Automobile urban artery cloud control energy-saving cruising system and method based on high-precision map

Abstract

The invention relates to an automobile urban artery cloud control energy-saving cruise system and method based on a high-precision map, and the method comprises a cloud control platform which is used for predicting the queuing dissipation time of at least one automobile based on a target high-precision map and corresponding road traffic information, so as to generate an automobile speed sequence meeting a preset optimal condition; the vehicle-mounted platform of the at least one automobile is in communication connection with the cloud control platform and is used for planning a target cruise speed of the at least one automobile based on the automobile speed sequence meeting the preset optimal condition and the actual state of the at least one automobile; and determining a vehicle speed track of at least one vehicle meeting a preset optimal condition based on the target cruising vehicle speed, and controlling the at least one vehicle to run according to the vehicle speed track meeting the preset optimal condition. The global vehicle speed is planned based on the dynamic change of the queuing dissipation time in combination with the traffic information of multiple intersections, so that frequent start and stop are effectively reduced, and the passing efficiency and the energy-saving effect of the vehicle are improved.

Description

Technical Field

[0001] This application relates to the technical field of green wave traffic, and particularly relates to an energy-saving cruise control system and method for urban arterial roads of vehicles based on a high-precision map. Background Art

[0002] In modern urban traffic systems, signal-controlled intersections, as traffic bottlenecks, directly affect vehicle passing efficiency and driving experience. When a vehicle approaches an intersection, affected by the signal state, driver operation habits, and the surrounding traffic environment, the phenomenon of "stop - start" frequently occurs. Vehicles are usually in a non-free-flow state, which not only increases the delay time but also significantly increases energy consumption. Therefore, optimizing the vehicle speed trajectory at signal-controlled intersections to reduce the number of stops and energy consumption is an important research direction in current energy-saving driving technologies.

[0003] Vehicle queuing at signal intersections is a common traffic phenomenon in urban roads. Accurately predicting the queue dissipation time, especially the departure state of the last vehicle in the queue, plays a key role in signal timing optimization, vehicle speed guidance, and vehicle cruise control. By predicting the departure time and speed of the last vehicle in the queue, the minimum green time of the signal can be optimized to ensure that vehicles can pass through the intersection smoothly without stopping, thereby achieving the goal of energy-saving driving.

[0004] In recent years, research on queue dissipation time has mainly focused on the following aspects. First, the estimation of queue length and the dissipation headway has been widely used in the evaluation of the traffic capacity of signal intersections. Some studies have shown that the dissipation headway follows a lognormal distribution related to the vehicle queue position, improving the vehicle following model and traffic capacity estimation. However, these methods mostly rely on idealized assumptions and do not fully consider the dynamic characteristics of different types of vehicles and driver behavior differences, which limits the practical application effect of the queue dissipation prediction model.

[0005] Another type of research uses video surveillance or probe vehicle data to construct a prediction model for queue dissipation. For example, an indirect prediction model for intersection queue length is constructed based on Gaussian processes, and the change trend of vehicle queue length within multiple signal cycles is analyzed using connected vehicle data. Although these models have a certain prediction accuracy in specific scenarios, there are still some deficiencies, mainly manifested in the fact that the models do not adequately consider the time-varying characteristics of traffic flow and rely on high-precision historical data. In addition, the low penetration rate of connected vehicle data is limited by the data sample size in the real traffic environment and is difficult to effectively capture the dynamic changes of queuing vehicles.

[0006] At present, most queue dissipation prediction methods can be classified into three categories: those based on macroscopic traffic flow theory, those based on kinematic models, and those based on sectional detection devices. However, most of these methods are based on the assumption of homogeneous traffic flow with uniform arrival and departure, and do not fully consider the differences in start-up response time, acceleration behavior, and stopping distance of different types of vehicles and drivers. Therefore, the existing models cannot guarantee the prediction accuracy in complex and changeable traffic scenarios and are difficult to adapt to the dynamic changes of queuing vehicles under heterogeneous traffic flow conditions.

[0007] On the basis of predicting the queue dissipation time, it is of great practical significance to reasonably plan the speed trajectory of vehicles, especially in the complex urban road environment with signal control. The cruise control system aims to dynamically adjust the cruise speed of vehicles according to signal phase information, the state of queuing vehicles, and traffic flow changes, so as to optimize vehicle energy conservation and traffic efficiency.

[0008] At present, the energy-saving driving methods for urban arterial roads based on vehicle-road collaborative technology usually rely on the processing unit on the vehicle side. These methods plan the vehicle speed curve by obtaining real-time traffic data, such as signal phases, vehicle positions, etc., so that the vehicle can pass through the intersection without stopping during the green light period, reducing the energy consumption caused by frequent starting and stopping. However, traditional cruise control systems often ignore the actual impact of queuing vehicles on speed execution. When there are queuing vehicles ahead, the vehicle may not be able to drive at the planned speed, resulting in difficult execution of the vehicle speed command and thus affecting the energy-saving effect.

[0009] Some studies have begun to focus on the speed optimization planning between consecutive intersections and proposed energy-saving driving strategies for multiple intersections. However, most of the current methods still assume a single intersection or ideal traffic flow and do not fully consider the impact of the dynamic interaction of queuing vehicles between different intersections on speed planning. Based on this, how to effectively integrate signal phases, the dissipation state of queuing vehicles, and the dynamic characteristics of the vehicle itself in a complex urban traffic environment to achieve a globally optimized cruise speed planning is still an urgent problem to be solved. Summary of the Invention

[0010] This application provides an automotive urban arterial road cloud-controlled energy-saving cruise system and method based on a high-precision map to solve the following problems in related technologies: First, the traditional queue dissipation time prediction module is based on idealized assumptions and does not fully consider the vehicle differences in heterogeneous traffic flow, resulting in insufficient prediction accuracy; second, the existing cruise control methods do not effectively combine the dynamic characteristics of queue dissipation, making the planned vehicle speed commands difficult to execute in the actual traffic environment; in addition, the distributed control method of deploying the processing unit on the vehicle side is limited by hardware costs and computing power and cannot perform real-time and efficient speed planning in complex traffic scenarios at multiple intersections.

