Obstacle avoidance method, system, electronic device and storage medium for automatic driving of vehicle

Abstract

This invention provides an obstacle avoidance method, system, electronic device, and storage medium for autonomous driving, belonging to the field of autonomous driving control technology. It includes: continuously performing dynamic window detection in front of the vehicle to obtain detection results; dividing the dynamic window into multiple detection areas based on vehicle driving parameters and a pre-set mapping relationship between vehicle driving parameters and detection areas; if the detection results contain obstacles, comparing the relative positional relationship between the obstacles and each detection area to obtain position comparison results; and determining the vehicle's obstacle avoidance control logic based on the position comparison results and a pre-set mapping relationship between the position comparison results and obstacle avoidance control logic for obstacle avoidance. This invention can effectively reduce the time and resource consumption of meaningless window creation, reduce the computational load on the central processing unit, improve the overall vehicle control performance such as control cycle, and increase the efficiency and experience of autonomous driving.

Description

Technical Field

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

[0002] In manual driving, when encountering obstacles such as narrow intersections or garage corners where the presence of effective obstacles cannot be determined, the human approach involves slowing down and repeatedly assessing the situation to achieve a relatively smooth driving control experience. In autonomous driving, when facing obstacles such as pedestrians, dogs, or other vehicles at narrow intersections or garage corners, common solutions rely on obstacle detection, failing to account for the less-than-ideal control results during actual driving, such as sudden stops, jerking, or stalling. Existing technologies typically employ dynamic time windows, with a preset time period as the window's cycle length, within which local paths are planned. By using the vehicle's onboard sensors to obtain attitude and obstacle poses and creating an environmental model, and comprehensively considering kinematic constraints, permissible speed constraints, dynamic constraints, and minimum turning radius constraints, combined with current vehicle speed, angle, and acceleration, the future detectable area is effectively detected to determine the final speed space. This can solve the problem of obstacle avoidance when obstacles are located at a greater distance, but it can also lead to excessively long local paths, preventing the use of the optimal path to bypass obstacles. Furthermore, the computational workload increases exponentially with the increase in the detection scale of each iteration's time window data, greatly reducing computational efficiency. Summary of the Invention

[0003] In view of the shortcomings of the prior art described above, the present invention provides an obstacle avoidance method, system, electronic device and storage medium for autonomous driving of vehicles to solve the above-mentioned technical problems.

[0004] This invention provides an obstacle avoidance method for autonomous vehicle driving, comprising:

[0005] Continuously perform dynamic window detection in front of the vehicle to obtain detection results;

[0006] Based on the vehicle driving parameters and the pre-set mapping relationship between the vehicle driving parameters and the detection area, the dynamic window is divided into multiple detection areas;

[0007] If the detection result contains an obstacle, the relative positional relationship between the obstacle and each of the detection areas is compared to obtain a position comparison result;

[0008] Based on the position comparison results and the pre-set mapping relationship between the position comparison results and obstacle avoidance control logic, the obstacle avoidance control logic of the vehicle is determined to perform obstacle avoidance.

[0009] Optionally, based on vehicle driving parameters and a pre-set mapping relationship between the vehicle driving parameters and the detection area, the dynamic window is divided into multiple detection areas, including: based on the risk level of collision with obstacles, the dynamic window is divided into a warning area, a deceleration area, and an emergency stop area, with the warning area, the deceleration area, and the emergency stop area arranged sequentially from far to near in the vehicle's driving direction.

[0010] Optionally, the relative positional relationship between the obstacle and each of the detection areas is compared to obtain a position comparison result, including:

[0011] The positional relationship between the obstacle and the emergency stop area is compared to obtain a first comparison result. If the first comparison result is that the obstacle is not in the emergency stop area, the positional relationship between the obstacle and the deceleration area is compared to obtain a second comparison result. If the second comparison result is that the obstacle is not in the deceleration area, the positional relationship between the obstacle and the warning area is compared.

