Intelligent driving method and system based on traffic flow speed regulation
By screening and processing vehicle sensor data, calculating the characteristic values of traffic flow speed, and formulating corresponding speed control strategies, the problems of low traffic speed perception accuracy and poor adaptability of speed decisions in the existing traffic speed regulation technology are solved, achieving a more efficient, safer and more personalized driving experience.
Patent Information
- Application Number
- CN202510067450.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-01-16
- Publication Date
- 2025-05-23
AI Technical Summary
The existing traffic speed regulation technology has low accuracy in traffic speed perception, poor adaptability of speed decision-making and control strategies, insufficient personalized settings for users, and it is difficult to improve the intelligent level of traffic speed regulation by collecting and processing on-board sensor data.
By collecting vehicle information data, filtering the speed reference sample vehicles, calculating the characteristic values of the traffic speed, and formulating a speed control strategy based on these characteristic values. The method includes initializing the preset number of velocity reference sample vehicles, constructing a screening strategy, filtering based on lane priority principles, speed difference, lateral distance and acceleration, and calculating the traffic velocity characteristic value through the velocity segment under weighted average, median or variance threshold.
It improves the accuracy and applicability of traffic speed perception, enhances the intelligence level of speed decision-making and control, provides a more personalized driving experience, and improves driving safety and comfort.
Smart Images
Figure CN120024329A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of intelligent network connection technology, and specifically to an intelligent driving method and system based on vehicle flow speed regulation. Background Art
[0002] With the rapid development of the automobile industry and the increasing pressure of urban traffic, intelligent driving technology has emerged to cope with traffic congestion, improve driving safety and optimize traffic flow. In recent years, the development of on-board sensors and the advancement of control algorithms have made it possible to monitor and analyze traffic speed in real time. Through on-board radars, laser rangefinders and cameras, vehicles can efficiently collect information about the surrounding environment. The integration of these technologies enables the autonomous driving system to dynamically adjust the driving speed by analyzing the data of surrounding vehicles, thereby achieving a more intelligent driving experience. The promotion of adaptive cruise control and traffic congestion assisted driving systems has also promoted the development of intelligent driving technologies related to traffic speed regulation, providing new solutions for the efficiency and safety of future transportation.
[0003] However, the existing intelligent driving systems still have obvious deficiencies in processing reference sample vehicles of traffic speed. Many systems rely on fixed speed limits and preset safety distances, which makes the vehicle's response ability weak under different traffic conditions and unable to adapt to complex and changeable road conditions. The current traffic speed detection mechanism mostly uses a single sensor for data collection. This method is easily disturbed in high-density traffic, resulting in the accuracy of speed data being affected, which in turn affects subsequent decision-making and control. These systems are often unable to screen out reference sample vehicles that match their own driving dynamics in real time, and lack a dynamic adjustment mechanism, which leads to the inability to effectively optimize speed decisions and control during driving. The existing technology lacks consideration of user driving habits and needs and cannot provide personalized speed control solutions. Therefore, how to achieve more accurate traffic speed perception, smarter speed decisions and control, and a more personalized driving experience has become an important direction for the development of traffic speed regulation technology. Summary of the invention
[0004] In view of the above-mentioned problems, the present invention is proposed.
[0005] Therefore, the technical problem solved by the present invention is: the existing vehicle speed control technology has the problems of low vehicle speed perception accuracy, poor adaptability of speed decision and control strategy, insufficient user personalized settings, and how to improve the intelligence level of vehicle speed control by collecting and processing vehicle-mounted sensor data.
[0006] To solve the above technical problems, the present invention provides the following technical solutions: an intelligent driving method based on traffic speed regulation, comprising collecting vehicle information data and screening speed reference sample vehicles; processing the data of the speed reference sample vehicles and calculating the characteristic value of the traffic speed; and formulating a speed control strategy based on the characteristic value of the traffic speed.
[0007] As a preferred solution of the intelligent driving method based on traffic speed regulation described in the present invention, wherein: the vehicle information data includes vehicle information data, surrounding vehicle information data, and distance information between the vehicle and surrounding vehicles; the vehicle information data includes vehicle speed data, vehicle position information, and vehicle acceleration data; the surrounding vehicle information data includes surrounding vehicle speed data, surrounding vehicle position information, and surrounding vehicle acceleration data.