[0011] In the first aspect of the embodiments of the present application, a cloud-controlled energy-saving cruise system for automobiles on urban arterial roads based on high-precision maps is provided, including: a cloud control platform for predicting the queue dissipation time of at least one automobile based on the target high-precision map and the corresponding road traffic information, so as to generate a vehicle speed sequence that meets the preset optimal conditions; the on-vehicle platforms of the at least one automobile, and the on-vehicle platforms of the at least one automobile are communicatively connected to the cloud control platform, and are used for planning the target cruise vehicle speed of the at least one automobile based on the vehicle speed sequence that meets the preset optimal conditions and the actual states of the at least one automobile, so as to determine the vehicle speed trajectory of the at least one automobile that meets the preset optimal conditions based on the target cruise vehicle speed, and control the at least one automobile to travel according to the vehicle speed trajectory that meets the preset optimal conditions.

[0012] Optionally, in an embodiment of the present application, the cloud control platform includes: a high-precision map module for generating at least one of static road information and dynamic traffic information including lane lines, intersections, stop lines, and crosswalks based on the real-time position information of the at least one automobile; a queue dissipation time prediction module for predicting the queue dissipation time of the at least one automobile at the intersection based on the at least one item of static road information and the dynamic traffic information according to a preset model; a scenario pre-analysis module for analyzing the queue dissipation time to determine the time window and speed range that meet the preset best conditions for the at least one automobile to pass through each section of the road; a vehicle speed planning module for determining the vehicle speed sequence that meets the preset optimal conditions based on the time window and the speed range that meet the preset best conditions according to a preset dynamic programming algorithm.

[0013] Optionally, in an embodiment of the present application, the queue dissipation time prediction module includes: a data set construction and cleaning unit for constructing a traffic data set based on real-time traffic data, and cleaning the data in the traffic data set to remove abnormal data and generate a cleaned data set; a model training unit for training the preset model using the cleaned data set to predict the queue dissipation time of the at least one automobile at the intersection.

[0014] Optionally, in an embodiment of the present application, the scenario pre-analysis module includes: a time pre-analysis unit for calculating the target passing time window for passing through consecutive intersections, so as to determine the time for the at least one automobile to pass through the consecutive intersections with a green light within the target passing time window; a speed pre-analysis unit for calculating the target passing speed range for the at least one automobile to pass through the consecutive intersections based on the time.

[0015] Optionally, in an embodiment of the present application, the calculation formula for the target passing time window is:

[0016]

[0017] Among them, are respectively the times when the j-th phase of the i-th intersection switches to green and red lights;

[0018] The calculation formula for the target passing speed range is:

[0019]

[0020] Among them, are respectively the fastest time and the slowest time to reach the i-th intersection, and L i is the length of the i-th section of the road, and v max , v min are the upper and lower limits of the driving speed of the at least one vehicle.

[0021] Optionally, in an embodiment of the present application, the vehicle speed planning module includes: a dynamic programming solution unit, which is used to establish a cost function of a control problem that satisfies preset optimal conditions for continuous intersection predictive cruise control with the energy consumption, driving time, and speed fluctuation of the at least one vehicle as the objectives, and generate a speed control sequence that satisfies the preset optimal conditions according to the control problem cost function.

[0022] Optionally, in an embodiment of the present application, the on-vehicle platform of the at least one vehicle includes: a vehicle speed command parsing module, which is used to perform matching positioning according to the real-time position and target waypoint of the at least one vehicle to obtain recommended driving information for the target waypoint, and parse at least one vehicle speed command including cruise vehicle speed, gear information, acceleration command, or deceleration command issued by the cloud control platform according to the recommended driving information to generate a parsed vehicle speed command; a cruise state control module, which is used to perform speed control on the at least one vehicle based on the parsed vehicle speed command and the traffic environment change in front of the at least one vehicle, and control the vehicle to travel along the vehicle speed trajectory that satisfies the preset optimal conditions according to the speed and distance differences between the vehicle in front and the at least one vehicle.

[0023] An embodiment of the second aspect of the present application provides a method for cloud-controlled energy-saving cruise of an automobile on an urban arterial road based on a high-precision map, including the following steps: predicting the queue dissipation time of at least one vehicle based on the target high-precision map and the corresponding road traffic information to generate a vehicle speed sequence that satisfies preset optimal conditions; planning the target cruise vehicle speed of the at least one vehicle based on the vehicle speed sequence that satisfies the preset optimal conditions and the actual state of the at least one vehicle, determining the vehicle speed trajectory that satisfies the preset optimal conditions of the at least one vehicle based on the target cruise vehicle speed, and controlling the at least one vehicle to travel along the vehicle speed trajectory that satisfies the preset optimal conditions.

