Intelligent driving method and device of vehicle, vehicle and computer readable storage medium

Abstract

This application provides an intelligent driving method, device, vehicle, computer-readable storage medium, and computer program product for a vehicle. The method includes: performing target detection processing on the vehicle's surrounding environment using radar and cameras; when a visual target is detected, determining whether the visual target meets a trust condition; wherein, a visual target refers to a target detected by the camera but not by the radar; when the visual target meets the trust condition, performing obstacle avoidance processing on the visual target; when the visual target does not meet the trust condition, not performing obstacle avoidance processing on the visual target. This application can reduce missed detections and improve vehicle driving safety.

Description

Technical Field

[0001] This application relates to vehicle technology, and more particularly to an intelligent driving method, apparatus, vehicle, computer-readable storage medium, and computer program product for a vehicle. Background Technology

[0002] Intelligent driving technology refers to the technology that uses various sensors to perceive and process the vehicle's surrounding environment, and then uses computer algorithms to analyze and make decisions, thereby achieving a series of automated driving functions. Currently, many vehicle models use a combination of radar and cameras, which enables multi-source information complementarity and improves the effectiveness of intelligent driving.

[0003] For radar + camera combination solutions, the fused target detected by both radar and camera is usually used as the final detection result to achieve intelligent driving. However, due to the limitations of individual sensor performance, there may be situations where the radar and camera perceive the same target differently, making fusion impossible. Such missed detections can further increase the risk of collisions. Summary of the Invention

[0004] This application provides a method, apparatus, vehicle, computer-readable storage medium, and computer program product for intelligent driving of a vehicle, which can reduce missed detections and improve vehicle driving safety.

[0005] The technical solution of this application is implemented as follows:

[0006] This application provides an intelligent driving method for a vehicle, including:

[0007] The vehicle's radar and cameras are used to perform target detection processing on the environment surrounding the vehicle.

[0008] When a visual target is detected, it is determined whether the visual target meets the credibility criteria; wherein, the visual target refers to a target detected by the camera but not by the radar.

[0009] When the visual target meets the credibility condition, obstacle avoidance processing is performed on the visual target;

[0010] When the visual target does not meet the credibility condition, no obstacle avoidance processing is performed on the visual target.

[0011] This application provides an intelligent driving device for a vehicle, comprising:

[0012] The target detection module is used to perform target detection processing on the environment surrounding the vehicle using the vehicle's radar and camera;

[0013] The judgment module is used to determine whether a visual target meets the credibility condition when a visual target is detected; wherein, the visual target refers to a target detected by the camera but not by the radar.

[0014] A visual obstacle avoidance module is used to perform obstacle avoidance processing on the visual target when the visual target meets the credibility condition;

[0015] The visual obstacle avoidance module is also used to not perform obstacle avoidance processing on the visual target when the visual target does not meet the credibility condition.

[0016] This application provides a vehicle, including:

[0017] Memory, used to store executable instructions;

[0018] The processor is configured to implement the intelligent driving method for the vehicle provided in this application by executing executable instructions stored in the memory.

[0019] This application provides a computer-readable storage medium storing executable instructions for implementing the intelligent driving method for a vehicle provided in this application when executed by a processor.

[0020] This application provides a computer program product including executable instructions for implementing the intelligent driving method for a vehicle provided in this application when executed by a processor.

[0021] This application has the following beneficial effects:

[0022] This application uses the vehicle's radar and cameras to perform target detection processing on the vehicle's surrounding environment. When a visual target is detected, it is determined whether the visual target meets the credibility criteria. A visual target refers to a target detected by the camera but not by the radar. When the visual target meets the credibility criteria, obstacle avoidance processing is performed; when the visual target does not meet the credibility criteria, no obstacle avoidance processing is performed. This application, for visual targets detected solely by the camera, first determines their credibility before performing obstacle avoidance processing, thereby reducing missed detections caused by relying on fused targets and improving vehicle safety during driving. Attached Figure Description

[0023] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0024] Figure 1 This is a first structural schematic diagram of the vehicle provided in an embodiment of this application;

[0025] Figure 2 This is a schematic diagram of the second structure of the vehicle provided in the embodiments of this application;