[0012] Optionally, the vehicle driving parameters include the current vehicle speed. Based on the position comparison result and a pre-set mapping relationship between the position comparison result and the obstacle avoidance control logic, the obstacle avoidance control logic of the vehicle is determined, including:

[0013] If the obstacle is located within the warning area, the vehicle continues to travel at the current speed;

[0014] If the obstacle is located within the deceleration zone, the current vehicle speed is compared with the preset target vehicle speed. If the current vehicle speed is less than or equal to the preset target vehicle speed, the vehicle continues to travel at the current vehicle speed. If the current vehicle speed is greater than the preset target vehicle speed, the vehicle decelerates to the preset target vehicle speed and continues to travel at the preset target vehicle speed.

[0015] If the obstacle is located within the emergency stop area, the vehicle shall be brought to a stop.

[0016] Optionally, before performing dynamic window detection of obstacles in front of the vehicle, the following steps are included:

[0017] The system detects the lane ahead of the vehicle and obtains the lane detection results.

[0018] The lane detection results are compared with a pre-set narrow path threshold. If the lane detection results meet the narrow path threshold, dynamic window detection is performed on obstacles in front of the vehicle.

[0019] Optionally, the vehicle driving parameters include current vehicle speed, current acceleration, wheel angle, vehicle position information, and braking distance.

[0020] Optionally, if the detection result indicates no obstacle, the vehicle continues to travel according to the vehicle driving parameters.

[0021] The present invention also provides an obstacle avoidance system for autonomous driving of vehicles, the system comprising:

[0022] The dynamic window detection module is used to continuously perform dynamic window detection in front of the vehicle and obtain the detection results;

[0023] The position comparison module is used to divide the dynamic window into multiple detection areas based on vehicle driving parameters and a pre-set mapping relationship between the vehicle driving parameters and the detection area. If the detection result is an obstacle, the module compares the relative positional relationship between the obstacle and each of the detection areas to obtain a position comparison result.

[0024] The obstacle avoidance module is used to determine the vehicle's obstacle avoidance control logic based on the position comparison result and the pre-set mapping relationship between the position comparison result and the obstacle avoidance control logic, so as to perform obstacle avoidance.

[0025] The present invention also provides an electronic device, the electronic device comprising:

[0026] One or more processors;

[0027] A storage device for storing one or more programs that, when executed by one or more processors, cause the electronic device to implement the obstacle avoidance method for autonomous driving of a vehicle as described in any of the preceding claims.

[0028] The present invention also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a computer processor, causes the computer to perform the obstacle avoidance method for autonomous driving of a vehicle as described above.

[0029] The beneficial effects of this invention are as follows: This invention provides a method, system, electronic device, and storage medium for obstacle avoidance in autonomous driving. When the vehicle is in autonomous driving mode, a designed variable-scale dynamic detection window method can be used. Utilizing the current vehicle's motion control model and information from sensors such as vehicle speed, acceleration, angular velocity, and braking time, the dynamic window is divided into multiple detection areas for accurate prediction. Combined with obstacle detection information, different obstacle avoidance strategies are adopted for different detection areas while ensuring driving safety. This allows the dynamic window to have different window detection thresholds based on different speeds, effectively reducing the time and resource consumption of meaningless window creation, decreasing the computational load on the central processing unit, improving the overall vehicle control performance such as control cycle, and increasing the efficiency and experience of autonomous driving.

[0030] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and do not limit this application. Attached Figure Description

[0031] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application. It is obvious that the drawings described below are merely some embodiments of this application, and those skilled in the art can obtain other drawings based on these drawings without any inventive effort. In the drawings:

[0032] Figure 1 This is a schematic diagram illustrating the division of a low-speed detection area as shown in an exemplary embodiment of this application;

[0033] Figure 2 This is a schematic diagram illustrating the division of a high-speed vehicle detection area, as shown in an exemplary embodiment of this application;

[0034] Figure 3 This is a flowchart illustrating an exemplary embodiment of the obstacle avoidance method for autonomous driving of a vehicle, as shown in this application.

[0035] Figure 4 This is a structural block diagram of an obstacle avoidance system for autonomous driving of a vehicle, as illustrated in an exemplary embodiment of this application.

[0036] Figure 5 This is a vehicle motion model diagram illustrating an exemplary embodiment of this application;

[0037] Figure 6 This is an exemplary embodiment of the present application illustrating a vehicle steering posture diagram;

[0038] Figure 7 A schematic diagram of the structure of a computer system suitable for implementing the electronic device of the present application is shown. Detailed Implementation

[0039] The embodiments of the present invention will be described below with reference to the accompanying drawings and preferred embodiments. Those skilled in the art can easily understand other advantages and effects of the present invention from the content disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and various details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of the present invention. It should be understood that the preferred embodiments are only for illustrating the present invention and not for limiting the scope of protection of the present invention.

