Automobile external signal interaction method and system

Abstract

The present invention relates to the field of autonomous driving technology, specifically to a method and system for interacting with external signals of an automobile, comprising the following steps: based on vehicle radar monitoring data, analyzing and identifying obstacles in multiple directions of the vehicle in real time, recording the position, moving speed and size information of multiple obstacles, and generating obstacle monitoring data. In the present invention, the position, speed and size of obstacles are analyzed in real time through vehicle radar monitoring data, and the types of obstacles, including pedestrians and vehicles, are identified. The scene type in which the automobile is located is analyzed in combination with image acquisition equipment and GPS sensors, and the signal strength is adjusted according to differentiated environmental conditions, thereby improving the interactive responsiveness and accuracy of the vehicle, enhancing the safety of the vehicle in a complex traffic environment and the effectiveness of operation, predicting the risk of collision by combining pedestrian and vehicle behavior data, and adjusting external signals according to real-time action parameters, thereby improving driving safety and reducing the probability of traffic accidents.

Description

Technical Field

[0001] The present invention relates to the field of autonomous driving technology, and in particular to a method and system for interacting with external signals of an automobile. Background Art

[0002] The field of autonomous driving technology develops and implements automated systems to enable cars to travel with minimal or no human intervention. It combines machine learning, artificial intelligence, sensor technology, and computer vision to achieve autonomous navigation and decision-making of vehicles. It uses radar, cameras, laser scanning, and maps to collect data on the surrounding environment and identify paths and obstacles, enabling cars to make decisions and perform operations, including acceleration, steering, and braking, with the aim of improving road safety, reducing traffic accidents, optimizing traffic flow, and improving the overall efficiency of the transportation system.

[0003] Among them, the automobile external signal interaction method aims to enable the automobile to achieve effective interaction with the external environment by collecting and responding to external signals, using intelligent decision-making to analyze and process data collected in the external environment, optimize the vehicle's response mechanism, and enable the vehicle to adjust the interactive functions according to the current driving mode, external environment and application scenarios, including automatic adjustment of lights and multiple signal devices to match target roads and traffic conditions, enhance the vehicle's autonomy and adaptability, improve driving safety, and provide drivers and passengers with an intelligent driving experience.

[0004] Traditional external signal interaction methods rely on preset rules and parameters to react in urban traffic scenarios with high environmental complexity and rapid changes, which limits the flexibility and accuracy of responding to emergencies. They are difficult to adapt to environmental changes under rapidly changing traffic conditions and extreme weather conditions, including rainy and foggy days when the output of light and sound signals is insufficient to provide the necessary warning effect due to visual impairment. In areas with dense pedestrians, including those around schools and hospitals, it is impossible to accurately assess the intentions and movements of pedestrians, making it difficult to provide effective warnings and adjust driving strategies in advance, resulting in increased driving safety risks and affecting the safety of pedestrians and vehicles. Summary of the invention

[0005] The purpose of the present invention is to solve the shortcomings of the prior art and to propose a method and system for automobile external signal interaction.

[0006] In order to achieve the above object, the present invention adopts the following technical solution, a method for interacting with external signals of an automobile, comprising the following steps:

[0007] S1: Based on the vehicle radar monitoring data, it analyzes and identifies obstacles in multiple directions of the vehicle in real time, records the location, moving speed and size information of multiple obstacles, and generates obstacle monitoring data;

[0008] S2: Based on the obstacle monitoring data, analyzing the speed, position, size and shape of multiple obstacles, identifying the types of multiple obstacles, and generating object type analysis results;

[0009] S3: According to the object type analysis result, the vehicle geographic location information and the surrounding environment image are collected and analyzed in real time through the image acquisition device and the GPS sensor, the type of the scene in which the vehicle is located is analyzed, and the environmental scene recognition result is generated;

[0010] S4: According to the environmental scene recognition result, evaluating the noise level and lighting conditions in the external environment, adjusting the vehicle external signal control parameters, and generating environmental response adjustment parameters;

[0011] S5: Based on the environmental response adjustment parameter, by analyzing the behavior data of multiple pedestrians and vehicles and combining the scene type in which the vehicle is located, predicting the behavior patterns of multiple pedestrians and vehicles, and generating pedestrian and vehicle behavior information;

[0012] S6: Based on the pedestrian and vehicle behavior information, the real-time operating parameters of the vehicle are monitored in real time, and the type and relative position information of the obstacle are combined to evaluate the vehicle collision risk and adjust the external signal strength to generate external signal control parameters.

[0013] As a further solution of the present invention, the obstacle monitoring data includes obstacle coordinate information, obstacle real-time speed data, and obstacle size information; the object type analysis results include obstacle type identification results, relative orientation calculation results, and movement trajectory prediction data; the environmental scene identification results include road type information, environmental building information, and traffic sign recognition records; the environmental response adjustment parameters include alarm volume adjustment results, light signal control parameters, and severe weather response adjustment parameters; the pedestrian and vehicle behavior information includes pedestrian behavior pattern prediction results, vehicle predicted moving direction, and pedestrian-vehicle interaction mode; the external signal control parameters include warning signal priority settings, signal response types for multiple obstacles, and signal transmission time interval adjustment parameters.

