An artificial intelligence-assisted intelligent decision support system and method

Abstract

This invention discloses an artificial intelligence-assisted intelligent decision support system and method, relating to the field of data analysis. It includes: a data acquisition module for collecting information on the vehicle's current driving road and driving status, storing and updating this information in real time; and an analysis module for editing the vehicle's current driving road information stored in the acquisition module in real time, and analyzing whether the vehicle's current driving road meets the conditions for obstacle avoidance based on the vehicle's current driving road and driving status information. This invention, through data acquisition and analysis, accurately determines whether the vehicle's current driving road meets the conditions for obstacle avoidance. In the evaluation phase, it comprehensively considers multiple factors to assess the safety of obstacle avoidance and collision safety, and formulates reasonable decision-making strategies based on different evaluation results, providing appropriate handling methods for vehicles facing obstacles.

Description

Technical Field

[0001] This invention relates to the field of data analysis technology, specifically to an artificial intelligence-assisted intelligent decision support system and method. Background Technology

[0002] Automatic obstacle avoidance technology is an advanced intelligent driving technology. It uses sensors to perceive the surrounding environment, such as cameras to identify obstacles and radar to measure distances. Then, it analyzes the data in real time through algorithms. When a danger is detected, the automatic control system will adjust the vehicle's direction and speed in a timely manner to avoid collisions and ensure driving safety.

[0003] Patent application No. 201811630368.0 discloses an obstacle avoidance method for autonomous vehicles. The method includes: acquiring the yaw angle change and turning radius of the autonomous vehicle; determining the position change information of the autonomous vehicle based on the yaw angle change and turning radius, the position change information including lateral position change information and longitudinal position change information; determining the future driving trajectory of the autonomous vehicle based on the position change information; acquiring the relative position change information between the obstacle and the autonomous vehicle using the autonomous vehicle's perception module; determining the speed and direction of movement of the obstacle based on the relative position change information and the obstacle's movement time; determining the future trajectory of the obstacle based on the speed and direction of movement; calculating the collision position and collision time between the autonomous vehicle and the obstacle based on the future driving trajectory of the autonomous vehicle and the future trajectory of the obstacle; calculating the avoidance start time of the autonomous vehicle based on the collision position and collision time; and when the avoidance start time is reached, the autonomous vehicle decelerates to avoid the obstacle. This application aims to provide an effective obstacle avoidance method for autonomous vehicles.

[0004] However, most existing automatic obstacle avoidance technologies focus on obstacle avoidance sensitivity and obstacle detection accuracy. Due to the different properties of obstacles, there are many cases where the harm caused by colliding with an obstacle is lower than the harm caused by avoiding an obstacle, but the decision result of existing technologies is to avoid obstacles.

[0005] To address this, an AI-assisted intelligent decision support system and method are proposed. Summary of the Invention

[0006] In view of the above-mentioned shortcomings of the existing technology, the present invention provides an artificial intelligence-assisted intelligent decision support system and method, which can effectively solve the problems of the existing technology.

[0007] To achieve the above objectives, the present invention is implemented through the following technical solutions;

[0008] This invention discloses an artificial intelligence-assisted intelligent decision support system, comprising:

[0009] The system comprises three modules: a data acquisition module, an analysis module, and an interaction module. The data acquisition module collects information about the vehicle's current road and driving status, storing and updating this information in real time. The analysis module edits the stored information about the vehicle's current road and driving status in real time, analyzing whether the road conditions allow for obstacle avoidance. The evaluation module receives the stored information about the vehicle's driving status and evaluates the safety levels for obstacle avoidance and collision. The decision-making module receives the evaluation results for obstacle avoidance and collision, and decides on the appropriate obstacle handling method based on these results. The message module receives the output data from the analysis, evaluation, and decision modules, summarizes the output data to generate a message, and submits it to the interaction module. The interaction module receives the messages from the message module and stores the message content. Users on the system end can retrieve the stored messages in the interaction module and iterate through or download them.

[0010] Furthermore, the acquisition module is equipped with a camera module and a sensing unit at its lower level. The camera module is used to acquire image data of the vehicle's direction of travel, and the sensing unit is used to sense the vehicle speed and obstacle parameter information in the direction of travel.

[0011] The image data of the vehicle's direction of travel collected by the camera module is the current road information of the vehicle collected by the acquisition module, and the vehicle speed and obstacle parameter information of the direction of travel sensed by the perception unit is the vehicle's driving status information.

