Decision method and device of autonomous vehicle, vehicle and storage medium

Abstract

This application relates to a decision-making method, device, vehicle, and storage medium for autonomous vehicles. The method includes: determining whether the autonomous vehicle has traveled to a path that meets preset corner narrowing conditions; if it has traveled to a path that meets preset corner narrowing conditions, detecting whether an obstacle ahead is within a current obstacle dynamic window, and acquiring obstacle information of the obstacle ahead and vehicle information of the autonomous vehicle; generating a decision result based on the obstacle information and vehicle information, thereby stopping the vehicle's current travel, waiting for the obstacle ahead to leave the current obstacle dynamic window, restarting the autonomous vehicle, or continuing the current travel of the autonomous vehicle. This application can detect relevant obstacles in narrow scenarios through a dynamic window, acquire relevant information about the obstacle ahead and the vehicle, generate a decision result, and control the vehicle to perform corresponding actions, thereby improving the safety and efficiency of the vehicle passing through narrow intersections and improving the user's driving experience.

Description

Technical Field

[0001] This application relates to the field of autonomous driving technology, and in particular to a decision-making method, device, vehicle, and storage medium for autonomous vehicles. Background Technology

[0002] With the rapid iteration and development of autonomous driving technology, its application in real-life scenarios is becoming increasingly widespread. However, autonomous vehicles often experience sudden stops, jams, or stalls when driving on narrow roads, making it inconvenient for them.

[0003] Currently, the relevant technology can detect narrow road sections and oncoming vehicles within a narrow road section area, determine the speed of oncoming vehicles, and control the vehicle to travel in narrow road sections according to the prior rules stored in the database. In addition, the relevant technology can also plan local paths within the dynamic window by using the time length as the period length of the dynamic window to detect and avoid unknown obstacles.

[0004] However, the relevant technologies can only detect and avoid obstacles, or drive according to stored prior rules, which is difficult to effectively improve the safety and efficiency of autonomous vehicles driving on narrow roads, and greatly affects the user's driving experience. Summary of the Invention

[0005] This application provides a decision-making method, device, vehicle, and storage medium for autonomous vehicles to address the problem that related technologies struggle to improve the safety and efficiency of autonomous vehicles driving on narrow roads.

[0006] The first aspect of this application provides a decision-making method for an autonomous vehicle, comprising the following steps: determining whether the autonomous vehicle has traveled to a path that meets a preset corner narrowing condition; if it has traveled to a path that meets the preset corner narrowing condition, detecting whether an obstacle ahead is within a current obstacle dynamic window, and when it is detected that the obstacle is within the current obstacle dynamic window, acquiring obstacle information of the obstacle ahead and vehicle information of the autonomous vehicle; and generating a decision result based on the obstacle information and the vehicle information, to stop the current driving of the autonomous vehicle, wait for the obstacle ahead to leave the current obstacle dynamic window, restart the autonomous vehicle, or continue the current driving of the autonomous vehicle.

[0007] Based on the above technical means, the embodiments of this application can detect relevant obstacles in narrow scenarios through dynamic windows, obtain relevant information about obstacles and vehicles ahead, generate decision results, and control the vehicle to perform corresponding actions, thereby improving the safety and efficiency of vehicles passing through narrow intersections and improving the user's driving experience.

[0008] Optionally, in one embodiment of this application, before restarting the autonomous vehicle, the method further includes: identifying the actual type of the obstacle in front; if the actual type is a dynamic obstacle, waiting for the obstacle to leave the current obstacle dynamic window; if the actual type is a static obstacle, providing a manual takeover prompt.

[0009] Based on the above-mentioned technical means, the embodiments of this application identify the actual type of obstacles in front of the vehicle to control the vehicle to perform corresponding operations, thereby effectively improving the safety and reliability of the vehicle and making the vehicle more technologically advanced and user-friendly.

[0010] Optionally, in one embodiment of this application, generating a decision result based on the obstacle information and the vehicle information includes: detecting that the obstacle ahead is in the actual area of ​​the autonomous vehicle; and matching the corresponding action of the autonomous vehicle according to the actual area and the actual type.

[0011] Based on the above technical means, this application embodiment detects the actual area where the obstacle is located in front to match the corresponding action of the autonomous vehicle. By using the dynamic obstacle detection window and the motion control model of the currently controlling vehicle, combined with the fusion information of obstacle detection, the efficiency of autonomous driving is effectively improved and the user's driving experience is enhanced while ensuring driving safety.

