.

[0123] In this embodiment, obtaining the vehicle's deceleration and obstacle avoidance range in the polar coordinate system includes:

[0124] Obtain the first angle of movement of the vehicle in the heading direction;

[0125] Obtain the second angle of the vehicle's movement in the heading direction;

[0126] The deceleration and obstacle avoidance angle of the vehicle in the polar coordinate system is obtained by the first angle of movement of the vehicle in the heading direction and the second angle of movement of the vehicle in the heading direction.

[0127] Figure 3 This is a schematic diagram of the obstacle avoidance area in an obstacle avoidance method for an autonomous vehicle according to an embodiment of the present invention.

[0128] like Figure 3 As shown, based on the positional relationship between the vehicle's ultrasonic radar and the obstacle at each moment, the position coordinates (object_x) of the obstacle detected by the vehicle's ultrasonic radar at each moment are obtained based on the vehicle coordinate system. n ,object_y n After that, the instantaneous turning center of the vehicle is obtained based on the change in the vehicle's heading angle during the vehicle's movement. In this embodiment, taking a right turn as an example, the instantaneous turning center of the vehicle in the vehicle coordinate system (x) is obtained. O y O), with the vehicle's instantaneous turning center (x O y O Establish a polar coordinate system with the pole as the reference point, and set the obstacle position coordinates (object_x) as the reference point. n ,object_y n Switch to using the vehicle's instantaneous turning center (x) O y O Using a polar coordinate system with poles as the base, we obtain the polar coordinates of the obstacle (R_object). n θ_object n );

[0129] Obtain the vehicle's deceleration and obstacle avoidance range R_object in polar coordinates. n (r min r max ), θ_object n (θ min θ max Specifically, the deceleration and obstacle avoidance range includes the deceleration and obstacle avoidance distance range R_object. n (r min r max and the deceleration and obstacle avoidance angle range θ_object n (θ min θ max );

[0130] The range of vehicle deceleration and obstacle avoidance distances in polar coordinates includes:

[0131] Obtain the first distance between the vehicle body and the instantaneous turning center;

[0132] Obtain the second distance between the vehicle body and the instantaneous turning center;

[0133] Obtain the vehicle's lateral warning distance;

[0134] The minimum deceleration and obstacle avoidance distance r of the vehicle in the polar coordinate system is obtained by subtracting the lateral warning distance from the first distance between the vehicle body and the instantaneous turning center. min Specifically, the minimum distance r for deceleration and obstacle avoidance. min The distance is obtained by subtracting the lateral warning distance from the nearest point between the vehicle body and the instantaneous turning center;

[0135] The maximum deceleration and obstacle avoidance distance r of the vehicle in the polar coordinate system is obtained by adding the second distance between the vehicle body and the instantaneous turning center to the lateral warning distance. max Specifically, the maximum distance r for deceleration and obstacle avoidance. max The distance is obtained by adding the lateral warning distance to the farthest point between the vehicle body and the instantaneous turning center;

[0136] Based on the minimum distance r for deceleration and obstacle avoidance minand the maximum distance r for deceleration and obstacle avoidance max Obtain the vehicle's deceleration and obstacle avoidance distance range R_object in polar coordinates. n (r min r max ).

[0137] In this embodiment, obtaining the vehicle's deceleration and obstacle avoidance angle range in the polar coordinate system includes:

[0138] Obtain the first angle θ of the vehicle's movement in the heading direction. min Specifically, the first angle θ min The angle θ (L / radius R of the vehicle's instantaneous turning center) is the angle corresponding to the forward movement of the farthest point of the front bumper in the vehicle's heading direction by L (L is the forward obstacle avoidance distance);

[0139] Obtain the second angle θ of the vehicle's movement in the heading direction. max Specifically, the second angle θ max The angle θ is the angle corresponding to the rear bumper of the vehicle moving backward by l (l is the rear obstacle avoidance distance) in the direction of the vehicle's heading angle.

[0140] The deceleration and obstacle avoidance angle of the vehicle in the polar coordinate system is obtained by the first angle of movement of the vehicle in the heading direction and the second angle of movement of the vehicle in the heading direction.

[0141] The vehicle deceleration obstacle avoidance range obtained in this embodiment optimizes the obstacle avoidance area during vehicle turning compared to the rectangular obstacle avoidance area calculation method. The optimized range is as follows:

[0142] 1) Reasonably release the area area_1 outside the curve that does not affect the driving route;

[0143] 2) Add warning zones area_2 and area_4 to the inside and outside of curves;

[0144] 3) Add an obstacle avoidance area area_3 at the center of the curve.

