Vehicle intelligent obstacle avoidance method and system

Abstract

The invention discloses a vehicle intelligent obstacle avoidance method and system, and the method comprises the steps: obtaining a planned advancing track of a target vehicle, and generating a planned driving plan according to the planned advancing track; detecting braking parameters of the target vehicle and obstacle information on the driving path based on the planned driving plan; performing intelligent calculation through an intelligent model according to the obstacle information, and determining an obstacle avoidance track of the target vehicle for each obstacle; and according to the obstacle avoidance track and the braking parameters of the target vehicle, determining respective time points and position points of deceleration and turning of the target vehicle passing through each obstacle, and sending out an intelligent prompt. According to the method, detailed lane changing time point and position point information can be provided for a driver, so that the driver in the driving skill can perform corresponding lane changing operation according to reminding, the driver does not need to perform judgment and decision making according to personal experience, the practicability and the experience feeling of the driver are improved, the obstacle avoidance efficiency and the success rate are guaranteed to the maximum extent, and the driving experience is improved. And the stability and the reliability are improved.

Description

Technical Field

[0001] The present invention relates to the field of vehicle driving assistance technology, and in particular to a vehicle intelligent obstacle avoidance method and system. Background Art

[0002] At present, with the increasing maturity of autonomous driving technology, all car companies have equipped their production vehicles with autonomous driving technology. Autonomous driving cars, also known as driverless cars, are intelligent cars that achieve unmanned driving through computer systems. Autonomous driving cars rely on artificial intelligence, visual computing, radar, monitoring devices and global positioning systems to work together, allowing computers to automatically and safely operate motor vehicles without any human active operation. However, due to the different autonomous driving algorithms of various car companies, there are also divisions in the level of autonomous driving. For car companies with small R&D costs, it is impossible to guarantee the safety of autonomous driving, so manual driving is still required. It is inevitable to encounter various types of obstacles during driving. The existing vehicle intelligent obstacle avoidance methods all monitor route obstacles and then issue voice reminders to enable drivers to understand the road conditions ahead for obstacle avoidance operations. There are the following problems: For drivers with relatively poor driving skills, it is impossible to avoid obstacles 100% without a reference obstacle avoidance path, resulting in traffic jams and even safety accidents, which reduces the user experience, practicality and reliability. Summary of the invention

[0003] In response to the above-mentioned problems, the present invention provides a vehicle intelligent obstacle avoidance method and system to solve the problem that the voice reminder obstacle avoidance mentioned in the background technology is not able to achieve 100% avoidance of obstacles for drivers with relatively poor driving skills without a reference obstacle avoidance path, resulting in traffic jams and even safety accidents, reducing the user experience, practicality and reliability.

[0004] A vehicle intelligent obstacle avoidance method comprises the following steps:

[0005] Obtain the planned trajectory of the target vehicle, and generate a planned driving plan based on the planned trajectory;

[0006] Detect the braking parameters of the target vehicle and the obstacle information on the driving path based on the planned driving plan;

[0007] The intelligent model performs intelligent calculations based on obstacle information to determine the target vehicle's obstacle avoidance trajectory for each obstacle;

[0008] According to the obstacle avoidance trajectory and the braking parameters of the target vehicle, the time and position points of deceleration and turning of the target vehicle passing each obstacle are determined and intelligent reminders are issued.

[0009] Preferably, the step of obtaining the planned moving trajectory of the target vehicle and generating a planned driving plan according to the planned moving trajectory includes:

[0010] Determine the departure and destination information of the target vehicle, and generate multiple driving routes based on the departure and destination information;

[0011] Obtaining a target path selected by a user from multiple driving paths as a planned driving path, and determining a planned travel trajectory of the target vehicle according to the path characteristics of the planned driving path;

[0012] Determine the planned driving road information according to the planned travel trajectory, and determine multiple road attributes according to the planned driving road information;

[0013] Based on a plurality of road attributes, stage recommended speed information on the planned driving road is determined, and a planned driving plan is generated according to the stage recommended speed information.

