A control method and system for unmanned vehicles based on artificial intelligence

Abstract

The present invention is applicable to the technical field of path control and experience optimization of unmanned vehicles, and provides a control method and system for unmanned vehicles based on artificial intelligence, the method comprising: continuously collecting local driving data corresponding to road conditions that have undergone path convergence changes while the unmanned vehicle is carrying the current passengers on a tour. The present invention achieves dynamic optimization of the path selection score of unmanned vehicles by constructing a scoring correction mechanism based on the correlation trend between the convergence strength of the path structure and the passenger experience response. The present invention, for the first time, introduces the decrease in the subjective experience index of individual passengers during the path convergence change process as a correction basis, and combines the changing trend of the value of scenic spot tours to construct a weighted adjustment model for the score value, which can identify the sensitive structure of "the more intense the convergence, the worse the experience", thereby making corrections to the score results that are more in line with actual perception.

Description

Technical Field

[0001] The present invention belongs to the technical field of unmanned vehicle path control and experience optimization, and in particular relates to a control method and system for an unmanned vehicle based on artificial intelligence. Background Art

[0002] Current autonomous vehicle path planning technologies generally use static map data, real-time traffic information, and path efficiency as the basis for decision-making. Path selection scores are generated by calculating indicators such as path length, time consumption, and road condition level, and paths are prioritized accordingly. This type of scoring system has been effective in improving traffic efficiency and avoiding congested paths, and is particularly suitable for autonomous driving applications in daily commuting or logistics transportation. However, in scenarios centered around passenger experience, such as scenic area tours and city sightseeing, traditional scoring mechanisms often overlook the direct impact of path structure on passenger perception. This is especially true when the path structure suddenly narrows from a spacious area to a confined space, which can easily trigger emotional reactions such as tension, oppression, or discomfort in passengers, leading to significant deviations between the actual experience and the scoring results.

[0003] Furthermore, existing technologies often fail to effectively perceive or model passengers' subjective feedback on route changes, and lack a dynamic adjustment mechanism for the passenger experience index within the rating system. In certain scenarios, even if a route excels in terms of efficiency and geographic factors, abrupt structural changes can still result in a negative passenger experience. However, since the rating system cannot detect these emotional responses, the route prioritization results fail to truly reflect user experiences, limiting the effectiveness and user satisfaction of autonomous driving systems in "experience-oriented" applications. Summary of the Invention

[0004] The purpose of the present invention is to provide a control method and system for an unmanned vehicle based on artificial intelligence, aiming to solve the problems raised in the background technology.

[0005] The present invention is implemented as follows: a control method for an unmanned vehicle based on artificial intelligence, the method comprising:

[0006] While the unmanned vehicle is carrying the current passenger on a tour, local driving data corresponding to the road conditions that have undergone path convergence changes are continuously collected;

[0007] After the collected local driving data reaches a preset amount, when the unmanned vehicle is about to enter a new path convergence change road condition, the initial path selection score corresponding to the path convergence change road condition is obtained and set as the score to be revised;

[0008] Based on the collected local driving data, a plurality of target data with increasing path convergence strength are extracted therefrom;

[0009] Analyze the experience index of the current passengers in each target data before and after the path convergence change, and calculate the corresponding decrease in the experience index;

[0010] Analyze whether the decrease in the experience index shows an increasing trend as the path convergence strength increases. If so, select several reference data whose path convergence strength is within the same preset range as the current path convergence change road condition;

[0011] Based on several reference data, the decline in the comprehensive experience index is determined, and the corresponding decline in the comprehensive scenic spot travel value is obtained. The score value to be revised is adjusted according to the decline in the comprehensive experience index and the decline in the comprehensive scenic spot travel value.

[0012] As a further limitation of the technical solution of the embodiment of the present invention, the path convergence change road condition refers to a typical road condition in which an unmanned vehicle drives from an area with ample space into an area with narrow space.

[0013] As a further limitation of the technical solution of the embodiment of the present invention, the step of extracting a plurality of target data with increasing path convergence strengths from the collected local driving data includes:

[0014] Analyze each local driving data in turn, and determine a first traffic space envelope parameter of the unmanned vehicle before entering the road condition with a convergent path change, and a second traffic space envelope parameter after entering the road condition with a convergent path change;

[0015] Calculating the difference between the first passage space envelope parameter and the second passage space envelope parameter to obtain the path convergence strength corresponding to the local driving data;

[0016] After completing the calculation of the path convergence strength corresponding to each local driving data, a number of target data are screened in a manner of increasing the path convergence strength.

[0017] As a further limitation of the technical solution of the embodiment of the present invention, the steps of respectively analyzing the experience index of the current passenger in each target data before and after the path convergence change and calculating the corresponding decrease in the experience index include:

[0018] Obtain facial video images of the current passenger in each target data before and after entering the road condition with path convergence change;

[0019] Based on the passenger's facial video image, an image recognition algorithm is used to determine a first experience index before entering the road condition with a convergent path change and a second experience index after entering the road condition;

[0020] The decrease in the experience index is calculated based on the first experience index and the second experience index.

[0021] As a further limitation of the technical solution of the embodiment of the present invention, based on a number of reference data, determining a decrease in the comprehensive experience index and obtaining a corresponding decrease in the comprehensive scenic spot visit value, and adjusting the score to be revised based on the decrease in the comprehensive experience index and the decrease in the comprehensive scenic spot visit value includes the following steps:

[0022] Calculate the average of the corresponding experience index decreases in all reference data to obtain the comprehensive experience index decrease;

[0023] Obtain a preset travel value reference table for the scenic spots where the unmanned vehicle is located, determine the first scenic spot travel value and the second scenic spot travel value before and after the unmanned vehicle enters the road condition with path convergence change in each reference data, and calculate the corresponding scenic spot travel value decrease;

[0024] The average of the decrease in the tourist attraction value of all reference data is taken to obtain the decrease in the comprehensive tourist attraction value;

[0025] Based on the decrease in the comprehensive experience index and the decrease in the comprehensive scenic spot travel value, the score to be corrected is weightedly corrected according to a preset correction function to obtain a corrected path selection score;

[0026] The modified path selection score is applied to the decision priority evaluation and path instruction generation of the current path convergence changing road conditions.