[0040] It should be noted that the illustrations provided in the following embodiments are only schematic representations of the basic concept of the present invention. Therefore, the drawings only show the components related to the present invention and are not drawn according to the actual number, shape and size of the components in the actual implementation. In the actual implementation, the form, quantity and proportion of each component can be arbitrarily changed, and the layout of the components may also be more complex.

[0041] In the following description, numerous details are explored to provide a more thorough explanation of embodiments of the invention. However, it will be apparent to those skilled in the art that embodiments of the invention may be practiced without these specific details. In other embodiments, well-known structures and devices are shown in block diagram form rather than in detail to avoid obscuring embodiments of the invention.

[0042] First, it's important to clarify that in manual driving, when encountering obstacles like those at narrow intersections or corners of garages where the presence of effective obstacles is uncertain, the human approach involves slowing down and repeatedly assessing the situation to achieve a relatively smooth driving experience. However, in autonomous driving, when facing obstacles such as pedestrians, dogs, or other vehicles at narrow intersections or corners of garages, common solutions rely on obstacle detection. This approach fails to account for the less-than-ideal control results during actual driving, such as sudden stops, jerking, or stalling. Existing technologies typically employ dynamic time windows, with a preset time period as the window's cycle length, within which a local path is planned. This involves using the vehicle's sensors to obtain attitude and obstacle poses, creating an environmental model, and comprehensively considering kinematic constraints, permissible speed constraints, dynamic constraints, and minimum turning radius constraints. Combined with current vehicle speed, angle, and acceleration, this effectively detects the future detectable area and determines the final speed space. This can address the issue of obstacles appearing at a greater distance and allowing for obstacle avoidance. However, this approach can lead to excessively long local paths, preventing the use of the optimal path to bypass obstacles. The larger the dynamic window, the more data needs to be analyzed. The computational load increases exponentially with the increase of the detection scale, which greatly reduces the computational efficiency.

[0043] Figure 1 This is a schematic diagram illustrating the division of the low-speed detection area in this embodiment. Figure 2 This is a schematic diagram illustrating the division of the high-speed state detection area in this embodiment. For example... Figure 1 and Figure 2 As shown, a dynamic window will be generated in front of the vehicle during its journey, and obstacles will be detected within the dynamic window.

[0044] Please see Figure 3 This embodiment provides an obstacle avoidance method for autonomous driving of vehicles, including the following steps:

[0045] S10: Continuously perform dynamic window detection in front of the vehicle and obtain the detection results;

[0046] S20: Based on the vehicle driving parameters and the pre-set mapping relationship between the vehicle driving parameters and the detection area, the dynamic window is divided into multiple detection areas;

[0047] S30: If the detection result includes an obstacle, then compare the relative positional relationship between the obstacle and each of the detection areas to obtain a position comparison result;

[0048] S40: Based on the position comparison result and the pre-set mapping relationship between the position comparison result and the obstacle avoidance control logic, determine the obstacle avoidance control logic of the vehicle to perform obstacle avoidance.

[0049] In step S20, which is the step of dividing the dynamic window into multiple detection areas, the dynamic window is divided into a warning area, a deceleration area, and an emergency stop area according to the risk of collision with the obstacle. The closer to the vehicle, the higher the risk of collision with the obstacle. Therefore, the warning area, the deceleration area, and the emergency stop area are set in the direction of vehicle travel from far to near.

[0050] Step S30, which is the step of comparing the relative positional relationships between the obstacle and each of the detection areas to obtain the position comparison result, includes the following steps:

[0051] The positional relationship between the obstacle and the emergency stop area is compared to obtain a first comparison result. If the first comparison result is that the obstacle is not in the emergency stop area, the positional relationship between the obstacle and the deceleration area is compared to obtain a second comparison result. If the second comparison result is that the obstacle is not in the deceleration area, the positional relationship between the obstacle and the warning area is compared.