[0014] As a further solution of the present invention, based on the vehicle radar monitoring data, the obstacles in multiple directions of the vehicle are analyzed and identified in real time, and the positions, moving speeds and size information of multiple obstacles are recorded. The steps of generating obstacle monitoring data are specifically as follows:

[0015] S101: Analyze the radar signal based on the vehicle radar monitoring data, identify objects in multiple directions of the vehicle, calculate the position information and moving speed of the objects, and obtain the radar signal analysis result;

[0016] S102: Analyze the relative directions and distances of multiple objects based on the radar signal analysis result, calculate the geometric dimensions of the objects, and obtain object feature information;

[0017] S103: Based on the object feature information, size, position and speed information of multiple obstacles are formatted and recorded to generate obstacle monitoring data.

[0018] As a further solution of the present invention, based on the obstacle monitoring data, the speed, position, size and shape of multiple obstacles are analyzed to identify the types of multiple obstacles, and the steps of generating object type analysis results are specifically as follows:

[0019] S201: performing morphological analysis on multiple obstacles and identifying shape features, including size and shape, according to the obstacle monitoring data, to obtain morphological feature analysis results;

[0020] S202: According to the morphological feature analysis result, combined with the moving speed and shape features, the types of multiple obstacles are identified, including pedestrians, vehicles, and road facilities, to obtain obstacle type information;

[0021] S203: According to the obstacle type information, the movement trajectories of multiple obstacles are continuously monitored and recorded through the identified obstacle information to generate an object type analysis result.

[0022] As a further solution of the present invention, according to the object type analysis result, the steps of collecting and analyzing the vehicle geographic location information and the surrounding environment image in real time through the image acquisition device and the GPS sensor, analyzing the type of the scene in which the vehicle is located, and generating the environmental scene recognition result are specifically as follows:

[0023] S301: According to the object type analysis result, the geographic coordinate information of the vehicle and the real-time image data of the surrounding environment are collected in real time through an image acquisition device and a GPS sensor to obtain geographic and image data;

[0024] S302: Based on the geographic and image data, identify various road types and traffic signs, including stop signs and traffic lights, through image analysis, evaluate the type of environment the current vehicle is in, and generate road environment feature information;

[0025] S303: Based on the road environment feature information, by comparing it with the features of multiple scenes and combining it with the vehicle location information, the scene type of the vehicle is identified, including commercial streets, school areas, hospital areas, and highways, and an environmental scene recognition result is generated.

[0026] As a further solution of the present invention, the steps of evaluating the noise level and lighting conditions in the external environment, adjusting the vehicle external signal control parameters, and generating the environmental response adjustment parameters are specifically as follows:

[0027] S401: Based on the environmental scene recognition result, the noise level of the environment is monitored in real time by a sound sensor, and a noise threshold is evaluated according to the scene type to obtain a noise level analysis result;

[0028] S402: Based on the noise level analysis result, in combination with the light sensor, the ambient light condition is evaluated in real time, and the warning light intensity of the vehicle is adjusted according to the lighting requirements of the differentiated time and scene, and a light parameter calculation result is generated;

[0029] S403: Based on the calculation result of the illumination parameters and taking into account the scene requirements, the sound and light setting parameters of the vehicle alarm are adjusted, including increasing the sound intensity in commercial areas and reducing the sound intensity in school areas, and generating environmental response adjustment parameters.

[0030] As a further solution of the present invention, based on the environmental response adjustment parameter, by analyzing the behavior data of multiple pedestrians and vehicles, combined with the scene type in which the vehicle is located, predicting the behavior patterns of multiple pedestrians and vehicles, and generating pedestrian and vehicle behavior information are specifically as follows:

[0031] S501: Based on the environmental response adjustment parameters, using urban traffic monitoring, collect and record the behavior data of pedestrians and vehicles in various scenarios, including movement paths and dwell time, to form a traffic behavior data set;

[0032] S502: Based on the traffic behavior data set, analyzing the behavior patterns of pedestrians and vehicles in various scenarios, including sidewalks and intersections, recording the behavior trends and pattern changes of people in various scenarios, and generating behavior pattern evaluation results;

[0033] S503: Based on the behavior pattern evaluation result and in combination with the scene type in which the vehicle is located, the behavior changes and movement paths of pedestrians and cars in multiple directions of the car are predicted to generate pedestrian and vehicle behavior information.

[0034] As a further solution of the present invention, according to the pedestrian and vehicle behavior information, the real-time operating parameters of the vehicle are monitored in real time, and the type and relative position information of the obstacle are combined to evaluate the vehicle collision risk and adjust the external signal strength. The steps of generating the external signal control parameters are specifically as follows:

[0035] S601: Based on the pedestrian and vehicle behavior information, multiple operating parameters of the vehicle are collected in real time, including vehicle speed and acceleration data, and the real-time position information of the vehicle is recorded to generate dynamic vehicle operation data;

[0036] S602: Based on the vehicle dynamic operation data and in combination with the identified obstacle type information, the relative positions of the vehicle and multiple surrounding obstacles are evaluated, and a Monte Carlo simulation algorithm is used to calculate the collision probability to obtain a collision risk analysis result;

[0037] S603: According to the collision risk analysis result, the vehicle external signal control parameters are adjusted to match the real-time traffic and environmental conditions, including enhancing the visibility of warning lights and adjusting the intensity of alarm sounds, and the external signal control parameters are generated.

[0038] As a further solution of the present invention, the Monte Carlo simulation algorithm is according to the formula:

[0039]

[0040] Calculate the collision probability, where P improved is the collision probability, N hit is the number of scenarios predicted to collide with obstacles in the simulation, α is the distance weight coefficient, D is the average obstacle distance, β is the speed weight coefficient, V is the average vehicle speed, γ is the density weight coefficient, S is the surrounding obstacle density, and N total is the total number of scenarios simulated.