[0027] As a further limitation of the technical solution of the embodiment of the present invention, the preset correction function is:

[0028] ;

[0029] in, Refers to the corrected path selection score value, Refers to the score value to be revised. Refers to the total number of reference data, and Refers to the The second experience index and the first experience index of the reference data before and after the driverless vehicle enters the path convergence change road condition, Refers to the The decline in the experience index corresponding to the reference data is Refers to the decline in the comprehensive experience index. and Refers to the The second scenic spot travel value and the first scenic spot travel value before and after the unmanned vehicle enters the path convergence change road condition in the reference data, Refers to the The decrease in the number of scenic spot visits corresponding to the reference data is: Refers to the decline in the value of comprehensive scenic spot visits, and are the adjustment weights for the decline in the comprehensive experience index and the decline in the comprehensive scenic spot travel value, respectively, and and Both are greater than 0.

[0030] A control system for an unmanned vehicle based on artificial intelligence, the system comprising: a data acquisition module, a module for determining a score to be revised, a target data extraction module, a module for calculating the decrease in user experience, a reference data screening module, and a module for adjusting the score to be revised, wherein:

[0031] A data collection module is configured to continuously collect local driving data corresponding to a road condition undergoing a path convergence change while the unmanned vehicle is carrying the current passenger on a tour; the path convergence change road condition being a typical road condition where the unmanned vehicle is driving from a spacious area into a narrow area;

[0032] A module for determining a score to be revised, configured to, after a preset amount of collected local driving data has been collected and when the unmanned vehicle is about to enter a new road condition with a new path convergence change, obtain an initial path selection score corresponding to the new road condition with a new path convergence change and set it as the score to be revised;

[0033] A target data extraction module is used to extract a plurality of target data with increasing path convergence strength from the collected local driving data;

[0034] The experience drop calculation module is used to analyze the experience index of the current passenger in each target data before and after the path convergence change, and calculate the corresponding experience index drop;

[0035] A reference data screening module is used to analyze whether the decrease in the experience index shows an increasing trend as the path convergence strength increases. If so, it screens out several reference data whose path convergence strength is within the same preset range as the current path convergence change road condition;

[0036] The score adjustment module to be revised is used to determine the decline in the comprehensive experience index based on several reference data, and obtain the corresponding decline in the comprehensive scenic spot travel value, and adjust the score to be revised according to the decline in the comprehensive experience index and the decline in the comprehensive scenic spot travel value.

[0037] As a further limitation of the technical solution of the embodiment of the present invention, the target data extraction module specifically includes:

[0038] a degree of freedom parameter determination unit, configured to analyze each local driving data in sequence and determine therefrom a first passage space envelope parameter of the unmanned vehicle before entering a road condition with a convergent path change, and a second passage space envelope parameter of the unmanned vehicle after entering the road condition with a convergent path change;

[0039] a path convergence strength calculation unit, configured to perform difference calculation on the first passage space envelope parameter and the second passage space envelope parameter to obtain a path convergence strength corresponding to the local driving data;

[0040] The target data screening unit is used to screen a plurality of target data in a manner of increasing the path convergence strength after completing the calculation of the path convergence strength corresponding to each local driving data.

[0041] As a further limitation of the technical solution of the embodiment of the present invention, the experience reduction calculation module specifically includes:

[0042] A facial information acquisition unit is used to respectively acquire facial video images of the current passenger in each target data before and after the passenger enters the road condition with a convergent path;

[0043] An experience index determining unit, configured to determine, based on the passenger's facial video image, a first experience index before entering the road condition with a convergent path change and a second experience index after entering the road condition using an image recognition algorithm;

[0044] The experience reduction calculation unit is used to calculate the experience index reduction based on the first experience index and the second experience index.

[0045] As a further limitation of the technical solution of the embodiment of the present invention, the score adjustment module to be corrected specifically includes:

[0046] A first comprehensive reduction calculation unit is used to calculate the average of the corresponding experience index reductions in all reference data to obtain the comprehensive experience index reduction;

[0047] a scenic spot travel value acquisition unit, configured to obtain a preset travel value reference table of the scenic spot where the unmanned vehicle is located, respectively determine the first scenic spot travel value and the second scenic spot travel value before and after the unmanned vehicle enters the road condition with path convergence change in each reference data, and calculate the corresponding scenic spot travel value decrease;

[0048] The second comprehensive decrease calculation unit is used to average the decreases of the scenic spot travel values ​​of all reference data to obtain the comprehensive scenic spot travel value decrease;

[0049] A score adjustment unit for correction, configured to perform weighted correction on the score to be corrected according to a preset correction function based on the decrease in the comprehensive experience index and the decrease in the comprehensive scenic spot travel value, to obtain a corrected route selection score;

[0050] A modified score value application unit, configured to apply the modified path selection score value to decision priority evaluation and path instruction generation for the current path convergence change road condition;

[0051] The preset correction function is:

[0052] ;

[0053] in, Refers to the corrected path selection score value, Refers to the score value to be revised. Refers to the total number of reference data, and Refers to the The second experience index and the first experience index of the reference data before and after the driverless vehicle enters the path convergence change road condition, Refers to the The decline in the experience index corresponding to the reference data is Refers to the decline in the comprehensive experience index. and Refers to the The second scenic spot travel value and the first scenic spot travel value before and after the unmanned vehicle enters the path convergence change road condition in the reference data, Refers to the The decrease in the number of scenic spot visits corresponding to the reference data is: Refers to the decline in the value of comprehensive scenic spot visits, and are the adjustment weights for the decline in the comprehensive experience index and the decline in the comprehensive scenic spot travel value, respectively, and and Both are greater than 0.