[0012] The obstacle parameter information includes obstacle images, distance between the obstacle and the vehicle, and obstacle specifications. When the acquisition module stores the current road information and vehicle driving status information, it simultaneously sets the information storage time interval. The information storage time interval is dynamically adjusted based on the vehicle speed, so that the information storage time interval follows the rule that the faster the vehicle speed, the shorter the information storage time interval, and vice versa. The information stored is updated based on the information storage time interval, so that the stored information is always the latest information collected that conforms to the information storage time interval.

[0013] Furthermore, the analysis logic in the analysis module for determining whether the vehicle's current driving road has the conditions for avoidance is expressed as follows:

[0014] Longitudinal avoidance judgment:

[0015] Lateral avoidance judgment:

[0016] Left-turning condition: When the lateral space on the left is greater than the critical turning radius and less than the lane width, the vehicle is deemed to be able to safely turn to the left to avoid the obstacle.

[0017] Right-hand turning conditions: When the lateral space on the right is greater than the critical turning radius and less than the lane width, the vehicle may safely turn to the right to avoid the obstacle.

[0018] In the formula: L is the longitudinal distance to the obstacle ahead; v is the current speed of the vehicle; t r 'a' represents the reaction time; 'a' represents the braking deceleration.

[0019] The parameters used in longitudinal and lateral obstacle avoidance judgments are derived from the vehicle's current road information and vehicle driving status information, with a reaction time t. r Defined by the system user;

[0020] If the formula for longitudinal obstacle avoidance is true, and any one or more of the formulas for lateral obstacle avoidance are met, it indicates that the current road where the vehicle is traveling has the conditions for obstacle avoidance; otherwise, it indicates that the current road where the vehicle is traveling does not have the conditions for obstacle avoidance.

[0021] Furthermore, if the analysis module determines that the conditions for avoidance are met, it will switch to the evaluation module. If the analysis module determines that the conditions for avoidance are not met, the vehicle's onboard unit will issue a preset voice prompt and repeat it. At the same time as the voice prompt is broadcast, the vehicle will terminate the operation of the emergency avoidance function.

[0022] Furthermore, when the evaluation module evaluates the safety of avoidance and the safety of collision, it prioritizes the evaluation of the safety of collision.

[0023] The decision module sets decision thresholds for avoidance safety and collision safety. The collision safety is evaluated first in the evaluation module and then sent to the decision module. The decision module compares the collision safety with the corresponding decision threshold. When the evaluation result is greater than or equal to the decision threshold, the vehicle is controlled to collide with the obstacle, and the avoidance safety evaluation operation is no longer executed.

[0024] When the collision safety assessment result is less than the decision threshold, the avoidance safety is further assessed. When the avoidance safety assessment result is greater than or equal to the corresponding decision threshold, the vehicle is controlled to avoid the obstacle. When both safety assessment results are less than their corresponding decision thresholds, the processing method corresponding to the assessment result with the largest ratio to the corresponding decision threshold is selected, and the vehicle passes the obstacle.

[0025] The obstacle handling methods include: avoiding obstacles and colliding with obstacles.

[0026] Furthermore, the collision avoidance safety assessment logic in the assessment module is expressed as follows:

[0027]

[0028] In the formula: I represents the avoidance safety factor; X is a preset constant greater than one; D brake D is the vehicle braking distance; S is the distance between the obstacle and the vehicle; R is the maximum value of the obstacle's length, width, and height; B is the safety redundancy factor. type F represents the vehicle type coefficient; F represents the braking force; F max The theoretical maximum braking force of the vehicle's braking system; t min t is the ideal braking response time; h is the remaining brake pad thickness; H is the initial brake pad thickness; d is the brake disc wear depth; D′ is the maximum allowable wear depth of the brake disc.

[0029] in, Used to indicate the urgency level of avoidance. Used to represent vehicle braking performance coefficient, vehicle type coefficient B type The values ​​follow the following order: sedans 0.8-1, SUVs 0.7-0.9, trucks 0.3-0.6, buses 0.4-0.7. The larger the vehicle mass, the higher the vehicle type coefficient B. type The smaller the value.

[0030] Furthermore, the formula for calculating the safety redundancy factor R is as follows:

[0031] R = R road ×R traffic ×R weather ;

[0032] In the formula: R road R traffic R weather These are the road condition coefficient, traffic flow coefficient, and weather condition coefficient.