[0041] A vehicle external signal interaction system, the vehicle external signal interaction system is used to execute the above-mentioned vehicle external signal interaction method, the system comprises:

[0042] The obstacle analysis module analyzes obstacles in multiple directions of the vehicle in real time based on the vehicle radar monitoring data, records the position, moving speed and size of multiple objects, and generates object recognition record data;

[0043] The object recognition module analyzes the shape and size of the obstacle based on the object recognition record data, and identifies the category of the object, including pedestrians, vehicles, and road facilities, and generates an obstacle recognition result;

[0044] Based on the obstacle recognition result, the scene analysis module uses image acquisition equipment and GPS sensors to analyze the vehicle's geographic location and environmental identification in real time, identify the road and area type where the vehicle is located, and adjust the vehicle's external signal control parameters to generate an environmental type response result;

[0045] The behavior prediction module analyzes the behavior data of pedestrians and vehicles in multiple scenes based on the environment type response result, predicts the behavior patterns of multiple pedestrians and vehicles in combination with the scene type in which the vehicle is located, and generates a behavior pattern prediction result;

[0046] The signal adjustment module monitors various parameters of the vehicle operation in real time, including speed and acceleration, based on the behavior pattern prediction results, and adjusts the intensity and type of the external warning signal in combination with the real-time environment and obstacle information to generate external signal control parameters.

[0047] Compared with the prior art, the advantages and positive effects of the present invention are:

[0048] In the present invention, the position, speed and size of obstacles are analyzed in real time through vehicle radar monitoring data, and the types of obstacles, including pedestrians and vehicles, are identified. The image acquisition device and GPS sensor are combined to analyze the type of scene the car is in, and the signal strength is adjusted according to differentiated environmental conditions to improve the interactive responsiveness and accuracy of the vehicle, enhance the safety of the vehicle in complex traffic environments and the effectiveness of operation. By combining pedestrian and vehicle behavior data, the risk of collision is predicted, and external signals are adjusted according to real-time action parameters to improve driving safety and reduce the probability of traffic accidents. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] Figure 1 It is a schematic diagram of the workflow of the present invention;

[0050] Figure 2 This is a detailed flow chart of S1 of the present invention;

[0051] Figure 3 This is a detailed flow chart of S2 of the present invention;

[0052] Figure 4 This is a detailed flow chart of S3 of the present invention;

[0053] Figure 5 This is a detailed flow chart of S4 of the present invention;

[0054] Figure 6 This is a detailed flow chart of S5 of the present invention;

[0055] Figure 7 This is a detailed flow chart of S6 of the present invention;

[0056] Figure 8 It is a system flow chart of the present invention. DETAILED DESCRIPTION

[0057] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with 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.

[0058] In the description of the present invention, it should be understood that the terms "length", "width", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside" and the like indicate positions or positional relationships based on the positions or positional relationships shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, in the description of the present invention, "multiple" means two or more, unless otherwise clearly and specifically defined.

[0059] See also Figure 1 The present invention provides a technical solution, a method for interacting with external signals of an automobile, comprising the following steps:

[0060] S1: Based on the vehicle radar monitoring data, it analyzes and identifies obstacles in multiple directions of the vehicle in real time, records the location, moving speed and size information of multiple obstacles, and generates obstacle monitoring data;

[0061] S2: Based on the obstacle monitoring data, the speed, position, size and shape of multiple obstacles are analyzed to identify the types of multiple obstacles and generate object type analysis results;

[0062] S3: Based on the object type analysis results, the image acquisition device and GPS sensor are used to collect and analyze the vehicle's geographic location information and surrounding environment images in real time, analyze the type of scene the vehicle is in, and generate environmental scene recognition results;

[0063] S4: Based on the environmental scene recognition results, evaluate the noise level and lighting conditions in the external environment, adjust the vehicle external signal control parameters, and generate environmental response adjustment parameters;

[0064] S5: Based on the environmental response adjustment parameters, the behavior data of multiple pedestrians and vehicles are analyzed, combined with the scene type in which the vehicle is located, and the behavior patterns of multiple pedestrians and vehicles are predicted to generate pedestrian and vehicle behavior information;

[0065] S6: Based on the pedestrian and vehicle behavior information, the real-time operating parameters of the vehicle are monitored in real time. Combined with the type and relative position information of the obstacle, the vehicle collision risk is evaluated and the external signal strength is adjusted to generate the external signal control parameters.

[0066] The obstacle monitoring data includes obstacle coordinate information, obstacle real-time speed data, and obstacle size information. The object type analysis results include obstacle type identification results, relative orientation calculation results, and movement trajectory prediction data. The environmental scene recognition results include road type information, environmental building information, and traffic sign recognition records. The environmental response adjustment parameters include alarm volume adjustment results, light signal control parameters, and severe weather response adjustment parameters. The pedestrian and vehicle behavior information includes pedestrian behavior pattern prediction results, vehicle predicted movement direction, and pedestrian-vehicle interaction mode. The external signal control parameters include warning signal priority settings, signal response types for multiple obstacles, and signal transmission time interval adjustment parameters.