[0012] Optionally, in one embodiment of this application, the actual area is a deceleration area, an emergency stop area, or a warning area.

[0013] Based on the above technical means, the embodiments of this application provide a basis for matching the obstacle detection results with the corresponding vehicle control actions by appropriately dividing the actual area.

[0014] Optionally, in one embodiment of this application, the vehicle information includes one or more of the following: speed, acceleration, left wheel steering angle, right wheel steering angle, and vehicle posture of the autonomous vehicle.

[0015] Based on the above technical means, this application embodiment obtains relevant vehicle information, providing a reliable basis for generating vehicle decision-making results, and effectively ensuring the efficiency of vehicles passing through narrow corner sections.

[0016] A second aspect of this application provides a decision-making device for an autonomous vehicle, comprising: a judgment module for judging whether the autonomous vehicle has traveled to a path that meets a preset corner narrowing condition; an acquisition module for detecting whether an obstacle ahead is within a current obstacle dynamic window if the vehicle has traveled to a path that meets the preset corner narrowing condition, and acquiring obstacle information of the obstacle ahead and vehicle information of the autonomous vehicle when the obstacle is detected to be within the current obstacle dynamic window; and a control module for generating a decision result based on the obstacle information and the vehicle information, to stop the current driving of the autonomous vehicle, wait for the obstacle ahead to leave the current obstacle dynamic window, restart the autonomous vehicle, or continue the current driving of the autonomous vehicle.

[0017] Optionally, in one embodiment of this application, it further includes: an identification module, configured to identify the actual type of the obstacle in front before restarting the autonomous vehicle; a waiting module, configured to wait for the obstacle in front to leave if the actual type is a dynamic obstacle; and a prompting module, configured to provide a manual takeover prompt if the actual type is a static obstacle.

[0018] Optionally, in one embodiment of this application, the control module includes: a detection unit for detecting that the obstacle in front is in the actual area of ​​the autonomous vehicle; and a matching unit for matching the corresponding action of the autonomous vehicle according to the actual area and the actual type.

[0019] Optionally, in one embodiment of this application, the actual area is a deceleration area, an emergency stop area, or a warning area.

[0020] Optionally, in one embodiment of this application, the vehicle information includes one or more of the following: speed, acceleration, left wheel steering angle, right wheel steering angle, and vehicle posture of the autonomous vehicle.

[0021] A third aspect of this application provides a vehicle, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the decision-making method for an autonomous vehicle as described in the above embodiments.

[0022] A fourth aspect of this application provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the decision-making method for an autonomous vehicle as described above.

[0023] Therefore, the embodiments of this application have the following beneficial effects:

[0024] (1) In the embodiments of this application, in narrow scenarios, relevant obstacles can be detected through dynamic windows, relevant information about obstacles and vehicles ahead can be obtained, decision results can be generated, and the vehicle can be controlled to perform corresponding actions, thereby improving the safety and efficiency of vehicles passing through narrow intersections and improving the user's driving experience.

[0025] (2) The embodiments of this application identify the actual type of obstacles in front of the vehicle to control the vehicle to perform corresponding operations, thereby effectively improving the safety and reliability of the vehicle and making the vehicle more technological and humanized.

[0026] (3) In this embodiment of the application, the actual area where the obstacle is located is detected to match the corresponding action of the autonomous vehicle. Thus, through the dynamic obstacle detection window, with the help of the motion control model of the currently controlled vehicle and the fusion information of obstacle detection, the driving efficiency of autonomous driving is effectively improved and the user's driving experience is improved while ensuring driving safety.

[0027] (4) The embodiments of this application provide a basis for matching the obstacle detection results with the corresponding vehicle control actions by appropriately dividing the actual area.

[0028] (5) The embodiments of this application obtain relevant vehicle information, providing a reliable basis for the generation of vehicle decision results, and effectively ensuring the efficiency of vehicles passing through narrow corner sections.