[0054] Compared with the prior art, the present invention has the following beneficial effects:

[0055] The present invention realizes the dynamic optimization of the path selection score of unmanned vehicles by constructing a scoring correction mechanism based on the correlation trend between the convergence strength of the path structure and the passenger experience response. Compared with the existing technology that only scores based on static maps, traffic efficiency and other factors, the present invention introduces the decline in the subjective experience index of individual passengers during the path convergence change process as the correction basis for the first time, and combines the changing trend of the value of scenic spot travel to construct a weighted adjustment model of the score value, which can identify the sensitive structure of "the more intense the convergence, the worse the experience", so as to make corrections to the scoring results that are more in line with actual perception. This method effectively enhances the path planning system's ability to express the trade-off between passenger psychological comfort and scene value, has higher intelligent adaptability and experience optimization value, and is particularly suitable for sightseeing and experience-oriented unmanned driving application scenarios. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] Figure 1 A flowchart of a method provided by an embodiment of the present invention;

[0057] Figure 2 A flowchart of obtaining a plurality of target data with successively increasing path convergence strengths in the method provided in an embodiment of the present invention;

[0058] Figure 3 This is a flow chart of calculating the decrease in the experience index in the method provided in an embodiment of the present invention;

[0059] Figure 4 A flow chart of weighted correction of the score value to be corrected in the method provided in an embodiment of the present invention;

[0060] Figure 5 An application architecture diagram of the system provided by an embodiment of the present invention;

[0061] Figure 6 A structural block diagram of a target data extraction module in a system provided by an embodiment of the present invention;

[0062] Figure 7 This is a structural block diagram of the user experience degradation calculation module in the system provided by an embodiment of the present invention;

[0063] Figure 8 This is a structural block diagram of the score adjustment module to be corrected in the system provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0064] In order to make the purpose, technical solutions and advantages of the present invention more clearly understood, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0065] Figure 1 A flow chart of a method provided by an embodiment of the present invention is shown.

[0066] Specifically, a control method for an unmanned vehicle based on artificial intelligence comprises the following steps:

[0067] Step S100 , while the driverless vehicle is carrying the current passenger on a tour, continuously collects local driving data corresponding to a road condition that undergoes a path convergence change. The path convergence change road condition refers to a typical road condition where the driverless vehicle moves from a spacious area to a narrow area.

[0068] In the embodiment of the present invention, the number of current passengers is not strictly limited. In principle, it can be one or more people. However, considering factors such as facial recognition accuracy, stability of experience index collection, and layout of space sensors in the vehicle, when the number of passengers is too large, it may interfere with data collection. Therefore, it is more suitable for scenarios with fewer passengers, especially for relatively static and low-speed unmanned driving application scenarios such as city tours, park transfers, and limited route sightseeing.

[0069] To accurately model the impact of path convergence changes on passenger perception, the system continuously collects local driving data corresponding to road conditions experiencing path convergence changes during the operation of the autonomous vehicle. This local driving data refers to the driving data segment from a certain distance before the vehicle enters the path convergence change to a certain distance after the change. It covers the entire process of driving behavior, environmental changes, and passenger reactions within the structural transition area.

[0070] The local driving data should include at least the following types of information:

[0071] (1) Environmental perception data of the unmanned vehicle, including forward free passage width, lateral distribution of obstacles, and path boundary change rate;

[0072] (2) Vehicle operating parameters, such as speed, acceleration, braking frequency, steering wheel angle change, etc.

[0073] (3) Passenger status data, including facial expression image sequences, physiological feature recognition data (such as posture micro-movements, blinking frequency, etc.) and experience index after timestamp calibration;

[0074] (4) Identification information of the scenic spot or area you are in, and a reference table of preset travel values ​​for the travel area.

[0075] The study of path convergence changes is motivated by the fact that these structural mutations often cause shifts in driving behavior (e.g., from cruising to decelerating to avoid obstacles), a contraction in visual depth, and drastic changes in passengers' subjective perception. In conventional path planning systems, these road conditions are often viewed as merely geometric changes. However, in practice, path convergence changes can easily induce discomfort, sudden motor reactions, and a decrease in passengers' subjective evaluations. This paper attempts to construct a scoring correction mechanism centered on passenger perception. By leveraging the recurring trend of "higher path convergence, greater decline in passenger experience" in historical local data, the current path score is dynamically adjusted, enabling the path selection strategy to consider not only safety and efficiency but also the user's psychological comfort and tour satisfaction.

[0076] Furthermore, the control method of the unmanned vehicle based on artificial intelligence further includes the following steps:

[0077] Step S200: After the collected local driving data reaches a preset amount, when the unmanned vehicle is about to enter a new path convergence change road condition, an initial path selection score value corresponding to the path convergence change road condition is obtained and set as the score value to be revised.

[0078] Step S300 : extracting a plurality of target data with successively increasing path convergence strengths based on the collected local driving data.

[0079] Specifically, Figure 2 A flow chart for obtaining several sets of target data with successively increasing path convergence strength is shown.

[0080] The process of extracting a plurality of target data with increasing path convergence strength based on the collected local driving data specifically includes the following steps:

[0081] Step S301, analyzing each local driving data in sequence, and determining a first passage space envelope parameter of the unmanned vehicle before entering a road condition with a convergent path change, and a second passage space envelope parameter after entering the road condition with a convergent path change;

[0082] Step S302: performing a difference calculation on the first passage space envelope parameter and the second passage space envelope parameter to obtain a path convergence strength corresponding to the local driving data;

[0083] Step S303 : After completing the calculation of the path convergence strength corresponding to each local driving data, a plurality of target data are screened in a manner of increasing the path convergence strength.

[0084] In an embodiment of the present invention, the preset number of local driving data is typically set based on experience as the minimum number of samples required to ensure statistical trend significance, preferably no less than five. The reaching of this preset number serves as a triggering point, and its purpose is to ensure that, before officially executing the score correction, there is sufficient data to support the determination of whether the trend characteristic of "the higher the path convergence strength, the more significant the decline in user experience" exists, thereby preventing analytical bias caused by too few samples. In other words, only when the accumulated local driving data reaches a statistically reliable number will the system initiate the correction process before the new path converges and changes in road conditions occur, thereby improving the stability and credibility of the score correction mechanism.