[0067] See also Figure 2 Based on the vehicle radar monitoring data, the system analyzes and identifies obstacles in multiple directions of the vehicle in real time, and records the location, moving speed and size information of multiple obstacles. The specific steps for generating obstacle monitoring data are as follows:

[0068] S101: Based on the vehicle radar monitoring data, the radar signal is analyzed, objects in multiple directions of the vehicle are identified, the position information and moving speed of the objects are calculated, and the process of obtaining the radar signal analysis result is specifically as follows;

[0069] In sub-step S101, based on the vehicle radar monitoring data, the collected radar signals are subjected to time-frequency analysis. By adopting the Doppler effect theory, the frequency change of the signal reflected by each object is used to estimate the speed relative to the radar, and the distance of the object is calculated by the time delay of the signal. The orientation of the object is located by the angle resolution and signal strength. The formula is: Among them, v b is the speed of the object relative to the radar, f b is the frequency shift caused by the Doppler effect, c b is the speed of light, f 0b is the radar transmitting frequency. The above method is used to combine the position information and speed information to obtain the radar signal analysis result.

[0070] S102: Based on the radar signal analysis result, the relative directions and distances of multiple objects are analyzed, the geometric dimensions of the objects are calculated, and the process of obtaining the feature information of the objects is specifically as follows;

[0071] In sub-step S102, based on the radar signal analysis results, the geometric dimensions of each detected object are calculated using triangulation. The width and height of the object are calculated using trigonometric functions based on the relative distance between the object and the radar and the radar's scanning angle. The relative directions are measured to calculate the spatial layout between the objects. The formula is: d b =2·t b ·sin(θ b / 2), where d b is the width or height of the object, t b is the straight-line distance from the radar to the object, θ b Scan the radar angle, identify the object size and spatial arrangement, and obtain object feature information.

[0072] S103: Based on the object feature information, the size, position and speed information of multiple obstacles are formatted and recorded, and the process of generating obstacle monitoring data is specifically as follows;

[0073] In sub-step S103, based on the object feature information, the size, position and speed information of the obstacle are sorted and standardized using data formatting technology. By creating a data recording template, the information of each obstacle is compiled into a database, and the consistency and accuracy of the information are ensured by a standardized method. The formula is: Among them, S b is the standardized information score, kb is the standardized coefficient, D b is the distance between the obstacle and the radar, v b is the obstacle speed, V max,b Generate obstacle detection data for the maximum speed in the measurement.

[0074] See also Figure 3 Based on the obstacle monitoring data, the speed, position, size and shape of multiple obstacles are analyzed to identify the types of multiple obstacles. The specific steps for generating object type analysis results are as follows:

[0075] S201: According to the obstacle monitoring data, a morphological analysis is performed on multiple obstacles and shape characteristics are identified, including size and shape, and the specific process of obtaining the morphological characteristic analysis result is as follows;

[0076] In sub-step S201, based on obstacle monitoring data, image processing technology is used to perform morphological analysis, edge detection algorithm is applied to determine the outer contour of the object, and shape matching technology is used to identify and classify the basic shapes of the object, including circle, rectangle, and polygon. The size and shape characteristics of the object are analyzed by parameterizing the target shape, including aspect ratio and area-to-perimeter ratio. The formula is: B c = l c ·w c , where A c is the area of ​​the circular object, r c is the radius of the circle, B c is the area of ​​the rectangular object, l c is the length of the rectangle, w c It is the width of the rectangle, records the morphological features, provides basic data for obstacle identification, and generates morphological feature analysis results.

[0077] S202: Based on the morphological feature analysis results, combined with the moving speed and shape features, the types of multiple obstacles are identified, including pedestrians, vehicles, and road facilities. The specific process of obtaining obstacle type information is as follows;

[0078] In sub-step S202, based on the morphological feature analysis results, combined with the object's moving speed information and shape features, a decision tree classification method is used to identify the type of obstacle, including objects with slow speed and rectangular shape are identified as pedestrians, and objects with fast speed and shape are identified as vehicles. The normalized shape parameters and speed data are used to classify objects to improve the accuracy and reliability of recognition. The formula is: Among them, T c is the object type, is the weight coefficient, It normalizes the features of objects, identifies the types of multiple obstacles, including pedestrians, vehicles, and road facilities, and generates obstacle type information.

[0079] S203: According to the obstacle type information, the process of continuously monitoring and recording the movement trajectories of multiple obstacles through the identified obstacle information to generate the object type analysis result is specifically as follows;

[0080] In sub-step S203, based on the obstacle type information, real-time tracking and monitoring technology is implemented to record the movement trajectory of each identified obstacle, and Kalman filtering is used to predict the location of the obstacle and continuously monitor the movement. The formula is: tc =p c +v tc ·Δt c , where p tc is the predicted position, p c is the current position, v tc is the moving speed, Δt c The moving trajectories of multiple obstacles are tracked and recorded for time intervals, and object type analysis results are generated.

[0081] See also Figure 4 According to the object type analysis results, the image acquisition device and GPS sensor are used to collect and analyze the vehicle's geographic location information and surrounding environment images in real time, analyze the type of scene the vehicle is in, and generate the environmental scene recognition results in the following specific steps:

[0082] S301: According to the object type analysis result, the geographic coordinate information of the vehicle and the real-time image data of the surrounding environment are collected in real time through the image acquisition device and the GPS sensor, and the specific process of obtaining the geographic and image data is as follows;

[0083] In sub-step S301, according to the object type analysis result, the image acquisition device and the GPS sensor are used to collect the vehicle's geographic coordinate information and the real-time image data of the surrounding environment in real time, including synchronously collecting data from multiple data sources and synchronizing the target data to the central processing unit. The formula is: Among them, G s is the geographic coordinate value of the vehicle’s current location, x s is the value of longitude information, y s The value of latitude information is used to obtain geographic and image data.