[0024] Optionally, in an embodiment of the present application, predicting the queue dissipation time of at least one vehicle based on the target high-precision map and the corresponding road traffic information to generate a vehicle speed sequence that meets the preset optimal conditions includes: generating at least one static road information and dynamic traffic information including lane lines, intersections, stop lines, and crosswalks based on the real-time position information of the at least one vehicle; predicting the queue dissipation time of the at least one vehicle at the intersection based on the at least one static road information and the dynamic traffic information according to a preset model; analyzing the queue dissipation time to determine the time window and speed range that meet the preset optimal conditions for the at least one vehicle to pass through each section of the road; and determining the vehicle speed sequence that meets the preset optimal conditions according to a preset dynamic programming algorithm based on the time window and speed range that meet the preset optimal conditions.

[0025] Optionally, in an embodiment of the present application, predicting the queue dissipation time of the at least one vehicle at the intersection based on the at least one static road information and the dynamic traffic information according to a preset model includes: constructing a traffic data set based on real-time traffic data, and cleaning the data in the traffic data set to remove abnormal data to generate a cleaned data set; and training the preset model using the cleaned data set to predict the queue dissipation time of the at least one vehicle at the intersection.

[0026] Optionally, in an embodiment of the present application, analyzing the queue dissipation time to determine the time window and speed range that meet the preset optimal conditions for the at least one vehicle to pass through each section of the road includes: a time pre-analysis unit for calculating the target passing time window for passing through consecutive intersections to determine the time for the at least one vehicle to pass through the consecutive intersections with a green light within the target passing time window; and a speed pre-analysis unit for calculating the target passing speed range for the at least one vehicle to pass through the consecutive intersections based on the time.

[0027] Optionally, in an embodiment of the present application, the calculation formula for the target passing time window is:

[0028]

[0029] where are the times when the j-th phase of the i-th intersection switches to green and red respectively;

[0030] The calculation formula for the target passing speed range is:

[0031]

[0032] where are the fastest time and the slowest time to reach the i-th intersection respectively, and L i is the length of the i-th road segment, and v max , v min are the upper and lower limits of the driving speed of the at least one vehicle.

[0033] Optionally, in an embodiment of the present application, for the time window and the speed range that meet the preset optimal conditions, a vehicle speed sequence that meets the preset optimal conditions is determined according to a preset dynamic programming algorithm, including: taking the energy consumption, driving time, and speed fluctuation of the at least one vehicle as the objectives, establishing a cost function of a control problem for continuous intersection predictive cruise control that meets the preset optimal conditions, and generating a speed control sequence that meets the preset optimal conditions according to the cost function of the control problem.

[0034] Optionally, in an embodiment of the present application, controlling the at least one vehicle to travel along the vehicle speed trajectory that meets the preset optimal conditions includes: matching and positioning according to the real-time position of the at least one vehicle and the target waypoint to obtain recommended driving information of the target waypoint, and parsing at least one vehicle speed instruction including cruise vehicle speed, gear information, acceleration instruction, or deceleration instruction sent by the cloud control platform according to the recommended driving information to generate a parsed vehicle speed instruction; based on the parsed vehicle speed instruction and the traffic environment change in front of the at least one vehicle, performing speed control on the at least one vehicle according to the speed and distance difference between the vehicle in front and the at least one vehicle, so as to control the vehicle to travel along the vehicle speed trajectory that meets the preset optimal conditions.

[0035] An embodiment of the third aspect of the present application provides an electronic device, including: a memory, a processor, and a computer program stored on the memory and executable on the processor, and the processor executes the program to implement the vehicle urban arterial cloud control energy-saving cruise method based on a high-precision map as described in the above embodiment.

[0036] Embodiments of the present application can utilize the vehicle - end, roadside device, and high - precision map data collected by the cloud control platform, combine the driving behavior of the vehicle and traffic signal constraints, construct a vehicle driving state prediction model from a global perspective, and through dynamic analysis and real - time updated algorithms, can accurately predict the queue dissipation time of vehicles at each intersection, effectively improving the traffic flow passing efficiency in complex urban environments; by constructing a queue dissipation time prediction model based on XGBoost, deeply mining large - scale traffic data, and automatically learning traffic flow rules, this technology can flexibly respond to the time - varying traffic characteristics of different road sections and signal cycles, dynamically update the queue dissipation time prediction, significantly improving the accuracy and stability of the queue dissipation time prediction, especially having obvious advantages in complex scenarios with long time, multiple road sections, and multiple lanes; combining the queue dissipation prediction results, using multi - source data from real - time roadside and the cloud for multi - intersection collaborative optimization, and realizing that vehicles pass through multiple intersections without stopping through intelligent prediction and cloud computing, the overall technical framework for improving the passing efficiency and its related implementation methods. Thus, it solves the problems in the related technologies. First, the traditional queue dissipation time prediction module is based on idealized assumptions and fails to fully consider the vehicle differences in heterogeneous traffic flows, resulting in insufficient prediction accuracy; second, the existing cruise control methods fail to effectively combine the dynamic characteristics of queue dissipation, making the planned vehicle speed commands difficult to execute in the actual traffic environment; in addition, the distributed control method of deploying processing units on the vehicle side is limited by hardware costs and computing capabilities and cannot perform real - time and efficient speed planning in complex multi - intersection traffic scenarios.