[0145] Figure 4 This is a schematic diagram of the structure of an obstacle avoidance device for an autonomous vehicle according to an embodiment of the present invention;

[0146] like Figure 4 As shown, an obstacle avoidance device for autonomous vehicles includes:

[0147] The current vehicle radar data acquisition module is used to acquire the vehicle radar data at the current moment;

[0148] The vehicle radar data acquisition module for the current moment and the previous moment is used to acquire vehicle radar data for the current moment and the previous moment.

[0149] The positional relationship acquisition module is used to obtain the positional relationship of the obstacle relative to the vehicle radar based on the vehicle radar data at the current moment and the vehicle radar data at the previous moment.

[0150] The position coordinate acquisition module is used to transform the positional relationship of the obstacle relative to the vehicle radar into the vehicle body coordinate system, and obtain the obstacle position coordinates detected by the vehicle radar at various times based on the vehicle body coordinate system.

[0151] The instantaneous turning center acquisition module is used to acquire the instantaneous turning center of the vehicle;

[0152] The polar coordinate system generation module is used to generate a polar coordinate system containing the polar coordinates of the obstacle's position based on the instantaneous turning center and the obstacle's position coordinates;

[0153] The obstacle avoidance range acquisition module is used to obtain the vehicle's obstacle avoidance range based on a polar coordinate system containing the location coordinates of obstacles.

[0154] It is worth noting that although this system only discloses basic functional modules such as the current moment vehicle radar data acquisition module, the current moment-previous moment vehicle radar data acquisition module, the position relationship acquisition module, the position coordinate acquisition module, the instantaneous turning center acquisition module, the polar coordinate system generation module, and the obstacle avoidance range acquisition module, this does not mean that this device is limited to the above-mentioned basic functional modules. On the contrary, what this invention intends to express is that, based on the above-mentioned basic functional modules, those skilled in the art can arbitrarily add one or more functional modules in combination with existing technology to form an infinite number of embodiments or technical solutions. That is to say, this system is open rather than closed. It should not be assumed that the scope of protection of the claims of this invention is limited to the above-disclosed basic functional modules just because this embodiment only discloses a few basic functional modules.

[0155] Figure 5 This is a structural diagram of an electronic device that can implement the obstacle avoidance method for autonomous vehicles according to the present invention.

[0156] like Figure 5 As shown, the electronic device includes a processor, a communication interface, a memory, and a communication bus. The processor, the communication interface, and the memory communicate with each other through the communication bus. The memory stores a computer program, which, when executed by the processor, causes the processor to perform steps for an obstacle avoidance method for an autonomous vehicle.

[0157] This application also provides a computer-readable storage medium storing a computer program executable by an electronic device, which, when run on the electronic device, causes the electronic device to perform steps of an obstacle avoidance method for an autonomous vehicle.

[0158] The communication bus mentioned in the above electronic devices can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. This communication bus can be divided into address bus, data bus, control bus, etc. For ease of illustration, only one thick line is used to represent it in the diagram, but this does not mean that there is only one bus or one type of bus.

[0159] The electronic device comprises a hardware layer, an operating system layer running on top of the hardware layer, and an application layer running on the operating system. The hardware layer includes hardware such as a central processing unit (CPU), a memory management unit (MMU), and memory. The operating system can be any one or more computer operating systems that control the electronic device through processes, such as Linux, Unix, Android, iOS, or Windows. Furthermore, in this embodiment of the invention, the electronic device can be a smartphone, tablet computer, or other handheld device, or a desktop computer, portable computer, or other electronic device; there is no particular limitation in this embodiment.

[0160] In this embodiment of the invention, the executing entity for electronic device control can be an electronic device itself, or a functional module within an electronic device capable of calling and executing a program. The electronic device can obtain the firmware corresponding to the storage medium. This firmware is provided by the supplier, and different storage media may have the same or different firmware; no limitation is made here. After obtaining the firmware corresponding to the storage medium, the electronic device can write this firmware into the storage medium; specifically, it burns the firmware corresponding to the storage medium into the storage medium. The process of burning the firmware into the storage medium can be implemented using existing technology, and will not be elaborated upon in this embodiment of the invention.

[0161] Electronic devices can also obtain reset commands corresponding to the storage media. The reset commands corresponding to the storage media are provided by the supplier. The reset commands corresponding to different storage media can be the same or different, and no restrictions are imposed here.

[0162] At this time, the storage medium of the electronic device is a storage medium on which the corresponding firmware has been written. The electronic device can respond to the reset command corresponding to the storage medium on which the corresponding firmware has been written, thereby resetting the storage medium on which the corresponding firmware has been written according to the reset command. The process of resetting the storage medium according to the reset command can be implemented by existing technology and will not be described in detail in this embodiment of the invention.

[0163] For ease of description, the above devices are described separately by function as various units and modules. Of course, in implementing this application, the functions of each unit and module can be implemented in one or more software and / or hardware.