[0029] Additional aspects and advantages of this application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of this application. Attached Figure Description

[0030] The above and / or additional aspects and advantages of this application will become apparent and readily understood from the following description of the embodiments taken in conjunction with the accompanying drawings, wherein:

[0031] Figure 1 This is a flowchart illustrating a decision-making method for an autonomous vehicle according to an embodiment of this application;

[0032] Figure 2 This is a schematic diagram of a vehicle motion model according to an embodiment of this application;

[0033] Figure 3 This is a schematic diagram illustrating the analytical posture of a vehicle according to an embodiment of this application;

[0034] Figure 4 This is a schematic diagram of a dynamic window scene and region division according to an embodiment of this application;

[0035] Figure 5This is a schematic diagram of a fixed window scene and region division according to an embodiment of this application;

[0036] Figure 6 This is an example diagram of a decision-making device for an autonomous vehicle according to an embodiment of this application;

[0037] Figure 7 This is a schematic diagram of the vehicle structure provided in an embodiment of this application.

[0038] Among them, 10-decision-making device for autonomous vehicles, 100-judgment module, 200-acquisition module, 300-control module, 701-memory, 702-processor, and 703-communication interface. Detailed Implementation

[0039] The embodiments of this application are described in detail below. Examples of these embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain this application, and should not be construed as limiting this application.

[0040] The following description, with reference to the accompanying drawings, illustrates a decision-making method, apparatus, vehicle, and storage medium for an autonomous vehicle according to embodiments of this application. Addressing the problems mentioned in the background section, this application provides a decision-making method for an autonomous vehicle. In this method, it is determined whether the autonomous vehicle has traveled to a path that meets preset corner narrowing conditions. If it has, it detects whether an obstacle ahead is within the current obstacle dynamic window and acquires obstacle information and vehicle information. Based on the obstacle and vehicle information, a decision result is generated to either stop the vehicle's current movement, wait for the obstacle ahead to leave the current obstacle dynamic window, restart the autonomous vehicle, or continue its current movement. This application can detect relevant obstacles in narrow scenarios through a dynamic window, acquire relevant information about the obstacle ahead and the vehicle, generate a decision result, and control the vehicle to perform corresponding actions, thereby improving the safety and efficiency of the vehicle passing through narrow intersections and enhancing the user's driving experience. This solves the problem that related technologies struggle to improve the safety and efficiency of autonomous vehicles traveling on narrow roads.

[0041] To facilitate the introduction of the decision-making method for autonomous vehicles according to the embodiments of this application, the derivation symbols, parameters, and their interpretations involved are explained below:

[0042] The coordinates of the center of the vehicle's front axle;

[0043] The coordinates of the center of the vehicle's rear axle;

[0044] l Vehicle heading angle;

[0045] v f Vehicle rear axle center speed;

[0046] v r The speed at the center of the vehicle's rear axle;

[0047] l f Front wheel deflection angle;

[0048] wheelbase;

[0049] M rear axle center;

[0050] N front axle center;

[0051] R is the rear wheel steering radius;

[0052] P steering center;

[0053] w is the yaw rate.

[0054] Specifically, Figure 1 This is a flowchart illustrating a decision-making method for an autonomous vehicle provided in an embodiment of this application.

[0055] like Figure 1 As shown, the decision-making method of this autonomous vehicle includes the following steps:

[0056] In step S101, it is determined whether the autonomous vehicle has traveled to a path that meets the preset narrow turning conditions.

[0057] It should be noted that the embodiments of this application can obtain information such as lane curvature and distance of the road segment where the vehicle is currently located through functions such as lane detection in autonomous vehicles. When the curvature of the lane is in its narrow curvature range or the distance between lanes is in the narrow distance range, it can be determined that the current road segment is a narrow corner road segment. At this time, the vehicle can remind the user through voice or other means, such as "The road ahead is narrow, please pay attention to traffic safety!"

[0058] In addition, those skilled in the art can determine narrow corner sections in other ways, such as using vehicle-mounted radar or cameras to obtain real-time information about the current road section and determine the narrow corner section based on information such as the distance of the current road section and the width of the vehicle body, without making specific limitations.

[0059] Therefore, embodiments of this application can provide a reliable basis for subsequent vehicle-related operations by determining whether an autonomous vehicle has traveled to a path that meets the conditions for a narrow turning corner.

[0060] In step S102, if the vehicle travels to a path that meets the preset turning narrow conditions, it detects whether the obstacle ahead is within the current obstacle dynamic window. If the obstacle is detected to be within the current obstacle dynamic window, it acquires the obstacle information of the obstacle ahead and the vehicle information of the autonomous vehicle.