[0014] Preferably, the detecting the braking parameters of the target vehicle and the obstacle information on the driving path based on the planned driving plan includes:

[0015] The braking speed of the target vehicle is detected by a speed sensor and a curve of the braking speed changing with time is constructed;

[0016] Obtain the age information of the driver of the target vehicle and set the straight-line distance for obstacle detection based on the age information;

[0017] Determine the obstacle detection medium according to the obstacle detection straight-line distance, and collect road data through the obstacle detection medium;

[0018] The collected data is input into the deep learning neural network model to determine the various obstacle types and specific parameters on the driving path.

[0019] Preferably, the step of obtaining the age information of the driver of the target vehicle and setting the obstacle detection straight-line distance according to the age information includes:

[0020] Collecting the facial image of the driver, predicting the approximate age information of the driver based on the facial image, and determining the population attribute of the driver based on the approximate age information;

[0021] Determine the average vision level and average reaction level of drivers according to the population attributes of drivers;

[0022] Determine a first detection straight-line distance of the obstacle according to the average vision level, and determine a reaction operation distance for the obstacle according to the average reaction level;

[0023] The first detection straight-line distance and the reaction operation distance are added to obtain a second detection straight-line distance, and the second detection straight-line distance is used as the obstacle detection distance.

[0024] Preferably, performing intelligent calculation according to obstacle information by using an intelligent model to determine the obstacle avoidance trajectory of the target vehicle for each obstacle includes:

[0025] Determine the obstacle type and specification as well as the distribution boundary information of the obstacle on the driving road according to the obstacle information;

[0026] Determine multiple obstacle avoidance path starting points and multiple obstacle avoidance path ending points according to obstacle types and specifications;

[0027] Obtain the tonnage information and vehicle length parameters of the target vehicle, and input the tonnage information and vehicle length parameters as well as multiple obstacle avoidance path starting points and multiple obstacle avoidance path ending points into the intelligent model for intelligent calculation;

[0028] The model output results are used to obtain multiple obstacle avoidance trajectories of the target vehicle for each obstacle.

[0029] Preferably, the method of determining the time point and position point of deceleration and turning of the target vehicle passing each obstacle according to the obstacle avoidance trajectory and the braking parameters of the target vehicle and issuing an intelligent reminder includes:

[0030] Determine the standard braking parameters corresponding to the obstacle avoidance trajectory and the respective time and position points of initial deceleration and turning;

[0031] calculating a braking parameter ratio of a standard braking parameter to a braking parameter of a target vehicle, and determining a braking distance ratio according to the braking parameter ratio;

[0032] Determine the time and position of the target vehicle's deceleration and turning when passing each obstacle according to the braking distance ratio;

[0033] Obtain the reminder method selected by the driver, and issue an intelligent obstacle avoidance reminder to the driver according to the reminder method; the reminder method includes: voice reminder and image reminder.

[0034] Preferably, it also includes:

[0035] Detect the degree of overlap between the driver's real-time obstacle avoidance path and the planned trajectory for each obstacle;

[0036] Determine the driver's obstacle avoidance experience index based on the overlap degree, and determine whether it is necessary to continue generating a planned obstacle avoidance trajectory for subsequent obstacles based on the obstacle avoidance experience index;

[0037] If not, all obstacle detection media of the target vehicle are activated and all-round obstacle detection is performed through the obstacle detection media.

[0038] Preferably, the step of inputting the tonnage information and the vehicle length parameters as well as the multiple obstacle avoidance path starting points and the multiple obstacle avoidance path ending points into the intelligent model for intelligent calculation includes:

[0039] Input the tonnage information and vehicle length parameters into the intelligent model to calculate the safe lane change distance parameters of the target vehicle;

[0040] Selecting a matching point from a plurality of obstacle avoidance path starting points and a plurality of obstacle avoidance path ending points according to a safe lane change distance parameter;

[0041] The obstacle avoidance trajectory of the starting point and the end point of the obstacle avoidance path is constructed according to the matching points and the safe lane change distance parameters.

[0042] Preferably, determining the reaction operation distance to the obstacle according to the average reaction level includes:

[0043] Determine the average time parameters for the driver to recognize obstacles and take reaction actions based on the average reaction level;

[0044] Obtain standard braking speed according to the planned driving plan;

[0045] The driver's reaction operation distance when responding to an obstacle is calculated based on the standard braking speed and the average time parameters for the driver to know the obstacle and perform reaction operations.