[0052] In some embodiments, the vehicle driving parameters include the current vehicle speed. Therefore, step S40, which determines the vehicle's obstacle avoidance control logic based on the position comparison result and a pre-set mapping relationship between the position comparison result and the obstacle avoidance control logic, includes the following sub-steps:

[0053] S41: If the obstacle is located within the warning area, the vehicle continues to travel at the current speed;

[0054] S42: If the obstacle is located within the deceleration area, compare the current vehicle speed with the preset target vehicle speed. If the current vehicle speed is less than or equal to the preset target vehicle speed, the vehicle continues to travel at the current vehicle speed. If the current vehicle speed is greater than the preset target vehicle speed, the vehicle decelerates to the preset target vehicle speed and continues to travel at the preset target vehicle speed.

[0055] S43: If the obstacle is located within the emergency stop area, bring the vehicle to a stop.

[0056] In some embodiments, before step S10, i.e. before the step of dynamically detecting obstacles in front of the vehicle, the following steps are included:

[0057] S01: Detect the lane ahead of the vehicle and obtain the lane detection results.

[0058] S02: Compare the lane detection result with a pre-set narrow path threshold. If the lane detection result meets the narrow path threshold, then perform dynamic window detection on obstacles in front of the vehicle.

[0059] In this embodiment, the vehicle driving parameters include current vehicle speed, current acceleration, wheel angle, vehicle body posture information, and braking distance. In step S20, the dynamic window is divided into multiple detection areas based on the vehicle driving parameters and the pre-set mapping relationship between the vehicle driving parameters and the detection area.

[0060] The detection area along the vehicle's direction of travel is larger when the current vehicle speed, acceleration, and braking distance are greater, i.e., along the length of the dynamic window. Conversely, the smaller the detection area along the vehicle's direction of travel, the smaller the size of the detection area along the length of the dynamic window. The size of the detection area in the width direction is related to the detector's detection range. The larger the detector's detection range in the vehicle's width direction, i.e., the normal direction of travel, the larger the width of the dynamic window, and thus the larger the size of the detection area in the width direction.

[0061] like Figure 1 and Figure 2 As shown, when the vehicle speed is relatively low (V1), the size of the detection area in the direction of vehicle travel is small, while when the vehicle speed is relatively high (V2), the size of the detection area in the direction of vehicle travel is large.

[0062] In step S30, if the detection result is no obstacle, the vehicle continues to drive according to the vehicle driving parameters.

[0063] Please see Figure 4 This embodiment also provides an obstacle avoidance system for autonomous driving of vehicles, the system comprising:

[0064] The dynamic window detection module is used to continuously perform dynamic window detection in front of the vehicle and obtain the detection results.

[0065] The position comparison module is used to divide the dynamic window into multiple detection areas based on vehicle driving parameters and a pre-set mapping relationship between the vehicle driving parameters and the detection area. If the detection result is an obstacle, the module compares the relative positional relationship between the obstacle and each of the detection areas to obtain a position comparison result.

[0066] The obstacle avoidance module is used to determine the vehicle's obstacle avoidance control logic based on the position comparison result and the pre-set mapping relationship between the position comparison result and the obstacle avoidance control logic, so as to perform obstacle avoidance.

[0067] The obstacle detection steps during autonomous driving are as follows:

[0068] (1) Confirm whether the vehicle is in a narrow path at a corner.

[0069] The vehicle's location is determined by lane detection results. For example, if the road ahead is narrow, allowing only one vehicle to pass at a time, and there is a turn, it can be confirmed that the vehicle is currently in a narrow path scenario.

[0070] (2) Dynamic window detection of obstacles in front of the vehicle using autonomous driving is performed, and the current vehicle driving parameters are collected. The vehicle driving parameters mainly include the current speed of the vehicle, the current wheel angle, and the current vehicle body posture information. Combined with the pre-set braking distance, the scale range of the dynamic window is analyzed and calculated.

[0071] Before performing obstacle dynamic window detection, the area in front of the vehicle can be detected using devices such as LiDAR and cameras. If an obstacle is present, a dynamic window is generated to perform obstacle dynamic window detection in front of the vehicle. This avoids performing dynamic window detection when there is no obstacle, which would increase the computational burden and energy consumption.