[0008] As a preferred solution of the intelligent driving method based on traffic flow speed regulation described in the present invention, wherein: the screening of speed reference sample vehicles includes initializing a preset number of speed reference sample vehicles and constructing a screening strategy; the screening strategy includes screening based on lane priority principle, speed difference, lateral distance priority principle and acceleration; when screening is based on the lane priority principle, the surrounding vehicles in the lane where the vehicle is located and the adjacent lane are preferentially selected as speed reference sample vehicles; when screening is based on speed difference, a first speed difference range is set according to the speed difference between the surrounding vehicles and the vehicle, and the surrounding vehicles exceeding the first speed difference range are excluded, and the surrounding vehicles in the first speed difference range are retained as speed reference sample vehicles; when screening is based on the lateral distance priority principle, the lateral distance between the vehicle and the surrounding vehicles is partitioned and the corresponding lateral distance threshold is set. The lower the lateral distance threshold, the higher the priority of the vehicle as a speed reference sample vehicle; when screening is based on acceleration, an upper limit threshold and a lower limit threshold of acceleration are set to exclude surrounding vehicles above the upper limit threshold of acceleration or below the lower limit threshold of acceleration.
[0009] As a preferred solution of the intelligent driving method based on traffic speed regulation described in the present invention, wherein: the screening of speed reference sample vehicles also includes when the number of screened speed reference sample vehicles is less than the preset number of speed reference sample vehicles, selecting the remaining surrounding vehicles in a random order for supplementation, and the supplementation method satisfies the screening strategy.
[0010] As a preferred solution of the intelligent driving method based on traffic speed regulation described in the present invention, wherein: the characteristic value of the traffic speed is calculated, including processing the speed data of the screened speed reference sample vehicles after the number of the screened speed reference sample vehicles meets the preset number of the speed reference sample vehicles, and calculating the characteristic value representing the current traffic speed; the characteristic value calculation method of the current traffic speed includes a first type of calculation method, a second type of calculation method, and a third type of calculation method; the first type of calculation method includes assigning weights to the speed data of the speed reference sample vehicles, and taking the result of weighted averaging as the characteristic value of the current traffic speed, and the weight influencing factors include the lane where the speed reference sample vehicle is located, the lateral distance between the vehicle and the speed reference sample vehicle, and the speed reference The acceleration of the sample vehicles is considered, the weight value is adjusted based on the lane priority principle and the lateral distance priority principle in the screening strategy, and the acceleration fluctuation threshold is set to adjust the weight value; the second calculation method includes arranging the speed data of the speed reference sample vehicles in sequence, and selecting the median of the sorted speed data as the characteristic value of the current traffic speed; the third calculation method includes counting the speed data of the speed reference sample vehicles according to the speed segment under the variance threshold, and selecting the speed segment with the highest frequency as the characteristic value of the current traffic speed; when in the highway scene, the first calculation method is used; when in urban congestion or complex road conditions, the second calculation method is used; when in a low-speed vehicle queue, the third calculation method is used.
[0011] As a preferred solution of the intelligent driving method based on traffic speed regulation described in the present invention, wherein: the speed control strategy is formulated including controlling the vehicle speed to be greater than the traffic speed when the traffic speed changes within a range and is lower than the road speed limit; when the vehicle speed difference exceeds a first speed difference range, the acceleration is higher than an upper acceleration threshold or lower than a lower acceleration threshold, the vehicle speed is regulated in real time according to the current traffic speed, the vehicle speed is controlled to gradually approach the traffic speed, a smooth speed adjustment curve is used, the speed change per second is limited to a speed change threshold per second, and the vehicle speed is dynamically adjusted according to navigation data to avoid sudden braking or acceleration.
[0012] As a preferred solution of the intelligent driving method based on traffic speed regulation described in the present invention, the speed control strategy also includes setting a percentage threshold value above or below the traffic flow value, and adjusting the upper or lower speed limit.
[0013] Another object of the present invention is to provide an intelligent driving system based on traffic speed regulation, which can calculate the characteristic value of traffic speed by processing the data of speed reference sample vehicles, thereby solving the problems of insufficient accuracy and weak anti-interference ability of current traffic speed calculation technology.
[0014] As a preferred solution of the intelligent driving system based on vehicle flow speed regulation described in the present invention, it includes: a sample screening module, a vehicle flow speed calculation module, and a decision and control module.