[0085] The initial route selection score refers to the priority score assigned to the current route's convergence-changing road conditions after a preliminary evaluation of multiple candidate road conditions in the vehicle routing system. This score is typically used to prioritize subsequent route instruction generation modules. This score may be derived based on a comprehensive assessment of factors such as route length, traffic density, and scenic index. However, this score has limitations because it does not account for passenger discomfort caused by sudden changes in route structure (such as entering a narrow area from a wide area). The present invention aims to modify this score through experience-driven adjustments to better align it with current passengers' actual preferences, thereby optimizing route selection strategies.

[0086] The passage space envelope parameter represents the size of the spatial boundary measured within a certain distance ahead of an autonomous vehicle, ensuring safe passage. It reflects the vehicle's lateral spatial envelope capability before and after changes in the path structure. This envelope parameter is derived by fusing multiple data sources, including lidar point cloud modeling, visual stereo ranging, and vehicle-to-everything (V2X) perception information. It is a common extended safety assessment metric in existing intelligent perception systems.

[0087] Specifically, in step S301, the first and second envelope parameters of the passageway space before and after the path convergence change are obtained. In step S302, the difference between the two is calculated to determine the path convergence strength corresponding to the local driving data. This is used to quantify the structural compression trend of "transitioning from a wide space to a narrow space," thereby establishing a logical basis for the impact of structural change on the user experience. A larger difference indicates a more dramatic spatial mutation, a higher convergence strength, and a more pronounced potential sense of oppression.

[0088] In addition to the difference calculation method, this embodiment also uses methods such as proportional reduction rate, envelope curve gradient change rate, or convergence angle indicators constructed based on the forward depth map to characterize the path convergence strength. For example, by calculating the proportional relationship between the envelope of the first and second passage spaces, the relative severity of the convergence can be more intuitively reflected; the change in the slope of the passage space boundary fitting curve can be used to characterize the trend gradient of spatial contraction; and the convergence angle indicator generated based on the depth map can be used to determine the degree of spatial convergence by analyzing the change in the angle between the obstacle boundaries on both sides of the vehicle's field of view. These methods complement the difference calculation and are applicable to convergence strength modeling under different sensor conditions and path geometry types.

[0089] In step S303, the system sorts the path convergence strengths corresponding to each local driving data set, prioritizing a number of target data sets with increasing convergence strength, wide coverage, and balanced distribution. These serve as the primary sample set for subsequent analysis of the user experience degradation trend, ensuring the representativeness and gradient continuity of the extracted trend relationship. This screening method not only improves the accuracy of trend fitting but also helps identify the nonlinear response range between user experience feedback and path changes.

[0090] Furthermore, the control method of the unmanned vehicle based on artificial intelligence further includes the following steps:

[0091] Step S400 , respectively analyzing the experience index of the current passenger before and after the path convergence change in each target data, and calculating the corresponding decrease in the experience index.

[0092] Specifically, Figure 3 A flow chart for calculating the decrease in the experience index is shown.

[0093] The following steps are used to analyze the passenger experience index before and after the route convergence change in each target data and calculate the corresponding decrease in the experience index:

[0094] Step S401, respectively obtaining facial video images of the current passenger in each target data before and after entering the road condition with path convergence change;

[0095] Step S402, based on the passenger's facial video image, using an image recognition algorithm to determine a first experience index before entering the road condition with a convergent path change and a second experience index after entering the road condition;

[0096] Step S403: Calculate the decrease in the experience index based on the first experience index and the second experience index.

[0097] In an embodiment of the present invention, the passenger's facial video image can be acquired in real time using a forward-facing or side-facing camera installed inside the autonomous vehicle. This camera is preferably installed in front of the seat or in the center of the vehicle. It can continuously capture changes in the passenger's facial expression without interfering with the passenger's normal activities, ensuring accurate image recognition at a high frame rate and high definition.

[0098] To extract the first and second experience indices, AI-based facial emotion recognition technology is preferred. Specifically, a convolutional neural network (CNN) model is constructed to analyze key facial features (such as raised eyebrows, drooping mouth corners, frowning, and pupil dilation) in the passenger's facial image. This is then combined with a pre-defined multi-dimensional emotion weighting model to quantify their current emotional state. This yields the first experience index before entering the route convergence change and the second experience index after entering the route convergence change. Perception accuracy can also be further enhanced by integrating facial muscle tension analysis and physiological signal feedback (such as blink frequency and forehead sweating).

[0099] If there are multiple passengers, the system will capture facial video images of each passenger before and after the route convergence change, and use an image recognition algorithm to extract the first and second experience indexes corresponding to each passenger. The system then calculates the drop in experience index for each passenger and averages the drop across all current passengers to arrive at the overall drop in experience index for that route change. This approach effectively reflects the overall perception trend in multi-passenger scenarios, avoids distorted ratings due to biased responses from a single passenger, and further enhances the objectivity and applicability of rating corrections.

[0100] The decline in the Experience Index, as the relative change between two time periods, reflects the degree of change in passengers' psychological comfort during the process of route convergence. This is manifested in negative emotional reactions such as increased tension, increased pressure, and spatial discomfort. The more significant the trend in this indicator, the greater the impact of the route spatial change on the passenger experience, and it clearly correlates with behavioral responses.

[0101] Furthermore, the control method of the unmanned vehicle based on artificial intelligence further includes the following steps:

[0102] Step S500 : analyzing whether the decrease in the experience index shows an increasing trend as the path convergence strength increases. If so, selecting a number of reference data whose path convergence strength is within the same preset range as the current path convergence change road condition.

[0103] In an embodiment of the present invention, the purpose of determining whether the decrease in the experience index shows an increasing trend as the intensity of path convergence increases is to identify whether the current passenger has a clear experience sensitivity to changes in path space convergence. The existence of this trend means that, under the current passenger's individual perception system, the higher the intensity of the change from wide to narrow path space, the more obvious the decline in their subjective experience, which further indicates that they have a consistent response characteristic to changes in path convergence. The identification of this characteristic provides a judgment premise for the subsequent correction of path selection scores, ensuring that corresponding score adjustments are only made when experience feedback has a strong correlation, thereby avoiding over-correction of scores when subjective responses are unclear or individual differences are large.