[0061] After determining that the vehicle has entered a narrow corner, the embodiments of this application can further perform dynamic obstacle window detection on the road environment ahead of the vehicle to detect whether the obstacle ahead is within the current obstacle dynamic window. When the obstacle ahead is within the obstacle dynamic window, obstacle information of the obstacle ahead and vehicle information of the autonomous vehicle are obtained, thereby providing data support for the vehicle to safely and efficiently pass through the narrow road section.

[0062] Specifically, the derivation process for obstacle dynamic window prediction in the embodiments of this application is as follows:

[0063] In the embodiments of this application, the kinematic model diagram of the vehicle is as follows: Figure 2 As shown, its corresponding mathematical expression is as follows:

[0064]

[0065] in, 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. The change in the vehicle's yaw angle is represented by l, where l represents the vehicle's yaw angle, and v represents the change in the vehicle's yaw angle. r ω represents the speed of the rear axle of the vehicle, and ω represents the speed of the vehicle's yaw angle.

[0066] The embodiments of this application assume that during the turning process of the autonomous vehicle, the vehicle's axle slip angle remains constant, that is, the instantaneous turning radius of the vehicle is the same as the radius of curvature of the road. Therefore, at the rear wheel travel axis (X... r ,Y r The velocity at point () is:

[0067]

[0068] The kinematic constraints of the front and rear axles are:

[0069]

[0070] Changes perpendicular to the direction of motion cancel each other out, as shown in the following equation:

[0071]

[0072] Based on the relationship between the angular velocities of the front and rear wheels, we can conclude that:

[0073]

[0074] The yaw rate that can be solved by substituting the above formulas into the kinematic constraint equations is:

[0075]

[0076] Next, the derivative of the relationship between the front and rear wheel angular velocities is obtained, as shown in the following equation:

[0077]

[0078] Substituting the equation for the vertical direction of motion, we get:

[0079]

[0080] Substituting the curvature motion control equations, we obtain the following formula:

[0081]

[0082] The above equation expands to the following equation:

[0083]

[0084]

[0085]

[0086]

[0087] The turning radius and front wheel deflection angle can be obtained from the yaw angle and vehicle speed, such as... Figure 3 As shown, its mathematical expression is as follows:

[0088]

[0089] From the derivation of the derivative and the above model, the vehicle kinematic model can be obtained as follows:

[0090]

[0091] This model can be further represented in a general form:

[0092]

[0093] State variable ε=[X r ,Y r [l] represents the position and yaw angle, and the control quantity v = [v] r ,δ f Given the velocity and front wheel deflection angle, substituting the state and control variables into the kinematic model transformation equations, the following derivation results can be obtained:

[0094]

[0095] Furthermore, embodiments of this application may incorporate a preceding matching dynamic window increment k = [X k ,Y k ,l k ], which represents the forward prediction dynamic window based on the current position in [X]. r ,Y r The prediction of the three variables, l], and the final dynamic window are shown in the following formula:

[0096]

[0097] Thus, the embodiments of this application complete the derivation of obstacle dynamic window prediction, providing theoretical support for the detection of related obstacle dynamic windows.

[0098] Optionally, in one embodiment of this application, the vehicle information includes one or more of the following: speed, acceleration, left wheel steering angle, right wheel steering angle, and vehicle posture of the autonomous vehicle.

[0099] It should be noted that when the obstacle in front is within the obstacle dynamic window, the embodiments of this application collect relevant data information of the current vehicle through devices such as vehicle speed sensors. The aforementioned vehicle information mainly includes vehicle speed, acceleration, left and right wheel turning angles, and vehicle body posture.

[0100] Therefore, the embodiments of this application provide a reliable basis for generating vehicle decision-making results by acquiring the corresponding vehicle information, which effectively ensures the efficiency of vehicles passing through narrow corner sections.

[0101] In step S103, a decision result is generated based on obstacle information and vehicle information, which is to either stop the current driving of the autonomous vehicle, wait for the obstacle in front to leave the current obstacle dynamic window, restart the autonomous vehicle, or continue the current driving of the autonomous vehicle.

[0102] After acquiring obstacle information of the obstacle ahead and vehicle information of the autonomous vehicle, the embodiments of this application can then generate a decision result based on the obstacle information and vehicle information, and control the vehicle to stop based on the decision result. After waiting for the obstacle ahead to leave the dynamic window prediction range, the autonomous vehicle is restarted; otherwise, the vehicle continues to drive. Thus, based on vehicle and obstacle information, while ensuring vehicle driving safety, the phenomenon of accidental braking is effectively reduced, and the driving efficiency of autonomous driving is greatly improved.