[0033] Among them, the road condition coefficient R road The values ​​are set as follows: 1.5-2 for highways, 1.2-1.5 for urban roads, and 1.3-1.6 for rural roads; Traffic flow coefficient R traffic The value follows: n is the number of vehicles passing through the road section containing the obstacle per unit time; weather condition coefficient R weather Value selection follows: Traffic management departments adjust road speed limits in real time based on weather conditions; the smaller the road speed limit, the higher the speed limit. weather The larger the value of R, the lower the value of R. weather The smaller the value.

[0034] Furthermore, the collision safety assessment logic in the assessment module is expressed as follows:

[0035]

[0036] Where: F is the collision safety level; D is the distance between the obstacle and the vehicle; V is the vehicle speed; ε is the impact resistance coefficient corresponding to the obstacle type identification result found in the preset obstacle type and impact resistance coefficient matching table after the obstacle type is identified based on the obstacle image and image recognition technology; τ is the size of the first contact surface between the obstacle and the vehicle during the collision, determined based on the obstacle specification parameters.

[0037] The obstacle type and impact resistance coefficient matching table is user-defined on the system side.

[0038] Furthermore, the acquisition module is connected to a camera module and a sensing unit via a wireless network, the acquisition module is connected to an analysis module via a wireless network, the analysis module is connected to an evaluation module and a decision module via a wireless network, and the decision module is connected to a message module and an interaction module via a wireless network.

[0039] On the other hand, an AI-assisted intelligent decision support method includes:

[0040] The system collects current road information and vehicle status information, stores and updates this information in real time. Based on the stored road and status information, it analyzes whether the vehicle has the conditions to avoid an obstacle. If the conditions are not met, the vehicle issues a preset voice prompt and simultaneously hands over control to a human. If the conditions are met, it assesses the safety of avoiding an obstacle and the safety of impact. Based on the assessment results, it decides on the obstacle handling method and drives over the obstacle. It analyzes the process data based on whether the conditions are met, and generates a message based on the assessment data and decision results for the safety of avoiding an obstacle and the safety of impact. The generated message is then recorded.

[0041] Compared with the known prior art, the technical solution provided by this invention has the following beneficial effects:

[0042] This invention provides an AI-assisted intelligent decision support system and method. During execution, this system and method can collect real-time information on the vehicle's driving road and driving status, and dynamically update this information based on vehicle speed to ensure data timeliness and accuracy. Through scientific analysis methods, it accurately determines whether the vehicle's current driving road conditions allow for obstacle avoidance. In the evaluation phase, it comprehensively considers multiple factors to assess the safety of obstacle avoidance and collision, and formulates reasonable decision-making strategies based on different evaluation results, providing appropriate handling methods for the vehicle when facing obstacles, effectively ensuring driving safety. Simultaneously, the system generates messages that users can retrieve, traverse, and download, facilitating subsequent viewing and analysis, and improving the intelligence and safety of vehicle driving decisions. Attached Figure Description

[0043] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0044] Figure 1 This is a schematic diagram of the structure of an artificial intelligence-assisted intelligent decision support system;

[0045] Figure 2 This is a flowchart illustrating an AI-assisted intelligent decision support method.

[0046] Figure 3 This is an example table of obstacle types and impact resistance coefficients. Detailed Implementation

[0047] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative effort are within the scope of protection of the present invention.

[0048] The present invention will be further described below with reference to embodiments.

[0049] Example 1:

[0050] This embodiment provides an artificial intelligence-assisted intelligent decision support system, such as... Figure 1 As shown, it includes:

[0051] The data acquisition module is used to collect information on the current road the vehicle is traveling on and the vehicle's driving status, and to store and update this information in real time.

[0052] The acquisition module is equipped with a camera module and a sensing unit. The camera module is used to acquire image data of the vehicle's direction of travel, and the sensing unit is used to sense the vehicle speed and obstacle parameter information in the direction of travel.

[0053] The image data of the vehicle's direction of travel collected by the camera module is the current road information of the vehicle collected by the acquisition module, and the vehicle speed and obstacle parameter information of the direction of travel sensed by the perception unit is the vehicle's driving status information.

[0054] The obstacle parameter information includes obstacle images, distance between the obstacle and the vehicle, and obstacle specifications. When the acquisition module stores the current road information and vehicle driving status information, it simultaneously sets the information storage time interval. The information storage time interval is dynamically adjusted based on the vehicle speed, so that the information storage time interval follows the rule that the faster the vehicle speed, the shorter the information storage time interval, and vice versa. The information stored is updated based on the information storage time interval, so that the stored information is always the latest information collected that conforms to the information storage time interval.