[0037] Additional aspects and advantages of the present application will be given in part in the following description, become apparent in part from the following description, or be understood through the practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] The above - mentioned and / or additional aspects and advantages of the present application will become apparent and be readily understood from the following description of the embodiments in conjunction with the drawings, where:

[0039] Figure 1 FIG. is a schematic structural diagram of an automotive urban arterial cloud - controlled energy - saving cruise system based on a high - precision map according to an embodiment of the present application;

[0040] Figure 2 FIG. is a schematic diagram of the architecture and composition of a cloud - controlled system according to an embodiment of the present application;

[0041] Figure 3 FIG. is a composition and principle block diagram of a specific example of an urban arterial cloud - controlled energy - saving cruise system based on a high - precision map according to an embodiment of the present application;

[0042] Figure 4It is a sub-module and principle block diagram deployed on a cloud control platform in a specific example of an urban arterial cloud control energy-saving cruise system based on a high-precision map according to an embodiment of the present application;

[0043] Figure 5 It is a schematic flow chart of a queuing dissipation time prediction model based on the XGBoost algorithm according to an embodiment of the present application;

[0044] Figure 6 It is a schematic diagram of a green wave passing area in a specific example of an urban arterial cloud control energy-saving cruise system based on a high-precision map according to an embodiment of the present application;

[0045] Figure 7 It is a fitting result diagram of an engine model in a specific example of an urban arterial cloud control energy-saving cruise system based on a high-precision map according to an embodiment of the present application;

[0046] Figure 8 It is a sub-module and principle block diagram deployed on a vehicle-mounted platform in a specific example of an urban arterial cloud control energy-saving cruise system based on a high-precision map according to an embodiment of the present application;

[0047] Figure 9 It is a flow chart of a method for an energy-saving cruise of an automobile on an urban arterial based on a high-precision map provided according to an embodiment of the present application;

[0048] Figure 10 It is a schematic structural diagram of an electronic device provided according to an embodiment of the present application. Detailed Description of the Embodiment

[0049] The embodiments of the present application will be described in detail below. The examples of the embodiments are shown in the accompanying drawings, where the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to explain the present application, and should not be construed as limiting the present application.

[0050] The following describes the vehicle urban arterial cloud-controlled energy-saving cruise system and method based on a high-precision map according to the embodiments of the present application. In view of the problems in the related art mentioned in the above background art, firstly, the traditional queue dissipation time prediction module is based on idealized assumptions and fails to fully consider the vehicle differences in heterogeneous traffic flows, resulting in insufficient prediction accuracy; secondly, the existing cruise control methods fail to effectively combine the dynamic characteristics of queue dissipation, making it difficult to execute the planned vehicle speed commands in the actual traffic environment; in addition, the distributed control method of deploying processing units on the vehicle side is limited by hardware costs and computing power and cannot perform real-time and efficient speed planning in complex traffic scenarios at multiple intersections. The present application provides a vehicle urban arterial cloud-controlled energy-saving cruise system based on a high-precision map. In this system, the vehicle terminal, roadside device, and high-precision map data collected by the cloud control platform can be used to construct a vehicle driving state prediction model from a global perspective in combination with the driving behavior of the vehicle and traffic signal constraints. Through dynamic analysis and real-time update algorithms, the queue dissipation time of vehicles at each intersection can be accurately predicted, effectively improving the traffic flow passing efficiency in complex urban environments; by constructing a queue dissipation time prediction model based on XGBoost, large-scale traffic data is deeply mined, and the traffic flow law is automatically learned. This technology can flexibly respond to the time-varying traffic characteristics of different road sections and signal cycles, dynamically update the queue dissipation time prediction, and significantly improve the accuracy and stability of the queue dissipation time prediction, especially having obvious advantages in complex scenarios with long time, multiple road sections, and multiple lanes; combining the queue dissipation prediction results, multi-source data from the real-time roadside and cloud are used for multi-intersection collaborative optimization, and vehicles can pass through multiple intersections without stopping through intelligent prediction and cloud computing, improving the overall technical framework of the passing efficiency and its related implementation methods. Thus, the problems in the related technology are solved. Firstly, the traditional queue dissipation time prediction module is based on idealized assumptions and fails to fully consider the vehicle differences in heterogeneous traffic flows, resulting in insufficient prediction accuracy; secondly, the existing cruise control methods fail to effectively combine the dynamic characteristics of queue dissipation, making it difficult to execute the planned vehicle speed commands in the actual traffic environment; in addition, the distributed control method of deploying processing units on the vehicle side is limited by hardware costs and computing power and cannot perform real-time and efficient speed planning in complex traffic scenarios at multiple intersections, etc.

[0051] Specifically, Figure 1 FIG. is a schematic structural diagram of a vehicle urban arterial cloud-controlled energy-saving cruise system based on a high-precision map provided by an embodiment of the present application.

[0052] As Figure 1 shown, the vehicle urban arterial cloud-controlled energy-saving cruise system 10 based on a high-precision map includes: a cloud control platform 100 and at least one vehicle-mounted platform 200 of a vehicle.

[0053] Specifically, the cloud control platform 100 is used to predict the queue dissipation time of at least one vehicle based on the target high-precision map and the corresponding road traffic information, so as to generate a vehicle speed sequence that meets the preset optimal conditions.

[0054] It can be understood that the embodiment of the present application proposes an intelligent vehicle urban arterial cloud control energy-saving cruise system based on a high-precision map based on the architecture of the cloud control system. The cloud control system is a complex Internet of Things cyber-physical system, and its architecture is as Figure 2 shown, including a cloud control basic platform, a cloud control application platform, roadside infrastructure, intelligent connected vehicles, a communication network, and an industry-related support platform. Through the logically coordinated and physically dispersed cloud control basic platform, the data collection, processing, and information interaction of vehicles and traffic systems can be carried out efficiently, providing support for traffic management and vehicle operation. Relying on this basic architecture, the core technology of the present application solves the limitations of traditional queue prediction and cruise control, and realizes multi-dimensional traffic information collaboration and optimization control across regions and intersections. The intelligent connected vehicle uploads the real-time operating state of the vehicle (such as vehicle identification code, position, speed, etc.) to the cloud control platform 100 through the cellular network. The edge cloud in the cloud control platform 100 is responsible for collecting the real-time traffic information of the road where the vehicle is located, mainly including signal timing, traffic flow, and road traffic conditions. These information are sensed through roadside infrastructure and transmitted to the edge cloud in real time. To achieve global optimization, the present application further uses the regional cloud for coordination on the basis of the edge cloud, collects the dynamic traffic information of multiple adjacent intersections, and provides traffic data support in a wider range. The regional cloud coordinates multiple edge clouds to provide information such as signal phases, traffic flows, and queue conditions of multiple intersections for the serving vehicles, and combines the high-precision map and the ground-based augmentation positioning platform to calculate the economic vehicle speed of the vehicle in real time.