[0046] A vehicle intelligent obstacle avoidance system, the system comprising:

[0047] A generation module is used to obtain the planned trajectory of the target vehicle and generate a planned driving plan according to the planned trajectory;

[0048] A detection module, used to detect the braking parameters of the target vehicle and obstacle information on the driving path based on the planned driving plan;

[0049] A determination module is used to perform intelligent calculations based on obstacle information through an intelligent model to determine the obstacle avoidance trajectory of the target vehicle for each obstacle;

[0050] The reminder module is used to determine the time and position points of the target vehicle's deceleration and turning when passing each obstacle based on the obstacle avoidance trajectory and the target vehicle's braking parameters, and issue an intelligent reminder.

[0051] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or understood by practicing the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures particularly pointed out in the written description and the accompanying drawings.

[0052] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] The accompanying drawings are used to provide further understanding of the present invention and constitute a part of the specification. They are used to explain the present invention together with the embodiments of the present invention and do not constitute a limitation of the present invention.

[0054] Figure 1 A working flow chart of a vehicle intelligent obstacle avoidance method provided by the present invention;

[0055] Figure 2 Another working flow chart of a vehicle intelligent obstacle avoidance method provided by the present invention;

[0056] Figure 3 Another working flow chart of a vehicle intelligent obstacle avoidance method provided by the present invention;

[0057] Figure 4 This is a schematic diagram of the structure of a vehicle intelligent obstacle avoidance system provided by the present invention. DETAILED DESCRIPTION

[0058] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present disclosure. Instead, they are merely examples of devices and methods consistent with some aspects of the present disclosure as detailed in the appended claims.

[0059] At present, with the increasing maturity of autonomous driving technology, all automobile companies have equipped their production vehicles with autonomous driving technology. Autonomous driving cars, also known as driverless cars, are intelligent cars that achieve driverless driving through computer systems. Autonomous driving cars rely on artificial intelligence, visual computing, radar, monitoring devices and global positioning systems to work together, allowing computers to automatically and safely operate motor vehicles without any human active operation. However, due to the different autonomous driving algorithms of various automobile companies, there are also divisions in the level of autonomous driving. For automobile companies with small R&D cost investment, it is impossible to guarantee the safety of autonomous driving, so manual driving is still required. Various types of obstacles will inevitably be encountered during driving. The existing vehicle intelligent obstacle avoidance methods all monitor route obstacles and then issue voice reminders to enable the driver to understand the road conditions ahead to perform obstacle avoidance operations. There are the following problems: For drivers with relatively poor driving skills, it is impossible to achieve 100% avoidance of obstacles without a reference obstacle avoidance path, resulting in traffic jams or even safety accidents, which reduces the user experience, practicality and reliability. In order to solve the above problems, this embodiment discloses a vehicle intelligent obstacle avoidance method.

[0060] A vehicle intelligent obstacle avoidance method, such as Figure 1 As shown, the following steps are included:

[0061] Step S101, obtaining a planned moving trajectory of a target vehicle, and generating a planned driving plan according to the planned moving trajectory;

[0062] Step S102: detecting the braking parameters of the target vehicle and obstacle information on the driving path based on the planned driving plan;

[0063] Step S103: performing intelligent calculations based on obstacle information through an intelligent model to determine an obstacle avoidance trajectory of the target vehicle for each obstacle;

[0064] Step S104: Determine the time points and positions of the target vehicle's deceleration and turning when passing each obstacle based on the obstacle avoidance trajectory and the target vehicle's braking parameters, and issue an intelligent reminder.

[0065] In this embodiment, the planned driving plan is represented by a preset plan of the driving lane and driving speed of the target vehicle on each road section;

[0066] In this embodiment, the braking parameters are represented as the braking speed information of the target vehicle, including: the driving speed and acceleration;

[0067] In this embodiment, the obstacle information is represented as comprehensive description information of the obstacles on the driving path including: obstacle type, size, shape, area occupied, etc.;

[0068] In this embodiment, the intelligent model is represented as an artificial intelligence model for calculating and generating obstacle avoidance trajectories.