[0055] The analysis module is used to edit the vehicle's current driving road information stored in the acquisition module in real time, and analyze whether the vehicle's current driving road has the conditions for avoidance based on the vehicle's current driving road information and vehicle driving status information.

[0056] The analysis logic in the analysis module to determine whether the vehicle's current road conditions allow for avoidance is expressed as follows:

[0057] Longitudinal avoidance judgment:

[0058] Lateral avoidance judgment:

[0059] Left-turning condition: When the lateral space on the left is greater than the critical turning radius and less than the lane width, the vehicle is deemed to be able to safely turn to the left to avoid the obstacle.

[0060] Right-hand turning conditions: When the lateral space on the right is greater than the critical turning radius and less than the lane width, the vehicle may safely turn to the right to avoid the obstacle.

[0061] In the formula: L is the longitudinal distance to the obstacle ahead; v is the current speed of the vehicle; t r 'a' represents the reaction time; 'a' represents the braking deceleration.

[0062] The parameters used in longitudinal and lateral obstacle avoidance judgments are derived from the vehicle's current road information and vehicle driving status information, with a reaction time t. r Defined by the system user;

[0063] If the formula for longitudinal obstacle avoidance is true, and any one or more of the formulas for lateral obstacle avoidance are met, it indicates that the current road where the vehicle is traveling has the conditions for obstacle avoidance; otherwise, it indicates that the current road where the vehicle is traveling does not have the conditions for obstacle avoidance.

[0064] If the analysis module determines that the conditions for avoidance are met, the system will switch to the evaluation module. If the analysis module determines that the conditions for avoidance are not met, the vehicle's onboard unit will issue a preset voice prompt and repeat it. At the same time as the voice prompt is played, the vehicle will terminate the operation of the emergency avoidance function.

[0065] The evaluation module is used to receive vehicle driving status information stored in the acquisition module and evaluate the avoidance safety and collision safety based on the vehicle driving status information.

[0066] When the assessment module evaluates avoidance safety and collision safety, it prioritizes assessing collision safety.

[0067] The decision module sets decision thresholds for avoidance safety and collision safety. The collision safety is evaluated first in the evaluation module and then sent to the decision module. The decision module compares the collision safety with the corresponding decision threshold. If the evaluation result is greater than or equal to the decision threshold, the vehicle is controlled to collide with the obstacle, and the avoidance safety evaluation operation is no longer executed.

[0068] When the collision safety assessment result is less than the decision threshold, the avoidance safety is further assessed. When the avoidance safety assessment result is greater than or equal to the corresponding decision threshold, the vehicle is controlled to avoid the obstacle. When both safety assessment results are less than their corresponding decision thresholds, the processing method corresponding to the assessment result with the largest ratio to the corresponding decision threshold is selected, and the vehicle passes the obstacle.

[0069] The obstacle handling methods include: avoiding obstacles and colliding with obstacles;

[0070] The collision safety assessment logic in the assessment module is expressed as follows:

[0071]

[0072] In the formula: I represents the avoidance safety factor; X is a preset constant greater than one; D brake D is the vehicle braking distance; S is the distance between the obstacle and the vehicle; R is the maximum value of the obstacle's length, width, and height; B is the safety redundancy factor. type F represents the vehicle type coefficient; F represents the braking force; F max The theoretical maximum braking force of the vehicle's braking system; t min t is the ideal braking response time; h is the remaining brake pad thickness; H is the initial brake pad thickness; d is the brake disc wear depth; D′ is the maximum allowable wear depth of the brake disc.

[0073] in, Used to indicate the urgency level of avoidance. Used to represent vehicle braking performance coefficient, vehicle type coefficient B type The values ​​follow the following order: sedans 0.8-1, SUVs 0.7-0.9, trucks 0.3-0.6, buses 0.4-0.7. The larger the vehicle mass, the higher the vehicle type coefficient B. type The smaller the value;

[0074] The formula for calculating the safety redundancy factor R is:

[0075] R = R road ×R traffic ×R weather ;

[0076] In the formula: R road R traffic R weather These are the road condition coefficient, traffic flow coefficient, and weather condition coefficient.