[0026] Figure 3A This is a first flowchart illustrating the intelligent driving method for a vehicle provided in an embodiment of this application;

[0027] Figure 3B This is a second flowchart illustrating the intelligent driving method for vehicles provided in this application embodiment;

[0028] Figure 4 This is a third flowchart illustrating the intelligent driving method for vehicles provided in this application embodiment. Detailed Implementation

[0029] To make the objectives, technical solutions, and advantages of this application clearer, the application will be further described in detail below with reference to the accompanying drawings. The described embodiments should not be regarded as limitations on this application. All other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0030] In the following description, references to "some embodiments" describe a subset of all possible embodiments; however, it is understood that "some embodiments" may be the same subset or different subsets of all possible embodiments and may be combined with each other without conflict. In the following description, the term "a plurality of" means at least two.

[0031] In the following description, the terms "first, second, third" are used merely to distinguish similar objects and do not represent a specific ordering of objects. It is understood that "first, second, third" may be interchanged in a specific order or sequence where permitted, so that the embodiments of this application described herein can be implemented in an order other than that illustrated or described herein.

[0032] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing embodiments of this application only and is not intended to limit this application.

[0033] This application provides a method, apparatus, vehicle, computer-readable storage medium, and computer program product for intelligent driving of a vehicle, which can reduce missed detections and improve vehicle driving safety.

[0034] See Figure 1 , Figure 1This is a schematic diagram of the architecture of a vehicle 100 provided in an embodiment of this application, showing a radar 100-1, a camera 100-2, and an intelligent driving system 100-3 within the vehicle 100. It is worth noting that the radar 100-1 and camera 100-2 can be considered as part of the intelligent driving system 100-3, or they can be considered independent of the intelligent driving system 100-3. In some embodiments, the intelligent driving system 100-3 may include a control unit and an actuator. The control unit is used to receive data from sensors and perform related calculations to obtain control commands. The actuator is used to control the vehicle to perform corresponding actions according to the control commands, such as acceleration, deceleration, and steering.

[0035] In some embodiments, the intelligent driving system 100-3 performs target detection processing on the surrounding environment of the vehicle (i.e., vehicle 100) using radar 100-1 and camera 100-2; when a visual target is detected, it determines whether the visual target meets the credibility condition; wherein, a visual target refers to a target detected by camera 100-2 but not detected by radar 100-1; when the visual target meets the credibility condition, obstacle avoidance processing is performed on the visual target; when the visual target does not meet the credibility condition, obstacle avoidance processing is not performed on the visual target.

[0036] In some embodiments, the vehicle 100 can implement the intelligent driving method provided in this application embodiment by running a computer program. For example, the computer program can be a native program or software module in an operating system; it can be a native application (APP), i.e., a program that needs to be installed in the operating system to run; it can also be a mini-program, i.e., a program that only needs to be downloaded to a browser environment to run; or it can be a mini-program that can be embedded in any APP, and the mini-program can be controlled by the user to run or close. In short, the above-mentioned computer program can be any form of application, module, or plugin.

[0037] See Figure 2 , Figure 2 This is a structural schematic diagram of the vehicle 100 provided in the embodiments of this application. Figure 2 The vehicle 100 shown includes at least one processor 110, a memory 150, at least one network interface 120, and a user interface 130. Various components in the vehicle 100 are coupled together via a bus system 140. It is understood that the bus system 140 is used to implement communication between these components. In addition to a data bus, the bus system 140 also includes a power bus, a control bus, and a status signal bus. However, for clarity, ... Figure 2 The general labeled all buses as Bus System 140.

[0038] The processor 110 can be an integrated circuit chip with signal processing capabilities, such as a general-purpose processor, a digital signal processor (DSP), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor, etc.

[0039] User interface 130 includes one or more output devices 131 that enable the presentation of media content, including one or more speakers and / or one or more visual displays. User interface 130 also includes one or more input devices 132, including user interface components that facilitate user input, such as a microphone, a touch screen display, other input buttons and controls.

[0040] The memory 150 may be removable, non-removable, or a combination thereof. Exemplary hardware devices include solid-state storage, hard disk drives, etc. The memory 150 may optionally include one or more storage devices physically located away from the processor 110.