[0055] In the actual execution process, the embodiment of the present application realizes the efficient energy-saving driving of intelligent connected vehicles in urban arterials through the vehicle-road cooperation method. The core architecture of the system consists of two parts: the cloud control platform 100 and the on-vehicle platform 200 of at least one vehicle, which respectively undertake key functions such as data processing, prediction, optimization, and vehicle speed execution. The module in the cloud control platform 100 predicts the queue dissipation time of at least one vehicle based on the target high-precision map and the corresponding road traffic information, and generates an optimal vehicle speed sequence, while the on-vehicle platform 200 of at least one vehicle receives and parses this information, and performs speed control in combination with the real-time state of the vehicle. The system forms a closed-loop optimization control process through the communication between the vehicle end and the cloud end, aiming to improve the traffic efficiency and energy consumption optimization level of vehicles in urban arterials.

[0056] As Figure 3As shown in the figure, the cloud control platform 100 is divided into two main parts: the cloud control application platform 11 and the cloud control basic platform 12. The cloud control basic platform 12 and the cloud control application platform 11 cooperate with each other to form a comprehensive urban intelligent transportation system, aiming to provide precise cruise control for vehicles. The high-precision map module 121 in the cloud control basic platform 12 serves as information support and is responsible for providing the dynamic and static information of the road and accurate vehicle positioning for the cloud control application platform 11. The main task of this module is to generate fine-grained map data of the current road section through high-precision map technology, combined with the real-time position information of the vehicle, including key static information such as lane lines, intersections, stop lines, crosswalks, etc., and real-time dynamic information provided by roadside perception devices, such as traffic light status, the length of the vehicle queue ahead, etc. These data lay the foundation for subsequent scenario analysis and speed planning. The cloud control application platform 11 mainly includes three key modules: the queue dissipation time prediction module 111, the scenario pre-analysis module 112, and the vehicle speed planning module 113. These modules work together to ensure that vehicles can achieve efficient and energy-saving cruise control on urban roads.

[0057] The cloud control system in this application can integrate multi-source data from the vehicle end, roadside perception devices, and high-precision maps, obtain wide-area traffic dynamic information in real time, and perform global optimization based on this to provide more accurate queue dissipation time prediction. This method expands the perception range and makes full use of the computing power of the cloud, effectively supporting the queue dissipation time prediction at signal intersections and the vehicle speed optimization scheme, providing technical support for urban traffic management.

[0058] It should be noted that the preset optimal conditions can be set by those skilled in the art according to the actual situation, and no specific limitations are made here.

[0059] Optionally, in an embodiment of this application, the cloud control platform 100 includes: a high-precision map module for generating at least one of static road information and dynamic traffic information including lane lines, intersections, stop lines, and crosswalks based on the real-time position information of at least one vehicle; a queue dissipation time prediction module for predicting the queue dissipation time of at least one vehicle at an intersection based on at least one of static road information and dynamic traffic information according to a preset model; a scenario pre-analysis module for analyzing the queue dissipation time to determine the time window and speed range for at least one vehicle to pass through each road section that meet the preset best conditions; and a vehicle speed planning module for determining a vehicle speed sequence that meets the preset optimal conditions based on the time window and speed range that meet the preset best conditions according to a preset dynamic programming algorithm.

[0060] It can be understood that the preset model in the embodiments of the present application can be an XGBoost model; the present application can use the XGBoost algorithm to predict the queuing dissipation time. Combined with the construction and cleaning of the dataset, the model can automatically extract the vehicle queuing dissipation rules from a large amount of historical traffic data. Especially considering the dynamic traffic characteristics under different road sections and signal cycles, by mining the internal rules in the data, the prediction accuracy is greatly improved. At the same time, the present application designs an iterative update mechanism based on discrete steps to dynamically correct the prediction error and ensure the stability and continuity of the model in long-term prediction. This adaptive update method ensures the real-time performance and the reliability of long-term prediction.

[0061] During the actual execution process, as Figure 4 shown, a specific example of the intelligent vehicle urban arterial cloud control energy-saving cruise system based on the high-precision map in the embodiments of the present application is deployed in a sub-module of the cloud control platform 100. The high-precision map module 121 provides basic map information and vehicle positioning services for the cloud control application platform 11 to ensure that the system operates in an accurate road environment. Then, the queuing dissipation time prediction module 111 predicts the traffic situation at the intersection ahead, especially the dissipation time of the queuing vehicles, through the XGBoost model. The scenario pre-analysis module 112 analyzes these prediction results to determine the best time window and speed range for the vehicle to pass through each road section. Finally, the vehicle speed planning module 113 uses the dynamic programming algorithm to generate the optimal speed sequence of the vehicle.