[0015] The sample screening module is used to collect vehicle information data and screen speed reference sample vehicles; the traffic speed calculation module is used to process the data of speed reference sample vehicles and calculate the characteristic value of traffic speed; the decision and control module is used to formulate a speed control strategy based on the characteristic value of traffic speed.
[0016] A computer device includes a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement a step of an intelligent driving method based on traffic flow speed regulation.
[0017] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of an intelligent driving method based on vehicle flow speed regulation.
[0018] Beneficial effects of the present invention: The intelligent driving method based on traffic speed regulation provided by the present invention collects surrounding vehicle information and road data through on-board sensors, screens speed reference sample vehicles, effectively improves the relevance and applicability of the speed reference, reduces unnecessary interference, and realizes accurate judgment of the traffic state, thereby laying a solid foundation for subsequent data processing, and processes the data of the speed reference sample vehicles, calculates the characteristic value of the traffic speed, and can obtain more accurate and reliable traffic speed characteristic value, which provides a scientific basis for the formulation of speed control strategy and improves driving safety and comfort. Based on the characteristic value of the traffic speed, a speed control strategy is formulated, and speed control parameters are adjusted, and the speed of the vehicle is regulated in real time, which can reduce the safety risks caused by frequent speed changes, not only improves driving stability and comfort, but also optimizes the user's driving experience. The present invention has achieved better results in terms of environmental data collection accuracy, traffic speed calculation reliability and speed control intelligence. BRIEF DESCRIPTION OF THE DRAWINGS
[0019] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.
[0020] Figure 1 An overall flow chart of an intelligent driving method based on traffic speed regulation provided for the first embodiment of the present invention.
[0021] Figure 2An overall flow chart of an intelligent driving system based on traffic speed regulation provided for the third embodiment of the present invention. DETAILED DESCRIPTION
[0022] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.
[0023] Example 1, reference Figure 1 , is an embodiment of the present invention, and provides an intelligent driving method based on vehicle flow speed regulation, comprising:
[0024] S1: Collect surrounding vehicle information and road data, and screen speed reference sample vehicles.
[0025] Furthermore, the vehicle information data includes the vehicle information data, surrounding vehicle information data, and the distance information between the vehicle and surrounding vehicles; the vehicle information data includes the vehicle speed data, the vehicle position information, and the vehicle acceleration data; the surrounding vehicle information data includes the surrounding vehicle speed data, the surrounding vehicle position information, and the surrounding vehicle acceleration data.
[0026] It should be noted that the on-board sensors used for data collection include on-board millimeter-wave radar, lidar, and cameras, and can also obtain road type and road speed limit data.
[0027] It should also be noted that screening the speed reference sample vehicles includes initializing a preset number of speed reference sample vehicles and constructing a screening strategy.
[0028] Screening strategies include screening based on lane priority principle, speed difference, lateral distance priority principle and acceleration.
[0029] When screening is performed based on the lane priority principle, the surrounding vehicles in the lane where the vehicle is located and the adjacent lanes are preferentially selected as speed reference sample vehicles.
[0030] When screening is performed based on speed difference, a first speed difference range is set by the speed difference between the surrounding vehicles and the vehicle, surrounding vehicles beyond the first speed difference range are excluded, and surrounding vehicles within the first speed difference range are retained as speed reference sample vehicles; a preferred parameter of the first speed difference range is ±15kph.
[0031] When screening is performed based on the lateral distance priority principle, the lateral distance between the vehicle and surrounding vehicles is partitioned and a corresponding lateral distance threshold is set. The lower the lateral distance threshold, the higher the priority of the vehicle as a speed reference sample.
[0032] When filtering based on acceleration, set the upper and lower acceleration thresholds to exclude surrounding vehicles with acceleration speeds higher than the upper and lower acceleration thresholds; the upper and lower acceleration thresholds can be set to 1.5 m / s respectively. 2 and -3m / s 2 .
[0033] It should also be noted that screening the speed reference sample vehicles also includes selecting the remaining surrounding vehicles in a random order to supplement when the number of screened speed reference sample vehicles is less than the preset number of speed reference sample vehicles, and the supplementation method satisfies the screening strategy.