[0104] It should be noted that determining an increasing trend does not require absolute monotonicity; rather, a certain degree of error or fluctuation is tolerated. Specifically, this can be confirmed by setting a threshold range for change or employing statistical analysis methods such as linear fitting and curve fitting to determine whether the overall trend exhibits a positive slope. This ensures robust trend determination while minimizing the impact of individual anomalous data points on the overall analysis results.

[0105] Once the trend is established, the system further selects reference data whose path convergence strength is within the same preset range as the current path convergence change. This process can be achieved by calculating the difference between the current path convergence strength and the path convergence strength corresponding to each local driving data point, and setting a comparison tolerance range as the preset range for matching. The preset range can be based on historical sample statistics, selecting the path convergence strength interval with the most significant decrease in the experience index, or using a fixed threshold (such as ±10%, ±0.5m, etc.) based on system tuning experience. This ensures that the selected reference data is representative and comparable in terms of convergence structure characteristics, ensuring the effectiveness and stability of the correction results.

[0106] Furthermore, the control method of the unmanned vehicle based on artificial intelligence further includes the following steps:

[0107] Step S600: Based on a number of reference data, determine the drop in the comprehensive experience index and obtain the corresponding drop in the comprehensive scenic spot travel value, and adjust the score value to be revised according to the drop in the comprehensive experience index and the drop in the comprehensive scenic spot travel value.

[0108] Specifically, Figure 4 A flow chart for weighted correction of the score value to be corrected is shown.

[0109] The steps of determining the decline in the comprehensive experience index based on a number of reference data and obtaining the corresponding decline in the comprehensive scenic spot visit value and adjusting the score value to be revised based on the decline in the comprehensive experience index and the decline in the comprehensive scenic spot visit value include:

[0110] Step S601, calculating the average of the corresponding experience index decreases in all reference data to obtain the comprehensive experience index decrease;

[0111] Step S602: Obtain a preset travel value reference table for the scenic spot where the unmanned vehicle is located, determine the first scenic spot travel value and the second scenic spot travel value before and after the unmanned vehicle enters the road condition with path convergence change in each reference data, and calculate the corresponding scenic spot travel value decrease;

[0112] Step S603, averaging the decreases in the scenic spot travel values ​​of all reference data to obtain a comprehensive decrease in the scenic spot travel value;

[0113] Step S604: Based on the decrease in the comprehensive experience index and the decrease in the comprehensive scenic spot travel value, weighted correction is performed on the score to be corrected according to a preset correction function to obtain a corrected route selection score;

[0114] Step S605 : Apply the corrected path selection score value to the decision priority evaluation and path instruction generation of the current path convergence change road condition.

[0115] The preset correction function is:

[0116] ;

[0117] in, Refers to the corrected path selection score value, Refers to the score value to be revised. Refers to the total number of reference data, and Refers to the The second experience index and the first experience index of the reference data before and after the driverless vehicle enters the path convergence change road condition, Refers to the The decline in the experience index corresponding to the reference data is Refers to the decline in the comprehensive experience index. and Refers to the The second scenic spot travel value and the first scenic spot travel value before and after the unmanned vehicle enters the path convergence change road condition in the reference data, Refers to the The decrease in the number of scenic spot visits corresponding to the reference data is: Refers to the decline in the value of comprehensive scenic spot visits, and are the adjustment weights for the decline in the comprehensive experience index and the decline in the comprehensive scenic spot travel value, respectively, and and Both are greater than 0.

[0118] In this embodiment of the present invention, step S601 is specifically implemented as follows: based on the previously selected reference data, the system sequentially extracts the current passenger's experience index before and after the route convergence change in each data set, calculates the experience index decrease using a pre-defined decrease calculation formula, and arithmetic averages the decrease results for all reference data to obtain the passenger's comprehensive experience index decrease within the current route convergence strength range. This average reflects the general experience decline trend for the passenger under similar road conditions.

[0119] In step S602, the preset travel value reference table is constructed based on the existing scenic spot evaluation system in the scenic spot management system or map content platform. This is a mature existing technology. Its sources may include visitor ratings, popularity ratings, subjective scoring systems, etc., and is formed by combining manual settings and data modeling. Using this reference table, the system determines the scenic spot evaluation values ​​before and after the unmanned vehicle enters the road conditions with path convergence changes in each set of reference data, namely the first scenic spot travel value and the second scenic spot travel value. The relative change in these values ​​is calculated and used as an indicator of the decline in scenic spot travel value.

[0120] In step S603, the system averages the decreases in the attraction visit value corresponding to each of the reference data points to obtain the comprehensive attraction visit value decrease within the range of path convergence strength. This metric is used to assess whether this type of road condition is generally associated with a decrease in attraction value, and further assist in determining whether the cause of the experience decline is mainly due to path factors.

[0121] Step S604 introduces two factors to weight the score to be revised because a decrease in the overall experience index reflects the passenger's subjective discomfort, while a decrease in the overall attraction visit value reflects objective environmental quality factors that may affect the experience. If the passenger's experience declines but the corresponding attraction rating also declines, this indicates that the poor experience may be affected by the attraction itself, and the system will adjust the score appropriately. On the other hand, if the attraction's value remains unchanged, or even improves, but the experience deteriorates, this indicates that the route structure has indeed caused a strong negative reaction to the passenger, and the system will increase the score penalty. This type of correction logic achieves a dynamic fusion of subjective and objective information, helping to generate more realistic and adaptive route scoring results.

[0122] In step S605, the revised route selection score is directly used in the route planning module for priority determination, alternative route comparison, and route instruction generation. For example, among multiple route branch selection nodes, the system will prioritize routes with higher revised scores to improve passenger experience continuity. If the current route score is significantly lowered due to user experience issues, the system can trigger route switching logic to avoid convergent sections with poor user experience.