[0103] Optionally, in one embodiment of this application, generating a decision result based on obstacle information and vehicle information includes: detecting that the obstacle ahead is in the actual area of ​​the autonomous vehicle; and matching the corresponding action of the autonomous vehicle according to the actual area and actual type.

[0104] It should be noted that the embodiments of this application utilize a vehicle kinematic model to study the vehicle's motion from a geometric perspective, including the changes in the vehicle's spatial pose and speed over time. When the vehicle is traveling at low speed on a good road surface, dynamic issues such as vehicle handling stability generally do not need to be considered. In this case, the path tracking controller designed based on the kinematic model has reliable control performance, and after multi-sensor fusion, it can perceive the accurate pose information of obstacles in the vehicle coordinate system in narrow paths.

[0105] Therefore, in the embodiments of this application, when an obstacle is detected in the forward dynamic window area of ​​the vehicle, that is, the actual area, there is no need to consider the drivable area on the left and right. The current vehicle speed, acceleration, left and right wheel angles and vehicle body posture information can be obtained immediately and matched with the corresponding actions of the autonomous vehicle to drive. At the same time, a new predicted vehicle body in the forward dynamic window and the probability of the obstacle appearing in the new window are regenerated.

[0106] Therefore, the embodiments of this application detect the actual area where the obstacle is located in front to match the corresponding actions of the autonomous vehicle. By using the dynamic obstacle detection window and the motion control model of the currently controlling vehicle, combined with the fusion information of obstacle detection, the efficiency of autonomous driving is effectively improved and the user's driving experience is enhanced while ensuring driving safety.

[0107] Optionally, in one embodiment of this application, the actual area is a deceleration area, an emergency stop area, or a warning area.

[0108] It should be noted that in the dynamic window determination of this application embodiment, the forward-looking dynamic window area, i.e., the actual area, is mainly divided into three parts: the emergency stop area S1, the deceleration area S2, and the warning area S3, as follows: Figure 4 As shown, the dynamic window created by the above vehicle kinematics model is subjected to forward prediction dynamic detection for a duration of K, and is updated in real time with a detection period of K.

[0109] Therefore, the embodiments of this application provide a basis for matching obstacle detection results with corresponding vehicle control actions by appropriately dividing the actual area.

[0110] Optionally, in one embodiment of this application, before restarting the autonomous vehicle, the method further includes: identifying the actual type of the obstacle in front; if the actual type is a dynamic obstacle, waiting for the obstacle to leave the current obstacle dynamic window; if the actual type is a static obstacle, providing a manual takeover prompt.

[0111] It should be noted that, in the embodiments of this application, the actual type of obstacle can be divided into: dynamic obstacle and static obstacle. When the actual type is a dynamic obstacle, the current obstacle dynamic window will wait for the obstacle in front to leave; when the actual type is a static obstacle, a manual takeover prompt will be given.

[0112] Specifically, the embodiments of this application, based on the actual region and actual type, describe the specific process of matching vehicle-related operations as follows:

[0113] 1. When an obstacle is in the emergency stop zone S1, the vehicle will be brought to a direct stop. If the probability of a collision is predicted to be high based on the real-time dynamic window model, the vehicle's movement will be judged according to the following two scenarios:

[0114] 1) If the detection result is a dynamic obstacle (such as a person, animal, etc.), wait for the obstacle to be removed from the S1 area before restarting the vehicle driving function.

[0115] 2) If the detection result is a static obstacle, the vehicle will stop immediately and the driver will be notified directly during this period to end the dynamic window detection and hand over the vehicle to manual control.

[0116] 2. When the obstacle is in deceleration zone S2, determine the current vehicle speed:

[0117] 1) If the driving speed is less than the set minimum speed V2, the current speed will be maintained and the judgment will continue until the obstacle triggers the S1 emergency stop zone to brake directly or triggers the S3 zone to restore the original control speed.

[0118] 2) If the vehicle speed is greater than the currently set minimum speed V2, the current speed V1 will be reduced to the minimum speed V2. The automatic driving task will continue as long as the obstacle is not in the emergency stop zone S1, and the controlled speed will be restored within the warning zone S3.