[0041] The memory 150 may include volatile memory or non-volatile memory, or both. The non-volatile memory may be read-only memory (ROM), and the volatile memory may be random access memory (RAM). The memory 150 described in this application embodiment is intended to include any suitable type of memory.

[0042] In some embodiments, memory 150 is capable of storing data to support various operations, examples of which include programs, modules, and data structures or subsets or supersets thereof, as illustrated below.

[0043] Operating system 151 includes system programs for handling various basic system services and performing hardware-related tasks, such as the framework layer, core library layer, driver layer, etc., for implementing various basic business functions and handling hardware-based tasks;

[0044] The network communication module 152 is used to reach other electronic devices via one or more (wired or wireless) network interfaces 120, exemplary network interfaces 120 including: Bluetooth, WiFi, and Universal Serial Bus (USB), etc.

[0045] Presentation module 153 is configured to enable the presentation of information (e.g., a user interface for operating peripheral devices and displaying content and information) via one or more output devices 131 (e.g., a display screen, a speaker, etc.) associated with user interface 130;

[0046] The input processing module 154 is used to detect and translate one or more user inputs or interactions from one or more input devices 132.

[0047] In some embodiments, the intelligent driving device for vehicles provided in this application can be implemented in software. Figure 2 A vehicle intelligent driving device 155 stored in memory 150 is shown. This device can be software in the form of programs and plug-ins, including the following software modules: a target detection module 1551, a judgment module 1552, and a visual obstacle avoidance module 1553. These modules are logically integrated and can therefore be arbitrarily combined or further separated according to their implemented functions. The functions of each module will be described below.

[0048] The intelligent driving method for vehicles provided in this application will be described in conjunction with exemplary applications and implementations of the vehicles provided in the embodiments of this application.

[0049] See Figure 3A , Figure 3A This is a flowchart illustrating an intelligent driving method for a vehicle provided in an embodiment of this application, which will be combined with... Figure 3A The steps shown are explained.

[0050] In step 101, the vehicle's radar and camera are used to perform target detection processing on the environment surrounding the vehicle.

[0051] Here, when the vehicle is in intelligent driving mode, its radar and cameras perform target detection processing on the surrounding environment, obtaining the target detection results corresponding to the radar and cameras respectively. There are no restrictions on the installation location or type of the radar and cameras.

[0052] It is worth noting that the targets involved in the embodiments of this application refer to various traffic entities participating in road traffic activities, such as other vehicles and pedestrians.

[0053] In some embodiments, the aforementioned target detection processing of the vehicle's surrounding environment using its radar and cameras can be achieved by using the vehicle's forward-facing radar and camera to detect targets in front of the vehicle. Considering that most collision risks are caused by the vehicle in front, or that in some special intelligent driving modes (such as cruise control mode) only the environment in front of the vehicle needs to be considered, using the vehicle's forward-facing radar and camera to detect targets in front of the vehicle can save costs while ensuring safety to a certain extent. In this case, the target to be detected can be another vehicle located in front of the vehicle and in the same lane as the vehicle.

[0054] In some embodiments, after the vehicle's surrounding environment is detected by its radar and camera, the intelligent driving method of the vehicle further includes: when a radar target is detected, no obstacle avoidance is performed on the radar target; wherein, a radar target refers to a target detected by radar but not by camera.

[0055] Here, radar has certain performance limitations. Taking millimeter-wave radar as an example, it has the following limitations: poor detection performance for stationary targets, inability to detect lateral movement of targets, inability to distinguish target types, and inability to detect lane lines (i.e., inability to determine whether a target is in the lane based on lane lines). Therefore, based on the target detection results of radar, unnecessary obstacle avoidance may occur in the following scenarios: ground metal plates, tunnel entrances, underground parking garage entrances, overpasses, and vehicles in adjacent lanes on curves.

[0056] Given that the probability of a radar target being a real target is relatively low, when a radar target is detected, no obstacle avoidance action is taken; that is, the radar target is ignored. Here, a radar target refers to a target detected by radar but not by a camera. By doing so, we minimize the impact on the user's driving experience due to unnecessary obstacle avoidance actions without increasing the risk of collision.

[0057] In some embodiments, when a radar target is detected, the intelligent driving method of the vehicle further includes: outputting a warning prompt.