[0069] The working principle of the above technical solution is: obtain the planned travel trajectory of the target vehicle, and generate a planned driving plan according to the planned travel trajectory; detect the braking parameters of the target vehicle and the obstacle information on the driving path based on the planned driving plan; perform intelligent calculations based on the obstacle information through an intelligent model to determine the obstacle avoidance trajectory of the target vehicle for each obstacle; determine the time points and position points of deceleration and turning of the target vehicle passing each obstacle according to the obstacle avoidance trajectory and the braking parameters of the target vehicle, and issue an intelligent reminder.

[0070] The beneficial effects of the above technical solution are as follows: by intelligently generating an obstacle avoidance trajectory and then calculating the time points and position points of the target vehicle's deceleration and turning after passing each obstacle based on the braking parameters of the target vehicle, an intelligent reminder can be issued, which can provide the driver with detailed lane change time and position point information, so that drivers with average or low driving skills can perform corresponding lane change operations according to the reminder, without the need for the driver to make judgments and decisions based on personal experience, thereby improving practicality and driver experience, maximizing obstacle avoidance efficiency and success rate, improving stability and reliability, and solving the problem in the prior art that voice reminder obstacle avoidance cannot achieve 100% avoidance of obstacles for drivers with relatively poor driving skills without a reference obstacle avoidance path, resulting in traffic jams or even safety accidents, reducing user experience, practicality and reliability.

[0071] In one embodiment, Figure 2 As shown, the step of obtaining the planned moving trajectory of the target vehicle and generating a planned driving plan according to the planned moving trajectory includes:

[0072] Step S201, determining the departure and destination information of the target vehicle, and generating multiple driving routes according to the departure and destination information;

[0073] Step S202: obtaining a target path selected by a user from multiple driving paths as a planned driving path, and determining a planned travel trajectory of the target vehicle according to the path characteristics of the planned driving path;

[0074] Step S203: determining planned driving road information according to the planned travel trajectory, and determining a plurality of road attributes according to the planned driving road information;

[0075] Step S204: determining the stage recommended speed information on the planned driving road based on multiple road attributes, and generating a planned driving plan according to the stage recommended speed information.

[0076] In this embodiment, the road attributes are represented by the classification attributes of the driving road, such as national roads, provincial roads, rural roads, expressways, etc.

[0077] The beneficial effects of the above technical solution are: generating multiple driving paths according to the departure and destination information of the target vehicle, selecting the target path as the planned driving path, thereby determining multiple road attributes, obtaining the stage recommended speed information on the planned driving road, and generating a planned driving plan, which can improve driving efficiency, help the vehicle to travel more efficiently, safely and reliably along the established route and at the established speed, and improve driving safety.

[0078] In one embodiment, the detecting the braking parameters of the target vehicle and the obstacle information on the driving path based on the planned driving plan includes:

[0079] The braking speed of the target vehicle is detected by a speed sensor and a curve of the braking speed changing with time is constructed;

[0080] Obtain the age information of the driver of the target vehicle and set the straight-line distance for obstacle detection based on the age information;

[0081] Determine the obstacle detection medium according to the obstacle detection straight-line distance, and collect road data through the obstacle detection medium;

[0082] The collected data is input into the deep learning neural network model to determine the various obstacle types and specific parameters on the driving path.

[0083] In this embodiment, the obstacle detection medium varies according to the length of the detection distance. It is detected by a vehicle-mounted camera within a short distance, by a laser radar within a medium distance, and by an ultrasonic sensor within a long distance.

[0084] The beneficial effects of the above technical solution are as follows: by setting the obstacle detection straight-line distance according to the driver's age information, a reasonable detection distance can be objectively and accurately set according to the driver's reaction to the obstacle, providing the driver with sufficient reaction time and distance, ensuring that a judgment and reaction can be made in time after seeing the obstacle, thereby improving safety. Furthermore, by determining the obstacle detection medium according to the obstacle detection straight-line distance, the obstacle detection accuracy and precision can be maximized. When the distance is far, it is detected by sensors, and when the distance is close, it is detected by vehicle-mounted radar and cameras, thereby improving stability and obstacle detection reliability.