[0164] It will be understood by those skilled in the art that, unless otherwise defined, all terms used herein (including technical and scientific terms) have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. It should also be understood that terms such as those defined in general dictionaries should be understood to have the meaning consistent with their meaning in the context of the prior art, and should not be interpreted in an idealized or overly formal sense unless specifically defined.

[0165] For the sake of simplicity, the method embodiments are described as a series of actions. However, those skilled in the art should understand that the embodiments of the present invention are not limited to the described order of actions, because according to the embodiments of the present invention, some steps can be performed in other orders or simultaneously. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions involved are not necessarily essential to the embodiments of the present invention.

[0166] As can be seen from the above description of the embodiments, those skilled in the art can clearly understand that this application can be implemented by means of software plus necessary general-purpose hardware platforms. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in various embodiments or some parts of the embodiments of this application.

[0167] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. An obstacle avoidance method for autonomous vehicles, characterized in that, include: Obtain vehicle radar data at the current moment; Obtain vehicle radar data from the previous moment at the current moment; The positional relationship of the obstacle relative to the vehicle radar is obtained based on the vehicle radar data at the current moment and the vehicle radar data at the previous moment. The positional relationship of the obstacle relative to the vehicle radar is transformed into the vehicle's body coordinate system to obtain the obstacle's position coordinates detected by the vehicle radar at various times based on the vehicle's body coordinate system. Obtain the instantaneous turning center of the vehicle; A polar coordinate system containing the polar coordinates of the obstacle's position is generated based on the instantaneous turning center and the obstacle's position coordinates; The obstacle avoidance range of the vehicle is obtained based on the polar coordinate system containing the polar coordinates of the obstacle's position.

2. The obstacle avoidance method for autonomous vehicles as described in claim 1, characterized in that, The vehicle radar data at the current moment includes forward ultrasonic radar data, angular ultrasonic radar data, lateral ultrasonic radar data, and the vehicle's movement relative to the previous moment. The vehicle radar data at the current moment and the previous moment includes forward ultrasonic radar data, angular ultrasonic radar data, and lateral ultrasonic radar data.

3. The obstacle avoidance method for autonomous vehicles as described in claim 2, characterized in that, The vehicle's movement conditions at the current moment relative to the previous moment include longitudinal movement conditions, longitudinal and lateral movement conditions, and longitudinal, lateral, and angular rotation conditions. The step of obtaining the positional relationship of the obstacle relative to the vehicle radar based on the vehicle radar data at the current moment and the vehicle radar data at the previous moment includes: Based on the described mobile conditions, obtain the corresponding vehicle radar data at the current moment and the vehicle radar data at the previous moment. Based on the vehicle radar data at the current moment and the vehicle radar data at the previous moment, the positional relationship between the forward ultrasonic radar, the corner ultrasonic radar, and the lateral ultrasonic radar corresponding to the moving condition and the obstacle is obtained respectively. The positional relationship of the obstacle relative to the vehicle's radar is obtained based on the positional relationship between the vehicle's forward ultrasonic radar and the obstacle, the positional relationship between the corner ultrasonic radar and the obstacle, and the positional relationship between the side ultrasonic radar and the obstacle.

4. The obstacle avoidance method for autonomous vehicles as described in claim 3, characterized in that, The step of obtaining the positional relationships between the forward ultrasonic radar, corner ultrasonic radar, and lateral ultrasonic radar corresponding to the movement condition and the obstacle based on the vehicle radar data at the current moment and the vehicle radar data at the previous moment includes: The angles between the obstacle and the centerlines of each ultrasonic radar at the current moment and the obstacle at the previous moment are obtained by using the vehicle radar data at the current moment, the distances between each ultrasonic radar and the obstacle at the previous moment, and the movement data of each ultrasonic radar at the current moment. The angles between the obstacle and the center lines of each ultrasonic radar at the current moment, and the angles between the obstacle and the center lines of each ultrasonic radar at the previous moment, are calculated using the following formulas. X radar =x n ·cos(α n +b r )-x n+1 ·cos(α n+1 +b r +a r ) Y radar =x n ·sin(a n +b r )-x n+1 ·sin(a n+1 +b r +a r ), From the above formula, Among them, X radar Y represents the longitudinal movement distance of the radar as it moves with the vehicle body. radar α is the lateral movement distance of the radar as the vehicle body moves. r β is the change in the heading angle of the vehicle. r x represents the angle between the initial position of the angular ultrasonic radar and the lateral ultrasonic radar and the vehicle body. n+1 x represents the distance between the ultrasonic radar and the obstacle at the current moment. n α represents the distance between the ultrasonic radar and the obstacle at the current moment and the previous moment. n+1 Let α be the angle between the obstacle and the centerline of the ultrasonic radar at the current moment. n The angle between the obstacle and the centerline of the ultrasonic radar at the current moment and the previous moment. The positional relationship between each ultrasonic radar and the obstacle at each moment is obtained based on the distance between each ultrasonic radar and the obstacle at each moment and the angle between the obstacle and the centerline of the ultrasonic radar.

