Obstacle avoidance decision control method and system for autonomous vehicle

Abstract

The invention discloses an obstacle avoidance decision control method and system for an autonomous vehicle, and belongs to the technical field of autonomous vehicle control. The method comprises the following steps: acquiring obstacle information of a driving road, in-vehicle passenger information and road information; vehicle driving tracks under different obstacle avoidance parameters are calculated based on the intelligent model; according to the ratio of the predicted passing time of the target vehicle to the average passing time, the road passing efficiency (gt, 1 is low efficiency, and 1 is not more than 1 is high efficiency) is determined, and corresponding obstacle avoidance parameter grades (A / B / C classes) are matched according to passenger age groups (juvenile / labor / old people groups); the maximum or minimum obstacle avoidance parameter is selected by combining the passing efficiency, and the braking or steering strategy is dynamically adjusted to complete obstacle avoidance. According to the method, the passenger characteristics and the road efficiency are fused to optimize the obstacle avoidance decision, and the control reliability is improved.

Description

TECHNICAL FIELD

[0001] The present application belongs to the technical field of automatic driving vehicle control, and particularly relates to an obstacle avoidance decision control method and system for an automatic driving vehicle. BACKGROUND

[0002] With the development of automatic driving technology, active safety technology as a core means of accident prevention is increasingly widely used in automatic driving vehicles. Among them, automatic emergency braking (AEB) and automatic emergency steering (AES) are two key technologies, which are used to control the longitudinal braking and lateral steering of the vehicle to respond to the sudden appearance of obstacles in front of the driving lane.

[0003] Currently, some technical solutions have been proposed to improve obstacle avoidance capability. For example: Chinese patent application CN119611348A proposes to calculate the time-space node of deceleration / turning based on obstacle avoidance trajectory and vehicle braking parameters, and send intelligent reminders to the driver to assist lane changing operation. Although this solution improves the practicality of obstacle avoidance and the driver experience, it does not consider the adaptability of different passengers to the dynamic response strength of obstacle avoidance, making it difficult to ensure passenger comfort.

[0004] Chinese patent application CN120024325A calculates the lateral speed in the lane changing obstacle avoidance process in real time by collecting vehicle lateral speed and tire pressure data. Although this solution enhances the safety of obstacle avoidance, it does not classify the collision avoidance strength in combination with the physical state of the driver, and also cannot guarantee passenger comfort.

[0005] In addition, when AEB and AES systems coexist, there is a lack of effective arbitration mechanism: The prior art does not solve the problem of collaborative judgment of AEB and AES, making it difficult to quickly decide on the timing of braking or steering in complex scenarios, affecting the reliability of obstacle avoidance control.

[0006] In summary, the prior art has the following defects: Ignoring passenger differences: without adjusting the obstacle avoidance strength according to individual factors such as passenger age and health status, the dynamic response (such as braking deceleration and steering acceleration) in the obstacle avoidance process may reduce passenger comfort.

[0007] Lack of arbitration mechanism: AEB and AES systems lack collaborative decision-making logic and cannot efficiently plan a combined obstacle avoidance strategy for braking and steering.

[0008] Therefore, there is an urgent need for an automatic driving obstacle avoidance decision-making scheme that ensures the effectiveness of obstacle avoidance and road traffic efficiency, improves comfort by adapting obstacle avoidance parameters to passenger characteristics, and establishes an AEB / AES collaborative arbitration mechanism to enhance system reliability. SUMMARY

[0009] The purpose of this invention is to provide an obstacle avoidance decision control method and system for autonomous vehicles, which can solve the technical problems that the dynamic response of the vehicle will seriously reduce the riding experience and comfort of the occupants when the vehicle avoids collisions according to different obstacle avoidance paths, and the reliability of obstacle avoidance control triggered by the vehicle during obstacle avoidance.

[0010] To solve the above-mentioned technical problems, the present invention is implemented as follows: This invention provides an obstacle avoidance decision control method for autonomous vehicles, comprising the following steps: Step S101: Obtain information on obstacles, occupants, and roads on the road; Step S102: Based on the intelligent model, perform intelligent calculations on obstacle information and target vehicle information to determine the vehicle's driving trajectory under different obstacle avoidance parameters; Step S103: Based on the estimated travel time of the target vehicle Average travel time The ratio determines the road traffic efficiency, and the occupants are classified into children (0-15 years old), working people (16-59 years old) and elderly people (60 years old and above) based on the age data of the occupants. Based on the classification results, the three types of obstacle avoidance parameters A, B and C are associated. Step S104: Match feasible obstacle avoidance trajectories based on vehicle obstacle avoidance parameters, select an obstacle avoidance strategy based on current traffic efficiency, and adjust the strategy in real time until obstacle avoidance is completed; wherein: The rule for determining road traffic efficiency is: when Events are defined as inefficient events when... The event is defined as a high-efficiency type II event; The obstacle avoidance strategy execution rules are as follows: in Class I events, the maximum obstacle avoidance parameter is used to control braking or steering first; in Class II events, the minimum obstacle avoidance parameter is used to control braking or steering first.