[0058] Here, when a radar target is detected, although no obstacle avoidance is performed, a warning prompt can be issued to alert the user to the vehicle's surroundings. This allows the user to take over the vehicle when necessary, further enhancing driving safety. The content and method of the warning are not limited; the content can be something like "There is a suspected vehicle nearby, please observe carefully," and the output method can be displaying it on the vehicle's infotainment screen or via voice prompts.

[0059] In some embodiments, after the vehicle's surrounding environment is detected by its radar and camera, the intelligent driving method of the vehicle further includes: when a fused target is detected, obstacle avoidance processing is performed on the fused target; wherein, the fused target refers to a target detected by both the camera and the radar.

[0060] Here, the fused target refers to a target detected by both the camera and radar; that is, a target detected through sensor fusion of radar and camera. When a fused target is detected, because it has high accuracy and is usually a real target, obstacle avoidance is performed on the fused target to improve vehicle safety during driving.

[0061] It is worth noting that obstacle avoidance of the merging target refers to controlling the vehicle to avoid collision with the merging target; in cruise assist driving mode, obstacle avoidance of the merging target can also refer to controlling the vehicle to maintain a safe distance between the vehicle and the merging target.

[0062] In step 102, when a visual target is detected, it is determined whether the visual target meets the credibility condition; wherein, a visual target refers to a target detected by a camera but not by radar.

[0063] Here, the camera perceives the movement of the target visually, and compared to radar, the probability of false alarms is lower. Although visual targets have a higher probability (compared to radar targets) of being real targets, to avoid accidental obstacle avoidance, when a visual target is detected, it is further judged whether the visual target meets the credibility criteria. Here, a visual target refers to a target detected by the camera but not by radar.

[0064] In step 103, when the visual target meets the credibility condition, obstacle avoidance processing is performed on the visual target.

[0065] When a visual target meets the credibility condition, it is proven to be a real target. Therefore, obstacle avoidance is performed on the visual target to eliminate the risk of collision. The credibility condition can be, for example, that the duration of the visual target's existence reaches a duration threshold. The principle behind this is that if the visual target is not a real target, its duration of existence would not be too long. Alternatively, a credibility condition can be, for example, that the rate of change of the visual target's velocity (acceleration / deceleration) is less than or equal to a rate of change threshold. The principle behind this is that real targets typically do not undergo excessive velocity changes.

[0066] In some embodiments, the above-mentioned obstacle avoidance processing for visual targets can be achieved by braking the vehicle according to deceleration; wherein the deceleration is calculated based on the motion parameters of the visual target; the motion parameters of the visual target include at least one of the following: the longitudinal distance between the visual target and the vehicle, the longitudinal velocity of the visual target, the lateral distance between the visual target and the vehicle, and the lateral velocity of the visual target.

[0067] Here, while detecting the visual target, the motion parameters of the visual target can also be detected simultaneously. These motion parameters include at least one of the following: the longitudinal distance between the visual target and the vehicle, the longitudinal velocity of the visual target, the lateral distance between the visual target and the vehicle, and the lateral velocity of the visual target. During obstacle avoidance, the deceleration required to prevent a collision between the vehicle and the visual target or to maintain a safe distance is calculated based on the motion parameters of the visual target. The vehicle is then braked based on the deceleration. The decision-making strategy used to calculate the deceleration is not limited. In this method, avoiding the visual target through braking achieves effective obstacle avoidance.

[0068] It is worth noting that the methods for obstacle avoidance of visual targets can also be applied to obstacle avoidance of fused targets.

[0069] In some embodiments, after the vehicle's radar and cameras perform target detection processing on the vehicle's surrounding environment, the intelligent driving method further includes: when both a fused target and a visual target are detected simultaneously, obstacle avoidance processing is performed on the fused target. Here, when both a fused target and a visual target are detected simultaneously, since the fused target is obtained through sensor fusion and has higher accuracy, the probability that the fused target is a real target is also higher (compared to the visual target). Therefore, obstacle avoidance processing can be performed only on the fused target, i.e., the visual target can be ignored.

[0070] In step 104, if the visual target does not meet the credibility condition, no obstacle avoidance processing is performed on the visual target.