[0119] 2-1) If the detection result is a dynamic obstacle (such as a person, animal, etc.), reduce the vehicle speed to V2 according to the preset minimum speed, and slowly bypass the uncertain dynamic obstacle until the dynamic obstacle no longer appears in the dynamic window.

[0120] 2-2) If the detection result is a static obstacle, there is no need to reduce the speed to execute automatic driving. Based on the relevant predictions in the local path planning based on the vehicle decision results, the vehicle driving is controlled to improve the overall driving smoothness.

[0121] 3. When the obstacle is in the detectable warning area S3, the probability of the obstacle appearing in the driving hazard area is extremely small. Therefore, deceleration is not considered to continue autonomous driving. However, the following two scenarios may still exist:

[0122] 1) Once you enter the deceleration zone S2, you can directly follow the corresponding steps described above to proceed.

[0123] 2) If the obstacle is not within the dynamic window, the detection results of the obstacle are not considered.

[0124] At this point, the decision-making module has set a relatively high safety threshold, so regardless of whether the detected obstacle is dynamic or static, there is no need to reduce the speed to perform automatic driving operation.

[0125] Therefore, the embodiments of this application identify the actual type of obstacle in front of the vehicle to control the vehicle to perform corresponding operations, thereby effectively improving the safety and reliability of the vehicle and making the vehicle more technologically advanced and user-friendly.

[0126] Furthermore, in the embodiments of this application, if the obstacle is not within the newly generated dynamic window, it means that the subsequent driving is no longer affected by the obstacle, there is no need to consider collision factors, there is no need to stop to avoid the obstacle, and the driving continues to prevent meaningless braking and avoidance; if the obstacle is still within the newly generated dynamic window, it means that the obstacle still appears, and the vehicle immediately stops, thereby effectively detecting obstacles within the dynamic window to control the safe and stable driving of the vehicle until the state machine reports that the vehicle has a large driving space.

[0127] Understandably, by using a dynamic obstacle detection window method and acquiring core vehicle data such as vehicle speed, acceleration, angular velocity, vehicle pose information, and obstacle pose information, compared to a fixed window method that only considers detecting forward obstacles, [the method offers advantages such as...]. Figure 5 As shown, the embodiments of this application can make more reasonable decisions on driving tasks and effectively improve vehicle driving efficiency.

[0128] According to the decision-making method for autonomous vehicles proposed in this application, the autonomous vehicle determines whether it has traveled to a path that meets preset corner narrowing conditions. If it has, it detects whether an obstacle ahead is within the current obstacle dynamic window and obtains obstacle information and vehicle information. Based on the obstacle information and vehicle information, a decision is generated to either stop the vehicle's current movement, wait for the obstacle ahead to leave the current obstacle dynamic window, restart the autonomous vehicle, or continue the current movement of the autonomous vehicle. This application can detect relevant obstacles in narrow scenarios through a dynamic window, obtain relevant information about the obstacle ahead and the vehicle, generate a decision, and control the vehicle to perform corresponding actions, thereby improving the safety and efficiency of the vehicle passing through narrow intersections and enhancing the user's driving experience.

[0129] Next, with reference to the accompanying drawings, a decision-making device for an autonomous vehicle according to an embodiment of this application is described.

[0130] Figure 6 This is a block diagram of the decision-making device for an autonomous vehicle according to an embodiment of this application.

[0131] like Figure 6 As shown, the decision-making device 10 of the autonomous vehicle includes: a judgment module 100, an acquisition module 200, and a control module 300.

[0132] The judgment module 100 is used to determine whether the autonomous vehicle has driven to a path that meets the preset narrow turning conditions.

[0133] The acquisition module 200 is used to detect whether the obstacle ahead is within the current obstacle dynamic window if the vehicle travels to a path that meets the preset turning narrow conditions, and to acquire the obstacle information of the obstacle ahead and the vehicle information of the autonomous vehicle when it is detected that the obstacle is within the current obstacle dynamic window.

[0134] The control module 300 is used to generate decision results based on obstacle information and vehicle information, to stop the current driving of the autonomous vehicle, wait for the obstacle in front to leave the current obstacle dynamic window, restart the autonomous vehicle, or continue the current driving of the autonomous vehicle.

[0135] Optionally, in one embodiment of this application, the decision-making device 10 of the autonomous vehicle of this application embodiment further includes: an identification module, a waiting module, and a prompting module.

[0136] The identification module is used to identify the actual type of obstacle ahead before restarting the autonomous vehicle.