[0011] Optionally, step S101 specifically includes: Road data and obstacle information are collected using visual sensors and lidar; The system uses facial recognition devices and electronic sensors to obtain information on the number of occupants, their facial details, weight, and body fat percentage. The location of the target vehicle and weather information are determined by vehicle-mounted radar, and the estimated travel time is calculated by combining this with vehicle-to-everything (V2X) network data. and average travel time .

[0012] Optionally, step S102 specifically includes: Based on the obstacle type, specifications and distribution boundary information, combined with the target vehicle's tonnage and length parameters, the obstacle avoidance trajectory area under different obstacle avoidance parameters is calculated through an intelligent model. by target vehicle speed , obstacle speed , distance , friction coefficient and gravity acceleration determine the obstacle avoidance opportunity: when trigger the obstacle avoidance operation.

[0013] Optionally, in step S103: The A-type obstacle avoidance parameter corresponds to the juvenile population, the B-type obstacle avoidance parameter corresponds to the working population, and the C-type obstacle avoidance parameter corresponds to the elderly population; Each type of obstacle avoidance parameter includes a combination of AEB braking deceleration and AES steering acceleration, and the braking deceleration and steering acceleration of A, B and C types gradually decrease.

[0014] Optionally, in step S104, the vehicle AEB adopts a TTC control algorithm, the maximum detection time of vehicle braking is , the relative speed of the vehicle and the obstacle is , and the dynamic adjustment of the obstacle avoidance strategy includes: When the distance between the target vehicle and the obstacle meets , it is determined that it is a normal obstacle avoidance state, and only AEB is activated; When , it is determined that it is an enhanced obstacle avoidance state, and the maximum obstacle avoidance parameter is used to activate AEB and / or AES; If AEB / AES alone can avoid obstacles, single control is performed; if joint activation is required to avoid obstacles, AEB and AES are simultaneously executed; if the obstacles still cannot be avoided, the maximum braking deceleration of AEB is output.

[0015] The application also provides an obstacle avoidance decision control system of an autonomous vehicle for executing the method, comprising: A detection module for acquiring obstacle information on a driving road, passenger information in the vehicle and road information; A calculation module for intelligently calculating the obstacle information and target vehicle information based on an intelligent model to determine the vehicle driving trajectory under different obstacle avoidance parameters; A determination module for determining the road traffic efficiency according to the ratio of the predicted passing time of the target vehicle to the average passing time of the road, and classifying the passengers into juvenile population, working population and elderly population according to the passenger age data, and associating the A, B and C type obstacle avoidance parameters based on the classification results; An obstacle avoidance module for matching a feasible obstacle avoidance trajectory according to the vehicle obstacle avoidance parameter, selecting an obstacle avoidance strategy in combination with the current traffic efficiency, and adjusting the strategy in real time until the obstacle avoidance is completed.

[0016] Optionally, the obstacle avoidance module is further configured to: In trajectory tracking control, the deviation of the actual driving trajectory of the vehicle from the predetermined trajectory is detected in real time; When the vehicle does not travel according to the predetermined trajectory, the obstacle detection and path planning are restarted until the obstacle avoidance completion condition is met: ; Among them, is the shortest longitudinal obstacle avoidance distance; is the lateral obstacle avoidance distance; is the AES steering acceleration.

[0017] Compared with the prior art, the present application has the following advantages: 1. The present application divides passengers into three groups: children (0-15 years old), workers (16-59 years old) and the elderly (60 years old and above) by collecting passenger age, health and other data, and matches the corresponding obstacle avoidance parameters (A / B / C). By dynamically adjusting the AEB braking deceleration and the AES steering acceleration (such as selecting the maximum parameter for a class of events and the minimum parameter for a class of events), the problem of ignoring the adaptability of passengers to obstacle avoidance intensity in the prior art is solved, and the riding comfort of passengers of different ages is significantly improved.