[0071] When a visual target does not meet the credibility criteria, it is proven that the visual target is not a real target. Therefore, no obstacle avoidance processing is performed on the visual target, that is, the visual target is ignored. In this way, without increasing the risk of collision, unnecessary obstacle avoidance processing can be avoided as much as possible to avoid affecting the user's riding experience.

[0072] In some embodiments, when the visual target does not meet the trust condition, the intelligent driving method of the vehicle further includes: outputting a warning prompt.

[0073] Here, when a visual target is detected, although no obstacle avoidance is performed, a warning prompt can be output to remind the user to pay attention to the surrounding environment of the vehicle, so that the user can take over the vehicle when necessary, further improving the safety of the vehicle during driving.

[0074] like Figure 3AAs shown, this embodiment of the application uses the vehicle's radar and camera to perform target detection processing on the vehicle's surrounding environment. When a visual target is detected, it is determined whether the visual target meets the credibility condition. Here, a visual target refers to a target detected by the camera but not by the radar. When the visual target meets the credibility condition, obstacle avoidance processing is performed on the visual target; when the visual target does not meet the credibility condition, obstacle avoidance processing is not performed on the visual target. This embodiment of the application, for visual targets detected only by the camera, first determines whether they are credible, and then performs obstacle avoidance processing based on their credibility, thereby reducing the missed detection caused by relying on fused targets and improving the safety of the vehicle during driving.

[0075] In some embodiments, see Figure 3B , Figure 3B This is a schematic flowchart of an intelligent driving method for a vehicle provided in an embodiment of this application. Figure 3A Step 103 shown can be implemented through steps 201 to 203, and will be explained in conjunction with each step.

[0076] In step 201, when the visual target meets the credibility condition, the visual target is determined as a credible visual target.

[0077] Here, when a visual target meets the credibility condition, the visual target is determined as a credible visual target, where a credible visual target can be understood as a real target.

[0078] In step 202, it is determined whether the credible visual target meets the risk conditions.

[0079] Here, determining whether a credible visual target meets the risk conditions essentially means determining whether there is a collision risk between the vehicle and the credible visual target. The risk conditions can be constraints imposed on the motion parameters of the credible visual target.

[0080] In some embodiments, the credibility condition is that the duration of the visual target's continued presence reaches a duration threshold; the risk condition includes at least one of the following: the longitudinal distance between the credible visual target and the vehicle is less than or equal to a distance threshold; the deceleration required to perform obstacle avoidance processing on the credible visual target is greater than or equal to a deceleration threshold. The calculation method for deceleration can be referred to above.

[0081] In some embodiments, before determining whether the visual target meets the trust condition, the intelligent driving method of the vehicle further includes: performing environmental recognition processing on the environment around the vehicle to obtain the current environment type; determining the duration threshold corresponding to the current environment type as the duration threshold in the trust condition; wherein, the current environment type is one of multiple environment types, and each environment type corresponds to a duration threshold.

[0082] Here, the duration threshold in the trusted condition can be preset or determined based on the current environment type of the vehicle's surroundings. The latter case will be explained below.

[0083] For example, when the vehicle's radar and cameras perform target detection processing on the vehicle's surrounding environment, environmental recognition processing is also performed on the vehicle's surrounding environment to obtain the current environment type. The environmental recognition processing can be achieved by at least one of the radar and cameras.

[0084] It's worth noting that the current environment type is just one of many, which can be preset, such as sunny, rainy, and foggy. Different environment types have different impacts on camera performance. For example, camera performance is worse in rainy weather than in sunny weather. Therefore, a corresponding duration threshold can be set based on the degree of interference with camera performance for each environment type. The duration threshold is positively correlated with the degree of performance interference; that is, the stronger the performance interference, the greater the probability that the visual target is not the real target. Therefore, a larger duration threshold needs to be set to enhance the constraint capability.

[0085] Since the current environment type of the vehicle's surroundings has been identified, the duration threshold corresponding to the current environment type is used as the duration threshold in the credibility condition. That is, when the duration of the visual target's continuous existence reaches the duration threshold corresponding to the current environment type, the visual target is determined as a credible visual target.

[0086] By employing the methods described above, the credibility conditions can be made more compatible with the vehicle's surrounding environment, thereby enabling a more accurate determination of whether a visual target is a real target.