[0077] Among them, the road condition coefficient R road The values ​​are set as follows: 1.5-2 for highways, 1.2-1.5 for urban roads, and 1.3-1.6 for rural roads; Traffic flow coefficient R traffic The value follows: n is the number of vehicles passing through the road section containing the obstacle per unit time; weather condition coefficient R weather Value selection follows: Traffic management departments adjust road speed limits in real time based on weather conditions; the smaller the road speed limit, the higher the speed limit. weather The larger the value of R, the lower the value of R. weather The smaller the value;

[0078] The collision safety assessment logic in the assessment module is represented as follows:

[0079]

[0080] Where: F is the collision safety level; D is the distance between the obstacle and the vehicle; V is the vehicle speed; ε is the impact resistance coefficient corresponding to the obstacle type identification result found in the preset obstacle type and impact resistance coefficient matching table after the obstacle type is identified based on the obstacle image and image recognition technology; τ is the size of the first contact surface between the obstacle and the vehicle during the collision, determined based on the obstacle specification parameters.

[0081] Among them, the obstacle type and impact resistance coefficient matching table is defined by the system user;

[0082] The above logical formula defines the evaluation logic for avoidance safety and collision safety, providing necessary and effective support for the decisions made by the decision-making module in this embodiment.

[0083] The decision-making module receives the obstacle avoidance safety and collision safety assessment results from the evaluation module and makes decisions on how to handle obstacles based on the assessment results.

[0084] The message module is used to receive the operational output data from the analysis module, evaluation module, and decision-making module, summarize the operational output data from the three modules to generate a message, and submit it to the interaction module.

[0085] The interaction module is used to receive messages from the message module and store the message content.

[0086] In this system, users retrieve stored messages in the interaction module and traverse or download the messages.

[0087] The acquisition module is connected to a camera module and a sensing unit via a wireless network. The acquisition module is also connected to an analysis module via a wireless network. The analysis module is connected to an evaluation module and a decision-making module via a wireless network. The decision-making module is connected to a message module and an interaction module via a wireless network.

[0088] In this embodiment, the acquisition module collects information on the vehicle's current road and driving status, stores and updates this information in real time. The camera module simultaneously collects image data of the vehicle's direction of travel. The perception unit senses the vehicle's speed and obstacle parameters in the direction of travel in real time. The analysis module, running in the background, edits the vehicle's current road information stored in the acquisition module in real time. Based on the current road and driving status information, it analyzes whether the current road provides avoidance conditions. The evaluation module receives the vehicle's driving status information stored in the acquisition module and evaluates the avoidance safety and collision safety based on this information. The decision module further receives the avoidance safety and collision safety evaluation results from the evaluation module, decides on the obstacle handling method based on the evaluation results, and receives the operational output data from the analysis, evaluation, and decision modules through the message module. It then summarizes the three operational output data to generate a message and submits it to the interaction module. Finally, the interaction module receives the message feedback from the message module and stores the message content.

[0089] Through the operation of the system in the above embodiments, the automatic obstacle avoidance function of the vehicle is further assisted, so that when the vehicle uses the automatic obstacle avoidance function, it makes adaptive decisions based on the analysis of collected information. When conditions permit, it does not avoid the obstacle but directly collides with and drives over the obstacle, so as to achieve the result that the damage caused by colliding with the obstacle is less than the damage caused by avoiding the obstacle.

[0090] Example 2:

[0091] At the implementation level, based on Example 1, this example refers to... Figure 2 A further detailed description of the AI-assisted intelligent decision support system in Example 1 is provided below:

[0092] An AI-assisted intelligent decision support method includes:

[0093] Step 1: Collect information on the current road the vehicle is traveling on and the vehicle's driving status, store the information on the road the vehicle is traveling on and update it in real time;

[0094] Step 2: Analyze whether the vehicle has the conditions to avoid a collision based on the stored road information and driving status information;

[0095] Step 3: If avoidance is not possible, the vehicle will issue a preset voice prompt and simultaneously hand over control to a human. Once avoidance is possible, assess the safety of avoidance and the safety of a collision.

[0096] Step 4: Based on the assessment results of avoidance safety and collision safety, decide on the obstacle handling method, and drive over the obstacle based on the decision results;

[0097] Step 5: Analyze the process data based on whether the avoidance conditions are met, and generate a message based on the process data and decision results of the avoidance safety degree and collision safety degree assessment.

[0098] Step 6: Record the generated message.