[0084] S302: Based on geographic and image data, a process of identifying various road types and traffic signs, including stop signs and traffic lights, through image analysis, evaluating the type of environment the current vehicle is in, and generating road environment feature information is as follows;

[0085] In sub-step S302, based on geographic and image data, image processing technology is used to analyze and identify road types and traffic signs. Different roads and traffic signs are identified through image feature extraction, including edge detection and color analysis, and feature vectors in the image are calculated. The formula is: s =α s ·A s +β s ·B s +γ s ·C s , where F s is the calculation result of the image feature vector, A s is the color histogram feature of the image, B s is the edge detection result, C s is the texture analysis result, α s is the weight coefficient of the color feature, which adjusts the contribution of color information in the overall feature vector, β s is the weight coefficient of the edge feature, which determines the importance of edge information in the feature vector, γ s It is the weight coefficient of texture features, which affects the contribution of texture information to the overall analysis results, evaluates the type of road environment the current car is in, and generates road environment feature information.

[0086] S303: Based on the road environment feature information, by comparing with the features of multiple scenes and combining with the vehicle location information, the scene type of the vehicle is identified, including a commercial street, a school area, a hospital area, and a highway. The specific process of generating the environmental scene recognition result is as follows;

[0087] In sub-step S303, based on the road environment feature information and the real-time location information of the vehicle, a classification algorithm is used to identify the scene type where the vehicle is located. The formula is: Among them, S s is the score of the scene type, is the weight of the k1th feature, It is the measurement value of the k1th feature. It identifies the environmental scene based on the data collected on site, helps the vehicle match differentiated road conditions, and generates environmental scene recognition results.

[0088] See also Figure 5 ,According to the environmental scene recognition results, the noise level and lighting conditions in the external environment are evaluated, and the vehicle external signal control parameters are adjusted. The steps of generating environmental response adjustment parameters are as follows:

[0089] S401: Based on the environmental scene recognition result, the noise level of the environment is monitored in real time through the sound sensor, and the noise threshold is evaluated according to the scene type to obtain the noise level analysis result. The specific process is as follows;

[0090] In sub-step S401, based on the environmental scene recognition result, the noise level of the environment is monitored in real time through the vehicle's built-in high-sensitivity sound sensor. Differentiated noise thresholds are preset according to differentiated scene types, including commercial areas and school areas, to evaluate whether the noise level of the current environment exceeds the normal range. Frequency analysis and sound intensity measurement technology are used to quantitatively analyze the environmental noise and adaptively adjust the sensitivity of the sensor. The formula is: Among them, L r Indicates the noise level (decibel), I r is the measured sound intensity, I 0r To refer to the sound intensity, usually the lowest audible sound below the hearing threshold, to ensure accurate assessment and recording of the noise level of the environment and generate noise level analysis results.

[0091] S402: Based on the noise level analysis result, in combination with the light sensor, the ambient light condition is evaluated in real time, and the warning light intensity of the vehicle is adjusted according to the lighting requirements of the differentiated time and scene, and the process of generating the light parameter calculation result is specifically as follows;

[0092] In sub-step S402, based on the noise level analysis results and combined with the data of the light sensor, the ambient light conditions are evaluated in real time, and the warning light intensity of the vehicle is automatically adjusted according to the changes in ambient light and the lighting requirements of the scene, including real-time monitoring of the light intensity and dynamic adjustment of the light brightness according to differentiated time periods and scene requirements. The formula is: Among them, E r is the ambient light evaluation coefficient, L current is the current measured light intensity, L scene,r The illumination intensity required for the target scene is calculated by adjusting the vehicle warning lights in combination with time and scene changes to generate illumination parameter calculation results.

[0093] S403: Based on the calculation result of the illumination parameter and considering the scene requirements, the sound and light setting parameters of the vehicle alarm are adjusted, including increasing the sound intensity in the commercial area and reducing the sound intensity in the school area. The specific process of generating the environmental response adjustment parameters is as follows;

[0094] In sub-step S403, based on the calculation results of the illumination parameters, the vehicle alarm system is adjusted according to the scene requirements, including the sound and light setting parameters. The alarm sound is enhanced in the commercial area to break through the noisy background, while the sound intensity is reduced in the school area to reduce interference. The light intensity is also adjusted according to the time period and ambient light adaptability to ensure that the warning effect does not cause excessive light pollution. The formula is: S r =k r ·(v r +d scene,r ), where S r Set parameters for the adjusted alarm, k ris the adjustment coefficient, v r is the ambient volume or light level, d scene,r The differentiated adjustment amount is based on the scene target requirements to ensure that the vehicle can adaptively adjust the alarm system in differentiated environments and generate environmental response adjustment parameters.

[0095] See also Figure 6 Based on the environmental response adjustment parameters, the behavior data of multiple pedestrians and vehicles are analyzed, combined with the scene type in which the vehicle is located, and the behavior patterns of multiple pedestrians and vehicles are predicted. The steps for generating pedestrian and vehicle behavior information are as follows:

[0096] S501: Based on the environmental response adjustment parameters, using urban traffic monitoring, collecting and recording the behavior data of pedestrians and vehicles in various scenarios, including movement paths and dwelling times, to form a traffic behavior data set, specifically, the process is as follows;

[0097] In sub-step S501, based on the environmental response adjustment parameters, the urban traffic monitoring system is used to collect and record the behavior data of pedestrians and vehicles in various scenarios in real time, including the movement paths of pedestrians and the driving trajectories of vehicles and the residence time at key locations. Data collection is carried out through high-definition cameras and sensor networks to ensure that the collected data accurately reflects traffic behavior. The formula is: Among them, P a represents the behavior path, v(t) is the speed at time t, t1 and t2 represent the start and end time of the observation period, dt represents a small time interval, which is used in integration to represent instantaneous changes in continuous time periods, d is the differential symbol, and t represents time, forming a traffic behavior data set.