[0018] 2. The present application generates driving trajectory regions (including the earliest / latest obstacle avoidance trajectory) under different obstacle avoidance parameters based on intelligent model comprehensive calculation of obstacle type, distribution boundary, vehicle tonnage / length and other parameters. By real-time detection of obstacle motion state (speed, distance) and road traffic efficiency (ratio of actual traffic time t e to average traffic time t a , the feasible obstacle avoidance path is dynamically matched and the strategy is adjusted (such as prioritizing the maximum obstacle avoidance parameter when the efficiency is low), ensuring the feasibility of the obstacle avoidance path and the efficiency of the vehicle control.

[0019] 3. The present application designs an obstacle avoidance state grading mechanism: when the obstacle distance , only AEB braking is activated; when , the enhanced obstacle avoidance state is entered, and AEB or / and AES is activated according to the maximum obstacle avoidance parameter; if it is still impossible to avoid obstacles, the maximum braking deceleration is output. This mechanism effectively coordinates the triggering time of longitudinal braking and lateral steering, and improves the reliability of obstacle avoidance control in complex scenarios.

[0020] 4. The present application defines the obstacle avoidance event category according to the road traffic efficiency (low efficiency , high efficiency ), and selects a differentiated control strategy (such as the minimum obstacle avoidance parameter for high-efficiency roads) according to the passenger parameters, which reduces the impact on road traffic efficiency while ensuring safety.

[0021] 5、The application dynamically adjusts the obstacle avoidance strategy until the obstacle avoidance is completed through real-time trajectory tracking and obstacle state detection (such as lateral distance s y and the constraint verification of steering acceleration a y , ensuring that the vehicle always travels along the predetermined trajectory and improving the stability of the obstacle avoidance process.

[0022] In summary, the application constructs a dynamic obstacle avoidance decision mechanism by fusing passenger characteristics, road efficiency, and multi-dimensional obstacle information, which has significant technical advantages in improving passenger comfort, optimizing system response accuracy, solving braking / steering arbitration problems, and the like, while taking into account the traffic efficiency and safety requirements. BRIEF DESCRIPTION OF DRAWINGS

[0023] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed in the embodiment description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor. Figure 1 The flowchart of the obstacle avoidance decision control method of the autonomous vehicle provided by the embodiments of the present application; Figure 2 The structural block diagram of the obstacle avoidance decision control system of the autonomous vehicle provided by the embodiments of the present application. DETAILED DESCRIPTION

[0024] The technical solutions in the embodiments of the present application will be described clearly and completely in conjunction with the drawings of the embodiments of the present application. Obviously, the described embodiments are only some embodiments of the present application, not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0025] The terms "first", "second", etc. in the specification and claims of the present application are used to distinguish similar objects, not to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged under appropriate circumstances, so that the embodiments of the present application can be implemented in an order other than those illustrated or described herein, and the objects distinguished by "first", "second", etc. are generally of a kind and do not limit the number of objects, for example, the first object can be one or more. In addition, "and / or" in the specification and claims indicates at least one of the connected objects, and the character " / ", generally indicates that the objects before and after are in an "or" relationship.

[0026] Please refer toFigure 1 As shown, the present invention provides an obstacle avoidance decision control method for autonomous vehicles, comprising the following steps: Step S101: Obtain information on obstacles, occupants, and roads on the road; Step S102: Based on the intelligent model, perform intelligent calculations on obstacle information and target vehicle information to determine the vehicle's driving trajectory under different obstacle avoidance parameters; Step S103: Based on the estimated travel time of the target vehicle Average travel time t a The ratio determines the road traffic efficiency, and the occupants are classified into children (0-15 years old), working people (16-59 years old) and elderly people (60 years old and above) based on the age data of the occupants. Based on the classification results, the three types of obstacle avoidance parameters A, B and C are associated. Step S104: Match feasible obstacle avoidance trajectories based on vehicle obstacle avoidance parameters, select an obstacle avoidance strategy based on current traffic efficiency, and adjust the strategy in real time until obstacle avoidance is completed; wherein: The rule for determining road traffic efficiency is: when Events are defined as inefficient events when... The event is defined as a high-efficiency type II event; The obstacle avoidance strategy execution rules are as follows: in Class I events, the maximum obstacle avoidance parameter is used to control braking or steering first; in Class II events, the minimum obstacle avoidance parameter is used to control braking or steering first.