[0099] In summary, the system and method described in the above embodiments can collect real-time information on the vehicle's driving road and driving status, and dynamically update this information based on vehicle speed, ensuring the timeliness and accuracy of the data. Through scientific analysis methods, it accurately determines whether the vehicle's current driving road conditions allow for obstacle avoidance. In the evaluation phase, it comprehensively considers multiple factors to assess the safety of obstacle avoidance and collision, and formulates reasonable decision-making strategies based on different evaluation results, providing appropriate handling methods for vehicles facing obstacles and effectively ensuring driving safety. Simultaneously, the messages generated by the system can be retrieved, traversed, and downloaded by the user, facilitating subsequent viewing and analysis, and improving the intelligence and safety of vehicle driving decisions.

[0100] The above embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions will not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. An artificial intelligence-assisted intelligent decision support system, characterized in that, include: The data acquisition module is used to collect information on the current road the vehicle is traveling on and the vehicle's driving status, and to store and update this information in real time. The analysis module is used to edit the vehicle's current driving road information stored in the acquisition module in real time, and analyze whether the vehicle's current driving road has the conditions for avoidance based on the vehicle's current driving road information and vehicle driving status information. The evaluation module is used to receive vehicle driving status information stored in the acquisition module and evaluate the avoidance safety and collision safety based on the vehicle driving status information. The decision-making module receives the obstacle avoidance safety and collision safety assessment results from the evaluation module and makes decisions on how to handle obstacles based on the assessment results. The message module is used to receive the operational output data from the analysis module, evaluation module, and decision-making module, summarize the operational output data from the three modules to generate a message, and submit it to the interaction module. The interaction module is used to receive messages from the message module and store the message content. In this system, users retrieve stored messages in the interaction module and traverse or download the messages. The collision safety assessment logic in the assessment module is expressed as follows: ； In the formula: To avoid compromising safety; This is a preset constant greater than one; This refers to the vehicle's braking distance. The distance between the obstacle and the vehicle; The maximum values ​​of the obstacle's length, width, and height; This is the safety redundancy factor; Vehicle type coefficient; For braking force; This represents the theoretical maximum braking force of the vehicle's braking system. Ideal braking response time; Braking response time; This refers to the remaining thickness of the brake pads. This refers to the initial thickness of the brake pads. This refers to the wear depth of the brake disc. This refers to the maximum allowable wear depth of the brake disc. in, Used to indicate the urgency level of avoidance. Used to represent vehicle braking performance coefficient, vehicle type coefficient The values ​​follow the following order: sedans 0.8-1, SUVs 0.7-0.9, trucks 0.3-0.6, buses 0.4-0.

7. The larger the vehicle mass, the higher the vehicle type coefficient. The smaller the value; The safety redundancy coefficient The calculation formula is: ； In the formula: These are the road condition coefficient, traffic flow coefficient, and weather condition coefficient. Among them, road condition coefficient The values ​​follow the following order: highways: 1.5 - 2; urban roads: 1.2 - 1.5; rural roads: 1.3 - 1.6; traffic flow coefficient. The value follows: , where n is the number of vehicles passing through the road section containing the obstacle per unit time; weather condition coefficient. The speed limit is determined by the traffic management department's real-time adjustment of road speed limits based on weather conditions; the lower the speed limit, the better. The larger the value, the lower the value. The smaller the value.

2. The AI-assisted intelligent decision support system according to claim 1, characterized in that, The acquisition module is equipped with a camera module and a sensing unit. The camera module is used to acquire image data of the vehicle's direction of travel, and the sensing unit is used to sense the vehicle speed and obstacle parameter information in the direction of travel. The image data of the vehicle's direction of travel collected by the camera module is the current road information of the vehicle collected by the acquisition module, and the vehicle speed and obstacle parameter information of the direction of travel sensed by the perception unit is the vehicle's driving status information. The obstacle parameter information includes obstacle images, distance between the obstacle and the vehicle, and obstacle specifications. When the acquisition module stores the current road information and vehicle driving status information, it simultaneously sets the information storage time interval. The information storage time interval is dynamically adjusted based on the vehicle speed, so that the information storage time interval follows the rule that the faster the vehicle speed, the shorter the information storage time interval, and vice versa. The information stored is updated based on the information storage time interval, so that the stored information is always the latest information collected that conforms to the information storage time interval.