[0098] S502: Based on the traffic behavior data set, analyze the behavior patterns of pedestrians and vehicles in various scenarios, including sidewalks and intersections, record the behavior trends and pattern changes of people in various scenarios, and generate the behavior pattern evaluation results. The specific process is as follows;

[0099] In sub-step S502, based on the traffic behavior data set, the behavior patterns of pedestrians and vehicles in various scenarios are analyzed, including recording and comparing the behavior trends and pattern changes in different time periods at multiple key locations such as sidewalks and intersections. Through statistical analysis and behavior modeling, the typical behavior patterns in the target scenario are identified. The formula is: Among them, M a is the behavior pattern evaluation result, c i2 is the behavior coefficient of the i2th scenario, The number of behavior data points for the i2th scene generates the behavior pattern evaluation result.

[0100] S503: Based on the behavior pattern evaluation results and in combination with the scene type in which the vehicle is located, the behavior changes and movement paths of pedestrians and vehicles in multiple directions of the vehicle are predicted, and the process of generating pedestrian and vehicle behavior information is specifically as follows;

[0101] In sub-step S503, based on the behavior pattern evaluation results and the scene type in which the vehicle is located, the behavior changes and movement paths of pedestrians and multiple vehicles in multiple directions are predicted, and the driving strategy is adjusted to match the scene changes. The formula is: Among them, F a is the behavior prediction function, a0 is the baseline behavior prediction, are the coefficients of the prediction model, The behavior feature value of the m2th scene type is used to generate pedestrian and vehicle behavior information.

[0102] See also Figure 7 ,According to the pedestrian and vehicle behavior information, the real-time operating parameters of the vehicle are monitored in real time, and the type and relative position information of the obstacle are combined to evaluate the vehicle collision risk and adjust the external signal strength. The specific steps for generating the external signal control parameters are as follows:

[0103] S601: Based on the pedestrian and vehicle behavior information, multiple vehicle operation parameters are collected in real time, including vehicle speed and acceleration data, and the real-time position information of the vehicle is recorded to generate the vehicle dynamic operation data. Specifically, the process is as follows;

[0104] In sub-step S601, based on the pedestrian and vehicle behavior information, the vehicle's operating parameters, including the vehicle's speed and acceleration data, are collected in real time using the vehicle's onboard sensor system. The vehicle's real-time location information is recorded using GPS technology to ensure the real-time and accuracy of the data, and the vehicle's dynamic operating data is constructed. The formula is: V p =v(t),A p =a(t), where V p is the vehicle speed, A p is the vehicle acceleration, v(t) and a(t) represent the speed and acceleration at time t, respectively, to ensure that the collected operating parameters accurately reflect the real-time dynamics of the vehicle and generate vehicle dynamic operating data.

[0105] S602: Based on the vehicle dynamic operation data and the identified obstacle type information, the relative positions of the vehicle and the surrounding multiple obstacles are evaluated, and the collision probability is calculated using the Monte Carlo simulation algorithm to obtain the collision risk analysis result. The specific process is as follows;

[0106] In sub-step S602, based on the vehicle dynamic operation data and combined with the identified obstacle type information, a Monte Carlo simulation algorithm is used to evaluate the relative position and movement trend of the vehicle and multiple surrounding obstacles, calculate the collision probability, and evaluate and analyze the collision risk by simulating differentiated driving scenarios and obstacle behaviors to generate a collision risk analysis result.

[0107] Monte Carlo simulation algorithm, according to the formula:

[0108]

[0109] Calculate the collision probability, where P improved is the collision probability, which is used to indicate the possibility of a vehicle colliding with an obstacle under target conditions, N hit is the number of scenarios predicted to collide with obstacles in the simulation, which is used to measure the number of actual collisions in the simulation test. α is the distance weight coefficient, which is used to adjust the influence of the distance factor in the collision probability calculation. D is the average obstacle distance, which is used to measure the average distance between the vehicle and the nearest obstacle. β is the speed weight coefficient, which is used to adjust the influence of the speed factor in the collision probability calculation. V is the average vehicle speed, which is used to indicate the average speed of the vehicle during the simulation. γ is the density weight coefficient, which is used to adjust the influence of the density factor in the collision probability calculation. S is the surrounding obstacle density, which is used to indicate the average density of obstacles in the area around the vehicle. N total The total number of scenarios simulated is used to indicate the total number of collision simulations.

[0110] The specific execution process of the formula is as follows:

[0111] Through the environmental monitoring system, the location of obstacles around the vehicle and the running speed data of the vehicle are obtained. According to real-time traffic monitoring, the statistical model is used to obtain the average obstacle distance D, the average vehicle speed V and the obstacle density S. The parameters are substituted into the formula to calculate the collision probability P. improved , used to adjust and optimize vehicle control parameters and enhance traffic safety management.

[0112] S603: According to the collision risk analysis result, adjusting the vehicle external signal control parameters to match the real-time traffic and environmental conditions, including enhancing the visibility of the warning light and adjusting the alarm sound intensity. The specific process of generating the external signal control parameters is as follows;

[0113] In sub-step S603, according to the collision risk analysis results, the vehicle external signal control parameters are adjusted to match the real-time traffic and environmental conditions, including enhancing the visibility of the warning light and adjusting the alarm sound intensity, improving the warning effect and matching the differentiated traffic environment, and dynamically adjusting the vehicle's warning system to respond to changes in the external environment by using a feedback control system. The formula is: S p=k p ·(λ p +μ p ), where S p is the external signal control parameter, k p is the adjustment coefficient, λ p is the warning light intensity parameter, μ p Generate external signal control parameters for the alarm sound intensity parameters to ensure that the vehicle effectively notifies surrounding pedestrians and vehicles in complex environments and reduces the risk of collision.