[0062] The vehicle speed planning module 113 is responsible for generating the urban cruising vehicle speed according to the results of the scenario pre-analysis module 112 by using the dynamic programming algorithm. The dynamic programming algorithm is an optimization algorithm aimed at finding the global optimal solution through a phased decision-making process. In this application, the task of the dynamic programming algorithm is to plan an optimal speed sequence for the vehicle based on the vehicle's current state, the traffic conditions ahead, and the predicted queue dissipation time. This module first receives the target time window and vehicle speed range provided by the scenario pre-analysis module 112, and constructs the optimal control problem of the vehicle by combining multiple constraints such as the vehicle's dynamics model and engine fuel consumption model. By solving the optimal control problem, the system can find a speed sequence that is both energy-saving and efficient in the current traffic environment, ensuring that the vehicle can pass through intersections smoothly, reducing fuel consumption and travel time. The process of dynamic programming solution is discrete, that is, the total distance from the current position of the vehicle to the target position is divided into several equally spaced road points, and each road point corresponds to a planned vehicle speed. In a specific embodiment of this application, the step size of the distance is set to 20 meters. The system will perform optimization and solution for each 20-meter interval respectively to generate the optimal speed value within this interval. During the actual driving process of the vehicle, the system will perform rolling iterative updates after each 20-meter distance step, and re-evaluate the optimal speed sequence of the remaining distance. This combination of dynamic programming and rolling update ensures that the vehicle can respond to changes in road conditions in real time, maintain the optimal cruising speed, and thus by constructing an XGBoost-based queue dissipation time prediction model, deeply mining large-scale traffic data, and automatically learning traffic flow rules. This technology can flexibly adapt to the time-varying traffic characteristics of different road sections and signal light cycles, dynamically update the queue dissipation time prediction, and significantly improve the accuracy and stability of the queue dissipation time prediction, especially having obvious advantages in complex scenarios with long time, multiple road sections, and multiple lanes.

[0063] Optionally, in an embodiment of the present application, the queue dissipation time prediction module includes: a data set construction and cleaning unit for constructing a traffic data set based on real-time traffic data and cleaning the data in the traffic data set to remove abnormal data and generate a cleaned data set; a model training unit for using the cleaned data set to train a preset model to predict the queue dissipation time of at least one vehicle at an intersection.

[0064] In the actual implementation process, the embodiment of the present application can take the queuing dissipation time prediction module 111 as the core of the cloud control application platform 11, and the queuing dissipation time prediction module 111 shoulders the main task of predicting the road traffic situation. First, based on the real-time traffic data collected by the roadside sensing devices, the system will construct a detailed traffic data set. These data are cleaned and integrated, and abnormal data are removed to ensure the high reliability of the data input into the model. The data cleaning process adopts a personalized interquartile range (IQR) method to remove possible outliers and prevent errors from affecting the prediction accuracy of the model. Next, based on the cleaned data set, the present application introduces the XGBoost algorithm to construct the queuing dissipation time prediction module 111. XGBoost is a machine learning method based on gradient boosting trees, which is good at dealing with non-linear relationships and complex feature interactions. By training on combinations of various traffic features, such as vehicle speed, lane information, queuing length, etc., the model can effectively predict the dissipation time of the queuing vehicles at the intersection in the future time period. This prediction result provides an important basis for subsequent scenario analysis and speed planning. The task of the scenario pre-analysis module 112 is to predict and analyze the future traffic scenario according to the results output by the prediction model.

[0065] Further, as Figure 5 shown, it is the operation flow of the queuing dissipation time prediction module 111 in a specific example of the intelligent vehicle urban arterial cloud control energy-saving cruise system based on high-precision maps in the embodiment of the present application. The present application constructs a highly comprehensive feature engineering framework through the deep integration of the cloud control platform 100, roadside sensing devices, and the high-precision map module 121 for accurately predicting the queuing dissipation time in urban roads. The cloud control platform 100 is responsible for obtaining the phase information of the traffic lights in real time, the roadside sensing devices are responsible for collecting the speed and position information of the vehicles, and the high-precision map provides accurate geographical location coordinates such as lane lines, intersection stop lines, and crosswalks. After complex integration and processing of these three types of data, a high-dimensional and information-rich traffic data set is constructed.

[0066] In the construction of feature engineering, the key step is to accurately identify and define the core time nodes of the queuing situation through the phase cycle of the signal lights. Specifically, when the green light is on, the last vehicle with a speed lower than 10 km / h in the current road section is defined as the end vehicle of the queue. By obtaining information such as the speed and position of the end vehicle, the system further derives a series of key features related to queuing. These features include, but are not limited to, the number of vehicles in front of the end vehicle (i.e., the queue length), the speed of the first vehicle in the queue (i.e., the starting speed of the leading vehicle), etc. In addition, the system comprehensively analyzes all the vehicles in front of the end vehicle, obtains their speed and position information, and calculates the starting speed of the first vehicle in front of the end vehicle, the average headway between vehicles, and the standard deviation of the headway. The combination of these features, especially the queue length, the starting speed of the leading vehicle, the speed of the end vehicle, the starting speed of the vehicles in front of the end vehicle, the average headway, and the standard deviation of the headway, has been proven through a large number of experiments to be the optimal feature set for the XGBoost model in predicting the queue dissipation time. Since roadside sensing devices may be interfered by various environmental and technical factors during data collection, resulting in data anomalies, such as some vehicles parking by the roadside for a long time or the sensor recording the movement trajectory of the same vehicle multiple times, these abnormal data are very likely to interfere with the accuracy of the model. Therefore, this application proposes a personalized data cleaning strategy based on the IQR (interquartile range) statistical method. IQR is an outlier detection method based on the data distribution, which effectively identifies and removes the outliers in the data set by calculating the interquartile range of the data set (i.e., the difference between the first quartile Q1 and the third quartile Q3). For road sections with less data volume or fewer queuing phenomena, the system measures the stability of each feature through the range (the difference between the maximum value and the minimum value), selects the feature with the largest range and applies the IQR method for cleaning, so as to effectively improve the stability of the data. For those road sections with a large data volume and complex queuing situations, the IQR method is applied to all features for global cleaning to ensure the overall quality and consistency of the data set, thus providing a high-quality data basis for subsequent model training.