3. The artificial intelligence-assisted intelligent decision support system according to claim 1, characterized in that, The analysis logic for determining whether the vehicle's current road conditions allow for avoidance in the analysis module is expressed as follows: Longitudinal avoidance judgment: ; Lateral avoidance judgment: Left-turning condition: When the lateral space on the left is greater than the critical turning radius and less than the lane width, the vehicle is deemed to be able to safely turn to the left to avoid the obstacle. Right-hand turning conditions: When the lateral space on the right is greater than the critical turning radius and less than the lane width, the vehicle may safely turn to the right to avoid the obstacle. In the formula: This refers to the longitudinal distance to the obstacle in front. The vehicle's current speed; Reaction time; For braking deceleration; The parameters used in longitudinal and lateral obstacle avoidance judgments are derived from the vehicle's current road information and vehicle driving status information, and the reaction time... Defined by the system user; If the formula for longitudinal obstacle avoidance is true, and any one or more of the formulas for lateral obstacle avoidance are met, it indicates that the current road where the vehicle is traveling has the conditions for obstacle avoidance; otherwise, it indicates that the current road where the vehicle is traveling does not have the conditions for obstacle avoidance.

4. The artificial intelligence-assisted intelligent decision support system according to claim 1, characterized in that, When the analysis module determines that the conditions for avoidance are met, it jumps to the evaluation module. When the analysis module determines that the conditions for avoidance are not met, the vehicle's onboard unit issues a preset voice prompt and repeats it. At the same time as the voice prompt is broadcast, the vehicle terminates the operation of the emergency avoidance function.

5. The artificial intelligence-assisted intelligent decision support system according to claim 1, characterized in that, When the evaluation module evaluates the safety of avoidance and the safety of collision, it prioritizes the evaluation of the safety of collision. The decision module sets decision thresholds for avoidance safety and collision safety. The collision safety is evaluated first in the evaluation module and then sent to the decision module. The decision module compares the collision safety with the corresponding decision threshold. When the evaluation result is greater than or equal to the decision threshold, the vehicle is controlled to collide with the obstacle, and the avoidance safety evaluation operation is no longer executed. When the collision safety assessment result is less than the decision threshold, the avoidance safety is further assessed. When the avoidance safety assessment result is greater than or equal to the corresponding decision threshold, the vehicle is controlled to avoid the obstacle. When both safety assessment results are less than their corresponding decision thresholds, the processing method corresponding to the assessment result with the largest ratio to the corresponding decision threshold is selected, and the vehicle passes the obstacle. The obstacle handling methods include: avoiding obstacles and colliding with obstacles.

6. The artificial intelligence-assisted intelligent decision support system according to claim 1, characterized in that, The collision safety assessment logic in the assessment module is expressed as follows: ； In the formula: For collision safety; The distance between the obstacle and the vehicle; Vehicle speed; After identifying obstacle types based on obstacle images and image recognition technology, the corresponding impact resistance coefficient is retrieved from a preset obstacle type and impact resistance coefficient matching table. The size of the first contact surface between the obstacle and the vehicle during a collision, determined based on the obstacle's specifications. The obstacle type and impact resistance coefficient matching table is user-defined on the system side.

7. The artificial intelligence-assisted intelligent decision support system according to claim 1, characterized in that, The acquisition module is connected to a camera module and a sensing unit via a wireless network. The acquisition module is also connected to an analysis module via a wireless network. The analysis module is connected to an evaluation module and a decision module via a wireless network. The decision module is connected to a message module and an interaction module via a wireless network.

8. An artificial intelligence-assisted intelligent decision support method, wherein the method is an implementation method of an artificial intelligence-assisted intelligent decision support system as described in any one of claims 1-7, characterized in that, include: Step 1: Collect information on the current road the vehicle is traveling on and the vehicle's driving status, store the information on the road the vehicle is traveling on and update it in real time; Step 2: Analyze whether the vehicle has the conditions to avoid a collision based on the stored road information and driving status information; Step 3: If avoidance is not possible, the vehicle will issue a preset voice prompt and simultaneously hand over control to a human. Once avoidance is possible, assess the safety of avoidance and the safety of a collision. Step 4: Based on the assessment results of avoidance safety and collision safety, decide on the obstacle handling method, and drive over the obstacle based on the decision results; Step 5: Analyze the process data based on whether the avoidance conditions are met, and generate a message based on the process data and decision results of the avoidance safety degree and collision safety degree assessment. Step 6: Record the generated message.

Images