[0072] (3) Obstacles are effectively detected and prevented, and detailed information about the obstacles is obtained. After corresponding logical judgment, the corresponding decision results are output. Among them, the relative positional relationship between the obstacle and the vehicle can be obtained by analyzing and calculating the vehicle motion model. The vehicle motion model includes parameters such as the vehicle's spatial pose, speed, and braking distance that change over time, which can reflect the vehicle's motion law from a geometric perspective. Therefore, when the vehicle is in a narrow path scenario, it is usually in an environment with a good road surface, such as a garage, and is traveling at a low speed. It is not necessary to consider vehicle dynamic characteristics such as vehicle handling stability. The path tracking controller based on the vehicle motion model has reliable control performance. When the information collected by multiple sensors is fused, it can perceive the accurate pose information of the obstacle in the vehicle coordinate system in a narrow path.

[0073] (4) If the decision result output is "emergency stop", then the current driving will be stopped, and the autonomous driving will be restarted after the obstacle moves out of the prediction range of the dynamic window. If the decision result output is "no emergency stop required", then the current autonomous driving will continue. When the obstacle no longer appears in the newly generated dynamic window, there is no need to stop to avoid the obstacle, and the driving will continue to prevent meaningless braking and avoidance. If the obstacle still appears in the newly generated dynamic window, then the vehicle will stop immediately.

[0074] Repeat steps (3) and (4) above to complete the effective detection of obstacles in the dynamic window and the dynamic operation of the vehicle until there is a large driving space in front of the vehicle and the vehicle leaves the narrow corner path scene, then exit the dynamic window detection.

[0075] During the dynamic window detection process, the dynamic window is mainly divided into three parts: an emergency stop area S1, a deceleration area S2, and a warning area S3. In this embodiment, the dynamic window also includes a pre-dynamic detection area that is performed for K time intervals when the dynamic window is created. The pre-dynamic detection area lasts for K time intervals and is updated periodically. Here, K is a pre-set pre-dynamic detection period that can be adjusted according to the actual situation.

[0076] When the obstacle is in the emergency stop zone S1, the vehicle will stop immediately.

[0077] When an obstacle is in deceleration zone S2, the vehicle's current speed is acquired. If the speed is already lower than the preset minimum speed V2, the vehicle maintains its current speed and continues to assess the situation until the obstacle triggers emergency stop zone S1 and comes to a complete stop, or triggers warning zone S3 and resumes its original speed control. If the speed exceeds the preset minimum speed V2, the vehicle reduces its speed from the current speed V1 to the minimum speed V2 until the obstacle triggers emergency stop zone S1 and comes to a complete stop, or triggers warning zone S3 and resumes its original speed control.

[0078] When an obstacle is within the detectable warning zone S3, it is considered extremely unlikely that the obstacle is in a dangerous driving area, and autonomous driving continues without considering deceleration. If the obstacle enters the deceleration zone S2, the control logic for the obstacle being in deceleration zone S2 is executed directly. If the obstacle no longer appears within the dynamic window, the obstacle detection result is no longer considered.

[0079] Specifically, such as Figure 5 and Figure 6 As shown, in the vehicle motion model, Here are the coordinates of the center of the vehicle's front axle. The coordinates of the rear axle center of the vehicle. The speed at the center of the rear axle of the vehicle. The speed at the center of the rear axle of the vehicle. For the front wheel deflection angle, Wheelbase Centered at the rear axle Centered on the front axle The rear wheel steering radius, For the center of rotation, ω represents the yaw rate.

[0080] The vehicle motion model is as follows:

[0081]

[0082] Among them, symbols This represents the change in the X-coordinate position of the rear axle center of the vehicle. This indicates the amount of change in the position of the rear axle center of the vehicle. This represents the change in the vehicle's yaw angle. This indicates the vehicle's yaw angle, also known as the heading angle. Indicates the speed of the rear axle of the vehicle. This indicates the speed at which the vehicle yaws.

[0083] Assuming the sideslip angle of the autonomous vehicle remains constant during a turn, meaning the instantaneous turning radius is the same as the road curvature radius, then the rear wheel travels along the axle... The velocity at that point is:

[0084]

[0085] The kinematic constraints of the front and rear axles are

[0086]

[0087] Changes perpendicular to the direction of motion cancel each other out, as shown in the following formula.

[0088]

[0089] Based on the relationship between the angular velocities of the front and rear wheels, we can obtain...