[0085] In one embodiment, Figure 3 As shown, the method of obtaining the age information of the target vehicle driver and setting the obstacle detection straight-line distance according to the age information includes:

[0086] Step S301, collecting a facial image of a driver, predicting the approximate age information of the driver based on the facial image, and determining the population attribute of the driver based on the approximate age information;

[0087] Step S302: determining the average vision level and average reaction level of the drivers according to the crowd attributes of the drivers;

[0088] Step S303, determining a first detection straight-line distance of the obstacle according to the average vision level, and determining a reaction operation distance to the obstacle according to the average reaction level;

[0089] Step S304: Add the first detection straight-line distance and the reaction operation distance to obtain a second detection straight-line distance, and use the second detection straight-line distance as the obstacle detection distance.

[0090] In this embodiment, the reaction operation distance is represented by the driving distance of the vehicle from the time when the driver discovers the obstacle to the time when the driver performs the operation reaction.

[0091] The beneficial effects of the above technical solution are: determining the population attributes of the driver based on the approximate age information of the driver, obtaining the average vision level and average reaction level of the driver, thereby determining the obstacle detection distance, and being able to set a safer obstacle detection distance based on the age information, ensuring driving safety and sufficient reaction time for the driver, thereby improving safety.

[0092] In one embodiment, the intelligent model performs intelligent calculation based on obstacle information to determine the obstacle avoidance trajectory of the target vehicle for each obstacle, including:

[0093] Determine the obstacle type and specification as well as the distribution boundary information of the obstacle on the driving road according to the obstacle information;

[0094] Determine multiple obstacle avoidance path starting points and multiple obstacle avoidance path ending points according to obstacle types and specifications;

[0095] Obtain the tonnage information and vehicle length parameters of the target vehicle, and input the tonnage information and vehicle length parameters as well as multiple obstacle avoidance path starting points and multiple obstacle avoidance path ending points into the intelligent model for intelligent calculation;

[0096] The model output results are used to obtain multiple obstacle avoidance trajectories of the target vehicle for each obstacle.

[0097] The beneficial effects of the above technical solution are: determining the obstacle type and specification as well as the distribution boundary information of the obstacle on the driving road based on the obstacle information, thereby determining multiple obstacle avoidance path starting points and multiple obstacle avoidance path end points, and combining the tonnage information and vehicle length parameters of the target vehicle to obtain multiple obstacle avoidance trajectories of the target vehicle for each obstacle, which allows the autonomous driving system to have a more comprehensive understanding of the surrounding environment, thereby more accurately considering various possible obstacle avoidance strategies during path planning, thereby improving the accuracy of the planned path.

[0098] In one embodiment, the method of determining the time point and position point of deceleration and turning of the target vehicle passing each obstacle according to the obstacle avoidance trajectory and the braking parameters of the target vehicle and issuing an intelligent reminder includes:

[0099] Determine the standard braking parameters corresponding to the obstacle avoidance trajectory and the respective time and position points of initial deceleration and turning;

[0100] calculating a braking parameter ratio of a standard braking parameter to a braking parameter of a target vehicle, and determining a braking distance ratio according to the braking parameter ratio;

[0101] Determine the time and position of the target vehicle's deceleration and turning when passing each obstacle according to the braking distance ratio;

[0102] Obtain the reminder method selected by the driver, and issue an intelligent obstacle avoidance reminder to the driver according to the reminder method; the reminder method includes: voice reminder and image reminder.

[0103] The beneficial effects of the above technical solution are: determining the time points and position points of the target vehicle's deceleration and turning when passing each obstacle based on the obstacle avoidance trajectory and the braking parameters of the target vehicle and issuing intelligent reminders, which can ensure that the driver can perceive the deceleration and turning conditions for each obstacle during driving, thereby improving driving stability and the obstacle avoidance success rate and efficiency.

[0104] In one embodiment, it further includes:

[0105] Detect the degree of overlap between the driver's real-time obstacle avoidance path and the planned trajectory for each obstacle;

[0106] Determine the driver's obstacle avoidance experience index based on the overlap degree, and determine whether it is necessary to continue generating a planned obstacle avoidance trajectory for subsequent obstacles based on the obstacle avoidance experience index;

[0107] If not, all obstacle detection media of the target vehicle are activated and all-round obstacle detection is performed through the obstacle detection media.