[0067] During the model training phase, the cleaned high-quality dataset is input into the XGBoost model for training according to the ratio of 80% training set and 20% test set. Since deep learning models are highly dependent on parameter combinations, for different road segments and lane types, this application adopts five-fold cross-validation to find the optimal parameter combination for each road segment and lane type. Through this cross-validation method, not only can the generalization ability of the model in different scenarios be ensured, but also the phenomena of overfitting or underfitting of the model can be effectively avoided. To further improve the adaptability and accuracy of the model, this application also combines dimensionality reduction and clustering methods to identify and classify road segments and lane types with similar characteristics, and then assigns the same hyperparameter combination to these road segments and lanes. This way can ensure that for road segments with different complexities of queuing situations, the model can adaptively adjust parameters, avoiding the problems of overfitting of the model for complex road segments or underfitting of simple road segments, thus greatly improving the prediction accuracy and stability of the model. Based on this feature engineering framework and model training strategy, the system can output accurate prediction results of queue dissipation time, and these prediction results can be further integrated into the calculation of the green wave passing time window to optimize the traffic efficiency of urban roads. During the model training phase, the cleaned high-quality dataset is input into the XGBoost model for training according to the ratio of 80% training set and 20% test set. The performance of deep learning models is highly dependent on parameter combinations, so this application uses five-fold cross-validation to find the optimal parameter set for each road segment and lane type. Subsequently, through dimensionality reduction and clustering methods, road segments and lane types with similar characteristics are identified and assigned the same hyperparameter combination. This process aims to avoid the problems of overfitting or underfitting of road segments with different complexities under the same model. There are the following 5 situations respectively:

[0068] 1) Road segments with relatively complex queuing situations and long vehicle queue lengths: Complex queuing situations usually require more model complexity (larger n_estimators and max_depth), and the learning process is accelerated through a slightly higher learning_rate.

[0069] 2) Road segments with moderately complex queuing situations, with a certain queue but not occurring frequently: For moderately complex queuing situations, select moderate n_estimators and max_depth to ensure that the model can capture a certain degree of complexity, and at the same time use a slightly higher subsample to improve the generalization ability of the model.

[0070] 3) Road segments with occasional and large fluctuations in queuing situations: For road segments with large fluctuations and uncertain queuing situations, select a higher n_estimators to increase the stability of the model, and at the same time accelerate the training speed through a higher learning_rate to reduce the risk of overfitting.

[0071] 4) The queuing situation is relatively slight, and there are occasionally sections with short - term queuing: For a slight queuing situation, usually smaller max_depth and n_estimators can be adopted, and a lower learning_rate can be used to avoid the model being too aggressive, ensuring the stability and prediction accuracy of the model.

[0072] 5) Additionally, considering that there are some sections where vehicles rarely appear, that is, the speed and position information of vehicles cannot be basically collected, resulting in extremely little data volume for these sections. To avoid the situation where five - fold cross - validation is not supported and the algorithm has no solution, for sections in the dataset with less than 10 pieces of data, five - fold cross - validation is no longer performed to find the optimal parameter combination, but instead the default parameters of the XGBoost model are adopted.

[0073] Table 1 shows the values of the XGBoost model parameters corresponding to each queuing situation. As shown in Table 1:

[0074] Table 1

[0075]

[0076] Table 2 shows the meaning table of the XGBoost model parameters. As shown in Table 2:

[0077] Table 2

[0078] Parameter Parameter meaning colsample_bytree The proportion of features randomly sampled when constructing each tree among all features learning_rate Learning rate max_depth Maximum tree depth n_estimators The number of base learners subsample The proportion of sampling in the samples min_child_weight The minimum sample weight required on a leaf node

[0079] Finally, through the above - mentioned data processing and model training, this application outputs a prediction result, and incorporates the predicted queuing dissipation time into the decision - making framework of the green - wave passing time window.

[0080] This application uses the data of vehicle - end, roadside devices, and high - precision maps collected by the cloud control platform, combines the driving behavior of vehicles and traffic signal constraints, and constructs a vehicle driving state prediction model from a global perspective. Through dynamic analysis and real - time updated algorithms, it can accurately predict the queuing dissipation time of vehicles at each intersection, effectively improving the traffic flow passing efficiency in complex urban environments.

[0081] Optionally, in an embodiment of this application, the scenario pre - analysis module includes: a time pre - analysis unit for calculating the target passing time window for passing through consecutive intersections to determine the time for at least one vehicle to pass through consecutive intersections with a green light within the target passing time window; a speed pre - analysis unit for calculating the target passing speed range for at least one vehicle to pass through consecutive intersections based on the time.