[0034] It should also be noted that by using on-board sensors to collect real-time information on the speed, position and spacing of surrounding vehicles, as well as obtaining road type and speed limit data, a comprehensive perception of the environment is achieved. The use of multiple sensors to collect multi-dimensional data improves the accuracy and timeliness of surrounding environmental information, thereby providing a reliable basis for subsequent data processing. By screening speed reference sample vehicles based on the lane priority principle, speed difference and lateral distance, it is ensured that the selected vehicle is relatively close to the driving state of the vehicle, effectively improving the relevance and applicability of the speed reference, excluding vehicles with significantly different driving states from the vehicle, reducing unnecessary interference, achieving accurate judgment of traffic conditions, and improving the reliability and safety of the intelligent driving system.
[0035] S2: Process the data of the speed reference sample vehicles and calculate the characteristic value of the traffic speed.
[0036] Furthermore, calculating the characteristic value of the traffic speed includes processing the speed data of the screened speed reference sample vehicles after the number of screened speed reference sample vehicles meets the preset number of speed reference sample vehicles, and calculating the characteristic value representing the current traffic speed.
[0037] The characteristic value calculation methods of the current vehicle flow speed include the first type of calculation method, the second type of calculation method, and the third type of calculation method.
[0038] The first type of calculation method includes assigning weights to the speed data of the speed reference sample vehicles, and taking the weighted average as the characteristic value of the current traffic speed. The weight influencing factors include the lane where the speed reference sample vehicle is located, the lateral distance between the vehicle and the speed reference sample vehicle, and the acceleration of the speed reference sample vehicle. The weight value is adjusted based on the lane priority principle and the lateral distance priority principle in the screening strategy, and the weight value is adjusted by setting the acceleration fluctuation threshold. In multiple lanes in the same direction, the innermost lane is usually given a higher priority. The weight of vehicles in this lane is set to 0.5, the weight of vehicles in the adjacent lane is set to 0.3, and the weight of vehicles in the remaining lanes is set to 0. .1; A preferred solution for adjusting the weight value based on the lateral distance priority principle includes selecting vehicles that are laterally closer to the vehicle based on the lateral distance, setting the distance threshold according to the actual situation, dividing the distance into short distance, medium distance and long distance, and short-distance vehicles have a higher screening priority, selecting vehicles that are laterally closer to the vehicle, dividing the lateral distance into short distance (less than 4 meters), medium distance (4 meters to 8 meters) and long distance (greater than 8 meters), and giving short-distance vehicles a higher screening priority. For every 1 meter reduction in the lateral distance, the weight increases by 0.1, and the weight is 0.5 when the distance is 0; The acceleration fluctuation threshold can be set at ±0.5m / s 2 At this time, the acceleration fluctuation is considered stable, and the weight of the stable vehicle is increased by 0.2.
[0039] The second calculation method includes arranging the speed data of the speed reference sample vehicles in order, and selecting the median of the sorted speed data as the characteristic value of the current traffic speed.
[0040] The third type of calculation method includes counting the speed data of the speed reference sample vehicles according to the speed segments under the variance threshold, and selecting the speed segment with the highest frequency as the characteristic value of the current traffic speed; the variance threshold can be selected as 5kph or 10kph.
[0041] When in a highway scenario, the first type of calculation method is used.
[0042] When in urban congestion or complex road conditions, the second type of calculation method is used.
[0043] When in a queue of vehicles traveling at a low speed, the third type of calculation method is used.
[0044] It should also be noted that a preferred solution for calculating the characteristic value of the vehicle flow speed includes constructing a neural network model to calculate the characteristic value of the vehicle flow speed. The model architecture includes an input layer, a hidden layer and an output layer. The input layer: inputs the speed, position, acceleration of the n selected vehicles and the relevant information of the vehicle (such as speed, lane, etc.), and takes the road type, speed limit, navigation road condition information (converted into quantifiable characteristic values, such as congestion level), and speed plate information as input features. The priority of the input features is different. The speed of the vehicle in the lane where the vehicle is located and the adjacent lane, the speed of the vehicle, the road speed limit information, and the speed plate information belong to a higher priority. The weights are set as: W v1 =0.3 (vehicle speed in the lane where the vehicle is located), W v2 =0.2(vehicle speed in adjacent lane), W s =0.2(vehicle speed), W lim =0.15 (road speed limit information), W sp =0.1 (speed plate information), the relative priority of the remaining lane vehicle speed, vehicle position, acceleration, and navigation road condition information is relatively low, and the weights are set as: W v3 =0.05(vehicle speed in the remaining lane), W p =0.03(vehicle position), W a =0.02(acceleration), W nav =0.05 (navigation road condition information), Hidden layer: set multiple hidden layers, each layer contains a number of neurons, neurons are connected by different weights, and activation functions (such as ReLU function) are used to perform nonlinear transformation on input data to improve the expression ability of the model. Through training with a large amount of sample data, the model can learn the complex relationship between vehicle speed, position, acceleration factors and traffic speed, as well as the influence of road environment information on traffic speed. Output layer: outputs the characteristic value representing the current traffic speed.