[0108] The beneficial effects of the above technical solution are: determining the driver's obstacle avoidance experience index based on the degree of overlap between the driver's real-time obstacle avoidance path and the planned trajectory for each obstacle, judging whether it is necessary to generate a planned obstacle avoidance trajectory for the obstacle, thereby performing all-round obstacle detection through an obstacle detection medium, which can enhance intelligent driving assistance and, at the same time, provide a more comprehensive field of view, effectively avoiding accidents caused by the driver's lack of concentration during driving, and greatly improving driving comfort.

[0109] In this embodiment, the degree of overlap between the driver's real-time obstacle avoidance path and the planned trajectory for each obstacle is detected, and the driver's obstacle avoidance experience index is determined according to the degree of overlap, including:

[0110] Detect the wheel trajectory when the driver operates to avoid each obstacle, and determine the driver's real-time obstacle avoidance path for each obstacle based on the wheel trajectory;

[0111] Determine the corresponding point of the key operation in the planned trajectory of each obstacle, and obtain the standard wheel posture parameter and the adjustable wheel posture parameter range at each point;

[0112] Determine the operation weight of each point, and construct the vehicle's obstacle avoidance excitation function for each obstacle based on the operation weight of each point and the standard wheel posture parameter and adjustable wheel posture parameter range of the point;

[0113] Compare the driver's real-time obstacle avoidance path for each obstacle with the planned trajectory of the obstacle to determine the path intersection at each point;

[0114] According to the path intersection of each point, the current wheel posture parameter range of the vehicle when passing each point is predicted;

[0115] Input the current wheel posture parameter interval of the vehicle when passing each point into the obstacle avoidance incentive function to obtain the obstacle avoidance incentive value;

[0116] Calculate the median value of the obstacle avoidance incentive value, and determine the average obstacle avoidance quality index of the driver for the obstacle according to the median value;

[0117] The driver's obstacle avoidance experience index is determined based on the driver's average obstacle avoidance quality index for obstacles according to a preset quality index-experience index mapping table.

[0118] The beneficial effects of the above technical solution are: by determining the key nodes of the obstacle avoidance trajectory of each obstacle and then obtaining standard wheel rotation information, the driver's obstacle avoidance experience index can be evaluated by combining the driver's actual operation wheel rotation information. The rationality of the driver's operating parameters can be evaluated from the key operation index of the obstacle avoidance trajectory to determine whether he has qualified obstacle avoidance experience, thereby ensuring the accuracy and objectivity of the evaluation results.

[0119] In one embodiment, the inputting of tonnage information and vehicle length parameters as well as multiple obstacle avoidance path starting points and multiple obstacle avoidance path ending points into the intelligent model for intelligent calculation includes:

[0120] Input the tonnage information and vehicle length parameters into the intelligent model to calculate the safe lane change distance parameters of the target vehicle;

[0121] Selecting a matching point from a plurality of obstacle avoidance path starting points and a plurality of obstacle avoidance path ending points according to a safe lane change distance parameter;

[0122] The obstacle avoidance trajectory of the starting point and the end point of the obstacle avoidance path is constructed according to the matching points and the safe lane change distance parameters.

[0123] The beneficial effects of the above technical solution are: obtaining the safe lane change distance parameters of the target vehicle according to the tonnage information and the vehicle length parameters, thereby selecting matching points from multiple obstacle avoidance path starting points and multiple obstacle avoidance path end points, and constructing obstacle avoidance trajectories of the obstacle avoidance path starting points and the obstacle avoidance path end points, which can effectively avoid collisions between autonomous vehicles and other objects, reduce the probability of traffic accidents, and thus improve the safety of vehicles and passengers. At the same time, obstacle avoidance trajectories can be automatically generated according to real-time environmental information, reducing the need for manual intervention, reducing the risk of human operating errors, and improving the degree of intelligent driving.

[0124] In one embodiment, determining the reaction operation distance to the obstacle according to the average reaction level includes:

[0125] Determine the average time parameters for the driver to recognize obstacles and take reaction actions based on the average reaction level;

[0126] Obtain standard braking speed according to the planned driving plan;

[0127] The driver's reaction operation distance when responding to an obstacle is calculated based on the standard braking speed and the average time parameters for the driver to know the obstacle and perform reaction operations.