[0090]

[0091] The above formulas, when combined and substituted into the kinematic constraint equations, can be used to solve for the yaw rate.

[0092]

[0093] Next, differentiating the relationship between the angular velocities of the front and rear wheels, we have:

[0094]

[0095] Substituting the equation for the vertical direction of motion into the equation...

[0096]

[0097] Substituting the curvature motion control equations, we get

[0098]

[0099] unfolding in a natural way

[0100]

[0101] The turning radius and front wheel deflection angle can be obtained from the yaw angle and vehicle speed, according to the following formula.

[0102]

[0103] From the derivation of the derivative and the above model, the vehicle kinematic model can be obtained as follows:

[0104]

[0105] This model can be further represented in a general form.

[0106]

[0107] state variables For position and yaw angle

[0108] Control quantity Speed ​​and front wheel deflection angle can be simply understood as the throttle and steering wheel angles.

[0109] Substituting the formula into the kinematic model transformation equation yields the following derivation:

[0110]

[0111] Combined with pre-matching dynamic window increment k represents the forward prediction dynamic window based on the current position. The prediction of the three variables, and the final dynamic window, can be represented as follows:

[0112]

[0113] The above completes the derivation of the obstacle dynamic window prediction. Based on the above derivation conclusions, if the obstacle is not within the prediction window, it means that subsequent driving will no longer be affected by this obstacle, and the driving decision module no longer needs to consider collision factors.

[0114] Based on the above inferences, and according to the currently given window length, a multi-scale sample set sequence is constructed. Based on speed... Calculate candidate scales, find the maximum value of the scale under each left and right wheel speed, and update it as the optimal scale.

[0115] When constructing a multi-scale sample window set, based on the current initial scale value and using a set safety threshold length as the benchmark, and according to the given dynamic window target position and target window scale information, a multi-scale sample set sequence is constructed to train the classifier. The multi-scale classifier is used to detect all candidate benchmark scales for the current braking time. The classifier's response value is obtained as a sequence matrix. The maximum window scale in each matrix is ​​identified and compared. The matrix with the largest maximum element value corresponds to the optimal scale for the new target, denoted as η.

[0116] All scaling ratios form a vector scalesi = v * (η ± am) m = 0, 1, ..., M, where a ∈ (0, 1) is the scaling ratio compensation. When it is positive, scalesi > 1, indicating the scale of magnification; when it is negative, scalesi < 1, indicating the scale of reduction.

[0117] The current obstacle window is scaled according to the set scaling ratio. The target velocity of the scaled multi-scale window is sampled to obtain the multi-scale base sample sequence xi. The scale is cyclically used to predict the time, thereby constructing a multi-scale sample set sequence. The multi-scale sample set sequence is a series of sample sets of different scales obtained by cyclically shifting dense sampling within a specified time at the base scale.

[0118] Based on the steps, detailed design derivation, and judgment conditions above, a multi-scale dynamic window classifier is constructed using core vehicle data (vehicle speed, acceleration, angular velocity, vehicle pose information, and obstacle pose information) as a sequence of predicted values ​​representing a confidence level matrix. The maximum element of the matrix represents the confidence level of the target at its optimal scale and optimal position, and the scale of the maximum element in the matrix is ​​the maximum value for the next iteration cycle. Compared to a fixed window that only considers the presence of forward obstacles, this approach allows for more reasonable decision-making for driving tasks, effectively improving overall driving efficiency and mitigating the negative impacts of meaningless braking and poor driver experience.

[0119] Embodiments of this application also provide an electronic device, including: one or more processors; and a storage device for storing one or more programs, which, when executed by the one or more processors, cause the electronic device to implement the obstacle avoidance method for autonomous driving provided in the above embodiments.

[0120] Figure 7 A schematic diagram of a computer system suitable for implementing the embodiments of this application is shown. It should be noted that... Figure 7 The computer system 1200 of the electronic device shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments of this application.

[0121] like Figure 7As shown, the computer system 1200 includes a Central Processing Unit (CPU) 1201, which can perform various appropriate actions and processes based on programs stored in Read-Only Memory (ROM) 1202 or programs loaded from storage portion 1208 into Random Access Memory (RAM) 1203, such as performing the methods described in the above embodiments. Various programs and data required for system operation are also stored in RAM 1203. The CPU 1201, ROM 1202, and RAM 1203 are interconnected via bus 1204. An Input / Output (I / O) interface 1205 is also connected to bus 1204.