[0123] This score correction function incorporates both penalties and compensations, primarily to ensure that route selection scores are more aligned with passenger experience and actual attraction evaluations. For example, the decline in the experience index reflects the degree to which a passenger's experience deteriorates after entering a confined space. A negative value indicates a significant decrease in the passenger's experience, necessitating a penalty on the original score, thereby reducing the priority of that route. This is the purpose of the "1 + decline in overall experience index" component, as the greater the decline in experience, the greater the absolute value of this product, ultimately lowering the overall score. On the other hand, the decline in the attraction visit value reflects the decrease in attraction attractiveness caused by the route convergence change. When the attraction evaluation increases, it means that the overall value of the attractions passed by the current route converges and changes. If the passenger experience still shows a significant decline at this time, it often indicates that the passenger is subjectively overly sensitive to the route structure change. Even if the actual attraction quality improves, psychological expectations or visual narrowing may still lead to negative experiences. Such abnormal reactions should not directly affect the route score. Therefore, the score correction mechanism should further weaken the original score to prevent the system from mistakenly interpreting individual abnormal feedback as a general trend. When the attraction evaluation decreases, it means that the route change has indeed led to a decrease in attraction quality. In this case, the system introduces a compensation term of "1-the decline in the comprehensive attraction visit value" to moderately adjust the score correction to avoid excessive reduction in the score due to objective environmental degradation, thereby achieving a dynamic balance between changes in experience and changes in attraction value. In summary, this design allows the correction function to both impose necessary penalties for experience decline and appropriately adjust the score based on the actual attraction's attractiveness. Together, these two effects make the final score more comprehensive reflecting the dual impact of the route on passengers' subjective experience and objective attraction evaluation.

[0124] It should be noted that while the preset correction function is concise and logically intuitive, it is not the only option. In other embodiments, alternative algorithms such as piecewise nonlinear weighting functions, exponential weighting models, and scoring mappings based on clustering or regression models can be introduced to achieve a more complex correspondence between the score and the dual variables of experience and attraction value, adapting to the needs of different passenger types, route environments, and scoring systems.

[0125] Further, Figure 5 The application architecture diagram of the system provided by the embodiment of the present invention is shown.

[0126] Among them, in another preferred embodiment provided by the present invention, a control system for an unmanned vehicle based on artificial intelligence includes:

[0127] The data acquisition module 100 is used to continuously collect local driving data corresponding to the road conditions that have undergone path convergence changes while the unmanned vehicle is carrying the current passengers on a tour; the path convergence change road conditions refer to the typical road conditions in which the unmanned vehicle drives from an area with ample space to an area with narrow space.

[0128] Furthermore, the control system of the unmanned vehicle based on artificial intelligence also includes:

[0129] The score determination module 200 is used to obtain the initial path selection score corresponding to the new path convergence change road condition after the collected local driving data reaches a preset amount, and set it as the score to be revised when the unmanned vehicle is about to enter the new path convergence change road condition.

[0130] The target data extraction module 300 is used to extract a plurality of target data with increasing path convergence strengths based on the collected local driving data.

[0131] Specifically, Figure 6 FIG. 3 is a block diagram showing the structure of the target data extraction module 300 in the system provided by an embodiment of the present invention.

[0132] In a preferred embodiment of the present invention, the target data extraction module 300 specifically includes:

[0133] The degree of freedom parameter determination unit 301 is configured to analyze each local driving data in sequence and determine a first passage space envelope parameter of the unmanned vehicle before entering a road condition with a convergent path change, and a second passage space envelope parameter of the unmanned vehicle after entering a road condition with a convergent path change;

[0134] A path convergence strength calculation unit 302 is configured to perform difference calculation on the first passage space envelope parameter and the second passage space envelope parameter to obtain a path convergence strength corresponding to the local driving data;

[0135] The target data screening unit 303 is configured to screen a plurality of target data in an ascending order of the path convergence strength after completing the calculation of the path convergence strength corresponding to each local driving data.

[0136] Furthermore, the control system of the unmanned vehicle based on artificial intelligence also includes:

[0137] The experience reduction calculation module 400 is used to analyze the experience index of the current passenger in each target data before and after the path convergence change, and calculate the corresponding experience index reduction.

[0138] Specifically, Figure 7 FIG. 4 is a structural block diagram of the user experience reduction calculation module 400 in the system provided by an embodiment of the present invention.

[0139] In a preferred embodiment of the present invention, the experience reduction calculation module 400 specifically includes:

[0140] The facial information acquisition unit 401 is used to respectively acquire facial video images of the current passenger in each target data before and after the passenger enters the road condition with a convergent path;

[0141] An experience index determining unit 402 is configured to determine, based on the passenger's facial video image, a first experience index before entering the road condition with a convergent path and a second experience index after entering the road condition with a convergent path, using an image recognition algorithm;

[0142] The experience reduction calculation unit 403 is configured to calculate the experience index reduction based on the first experience index and the second experience index.

[0143] Furthermore, the control system of the unmanned vehicle based on artificial intelligence also includes:

[0144] The reference data screening module 500 is used to analyze whether the decrease in the experience index shows an increasing trend with the increase in the path convergence strength. If so, it screens out several reference data whose path convergence strength is within the same preset range as the current path convergence change road condition.

[0145] Furthermore, the control system of the unmanned vehicle based on artificial intelligence also includes:

[0146] The score adjustment module 600 is used to determine the decrease in the comprehensive experience index based on a number of reference data, and obtain the corresponding decrease in the comprehensive scenic spot travel value, and adjust the score value to be revised according to the decrease in the comprehensive experience index and the decrease in the comprehensive scenic spot travel value.

[0147] Specifically, Figure 8 FIG. 6 is a structural block diagram of the score adjustment module 600 to be corrected in the system provided by an embodiment of the present invention.