[0128] The beneficial effect of the above technical solution is: based on the standard braking speed and the average time parameters of the driver's reaction operation, the reaction operation distance of the driver when responding to an obstacle is calculated, which can help the driver to determine the reaction operation distance in time, avoid collision with obstacles, and improve driving safety.

[0129] In one embodiment, this embodiment also discloses a vehicle intelligent obstacle avoidance system, such as Figure 4 As shown, the system includes:

[0130] A generation module 401 is used to obtain a planned moving trajectory of a target vehicle and generate a planned driving plan according to the planned moving trajectory;

[0131] A detection module 402, for detecting the braking parameters of the target vehicle and obstacle information on the driving path based on the planned driving plan;

[0132] The determination module 403 is used to perform intelligent calculation based on the obstacle information through the intelligent model to determine the obstacle avoidance trajectory of the target vehicle for each obstacle;

[0133] The reminder module 404 is used to determine the time point and position point of deceleration and turning of the target vehicle passing each obstacle according to the obstacle avoidance trajectory and the braking parameters of the target vehicle and issue an intelligent reminder.

[0134] The working principle and beneficial effects of the above technical solution have been explained in the method embodiment and will not be repeated here.

[0135] Other embodiments of the present disclosure will be readily apparent to those skilled in the art after considering the specification and practicing the disclosure disclosed herein. This application is intended to cover any variations, uses, or adaptations of the present disclosure that follow the general principles of the present disclosure and include common knowledge or customary techniques in the art that are not disclosed in the present disclosure. The specification and examples are to be considered exemplary only, and the true scope and spirit of the present disclosure are indicated by the following claims.

[0136] It should be understood that the present disclosure is not limited to the exact structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.

Claims

1. A vehicle intelligent obstacle avoidance method, characterized in that: The following steps are involved: Obtain the planned trajectory of the target vehicle, and generate a planned driving plan based on the planned trajectory; Detect the braking parameters of the target vehicle and the obstacle information on the driving path based on the planned driving plan; The intelligent model performs intelligent calculations based on obstacle information to determine the target vehicle's obstacle avoidance trajectory for each obstacle; According to the obstacle avoidance trajectory and the braking parameters of the target vehicle, the time and position points of deceleration and turning of the target vehicle passing each obstacle are determined and intelligent reminders are issued.

2. The vehicle intelligent obstacle avoidance method according to claim 1, characterized in that: The step of obtaining the planned moving trajectory of the target vehicle and generating a planned driving plan according to the planned moving trajectory includes: Determine the departure and destination information of the target vehicle, and generate multiple driving routes based on the departure and destination information; Obtaining a target path selected by a user from multiple driving paths as a planned driving path, and determining a planned travel trajectory of the target vehicle according to the path characteristics of the planned driving path; Determine the planned driving road information according to the planned travel trajectory, and determine multiple road attributes according to the planned driving road information; Based on a plurality of road attributes, stage recommended speed information on the planned driving road is determined, and a planned driving plan is generated according to the stage recommended speed information.

3. The vehicle intelligent obstacle avoidance method according to claim 1, characterized in that: The detecting the braking parameters of the target vehicle and the obstacle information on the driving path based on the planned driving plan includes: The braking speed of the target vehicle is detected by a speed sensor and a curve of the braking speed changing with time is constructed; Obtain the age information of the driver of the target vehicle and set the straight-line distance for obstacle detection based on the age information; Determine the obstacle detection medium according to the obstacle detection straight-line distance, and collect road data through the obstacle detection medium; The collected data is input into the deep learning neural network model to determine the various obstacle types and specific parameters on the driving path.

4. The vehicle intelligent obstacle avoidance method according to claim 3, characterized in that: The step of obtaining the age information of the driver of the target vehicle and setting the obstacle detection straight-line distance according to the age information includes: Collecting the facial image of the driver, predicting the approximate age information of the driver based on the facial image, and determining the population attribute of the driver based on the approximate age information; Determine the average vision level and average reaction level of drivers according to the population attributes of drivers; Determine a first detection straight-line distance of the obstacle according to the average vision level, and determine a reaction operation distance for the obstacle according to the average reaction level; The first detection straight-line distance and the reaction operation distance are added to obtain a second detection straight-line distance, and the second detection straight-line distance is used as the obstacle detection distance.