[0137] The waiting module is used to wait for the obstacle in front to leave the current obstacle's dynamic window if the actual type is a dynamic obstacle.

[0138] The prompt module is used to provide a manual takeover prompt if the actual obstacle type is static.

[0139] Optionally, in one embodiment of this application, the control module 300 includes a detection unit and a matching unit.

[0140] The detection unit is used to detect obstacles ahead that are actually within the area of ​​the autonomous vehicle.

[0141] The matching unit is used to match the corresponding actions of the autonomous vehicle based on the actual area and type.

[0142] Optionally, in one embodiment of this application, the actual area is a deceleration area, an emergency stop area, or a warning area.

[0143] Optionally, in one embodiment of this application, the vehicle information includes one or more of the following: speed, acceleration, left wheel steering angle, right wheel steering angle, and vehicle posture of the autonomous vehicle.

[0144] It should be noted that the foregoing explanation of the decision-making method embodiment for autonomous vehicles also applies to the decision-making device of the autonomous vehicle in this embodiment, and will not be repeated here.

[0145] According to the decision-making device for autonomous vehicles proposed in this application, the device determines whether the autonomous vehicle has traveled to a path that meets preset corner narrowing conditions. If it has, it detects whether an obstacle ahead is within the current obstacle dynamic window and acquires obstacle information and vehicle information. Based on the obstacle and vehicle information, it generates a decision result to either stop the vehicle's current movement, wait for the obstacle ahead to leave the current obstacle dynamic window, restart the autonomous vehicle, or continue the current movement of the autonomous vehicle. This application can detect relevant obstacles in narrow scenarios through a dynamic window, acquire relevant information about the obstacle ahead and the vehicle, generate a decision result, and control the vehicle to perform corresponding actions, thereby improving the safety and efficiency of the vehicle passing through narrow intersections and enhancing the user's driving experience.

[0146] Figure 7 A schematic diagram of the structure of a vehicle provided in an embodiment of this application. The vehicle may include:

[0147] The memory 701, the processor 702, and the computer program stored on the memory 701 and executable on the processor 702.

[0148] When the processor 702 executes the program, it implements the decision-making method for autonomous vehicles provided in the above embodiments.

[0149] Furthermore, the vehicle also includes:

[0150] Communication interface 703 is used for communication between memory 701 and processor 702.

[0151] The memory 701 is used to store computer programs that can run on the processor 702.

[0152] The memory 701 may include high-speed RAM memory, and may also include non-volatile memory, such as at least one disk storage device.

[0153] If the memory 701, processor 702, and communication interface 703 are implemented independently, then the communication interface 703, memory 701, and processor 702 can be interconnected via a bus to complete communication between them. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of representation, Figure 7 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0154] Optionally, in a specific implementation, if the memory 701, processor 702, and communication interface 703 are integrated on a single chip, then the memory 701, processor 702, and communication interface 703 can communicate with each other through an internal interface.

[0155] The processor 702 may be a central processing unit (CPU), an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of this application.

[0156] This embodiment also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the decision-making method for the autonomous vehicle described above.

[0157] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0158] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this application, "N" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0159] Any process or method described in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or N executable instructions for implementing custom logic functions or processes, and the scope of the preferred embodiments of this application includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as should be understood by those skilled in the art to which embodiments of this application pertain.

[0160] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include: an electrical connection having one or more wires (electronic device), a portable computer disk drive (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Alternatively, the computer-readable medium may be paper or other suitable media on which the program can be printed, since the program can be obtained electronically by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in a computer memory.

[0161] It should be understood that the various parts of this application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, the N steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0162] Those skilled in the art will understand that all or part of the steps of the methods in the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, the program includes one or a combination of the steps of the method embodiments.

[0163] Furthermore, the functional units in the various embodiments of this application can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into a module. The integrated module can be implemented in hardware or as a software functional module. If the integrated module is implemented as a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium.

[0164] The storage medium mentioned above can be a read-only memory, a disk, or an optical disk, etc. Although embodiments of this application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting this application. Those skilled in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of this application.