[0114] See also Figure 8 , a vehicle external signal interaction system, the vehicle external signal interaction system is used to execute the above-mentioned vehicle external signal interaction method, the system comprises:

[0115] The obstacle analysis module analyzes obstacles in multiple directions of the vehicle in real time based on the vehicle radar monitoring data, records the position, moving speed and size of multiple objects, and generates object recognition record data;

[0116] The object recognition module analyzes the shape and size of obstacles based on the object recognition record data, and identifies the categories of objects, including pedestrians, vehicles, and road facilities, and generates obstacle recognition results;

[0117] Based on the obstacle recognition results, the scene analysis module uses image acquisition equipment and GPS sensors to analyze the vehicle's geographic location and environmental identification in real time, identify the road and area type the vehicle is in, and adjust the vehicle's external signal control parameters to generate environmental type response results;

[0118] The behavior prediction module analyzes the behavior data of pedestrians and vehicles in multiple scenes based on the environmental type response results, and predicts the behavior patterns of multiple pedestrians and vehicles in combination with the scene type in which the vehicle is located, and generates behavior pattern prediction results;

[0119] The signal adjustment module monitors various parameters of vehicle operation, including speed and acceleration, in real time based on the behavior pattern prediction results. It adjusts the intensity and type of external warning signals and generates external signal control parameters based on real-time environment and obstacle information.

[0120] The above are only preferred embodiments of the present invention and are not intended to limit the present invention in other forms. Any technician familiar with the profession may use the technical contents disclosed above to change or modify them into equivalent embodiments with equivalent changes and apply them to other fields. However, any simple modification, equivalent change and modification made to the above embodiments based on the technical essence of the present invention without departing from the technical solution of the present invention still falls within the protection scope of the technical solution of the present invention.

Claims

1. A method for interacting with external signals of an automobile, characterized in that: The following steps are involved: Based on vehicle radar monitoring data, it analyzes and identifies obstacles in multiple directions of the vehicle in real time, records the location, moving speed and size information of multiple obstacles, and generates obstacle monitoring data; Based on the obstacle monitoring data, analyzing the speed, position, size and shape of multiple obstacles, identifying the types of multiple obstacles, and generating object type analysis results; According to the object type analysis result, the vehicle geographic location information and surrounding environment images are collected and analyzed in real time through image acquisition equipment and GPS sensors, the type of scene in which the vehicle is located is analyzed, and an environmental scene recognition result is generated; According to the environmental scene recognition result, evaluating the noise level and lighting conditions in the external environment, adjusting the vehicle external signal control parameters, and generating environmental response adjustment parameters; Based on the environmental response adjustment parameters, by analyzing the behavior data of multiple pedestrians and vehicles and combining the scene type in which the vehicle is located, the behavior patterns of multiple pedestrians and vehicles are predicted to generate pedestrian and vehicle behavior information; Based on the pedestrian and vehicle behavior information, the real-time operating parameters of the vehicle are monitored in real time, and the type and relative position information of the obstacle are combined to evaluate the vehicle collision risk and adjust the external signal strength to generate the external signal control parameters; According to the pedestrian and vehicle behavior information, the real-time operating parameters of the vehicle are monitored in real time, and the type and relative position information of the obstacle are combined to evaluate the vehicle collision risk and adjust the external signal strength. The steps of generating the external signal control parameters are specifically as follows: Based on the pedestrian and vehicle behavior information, multiple operating parameters of the vehicle are collected in real time, including vehicle speed and acceleration data, real-time vehicle location information is recorded, and vehicle dynamic operation data is generated; Based on the vehicle dynamic operation data and in combination with the identified obstacle type information, the relative positions of the vehicle and multiple surrounding obstacles are evaluated, and the collision probability is calculated using a Monte Carlo simulation algorithm to obtain a collision risk analysis result; According to the collision risk analysis results, the vehicle external signal control parameters are adjusted to match the real-time traffic and environmental conditions, including enhancing the visibility of warning lights and adjusting the intensity of alarm sounds, to generate external signal control parameters.

2. The vehicle external signal interaction method according to claim 1, characterized in that: The obstacle monitoring data includes obstacle coordinate information, obstacle real-time speed data, and obstacle size information; the object type analysis results include obstacle type identification results, relative orientation calculation results, and movement trajectory prediction data; the environmental scene identification results include road type information, environmental building information, and traffic sign recognition records; the environmental response adjustment parameters include alarm volume adjustment results, light signal control parameters, and severe weather response adjustment parameters; the pedestrian and vehicle behavior information includes pedestrian behavior pattern prediction results, vehicle predicted movement direction, and pedestrian-vehicle interaction mode; the external signal control parameters include warning signal priority settings, signal response types for multiple obstacles, and signal transmission time interval adjustment parameters.

3. The vehicle external signal interaction method according to claim 1, characterized in that: Based on the vehicle radar monitoring data, the obstacles in multiple directions of the vehicle are analyzed and identified in real time, and the location, moving speed and size information of multiple obstacles are recorded. The specific steps for generating obstacle monitoring data are as follows: Based on the vehicle radar monitoring data, the radar signal is analyzed to identify objects in multiple directions of the vehicle, calculate the location information and moving speed of the objects, and obtain the radar signal analysis results; Based on the radar signal analysis results, the relative directions and distances of multiple objects are analyzed, the geometric dimensions of the objects are calculated, and the feature information of the objects is obtained; Based on the object feature information, the size, position and speed information of multiple obstacles are formatted and recorded to generate obstacle monitoring data.