5. The vehicle intelligent obstacle avoidance method according to claim 1, characterized in that: The intelligent model performs intelligent calculation based on obstacle information to determine the obstacle avoidance trajectory of the target vehicle for each obstacle, including: Determine the obstacle type and specification as well as the distribution boundary information of the obstacle on the driving road according to the obstacle information; Determine multiple obstacle avoidance path starting points and multiple obstacle avoidance path ending points according to obstacle types and specifications; Obtain the tonnage information and vehicle length parameters of the target vehicle, and input the tonnage information and vehicle length parameters as well as multiple obstacle avoidance path starting points and multiple obstacle avoidance path ending points into the intelligent model for intelligent calculation; The model output results are used to obtain multiple obstacle avoidance trajectories of the target vehicle for each obstacle.

6. The vehicle intelligent obstacle avoidance method according to claim 1, characterized in that: The method of determining the respective time points and positions of the deceleration and turning of the target vehicle passing each obstacle according to the obstacle avoidance trajectory and the braking parameters of the target vehicle and issuing an intelligent reminder includes: Determine the standard braking parameters corresponding to the obstacle avoidance trajectory and the respective time and position points of initial deceleration and turning; calculating a braking parameter ratio of a standard braking parameter to a braking parameter of a target vehicle, and determining a braking distance ratio according to the braking parameter ratio; Determine the time and position of the target vehicle's deceleration and turning when passing each obstacle according to the braking distance ratio; Obtain the reminder method selected by the driver, and issue an intelligent obstacle avoidance reminder to the driver according to the reminder method; the reminder method includes: voice reminder and image reminder.

7. The vehicle intelligent obstacle avoidance method according to claim 1, characterized in that: Also includes: Detect the degree of overlap between the driver's real-time obstacle avoidance path and the planned trajectory for each obstacle; Determine the driver's obstacle avoidance experience index based on the overlap degree, and determine whether it is necessary to continue generating a planned obstacle avoidance trajectory for subsequent obstacles based on the obstacle avoidance experience index; If not, all obstacle detection media of the target vehicle are activated and all-round obstacle detection is performed through the obstacle detection media.

8. The vehicle intelligent obstacle avoidance method according to claim 5, characterized in that: The tonnage information and vehicle length parameters as well as multiple obstacle avoidance path starting points and multiple obstacle avoidance path ending points are input into the intelligent model for intelligent calculation, including: Input the tonnage information and vehicle length parameters into the intelligent model to calculate the safe lane change distance parameters of the target vehicle; Selecting a matching point from a plurality of obstacle avoidance path starting points and a plurality of obstacle avoidance path ending points according to a safe lane change distance parameter; The obstacle avoidance trajectory of the starting point and the end point of the obstacle avoidance path is constructed according to the matching points and the safe lane change distance parameters.

9. The vehicle intelligent obstacle avoidance method according to claim 4, characterized in that: The step of determining the reaction operation distance to the obstacle according to the average reaction level includes: Determine the average time parameters for the driver to recognize obstacles and take reaction actions based on the average reaction level; Obtain standard braking speed according to the planned driving plan; The driver's reaction operation distance when responding to an obstacle is calculated based on the standard braking speed and the average time parameters for the driver to know the obstacle and perform reaction operations.

10. A vehicle intelligent obstacle avoidance system, characterized in that: The system includes: A generation module is used to obtain the planned trajectory of the target vehicle and generate a planned driving plan according to the planned trajectory; A detection module, used to detect the braking parameters of the target vehicle and obstacle information on the driving path based on the planned driving plan; A determination module is used to perform intelligent calculations based on obstacle information through an intelligent model to determine the obstacle avoidance trajectory of the target vehicle for each obstacle; The reminder module is used to determine the time and position points of the target vehicle's deceleration and turning when passing each obstacle based on the obstacle avoidance trajectory and the target vehicle's braking parameters, and issue an intelligent reminder.

Images