[0045] It should also be noted that the weighted average method can assign different weights according to the driving status of the vehicle and the distance from the vehicle, which enhances the reference to key vehicles and makes the traffic speed results more reflective of the actual traffic conditions. The combined use of the median method and the mode method can further reduce the impact of extreme values on the traffic speed calculation, achieve more robust and accurate speed feature value extraction, and obtain more accurate and reliable traffic speed feature values, providing a scientific basis for the formulation of subsequent speed control strategies, thereby improving driving safety and comfort, and improving the coordination between vehicles and the traffic environment.
[0046] S3: Develop a speed control strategy based on the characteristic value of the vehicle flow speed.
[0047] Furthermore, the speed control strategy is formulated to include controlling the vehicle speed to be greater than the traffic speed when the traffic speed varies within a range and is lower than the road speed limit.
[0048] When the vehicle speed difference exceeds the first speed difference range, the acceleration is higher than the upper acceleration threshold or lower than the lower acceleration threshold, the vehicle speed is adjusted in real time according to the current traffic speed, and the vehicle speed is controlled to gradually approach the traffic speed. A smooth speed adjustment curve is used, and the speed change limit per second and the speed change threshold per second are set. The vehicle speed is dynamically adjusted according to the navigation data to avoid sudden braking or acceleration. An optimal value of the speed change threshold per second is 5kph.
[0049] It should also be noted that formulating a speed control strategy also includes setting a percentage threshold value that is above or below the traffic flow value, and adjusting the upper or lower speed limit.
[0050] By providing a user interface, dynamic adjustment of the upper and lower speed limits is achieved. The upper speed limit can be set as the vehicle's driving speed shall not exceed "traffic speed + percentage adjustment value", and the lower speed limit is set as the vehicle's driving speed shall not be lower than "traffic speed - percentage adjustment value". This mechanism allows users to flexibly adjust the vehicle speed according to personal needs. For example, when the user wants to drive slightly faster than the traffic flow to improve traffic efficiency, the percentage higher than the traffic speed can be set, which is suitable for scenarios such as highways; when the user wants to drive more cautiously, the percentage lower than the traffic speed can be set, which is suitable for complex traffic environments such as congested roads or driving in rainy days, thereby taking into account both driving efficiency and safety.
[0051] It should also be noted that, based on the calculated traffic speed characteristic value, the corresponding speed control strategy is formulated and the speed control parameters are adjusted, which can intelligently adjust the vehicle speed to match the traffic status. In particular, when the traffic speed is stable and lower than the speed limit, appropriately increasing the vehicle speed can effectively improve driving efficiency and avoid traffic delays caused by too low a speed. In the case of large fluctuations in traffic speed, a smooth transition strategy is adopted to adjust the vehicle speed in real time, which can reduce the safety risks caused by frequent speed changes and improve driving stability and comfort. An interface is provided for users, allowing users to set an upper or lower speed limit according to their personal driving habits, which provides convenience for personalized driving and enhances the user's driving experience and sense of security.
[0052] Example 2 is an embodiment of the present invention, which provides an intelligent driving method based on vehicle speed regulation. In order to verify the beneficial effects of the present invention, scientific demonstration is carried out through economic benefit calculation and simulation experiments.