4. The vehicle external signal interaction method according to claim 1, characterized in that: Based on the obstacle monitoring data, the speed, position, size and shape of multiple obstacles are analyzed to identify the types of multiple obstacles, and the steps of generating object type analysis results are specifically as follows: According to the obstacle monitoring data, a morphological analysis is performed on a plurality of obstacles and shape characteristics are identified, including size and shape, to obtain a morphological characteristic analysis result; According to the morphological feature analysis results, combined with the moving speed and shape features, the types of multiple obstacles are identified, including pedestrians, vehicles, and road facilities, to obtain obstacle type information; According to the obstacle type information, the movement trajectories of multiple obstacles are continuously monitored and recorded through the identified obstacle information to generate object type analysis results.

5. The vehicle external signal interaction method according to claim 1, characterized in that: According to the object type analysis result, the steps of collecting and analyzing the vehicle's geographic location information and surrounding environment images in real time through image acquisition equipment and GPS sensors, analyzing the type of scene the vehicle is in, and generating environmental scene recognition results are specifically as follows: According to the object type analysis result, the geographic coordinate information of the vehicle and the real-time image data of the surrounding environment are collected in real time through the image acquisition device and the GPS sensor to obtain geographic and image data; Based on the geographic and image data, identify various road types and traffic signs, including stop signs and traffic lights, through image analysis, evaluate the type of environment the vehicle is currently in, and generate road environment feature information; According to the road environment characteristic information, by comparing with the characteristics of multiple scenes and combining with the vehicle location information, the scene type of the vehicle is identified, including commercial streets, school areas, hospital areas, and highways, and an environmental scene recognition result is generated.

6. The vehicle external signal interaction method according to claim 1, characterized in that: According to the environmental scene recognition result, the steps of evaluating the noise level and lighting conditions in the external environment, adjusting the vehicle external signal control parameters, and generating the environmental response adjustment parameters are specifically as follows: Based on the environmental scene recognition result, the noise level of the environment is monitored in real time by a sound sensor, and the noise threshold is evaluated according to the scene type to obtain a noise level analysis result; Based on the noise level analysis results, in combination with the light sensor, the ambient light conditions are evaluated in real time, and the warning light intensity of the vehicle is adjusted according to the lighting requirements of the differentiated time and scene, and the light parameter calculation results are generated; Based on the calculation results of the illumination parameters and taking into account the scene requirements, the sound and light setting parameters of the vehicle alarm are adjusted, including enhancing the sound intensity in commercial areas and reducing the sound intensity in school areas, thereby generating environmental response adjustment parameters.

7. The vehicle external signal interaction method according to claim 1, characterized in that: Based on the environmental response adjustment parameter, by analyzing the behavior data of multiple pedestrians and vehicles and combining the scene type in which the vehicle is located, the behavior patterns of multiple pedestrians and vehicles are predicted, and the steps of generating pedestrian and vehicle behavior information are specifically as follows: Based on the environmental response adjustment parameters, using urban traffic monitoring, collect and record the behavior data of pedestrians and vehicles in various scenarios, including movement paths and dwell time, to form a traffic behavior data set; Based on the traffic behavior dataset, analyze the behavior patterns of pedestrians and vehicles in various scenarios, including sidewalks and intersections, record the behavior trends and pattern changes of people in various scenarios, and generate behavior pattern evaluation results; According to the behavior pattern evaluation results, combined with the scene type in which the vehicle is located, the behavior changes and movement paths of pedestrians and cars in multiple directions of the car are predicted to generate pedestrian and vehicle behavior information.

8. The vehicle external signal interaction method according to claim 1, characterized in that: The Monte Carlo simulation algorithm is based on the formula: Calculate the collision probability, where is the collision probability, is the number of scenarios predicted to collide with obstacles in the simulation, is the distance weight coefficient, is the average obstacle distance, is the speed weight coefficient, is the average vehicle speed, is the density weight coefficient, is the density of surrounding obstacles, is the total number of scenarios simulated.

9. An automobile external signal interaction system, characterized in that: According to the automobile external signal interaction method according to any one of claims 1 to 8, the system comprises: The obstacle analysis module analyzes obstacles in multiple directions of the vehicle in real time based on the vehicle radar monitoring data, records the position, moving speed and size of multiple objects, and generates object recognition record data; The object recognition module analyzes the shape and size of the obstacle based on the object recognition record data, and identifies the category of the object, including pedestrians, vehicles, and road facilities, and generates an obstacle recognition result; Based on the obstacle recognition result, the scene analysis module uses image acquisition equipment and GPS sensors to analyze the vehicle's geographic location and environmental identification in real time, identify the road and area type where the vehicle is located, and adjust the vehicle's external signal control parameters to generate an environmental type response result; The behavior prediction module analyzes the behavior data of pedestrians and vehicles in multiple scenes based on the environment type response result, predicts the behavior patterns of multiple pedestrians and vehicles in combination with the scene type in which the vehicle is located, and generates a behavior pattern prediction result; The signal adjustment module monitors various parameters of the vehicle operation in real time, including speed and acceleration, based on the behavior pattern prediction results, and adjusts the intensity and type of the external warning signal in combination with the real-time environment and obstacle information to generate external signal control parameters.

Images