5. The obstacle avoidance method for autonomous vehicles as described in claim 4, characterized in that, The step of converting the positional relationship of the obstacle relative to the vehicle radar into the vehicle's body coordinate system includes: Based on the positional relationship between the vehicle's ultrasonic radar and the obstacle at each moment, the position coordinates of the obstacle detected by the vehicle's ultrasonic radar at each moment are obtained based on the vehicle coordinate system. Transform the position coordinates of the obstacle at each moment into the vehicle coordinate system.

6. The obstacle avoidance method for autonomous vehicles as described in claim 5, characterized in that, The step of generating a polar coordinate system containing the polar coordinates of the obstacle's position based on the instantaneous turning center and the obstacle's position coordinates includes: A polar coordinate system is generated based on the instantaneous turning center of the vehicle as the pole; The position coordinates of the obstacle are transformed into a polar coordinate system with the instantaneous turning center of the vehicle as the pole to obtain the polar coordinates of the obstacle.

7. The obstacle avoidance method for autonomous vehicles as described in claim 6, characterized in that, The process of obtaining the obstacle avoidance range of the vehicle based on the polar coordinate system containing the obstacle's position coordinates includes: Obtain the radius of the instantaneous turning center of the vehicle; Obtain the deceleration and obstacle avoidance range of the vehicle in the polar coordinate system; Obtain the vehicle's real-time driving path; Based on the vehicle's real-time driving path, determine whether the vehicle has exceeded the deceleration and obstacle avoidance range. If so, then... An obstacle avoidance signal is generated and sent to the vehicle braking system so that the vehicle braking system performs obstacle avoidance braking according to the obstacle avoidance signal.

8. The obstacle avoidance method for autonomous vehicles as described in claim 7, characterized in that, The deceleration and obstacle avoidance range includes the deceleration and obstacle avoidance distance range and the deceleration and obstacle avoidance angle range; The process of obtaining the vehicle's deceleration and obstacle avoidance range in the polar coordinate system includes: Obtain the first distance between the vehicle body and the instantaneous turning center; Obtain the second distance between the vehicle body and the instantaneous turning center; Obtain the lateral warning distance of the vehicle; The minimum deceleration and obstacle avoidance distance of the vehicle in the polar coordinate system is obtained by subtracting the lateral warning distance from the first distance between the vehicle body and the instantaneous turning center. The maximum deceleration and obstacle avoidance distance of the vehicle in the polar coordinate system is obtained by adding the second distance between the vehicle body and the instantaneous turning center to the lateral warning distance. The deceleration and obstacle avoidance distance range of the vehicle in the polar coordinate system is obtained based on the minimum and maximum deceleration and obstacle avoidance distances.

9. The obstacle avoidance method for autonomous vehicles as described in claim 8, characterized in that, The process of obtaining the vehicle's deceleration and obstacle avoidance range in the polar coordinate system includes: Obtain the first angle at which the vehicle moves in the heading direction; Obtain the second angle of the vehicle's movement in the heading direction; The deceleration and obstacle avoidance angle of the vehicle in the polar coordinate system is obtained based on the first angle of movement of the vehicle in the heading direction and the second angle of movement of the vehicle in the heading direction.

10. An obstacle avoidance device for an autonomous vehicle, characterized in that, include: The current-time vehicle radar data acquisition module is used to acquire the current-time vehicle radar data. The current moment previous moment vehicle radar data acquisition module is used to acquire the current moment previous moment vehicle radar data. A positional relationship acquisition module is used to acquire the positional relationship of an obstacle relative to the vehicle radar based on the vehicle radar data at the current moment and the vehicle radar data at the previous moment. A position coordinate acquisition module is used to transform the positional relationship of the obstacle relative to the vehicle radar into the vehicle body coordinate system, and obtain the obstacle position coordinates detected by the vehicle radar at various times based on the vehicle body coordinate system. Instantaneous turning center acquisition module, the instantaneous turning center acquisition module is used to acquire the instantaneous turning center of the vehicle; A polar coordinate system generation module is used to generate a polar coordinate system containing the polar coordinates of the obstacle position based on the instantaneous turning center and the obstacle position coordinates. An obstacle avoidance range acquisition module is used to obtain the obstacle avoidance range of the vehicle based on the polar coordinate system containing the polar coordinates of the obstacle positions.

Images