Claims

1. A decision-making method of an autonomous vehicle, characterized by, Includes the following steps: Determine whether the autonomous vehicle has traveled to a path that meets the preset turning and narrow conditions; If the vehicle travels to a path that meets the preset corner narrow conditions, it will detect whether the obstacle ahead is within the current obstacle dynamic window. If it is detected that the obstacle is within the current obstacle dynamic window, it will acquire the obstacle information of the obstacle ahead and the vehicle information of the autonomous vehicle. as well as Based on the obstacle information and the vehicle information, a decision result is generated to either stop the current driving of the autonomous vehicle, wait for the obstacle in front to leave the current obstacle dynamic window, restart the autonomous vehicle, or continue the current driving of the autonomous vehicle. Using a vehicle kinematics model, the motion of the vehicle is studied from a geometric perspective, including changes in the vehicle's spatial pose and speed over time. The forward-looking dynamic window area, i.e., the actual area, is mainly divided into three parts: an emergency stop area, a deceleration area, and a warning area. A forward-predictive dynamic detection of K-times is performed on the dynamic window created by the vehicle kinematics model, and the detection cycle is used to update it in real time. When an obstacle is detected in the vehicle's forward-looking dynamic window area, i.e., the actual area, the current vehicle speed, acceleration, left and right wheel angles, and vehicle pose information are obtained without considering the drivable areas on the left and right, and matched with the autonomous driving vehicle. The vehicle moves according to the corresponding actions, and at the same time, a new predicted vehicle body and the probability of obstacles appearing in the new dynamic window are regenerated. If the obstacle is not in the newly generated dynamic window, it means that the subsequent driving is no longer affected by the obstacle, collision factors no longer need to be considered, and there is no need to stop to avoid the obstacle. Driving continues to prevent meaningless braking and avoidance. If the obstacle is still in the newly generated dynamic window, it means that the obstacle still appears, and the vehicle immediately stops. In this way, by effectively detecting obstacles in the dynamic window, the safe and stable driving of the vehicle is controlled until the state machine reports that the vehicle has a large driving space.

2. The method according to claim 1, characterized in that, Before restarting the autonomous vehicle, the following are also included: Identify the actual type of the obstacle ahead; If the actual type is a dynamic obstacle, then wait for the obstacle in front to leave before viewing the current obstacle dynamic window; If the actual type is a static obstacle, then a manual takeover prompt will be given.

3. The method according to claim 2, characterized in that, The generation of decision results based on the obstacle information and the vehicle information includes: The obstacle ahead is detected to be within the actual area of ​​the autonomous vehicle; The corresponding actions of the autonomous vehicle are matched according to the actual area and the actual type.

4. The method according to claim 3, characterized in that, The actual area is a deceleration area, an emergency stop area, or a warning area.

5. The method according to any one of claims 1-4, characterized in that, The vehicle information includes one or more of the following: speed, acceleration, left wheel steering angle, right wheel steering angle, and vehicle posture.

6. A decision-making device for an autonomous vehicle, characterized in that, For implementing the method as described in any one of claims 1-5, comprising: The judgment module is used to determine whether the autonomous vehicle has driven to a path that meets the preset turning and narrow conditions; The acquisition module is configured to, if driving onto a path that meets the preset corner narrowing condition, detect whether an obstacle ahead is within the current obstacle dynamic window, and, upon detection that it is within the current obstacle dynamic window, acquire obstacle information of the obstacle ahead and vehicle information of the autonomous vehicle; and The control module is used to generate a decision result based on the obstacle information and the vehicle information, to stop the current driving of the autonomous vehicle, wait for the obstacle in front to leave the current obstacle dynamic window, restart the autonomous vehicle, or continue the current driving of the autonomous vehicle.

7. The apparatus according to claim 6, characterized in that, Also includes: A recognition module is used to identify the actual type of the obstacle ahead before restarting the autonomous vehicle; A waiting module is used to wait for the obstacle in front to leave when the actual type is a dynamic obstacle, and then view the current obstacle dynamic window. The prompting module is used to provide a manual takeover prompt if the actual type is a static obstacle.

8. The apparatus according to claim 7, characterized in that, The control module includes: The detection unit is used to detect that the obstacle in front is located within the actual area of ​​the autonomous vehicle; A matching unit is used to match the corresponding actions of the autonomous vehicle based on the actual area and the actual type.

9. A vehicle, characterized in that, include: A memory, a processor, and a computer program stored in the memory and executable on the processor, the processor executing the program to implement the decision-making method for an autonomous vehicle as described in any one of claims 1-5.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, The program is executed by the processor to implement the decision-making method for an autonomous vehicle as described in any one of claims 1-5.

Images