[0087] In step 203, when a credible visual target meets the risk conditions, obstacle avoidance processing is performed on the credible visual target.

[0088] Here, when the credible visual target meets the risk conditions, it proves that there is a collision risk between the vehicle and the credible visual target. Therefore, obstacle avoidance processing is performed on the credible visual target to eliminate the collision risk.

[0089] exist Figure 3B middle, Figure 3A Following step 202, in step 204, if the credible visual target does not meet the risk conditions, obstacle avoidance processing is not performed on the credible visual target.

[0090] Here, when the credible visual target does not meet the risk conditions, it proves that there is no collision risk between the vehicle and the credible visual target. Therefore, no obstacle avoidance processing is performed on the credible visual target, thereby avoiding the impact on the user's driving experience due to unnecessary obstacle avoidance processing.

[0091] In some embodiments, steps 202 to 204 described above can also be applied to the fusion target.

[0092] like Figure 3B As shown, in this embodiment of the application, based on the visual target meeting the credibility condition, it further determines whether the visual target meets the risk condition, and performs obstacle avoidance processing when the risk condition is met, and does not perform obstacle avoidance processing when the risk condition is not met, thereby enhancing the necessity of obstacle avoidance processing and avoiding unnecessary obstacle avoidance processing that would affect the user's driving experience.

[0093] The following will describe an exemplary application of the embodiments of this application in a practical application scenario. Taking a vehicle equipped with a forward-facing millimeter-wave radar and a forward-facing camera (forward-facing camera), and the vehicle activating cruise control mode, as an example, the cruise control mode is implemented through a cruise control system, which includes the following modules:

[0094] 1) Cruise Assist System Control Module: Used to output the operating status of the cruise assist function and acceleration / deceleration requests. If the cruise assist function is in "active," it means the cruise assist function is running, i.e., the vehicle is currently in cruise assist mode.

[0095] 2) Cruise Assist Driving System Perception Module: This module detects vehicles ahead of the vehicle using forward-facing millimeter-wave radar and a forward-facing camera, outputting the type of the perceived target and its motion parameters. The perceived target refers to any other vehicle detected. There are three types of perceived targets: ① Fusion target (Radar+Vision); ② Radar target (Radaronly); ③ Vision target (Vision only). The motion parameters of the perceived target include: the longitudinal distance between the perceived target and the vehicle, the longitudinal velocity of the perceived target, the lateral distance between the perceived target and the vehicle, and the lateral velocity of the perceived target.

[0096] 3) Power and Braking Control Module: Used to execute acceleration / deceleration requests output by the cruise assist driving system control module.

[0097] Based on this, such as Figure 4 As shown, the embodiments of this application have formulated different braking strategies for different types of perceived targets, which will be described separately below.

[0098] 1) Target Fusion. The cruise assist driving system control module calculates the deceleration based on the motion parameters of the fused target and outputs a deceleration request. The power and braking control module then applies the deceleration request to the vehicle for braking (deceleration).

[0099] 2) Radar targets. The cruise assist driving system control module does not output a deceleration request, that is, it ignores radar targets, thereby preventing accidental braking.

[0100] 3) Visual Targets. The braking strategy for visual targets includes strategy a and strategy b. In strategy a, it is determined whether the duration of the visual target's presence reaches 100ms (corresponding to the duration threshold mentioned above). If the duration reaches 100ms, the visual target is identified as a credible visual target, and strategy b is executed. In strategy b, it is determined whether the credible visual target simultaneously satisfies conditions ① and ②. If both conditions are met, the cruise assist driving system control module does not output a deceleration request; if either condition is not met, the cruise assist driving system control module outputs a deceleration request, and the power and braking control module performs braking on the vehicle according to the deceleration request.

[0101] Among them, condition ①: The longitudinal distance between the credible visual target output by the cruise assist driving system perception module and the vehicle is greater than 80m (corresponding to the distance threshold mentioned above).

[0102] Condition ②: The deceleration calculated by the cruise assist system control module is less than 1 m / s². 2 (Corresponding to the deceleration threshold mentioned above).

[0103] The embodiments of this application can achieve at least the following technical effects:

[0104] 1) It can reduce the missed detections caused by relying solely on the fusion target, and brake the vehicle in time when there is a collision risk, thereby improving vehicle safety.