[0027] Step S101 specifically includes: Road data and obstacle information are collected using visual sensors and lidar; The system uses facial recognition and electronic sensors to obtain parameters such as the number of occupants, facial information, weight, and body fat percentage. The location of the target vehicle and weather information are determined by vehicle-mounted radar, and the estimated travel time is calculated by combining this with vehicle-to-everything (V2X) network data. and average travel time t a .

[0028] Step S102 specifically includes: Based on the obstacle type, specifications and distribution boundary information, combined with the target vehicle's tonnage and length parameters, the obstacle avoidance trajectory area under different obstacle avoidance parameters is calculated through an intelligent model. Speed ​​of the target vehicle obstacle speed ,spacing coefficient of friction and gravitational acceleration Determining when to avoid obstacles: When Obstacle avoidance is triggered at certain times.

[0029] In step S103: The A-type obstacle avoidance parameter corresponds to a juvenile population, the B-type obstacle avoidance parameter corresponds to a labor population, and the C-type obstacle avoidance parameter corresponds to an elderly population. Each type of obstacle avoidance parameter includes a combination of AEB braking deceleration and AES steering acceleration, and the braking deceleration and steering acceleration of the A, B, and C types gradually decrease.

[0030] Optionally, in step S104, the vehicle AEB adopts a TTC control algorithm, the maximum detection time for controlling vehicle braking is , the relative speed of the vehicle and the obstacle is , and the dynamic adjustment of the obstacle avoidance strategy includes: When the distance between the target vehicle and the obstacle satisfies , it is determined that the normal obstacle avoidance state is activated only AEB; When , it is determined that the enhanced obstacle avoidance state is activated AEB and / or AES using the maximum obstacle avoidance parameter; If AEB / AES alone can avoid obstacles, single control is executed; if joint activation is required to avoid obstacles, AEB and AES are simultaneously executed; if the obstacle cannot be avoided, the maximum braking deceleration of AEB is output.

[0031] The application also provides an obstacle avoidance decision control system of an autonomous vehicle for executing the method, which includes a detection module 1, a calculation module 2, a determination module 3, and an obstacle avoidance module 4.

[0032] The detection module 1 is used to obtain obstacle information on the driving road, passenger information in the vehicle, and road information.

[0033] The calculation module 2 is used to intelligently calculate the obstacle information and target vehicle information based on an intelligent model to determine the vehicle driving trajectory under different obstacle avoidance parameters.

[0034] The determination module 3 is used to determine the road traffic efficiency according to the ratio of the predicted passing time of the target vehicle to the average passing time of the road, and to classify the passengers into a juvenile population, a labor population, and an elderly population according to the passenger age data, and to associate the A, B, and C three types of obstacle avoidance parameters based on the classification results.

[0035] The obstacle avoidance module 4 is used to match a feasible obstacle avoidance trajectory according to the vehicle obstacle avoidance parameter, select an obstacle avoidance strategy in combination with the current traffic efficiency, and adjust the strategy in real time until the obstacle avoidance is completed.

[0036] The obstacle avoidance module 4 is further configured to: In the trajectory tracking control, the deviation between the actual driving trajectory of the vehicle and the predetermined trajectory is detected in real time. When the vehicle does not travel along the predetermined trajectory, the obstacle detection and path planning are restarted until the obstacle avoidance completion condition is met: ; wherein, is the shortest longitudinal obstacle avoidance distance, taking the standard lane width 3.75m; is the lateral obstacle avoidance distance; is the AES steering acceleration.

[0037] It should be noted that in this document, the terms "comprising", "including", or any other variant thereof are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements recited, but can also include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element preceded by "comprises a" does not, without more constraints, foreclose the existence of additional identical elements in the process, method, article, or apparatus that includes the recited element.

[0038] In addition, it should be noted that the scope of the methods and systems of the embodiments of the present application is not limited to performing functions in the order discussed or illustrated, and includes performing functions in a substantially simultaneous manner or in the reverse order, for example, the described methods can be performed in an order other than that described, and various steps can be added, omitted, or combined, in addition, features described with respect to certain examples can be combined in other examples.

[0039] The embodiments of the present application are described above with reference to the accompanying drawings, but the present application is not limited to the specific embodiments described above, which are merely illustrative, rather than limiting, and a person of ordinary skill in the art can make many forms under the inspiration of the present application without departing from the purpose of the present application and the scope protected by the claims, all of which belong to the protection of the present application.