[0148] In a preferred embodiment of the present invention, the score adjustment module 600 to be revised specifically includes:

[0149] The first comprehensive reduction calculation unit 601 is used to calculate the average of the corresponding experience index reductions in all reference data to obtain the comprehensive experience index reduction;

[0150] The scenic spot visit value acquisition unit 602 is used to obtain a preset visit value reference table of the scenic spot where the unmanned vehicle is located, determine the first scenic spot visit value and the second scenic spot visit value before and after the unmanned vehicle enters the road condition with path convergence change in each reference data, and calculate the corresponding scenic spot visit value decrease;

[0151] The second comprehensive decrease calculation unit 603 is used to average the decreases of the scenic spot travel values ​​of all reference data to obtain the comprehensive scenic spot travel value decrease;

[0152] The score adjustment unit 604 is configured to perform weighted correction on the score to be corrected according to a preset correction function based on the decrease in the comprehensive experience index and the decrease in the comprehensive scenic spot travel value, to obtain a corrected route selection score;

[0153] A modified score application unit 605 is configured to apply the modified path selection score to the decision priority evaluation and path instruction generation of the current path convergence change road condition;

[0154] The preset correction function is:

[0155] ;

[0156] in, Refers to the corrected path selection score value, Refers to the score value to be revised. Refers to the total number of reference data, and Refers to the The second experience index and the first experience index of the reference data before and after the driverless vehicle enters the path convergence change road condition, Refers to the The decline in the experience index corresponding to the reference data is Refers to the decline in the comprehensive experience index. and Refers to the The second scenic spot travel value and the first scenic spot travel value before and after the unmanned vehicle enters the path convergence change road condition in the reference data, Refers to the The decrease in the number of scenic spot visits corresponding to the reference data is: Refers to the decline in the value of comprehensive scenic spot visits, and are the adjustment weights for the decline in the comprehensive experience index and the decline in the comprehensive scenic spot travel value, respectively, and and Both are greater than 0.

[0157] It should be understood that, although the various steps in the flow chart of each embodiment of the present invention are shown in sequence according to the indication of the arrows, these steps are not necessarily performed in sequence according to the order indicated by the arrows. Unless otherwise specified herein, the execution of these steps is not strictly limited in order, and these steps can be performed in other orders. Moreover, at least a portion of the steps in each embodiment may include a plurality of sub-steps or a plurality of stages, and these sub-steps or stages are not necessarily performed at the same time, but can be performed at different times, and the execution order of these sub-steps or stages is not necessarily performed in sequence, but can be performed in turn or alternately with at least a portion of other steps or sub-steps or stages of other steps.

[0158] Those skilled in the art will appreciate that all or part of the processes in the above-described method embodiments can be implemented by instructing the relevant hardware through a computer program. The program can be stored in a non-volatile computer-readable storage medium. When executed, the program can include the processes of the above-described method embodiments. Any reference to memory, storage, database, or other media used in the various embodiments provided herein may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct RAMbus dynamic RAM (DRDRAM), and RAMbus dynamic RAM (RDRAM).

[0159] The technical features of the above-mentioned embodiments can be combined arbitrarily. In order to make the description concise, not all possible combinations of the technical features in the above-mentioned embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0160] The above-described embodiments merely illustrate several implementations of the present invention, and while their descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present invention. It should be noted that a person skilled in the art would be able to make numerous variations and improvements without departing from the spirit of the present invention, all of which fall within the scope of protection of the present invention. Therefore, the scope of protection of the present invention shall be determined by the appended claims.

[0161] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A control method for an unmanned vehicle based on artificial intelligence, characterized in that: The method comprises: While the unmanned vehicle is carrying the current passenger on a tour, local driving data corresponding to the road conditions that have undergone path convergence changes are continuously collected; After the collected local driving data reaches a preset amount, when the unmanned vehicle is about to enter a new path convergence change road condition, the initial path selection score corresponding to the path convergence change road condition is obtained and set as the score to be revised; Based on the collected local driving data, a plurality of target data with increasing path convergence strength are extracted therefrom; Analyze the experience index of the current passengers in each target data before and after the path convergence change, and calculate the corresponding decrease in the experience index; Analyze whether the decrease in the experience index shows an increasing trend as the path convergence strength increases. If so, select several reference data whose path convergence strength is within the same preset range as the current path convergence change road condition; Based on several reference data, the decline in the comprehensive experience index is determined, and the corresponding decline in the comprehensive scenic spot travel value is obtained. The score value to be revised is adjusted according to the decline in the comprehensive experience index and the decline in the comprehensive scenic spot travel value.

2. The control method of an unmanned vehicle based on artificial intelligence according to claim 1, characterized in that: The path convergence change road condition refers to a typical road condition in which an unmanned vehicle drives from an area with ample space into an area with narrow space.

3. The control method of an unmanned vehicle based on artificial intelligence according to claim 2, characterized in that: The steps of extracting a plurality of target data with increasing path convergence strengths based on the collected local driving data include: Analyze each local driving data in turn, and determine a first traffic space envelope parameter of the unmanned vehicle before entering the road condition with a convergent path change, and a second traffic space envelope parameter after entering the road condition with a convergent path change; Calculating the difference between the first passage space envelope parameter and the second passage space envelope parameter to obtain the path convergence strength corresponding to the local driving data; After completing the calculation of the path convergence strength corresponding to each local driving data, a number of target data are screened in a manner of increasing the path convergence strength.

4. The control method of an unmanned vehicle based on artificial intelligence according to claim 3, characterized in that: The steps of analyzing the passenger experience index before and after the route convergence change in each target data and calculating the corresponding decrease in the experience index include: Obtain facial video images of the current passenger in each target data before and after entering the road condition with path convergence change; Based on the passenger's facial video image, an image recognition algorithm is used to determine a first experience index before entering the road condition with a convergent path change and a second experience index after entering the road condition; The decrease in the experience index is calculated based on the first experience index and the second experience index.