[0105] 2) It can reduce the possibility of mis-braking on targets ahead without increasing the risk of collision.

[0106] The following continues to describe the exemplary structure of the intelligent driving device 155 for a vehicle provided in the embodiments of this application as a software module. In some embodiments, such as Figure 2 As shown, the software modules stored in the vehicle's intelligent driving device 155 in the memory 150 may include: a target detection module 1551, used to perform target detection processing on the vehicle's surrounding environment using the vehicle's radar and camera; a judgment module 1552, used to determine whether a visual target meets the credibility condition when a visual target is detected; wherein, a visual target refers to a target detected by the camera but not by the radar; a visual obstacle avoidance module 1553, used to perform obstacle avoidance processing on the visual target when the visual target meets the credibility condition; and a visual obstacle avoidance module 1554, also used to not perform obstacle avoidance processing on the visual target when the visual target does not meet the credibility condition.

[0107] In some embodiments, the visual obstacle avoidance module 1553 is further configured to: determine the visual target as a credible visual target when the visual target meets the credibility condition; determine whether the credible visual target meets the risk condition; perform obstacle avoidance processing on the credible visual target when the credible visual target meets the risk condition; and not perform obstacle avoidance processing on the credible visual target when the credible visual target does not meet the risk condition.

[0108] In some embodiments, the credible condition is that the duration of the visual target's continued presence reaches a duration threshold; the risk condition includes at least one of the following: the longitudinal distance between the credible visual target and the vehicle is less than or equal to a distance threshold; the deceleration required to perform obstacle avoidance processing on the credible visual target is greater than or equal to a deceleration threshold.

[0109] In some embodiments, the visual obstacle avoidance module 1553 is further configured to: perform environmental recognition processing on the environment surrounding the vehicle to obtain the current environment type; determine the duration threshold corresponding to the current environment type as the duration threshold in the trust condition; wherein the current environment type is one of multiple environment types, and each environment type corresponds to a duration threshold.

[0110] In some embodiments, the vehicle's intelligent driving device 155 further includes a radar obstacle avoidance module, which is used to: when a radar target is detected, not to perform obstacle avoidance processing on the radar target; wherein, a radar target refers to a target detected by radar but not by a camera.

[0111] In some embodiments, the vehicle's intelligent driving device 155 further includes a warning module for outputting a warning prompt when a visual target does not meet the credibility condition or when a radar target is detected.

[0112] In some embodiments, the vehicle's intelligent driving device 155 further includes a fusion obstacle avoidance module, used to: perform obstacle avoidance processing on the fusion target when a fusion target is detected; wherein, the fusion target refers to a target detected by a camera and also by radar.

[0113] In some embodiments, the visual obstacle avoidance module 1553 is further configured to: brake the vehicle according to the deceleration; wherein the deceleration is calculated based on the motion parameters of the visual target; the motion parameters of the visual target include at least one of the following: the longitudinal distance between the visual target and the vehicle, the longitudinal velocity of the visual target, the lateral distance between the visual target and the vehicle, and the lateral velocity of the visual target.

[0114] This application provides a computer program product or computer program, which includes executable instructions stored in a computer-readable storage medium. The vehicle's processor reads the executable instructions from the computer-readable storage medium and executes the executable instructions, causing the vehicle to implement the intelligent driving method described in this application embodiment.

[0115] This application provides a computer-readable storage medium storing executable instructions, wherein the executable instructions are stored and, when executed by a processor, will cause the processor to implement the intelligent driving method for a vehicle provided in this application.

[0116] In some embodiments, the computer-readable storage medium may be a memory such as FRAM, ROM, PROM, EPROM, EEPROM, flash memory, magnetic surface memory, optical disk, or CD-ROM; or it may be a variety of devices including one or any combination of the above-mentioned memories.

[0117] In some embodiments, executable instructions may take the form of a program, software, software module, script, or code, written in any form of programming language (including compiled or interpreted languages, or declarative or procedural languages), and may be deployed in any form, including as a standalone program or as a module, component, subroutine, or other unit suitable for use in a computing environment.

[0118] As an example, executable instructions may, but do not necessarily, correspond to files in a file system. They may be stored as part of a file that holds other programs or data, for example, in one or more scripts in a Hyper Text Markup Language (HTML) document, in a single file dedicated to the program in question, or in multiple collaborating files (e.g., a file that stores one or more modules, subroutines, or code sections).