[0122] The following components are connected to I / O interface 1205: an input section 1206 including a keyboard, mouse, etc.; an output section 1207 including a cathode ray tube (CRT), liquid crystal display (LCD), etc., and speakers, etc.; a storage section 1208 including a hard disk, etc.; and a communication section 1209 including a network interface card such as a LAN (Local Area Network) card, modem, etc. The communication section 1209 performs communication processing via a network such as the Internet. A drive 1210 is also connected to I / O interface 1205 as needed. Removable media 1211, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., are installed on drive 1210 as needed so that computer programs read from them can be installed into storage section 1208 as needed.

[0123] Specifically, according to embodiments of this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program including a computer program for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication section 1209, and / or installed from removable medium 1211. When the computer program is executed by central processing unit (CPU) 1201, it performs various functions defined in the system of this application.

[0124] It should be noted that the computer-readable medium shown in the embodiments of this application can be a computer-readable signal medium or a computer-readable storage medium, or any combination of the two. A computer-readable storage medium can be, for example, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), flash memory, optical fiber, portable compact disc read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this application, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, carrying a computer-readable computer program. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media can also be any computer-readable medium other than computer-readable storage media, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The computer program contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to wireless, wired, etc., or any suitable combination thereof.

[0125] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. Each block in a flowchart or block diagram may represent a module, segment, or portion of code, which contains one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram or flowchart, and combinations of blocks in a block diagram or flowchart, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0126] The units described in the embodiments of this application can be implemented in software or hardware, and the described units can also be located in a processor. The names of these units do not necessarily limit the specific unit itself.

[0127] Another aspect of this application provides a computer-readable storage medium storing a computer program thereon, which, when executed by a computer's processor, causes the computer to perform the obstacle avoidance method for autonomous driving of a vehicle as described above. This computer-readable storage medium may be included in the electronic device described in the above embodiments, or it may exist independently and not incorporated into the electronic device.

[0128] Another aspect of this application provides a computer program product or computer program including computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform the obstacle avoidance method for autonomous driving provided in the various embodiments described above.

[0129] This embodiment of the vehicle autonomous driving obstacle avoidance method, system, electronic equipment, and storage medium enables precise prediction when the vehicle is in autonomous driving mode. It utilizes a designed variable-scale dynamic detection window method, leveraging the vehicle's motion control model and information from sensors such as vehicle speed, acceleration, angular velocity, and braking time, combined with fused obstacle detection information. While ensuring driving safety, this effectively reduces the time and resource consumption of meaningless window creation, improving autonomous driving efficiency and user experience, and enhancing overall vehicle control performance. Simultaneously, the dynamic window is divided into three regions for detection, and the current speed and braking distance are considered to calculate the current variable-length detection window. This allows the dynamic window to have different detection thresholds based on different speeds, reducing the computational load on the central processing unit and improving overall vehicle control performance, such as control cycle time.

[0130] The above embodiments are merely illustrative of the principles and effects of the present invention and are not intended to limit the invention. Any person skilled in the art can modify or alter the above embodiments without departing from the spirit and scope of the present invention. Therefore, all equivalent modifications or alterations made by those skilled in the art without departing from the spirit and technical concept disclosed in the present invention should still be covered by the claims of the present invention.

Claims

1. A method for obstacle avoidance for automatic driving of a vehicle, characterized by, The method comprises the following steps: continuously performing dynamic window detection on the front of the vehicle to obtain a detection result; dividing the dynamic window into a plurality of detection regions according to vehicle driving parameters and a pre-set mapping relationship between the vehicle driving parameters and the detection regions; if the detection result contains an obstacle, comparing the relative positional relationship between the obstacle and each of the detection regions to obtain a positional comparison result; determining the obstacle avoidance control logic of the vehicle according to the positional comparison result and a pre-set mapping relationship between the positional comparison result and the obstacle avoidance control logic to perform obstacle avoidance; wherein determining the mapping relationship between the vehicle driving parameters and the detection regions comprises: based on the vehicle motion model and the current window length, constructing a multi-scale sample set sequence, and training a classifier; using the classifier to detect all candidate reference scales of the current braking time, obtaining a response value of the classifier as a sequence matrix, finding the maximum window scale in each matrix and comparing them, and the matrix with the maximum element value corresponds to the new optimal scale.