5. The control method of an unmanned vehicle based on artificial intelligence according to claim 4, characterized in that: Based on a number of reference data, determining a decrease in the comprehensive experience index and obtaining a corresponding decrease in the comprehensive scenic spot visit value, and adjusting the score to be revised based on the decrease in the comprehensive experience index and the decrease in the comprehensive scenic spot visit value include the following steps: Calculate the average of the corresponding experience index decreases in all reference data to obtain the comprehensive experience index decrease; Obtain a preset travel value reference table for the scenic spots where the unmanned vehicle is located, determine the first scenic spot travel value and the second scenic spot travel value before and after the unmanned vehicle enters the road condition with path convergence change in each reference data, and calculate the corresponding scenic spot travel value decrease; The average of the decrease in the tourist attraction value of all reference data is taken to obtain the decrease in the comprehensive tourist attraction value; Based on the decrease in the comprehensive experience index and the decrease in the comprehensive scenic spot travel value, the score to be corrected is weightedly corrected according to a preset correction function to obtain a corrected path selection score; The modified path selection score is applied to the decision priority evaluation and path instruction generation of the current path convergence changing road conditions.

6. The control method of an unmanned vehicle based on artificial intelligence according to claim 5, characterized in that: The preset correction function is: ； in, Refers to the corrected path selection score value, Refers to the score value to be revised. Refers to the total number of reference data, and Refers to the The second experience index and the first experience index of the reference data before and after the driverless vehicle enters the path convergence change road condition, Refers to the The decline in the experience index corresponding to the reference data is Refers to the decline in the comprehensive experience index. and Refers to the The second scenic spot travel value and the first scenic spot travel value before and after the unmanned vehicle enters the path convergence change road condition in the reference data, Refers to the The decrease in the number of scenic spot visits corresponding to the reference data is: Refers to the decline in the value of comprehensive scenic spot visits, and are the adjustment weights for the decline in the comprehensive experience index and the decline in the comprehensive scenic spot travel value, respectively, and and Both are greater than 0.

7. A control system for an unmanned vehicle based on artificial intelligence, characterized in that: The system includes: a data acquisition module, a module for determining the score to be revised, a target data extraction module, a module for calculating the decrease in experience, a reference data screening module, and a module for adjusting the score to be revised, wherein: A data collection module is configured to continuously collect local driving data corresponding to a road condition undergoing a path convergence change while the unmanned vehicle is carrying the current passenger on a tour; the path convergence change road condition being a typical road condition where the unmanned vehicle is driving from a spacious area into a narrow area; A module for determining a score to be revised, configured to, after a preset amount of collected local driving data has been collected and when the unmanned vehicle is about to enter a new road condition with a new path convergence change, obtain an initial path selection score corresponding to the new road condition with a new path convergence change and set it as the score to be revised; A target data extraction module is used to extract a plurality of target data with increasing path convergence strength from the collected local driving data; The experience drop calculation module is used to analyze the experience index of the current passenger in each target data before and after the path convergence change, and calculate the corresponding experience index drop; A reference data screening module is used to analyze whether the decrease in the experience index shows an increasing trend as the path convergence strength increases. If so, it screens out several reference data whose path convergence strength is within the same preset range as the current path convergence change road condition; The score adjustment module to be revised is used to determine the decline in the comprehensive experience index based on several reference data, and obtain the corresponding decline in the comprehensive scenic spot travel value, and adjust the score to be revised according to the decline in the comprehensive experience index and the decline in the comprehensive scenic spot travel value.

8. The control system of an unmanned vehicle based on artificial intelligence according to claim 7, characterized in that: The target data extraction module specifically includes: a degree of freedom parameter determination unit, configured to analyze each local driving data in sequence and determine therefrom a first passage space envelope parameter of the unmanned vehicle before entering a road condition with a convergent path change, and a second passage space envelope parameter of the unmanned vehicle after entering the road condition with a convergent path change; a path convergence strength calculation unit, configured to perform difference calculation on the first passage space envelope parameter and the second passage space envelope parameter to obtain a path convergence strength corresponding to the local driving data; The target data screening unit is used to screen a plurality of target data in a manner of increasing the path convergence strength after completing the calculation of the path convergence strength corresponding to each local driving data.

9. The control system of an unmanned vehicle based on artificial intelligence according to claim 8, characterized in that: The experience reduction calculation module specifically includes: A facial information acquisition unit is used to respectively acquire facial video images of the current passenger in each target data before and after the passenger enters the road condition with a convergent path; An experience index determining unit, configured to determine, based on the passenger's facial video image, a first experience index before entering the road condition with a convergent path change and a second experience index after entering the road condition using an image recognition algorithm; The experience reduction calculation unit is used to calculate the experience index reduction based on the first experience index and the second experience index.

10. The control system of an unmanned vehicle based on artificial intelligence according to claim 9, characterized in that: The score adjustment module to be revised specifically includes: A first comprehensive reduction calculation unit is used to calculate the average of the corresponding experience index reductions in all reference data to obtain the comprehensive experience index reduction; a scenic spot travel value acquisition unit, configured to obtain a preset travel value reference table of the scenic spot where the unmanned vehicle is located, respectively determine the first scenic spot travel value and the second scenic spot travel value before and after the unmanned vehicle enters the road condition with path convergence change in each reference data, and calculate the corresponding scenic spot travel value decrease; The second comprehensive decrease calculation unit is used to average the decreases of the scenic spot travel values ​​of all reference data to obtain the comprehensive scenic spot travel value decrease; A score adjustment unit for correction, configured to perform weighted correction on the score to be corrected according to a preset correction function based on the decrease in the comprehensive experience index and the decrease in the comprehensive scenic spot travel value, to obtain a corrected route selection score; A modified score value application unit, configured to apply the modified path selection score value to decision priority evaluation and path instruction generation for the current path convergence change road condition; The preset correction function is: ； in, Refers to the corrected path selection score value, Refers to the score value to be revised. Refers to the total number of reference data, and Refers to the The second experience index and the first experience index of the reference data before and after the driverless vehicle enters the path convergence change road condition, Refers to the The decline in the experience index corresponding to the reference data is Refers to the decline in the comprehensive experience index. and Refers to the The second scenic spot travel value and the first scenic spot travel value before and after the unmanned vehicle enters the path convergence change road condition in the reference data, Refers to the The decrease in the number of scenic spot visits corresponding to the reference data is: Refers to the decline in the value of comprehensive scenic spot visits, and are the adjustment weights for the decline in the comprehensive experience index and the decline in the comprehensive scenic spot travel value, respectively, and and Both are greater than 0.

Images