[0119] The above are merely embodiments of this application and are not intended to limit the scope of protection of this application. Any modifications, equivalent substitutions, and improvements made within the spirit and scope of this application are included within the scope of protection of this application.

Claims

1. A method for intelligent driving of a vehicle, characterized in that, include: The vehicle's radar and cameras are used to perform target detection processing on the environment surrounding the vehicle. When a visual target is detected, it is determined whether the visual target meets the credibility condition; wherein, the visual target refers to a target detected by the camera but not by the radar, and the credibility condition is that the duration of the visual target's continuous existence reaches a duration threshold. Before determining whether the visual target meets the credibility condition, the method further includes: The environment around the vehicle is subjected to environmental recognition processing to obtain the current environment type; The duration threshold corresponding to the current environment type is determined as the duration threshold in the trusted condition; The current environment type is one of several environment types, and each environment type corresponds to a duration threshold. When the visual target meets the credibility condition, obstacle avoidance processing is performed on the visual target; When the visual target does not meet the credibility condition, no obstacle avoidance processing is performed on the visual target.

2. The method according to claim 1, characterized in that, When the visual target meets the credibility condition, obstacle avoidance processing is performed on the visual target, including: When the visual target meets the credibility condition, the visual target is determined as a credible visual target; Determine whether the credible visual target meets the risk conditions; When the trusted visual target meets the risk conditions, obstacle avoidance processing is performed on the trusted visual target; The method further includes: When the trusted visual target does not meet the risk conditions, no obstacle avoidance processing is performed on the trusted visual target.

3. The method according to claim 2, characterized in that, The risk conditions include at least one of the following: the longitudinal distance between the trusted visual target and the vehicle is less than or equal to a distance threshold; the deceleration required to perform obstacle avoidance processing on the trusted visual target is greater than or equal to a deceleration threshold.

4. The method according to claim 1, characterized in that, After performing target detection processing on the vehicle's surrounding environment using the vehicle's radar and cameras, the method further includes: When a radar target is detected, no obstacle avoidance action is taken for the radar target; The radar target refers to a target that is detected by the radar but not by the camera.

5. The method according to claim 4, characterized in that, The method further includes: When the visual target does not meet the credibility condition, or when the radar target is detected, an early warning prompt is output.

6. The method according to claim 1, characterized in that, After performing target detection processing on the vehicle's surrounding environment using the vehicle's radar and cameras, the method further includes: When a fusion target is detected, obstacle avoidance processing is performed on the fusion target; The fused target refers to a target detected by both the camera and the radar.

7. The method according to claim 1, characterized in that, The obstacle avoidance process for the visual target includes: The vehicle is braked based on its deceleration. The deceleration is calculated based on the motion parameters of the visual target; the motion parameters of the visual target include at least one of the following: the longitudinal distance between the visual target and the vehicle, the longitudinal velocity of the visual target, the lateral distance between the visual target and the vehicle, and the lateral velocity of the visual target.

8. An intelligent driving device for a vehicle, characterized in that, include: The target detection module is used to perform target detection processing on the environment surrounding the vehicle using the vehicle's radar and camera; The judgment module is used to determine whether the visual target meets the credibility condition when a visual target is detected; wherein, the visual target refers to a target detected by the camera but not by the radar, and the credibility condition is that the duration of the visual target's continuous existence reaches a duration threshold. The visual obstacle avoidance module is used to perform environmental recognition processing on the environment around the vehicle to obtain the current environment type; determine the duration threshold corresponding to the current environment type as the duration threshold in the credibility condition; wherein, the current environment type is one of multiple environment types, and each environment type corresponds to a duration threshold; when the visual target meets the credibility condition, obstacle avoidance processing is performed on the visual target; The visual obstacle avoidance module is also used to not perform obstacle avoidance processing on the visual target when the visual target does not meet the credibility condition.

9. A vehicle, characterized in that, include: Memory, used to store executable instructions; A processor, when executing executable instructions stored in the memory, implements the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, It stores executable instructions for implementing the method according to any one of claims 1 to 7 when executed by a processor.

Images