[0053] First, a 10-kilometer-long multi-lane road was selected as the test section, which experienced real traffic flow during peak and off-peak hours. The experiment was equipped with an intelligent car that integrated multiple sensors, including millimeter-wave radar, lidar and high-definition camera, to collect various data of the surrounding environment in real time to ensure the comprehensiveness of environmental monitoring; during the experiment, the on-board sensor system was used to accurately obtain information about surrounding vehicles in real time. The system combined GPS positioning with map data to obtain the type of road, speed limit information and related road condition data. During the data collection process, different parameters were set to limit the range to screen out vehicles with reference value. The system first performed preliminary processing on the data collected by the on-board sensors, and then calculated the data. The system uses a method to fuse these data to improve the reliability and timeliness of information; after algorithm processing, the system performs speed reference sample vehicle screening. Based on the lane priority rule, the system gives priority to the 15 vehicles in the lane where the vehicle is located and the adjacent lanes. Through the set algorithm rules, the system filters out vehicles that are not within this speed range, and focuses on observing vehicles with a speed difference of ±15km / h with the vehicle to ensure that vehicles with a small speed difference are selected. A weighted evaluation method is used to ensure that the selected speed reference vehicle can adapt to the high-speed driving environment in actual use; the system selects vehicles that are relatively close to the vehicle in lateral distance, and the threshold of vehicle distance is set into three categories: short distance (less than 4 meters), medium distance (4 to 8 meters) and long distance (greater than 8 meters), and selects 3 close-range vehicles for priority processing; uses the spatial information of multi-lane roads to ensure that the selected vehicle status is similar to the environment of the vehicle, effectively improving the reliability of the speed reference sample; after completing the screening of the speed reference sample, the system processes the speed data and uses statistical analysis methods to calculate the vehicle speed characteristic value; the system determines the effective speed reference through the weighted average method, and combines the median method and the majority method to extract the characteristic value of the vehicle speed; comprehensively evaluates different vehicles according to the set weights, so that the entire calculation is more in line with the actual traffic conditions; in the experiment, the artificial intelligence model is used to learn the relationship between vehicle speed, position and acceleration through a multi-layer neural network to further improve the calculation of speed characteristic values accuracy; after the calculation of the traffic speed characteristic value is completed, the intelligent driving system formulates a flexible speed control strategy according to the obtained characteristics. If the calculated traffic speed is stable and lower than the speed limit, the system will automatically adjust the vehicle speed and moderately increase it to 5 kilometers higher than the traffic speed to ensure the optimization of driving efficiency; in the case of large fluctuations in traffic speed, the intelligent system reduces the speed and adopts a smooth transition strategy to ensure driving comfort and safety; the system sets a user interface to allow drivers and passengers to adjust the upper and lower speed limits according to personal needs to meet different driving habits and needs; it can be seen from the experimental results that the present invention can flexibly adapt to complex road environments, ensure vehicle safety and driving efficiency, and better realize the dynamic coordination between people and vehicles.
[0054] Example 3, reference Figure 2 , is an embodiment of the present invention, and provides an intelligent driving system based on vehicle flow speed regulation, including a sample screening module, a vehicle flow speed calculation module, and a decision and control module.
[0055] The sample screening module is used to collect vehicle information data and screen speed reference sample vehicles; the vehicle flow speed calculation module is used to process the data of the speed reference sample vehicles and calculate the characteristic value of the vehicle flow speed; the decision and control module is used to formulate a speed control strategy based on the characteristic value of the vehicle flow speed.
[0056] If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods of each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.
[0057] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.
[0058] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering, or processing in another suitable manner as necessary, and then stored in a computer memory.
[0059] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc. It should be noted that the above embodiments are only used to illustrate the technical solution of the present invention and are not limited. Although the present invention is described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that the technical solution of the present invention can be modified or replaced by equivalents without departing from the spirit and scope of the technical solution of the present invention, which should be included in the scope of the claims of the present invention.
[0060] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.
Claims
1. An intelligent driving method based on traffic speed regulation, characterized in that: include: Collect vehicle information data and screen speed reference sample vehicles; Process the data of speed reference sample vehicles to calculate the characteristic value of vehicle flow speed; Develop a speed control strategy based on the characteristic value of traffic speed.
2. The intelligent driving method based on vehicle flow speed regulation according to claim 1, characterized in that: The vehicle information data includes vehicle information data, surrounding vehicle information data, and distance information between the vehicle and surrounding vehicles; The vehicle information data includes the vehicle's speed data, the vehicle's position information, and the vehicle's acceleration data; The surrounding vehicle information data includes speed data of surrounding vehicles, position information of surrounding vehicles, and acceleration data of surrounding vehicles.