2. The method for automatic driving obstacle avoidance of a vehicle according to claim 1, wherein, dividing the dynamic window into a plurality of detection regions according to vehicle driving parameters and a pre-set mapping relationship between the vehicle driving parameters and the detection regions, comprising: dividing the dynamic window into a warning region, a deceleration region and an emergency stop region according to the risk degree of collision with the obstacle, and the warning region, the deceleration region and the emergency stop region are sequentially arranged in the driving direction of the vehicle from far to near.

3. The method of claim 2, wherein, comparing the relative positional relationship between the obstacle and each of the detection regions to obtain a positional comparison result, comprising: comparing the positional relationship between the obstacle and the emergency stop region to obtain a first comparison result, if the first comparison result is that the obstacle is not in the emergency stop region, comparing the positional relationship between the obstacle and the deceleration region to obtain a second comparison result, if the second comparison result is that the obstacle is not in the deceleration region, comparing the positional relationship between the obstacle and the warning region.

4. The method of claim 3, wherein, The vehicle driving parameters include the current vehicle speed, and determining the obstacle avoidance control logic of the vehicle according to the positional comparison result and a pre-set mapping relationship between the positional comparison result and the obstacle avoidance control logic, comprising: if the obstacle is located in the warning region, the vehicle continues to drive at the current vehicle speed; if the obstacle is located in the deceleration region, comparing the current vehicle speed with a pre-set target vehicle speed, if the current vehicle speed is less than or equal to the pre-set target vehicle speed, the vehicle continues to drive at the current vehicle speed, if the current vehicle speed is greater than the pre-set target vehicle speed, the vehicle decelerates to the pre-set target vehicle speed and continues to drive at the pre-set target vehicle speed; if the obstacle is located in the emergency stop region, the vehicle is stopped.

5. The method of claim 1 to 4, wherein, Before performing dynamic window detection on the obstacle in front of the vehicle, comprising: detecting the lane in front of the vehicle driving to obtain a lane detection result, comparing the lane detection result with a pre-set narrow path threshold, if the lane detection result meets the narrow path threshold, performing dynamic window detection on the obstacle in front of the vehicle.

6. The obstacle avoidance method for automatic driving of a vehicle according to any one of claims 1 to 4, characterized in that, The vehicle driving parameters include current vehicle speed, current acceleration, wheel rotation angle, vehicle body posture information and brake distance.

7. The method of claim 1-4, wherein, If the detection result is no obstacle, the vehicle continues driving according to the vehicle driving parameters.

8. A barrier avoidance system for automatic driving of a vehicle, characterized in that The system comprises: a dynamic window detection module for continuously detecting a front of the vehicle in a dynamic window to obtain a detection result; a position comparison module for dividing the dynamic window into a plurality of detection regions according to the vehicle driving parameters and a pre-set mapping relationship between the vehicle driving parameters and the detection regions, and comparing relative position relationships between the obstacle and each of the detection regions if the detection result is an obstacle to obtain a position comparison result; an obstacle avoidance module for determining an obstacle avoidance control logic of the vehicle according to the position comparison result and a pre-set mapping relationship between the position comparison result and the obstacle avoidance control logic to perform obstacle avoidance; wherein the mapping relationship between the vehicle driving parameters and the detection regions is determined by constructing a multi-scale sample set sequence based on a vehicle motion model and a current window length, and training a classifier; the classifier is used to detect all candidate reference scales of the current brake time, obtain a response value of the classifier as a sequence matrix, find out a maximum window scale in each matrix and compare them, and the scale corresponding to the matrix with the maximum element value is a new optimal scale.

9. An electronic device, comprising: The electronic device comprises: one or more processors; a storage device for storing one or more programs, which, when executed by the one or more processors, cause the electronic device to implement the obstacle avoidance method for automatic driving of the vehicle according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, A computer program is stored thereon, which, when executed by a processor of a computer, causes the computer to perform the obstacle avoidance method for automatic driving of the vehicle according to any one of claims 1 to 7.

Images