Claims

1. A method for obstacle avoidance decision-making and control of an autonomous vehicle, characterized in that, Includes the following steps: Step S101: Obtain information on obstacles, occupants, and roads on the road; Step S102: Based on the intelligent model, perform intelligent calculations on obstacle information and target vehicle information to determine the vehicle's driving trajectory under different obstacle avoidance parameters; Step S103: Based on the estimated travel time of the target vehicle With average road travel time The ratio determines the road traffic efficiency, and passengers are classified into teenagers, working people and the elderly based on the age data of the passengers. Based on the classification results, three types of obstacle avoidance parameters, A, B and C, are associated. Step S104: Match feasible obstacle avoidance trajectories based on vehicle obstacle avoidance parameters, select an obstacle avoidance strategy based on current traffic efficiency, and adjust the strategy in real time until obstacle avoidance is completed; wherein: The rule for determining road traffic efficiency is: when Events are defined as inefficient events when... Time is defined as a high-efficiency type II event; The obstacle avoidance strategy execution rules are as follows: in Class I events, the maximum obstacle avoidance parameter is used to control braking or steering first; in Class II events, the minimum obstacle avoidance parameter is used to control braking or steering first.

2. The method according to claim 1, characterized in that, Step S101 specifically includes: Road data and obstacle information are collected using visual sensors and lidar; The system uses facial recognition devices and electronic sensors to obtain information on the number of occupants, their facial details, weight, and body fat percentage. The location of the target vehicle and weather information are determined by vehicle-mounted radar, and the estimated travel time is calculated by combining this with vehicle-to-everything (V2X) network data. and average travel time .

3. The method according to claim 1, characterized in that, Step S102 specifically includes: Based on the obstacle type, specifications and distribution boundary information, combined with the target vehicle's tonnage and length parameters, the obstacle avoidance trajectory area under different obstacle avoidance parameters is calculated through an intelligent model. Speed ​​of the target vehicle obstacle speed ,spacing coefficient of friction and gravitational acceleration Determining when to avoid obstacles: When Obstacle avoidance is triggered at certain times.

4. The method according to claim 1, characterized in that, In step S103: Type A obstacle avoidance parameters correspond to the youth population, Type B obstacle avoidance parameters correspond to the working population, and Type C obstacle avoidance parameters correspond to the elderly population. Each obstacle avoidance parameter includes a combination of AEB braking deceleration and AES steering acceleration, with the braking deceleration and steering acceleration decreasing progressively for categories A, B, and C.

5. The method according to claim 1, characterized in that, In step S104, the vehicle's AEB uses the TTC control algorithm, and the maximum detection time for controlling the vehicle's braking is... The relative speed between the vehicle and the obstacle is The dynamic adjustment of obstacle avoidance strategies includes: When the distance between the target vehicle and the obstacle meets the requirements When the time is right, it is determined to be a normal obstacle avoidance state, and only AEB is activated; When satisfied When the condition is determined to be an enhanced obstacle avoidance state, AEB and / or AES are activated using the maximum obstacle avoidance parameters; If AEB / AES can avoid obstacles when activated alone, then single control is executed; if they need to be activated together to avoid obstacles, then AEB and AES are executed simultaneously; if obstacle avoidance is still not possible, AEB outputs the maximum braking deceleration.

6. An obstacle avoidance decision control system for an autonomous vehicle performing the method according to any one of claims 1-5, characterized in that, include: The detection module is used to acquire information on obstacles, occupants, and roads on the road. The calculation module is used to perform intelligent calculations on obstacle information and target vehicle information based on the intelligent model to determine the vehicle's trajectory under different obstacle avoidance parameters; The determination module is used to determine the road traffic efficiency based on the ratio of the target vehicle's estimated travel time to the average road travel time, and to classify passengers into teenagers, working people and the elderly based on passenger age data, and to associate the three types of obstacle avoidance parameters A, B and C based on the classification results; The obstacle avoidance module is used to match feasible obstacle avoidance trajectories based on vehicle obstacle avoidance parameters, select obstacle avoidance strategies based on current traffic efficiency, and adjust the strategies in real time until obstacle avoidance is completed.

7. The system according to claim 6, characterized in that, The obstacle avoidance module is further configured as follows: In trajectory tracking control, the deviation between the vehicle's actual driving trajectory and the predetermined trajectory is detected in real time; If the vehicle deviates from the predetermined trajectory, obstacle detection and path planning will be restarted until the obstacle avoidance conditions are met. ； in, This represents the shortest longitudinal obstacle avoidance distance. This refers to the lateral obstacle avoidance distance. This refers to the steering acceleration of the AES.

Images