3. The intelligent driving method based on vehicle flow speed regulation according to claim 2, characterized in that: The screening of speed reference sample vehicles includes initializing a preset number of speed reference sample vehicles and constructing a screening strategy; Screening strategies include screening based on lane priority principle, speed difference, lateral distance priority principle, and acceleration; When screening based on the lane priority principle, the surrounding vehicles in the lane where the vehicle is located and the adjacent lanes are preferentially selected as speed reference sample vehicles; When screening is performed based on speed difference, a first speed difference range is set according to the speed difference between the surrounding vehicles and the vehicle, surrounding vehicles beyond the first speed difference range are excluded, and surrounding vehicles within the first speed difference range are retained as speed reference sample vehicles; When screening based on the lateral distance priority principle, the lateral distance between the vehicle and the surrounding vehicles is partitioned and the corresponding lateral distance threshold is set. The lower the lateral distance threshold, the higher the priority of the vehicle as a speed reference sample; When filtering based on acceleration, an upper acceleration threshold and a lower acceleration threshold are set to exclude surrounding vehicles with acceleration values higher than the upper acceleration threshold or lower than the lower acceleration threshold.
4. The intelligent driving method based on vehicle flow speed regulation according to claim 3, characterized in that: The screening of speed reference sample vehicles also includes selecting remaining surrounding vehicles in a random order to supplement when the number of screened speed reference sample vehicles is less than a preset number of speed reference sample vehicles, and the supplementation method satisfies the screening strategy.
5. The intelligent driving method based on vehicle flow speed regulation according to claim 4, characterized in that: The calculating of the characteristic value of the vehicle flow speed includes processing the speed data of the screened speed reference sample vehicles after the number of the screened speed reference sample vehicles meets the preset number of the speed reference sample vehicles, and calculating the characteristic value representing the current vehicle flow speed; The characteristic value calculation methods of the current vehicle flow speed include the first type of calculation method, the second type of calculation method, and the third type of calculation method; The first type of calculation method includes assigning weights to the speed data of the speed reference sample vehicles, and taking the weighted average result as the characteristic value of the current traffic speed. The weight influencing factors include the lane where the speed reference sample vehicles are located, the lateral distance between the vehicle and the speed reference sample vehicles, and the acceleration of the speed reference sample vehicles. The weight value is adjusted based on the lane priority principle and the lateral distance priority principle in the screening strategy, and the acceleration fluctuation threshold is set to adjust the weight value. The second type of calculation method includes arranging the speed data of the speed reference sample vehicles in order, and selecting the median of the sorted speed data as the characteristic value of the current traffic flow speed; The third type of calculation method includes counting the speed data of the speed reference sample vehicles according to the speed segments under the variance threshold, and selecting the speed segment with the highest frequency as the characteristic value of the current traffic speed; When in a highway scenario, the first type of calculation method is used; When in urban congestion or complex road conditions, the second type of calculation method is used; When in a queue of vehicles traveling at a low speed, the third type of calculation method is used.
6. The intelligent driving method based on vehicle flow speed regulation according to claim 5, characterized in that: The speed control strategy includes controlling the vehicle speed to be greater than the traffic speed when the traffic speed varies within a certain range and is lower than the road speed limit; When the vehicle speed difference exceeds the first speed difference range, the acceleration is higher than the upper acceleration threshold or lower than the lower acceleration threshold, the vehicle speed is adjusted in real time according to the current traffic speed, and the vehicle speed is controlled to gradually approach the traffic speed. A smooth speed adjustment curve is used, and the speed change limit per second and the speed change threshold per second are set. The vehicle speed is dynamically adjusted according to the navigation data to avoid sudden braking or acceleration.
7. The intelligent driving method based on vehicle flow speed regulation according to claim 6, characterized in that: The formulating of the speed control strategy also includes setting a percentage threshold value that is higher than or lower than the traffic flow value, and adjusting the upper or lower speed limit.
8. A system using the intelligent driving method based on vehicle flow speed regulation as claimed in any one of claims 1 to 7, characterized in that: It includes sample screening module, traffic speed calculation module, and decision and control module; The sample screening module is used to collect vehicle information data and screen speed reference sample vehicles; The vehicle flow speed calculation module is used to process the data of the speed reference sample vehicles and calculate the characteristic value of the vehicle flow speed; The decision and control module is used to formulate a speed control strategy based on the characteristic value of the vehicle flow speed.
9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the intelligent driving method based on traffic speed regulation described in any one of claims 1 to 7 are implemented.
10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the intelligent driving method based on traffic speed regulation described in any one of claims 1 to 7 are implemented.