[0082] During the actual execution process, the scenario pre-analysis module 112 in the embodiments of the present application includes a time pre-analysis unit 1121 and a speed pre-analysis unit 1122. Scenario pre-analysis is to evaluate the future road traffic conditions based on the prediction results of queue dissipation time. The system will analyze the current road section and multiple subsequent road sections, and speculate on the possible traffic conditions that the vehicle may encounter when passing through these road sections, especially making an early judgment on the possible red lights or queuing phenomena at signal intersections. Through this pre-judgment, the system can provide a reasonable passing time window for the vehicle to help it avoid traffic congestion and improve driving efficiency. The function of the speed pre-analysis unit 1122 is to estimate the optimal passing speed of the vehicle according to the actual traffic conditions of each road section after determining the future passing scenario. This module will combine the dissipation time of queuing vehicles, the current vehicle speed, and the geometric structure of the road to derive the optimal vehicle speed range for passing through each intersection. The time pre-analysis unit 1121 is used to calculate the target passing time window for passing through consecutive intersections, so that within this time window, the service vehicle can pass through the intersection when the traffic light is green.

[0083] The time pre-analysis sub-module 121 is used to calculate the target passing time window for passing through consecutive intersections, so that within this time window, the service vehicle can pass through the intersection when the traffic light is green. Since the initial speed of entering each road section is unknown, the time spent passing through each road section is calculated using a conservative estimation formula, that is, it is assumed that the vehicles entering the road section will all experience the speed change process between the upper and lower limits. The calculation formula for the driving time interval reaching the intersection is as follows:

[0084]

[0085] Where, t low 、t high are the minimum and maximum passing times spent by the vehicle driving on the i-th road section; L i is the length of the i-th road section; v max 、v min are the upper and lower limits of the vehicle driving speed. The upper limit is set according to the road speed limit, and the lower limit is set to prevent the vehicle from driving at an extremely low speed and affecting the driving of the following vehicle; a max 、a min are the upper and lower limits of the vehicle acceleration.

[0086] Where, in an embodiment of the present application, according to the roadside data collected by the cloud, the traffic light phases and timing information of each intersection can be obtained. The intersection of the estimated road section driving time interval and the green light window is used to obtain the passable time interval, that is, the calculation formula for the target passing time window is:

[0087]

[0088] Where, They are the times when the j-th phase of the i-th intersection switches to green and red respectively.

[0089] Figure 6 It is a schematic diagram after time pre-analysis. The passable intervals obtained by processing reduce the invalid optimization process of infeasible solutions.

[0090] The speed pre-analysis sub-module 1122 is used to calculate the target passing speed interval for passing through consecutive intersections, so that the vehicle can pass through consecutive intersections within the target passing time window.

[0091] Assume that the fastest and slowest moments of arriving at the i-th intersection are After selecting the target passing time interval, the upper and lower limits of the speed to be traveled on each road section can be determined. That is, the calculation formula for the target passing speed interval is:

[0092]

[0093] Among them, They are the fastest moment and the slowest moment of arriving at the i-th intersection respectively. L i is the length of the i-th road section, and v max , v min are the upper and lower limit values of the driving speed of at least one vehicle.

[0094] The obtained are the passing speed intervals of each road section. Driving within this interval can enable the vehicle to pass through the intersection within the target passing time interval. Since the speed and moment of entering the next road section are unknown before the specific speed curve comes out, the passing speed interval should be dynamically adjusted after the speed curve of each road section is driven.

[0095] Optionally, in an embodiment of the present application, the vehicle speed planning module includes: a dynamic programming solving unit, which is used to establish a cost function of a control problem that satisfies preset optimal conditions for predictive cruise control of consecutive intersections with the energy consumption, driving time, and speed fluctuation of at least one vehicle as the objectives, and generate a speed control sequence that satisfies the preset optimal conditions according to the control problem cost function.

[0096] In the embodiment of the present application, the vehicle speed planning module 113 includes a dynamic programming solving unit, that is, the dynamic programming solving algorithm 1131, which is used to construct an optimal control problem for the urban arterial road passing scenario, so as to realize that under the urban driving rules, given an optimal control law, the transfer process of the vehicle power system control from the initial value to the final value state has optimal performance.

[0097] The predictive cruise control problem pays more attention to the longitudinal driving of the vehicle and does not consider the lateral dynamic situation of the vehicle. Therefore, only a vehicle longitudinal dynamics model is established. The traction force for the vehicle to drive longitudinally needs to overcome the rolling resistance F generated by the contact between the tire and the groundf 1. The air resistance F acting on the vehicle body w 2. The gradient resistance F when driving on a slope i and the acceleration resistance F j . The calculation formula for the driving resistance is as follows:

[0098]

[0099] In the formula, m represents the vehicle mass (kg); g represents the acceleration due to gravity (m / s 2 ); f represents the rolling resistance coefficient; α represents the road slope angle; C d represents the air resistance coefficient; A represents the frontal area (m 2 ); ρ represents the air density (kg / m 3 ); v represents the driving speed (m / s); δ represents the conversion coefficient of the rotating mass.

[0100] Then there is the longitudinal dynamics equation:

[0101] F d = F f + F w + F i + F j

[0102] In order to calculate the fuel consumption of the vehicle more accurately, an engine fuel consumption model of the vehicle is established. This polynomial is a quadratic polynomial function of the engine speed and the engine torque T tq .

[0103]

[0104] Among them, ξ i,j is the fitting coefficient. The specific fitting parameters are shown in the following table, and the fitting results are as Figure 7 shown.

[0105] Table 3 is the vehicle parameter table. Among them, as shown in Table 3:

[0106] Table 3

[0107]

[0108]

[0109] Table 4 is the polynomial parameter table of the fuel consumption model. Among them, as shown in Table 4:

[0110] Table 4

[0111] Parameter Symbol Numerical value Constant term <![CDATA[ξ 0,0 > 0.001766 First-order rotational speed term <![CDATA[ξ 1,0 > -2.387e-06 First-order torque term <![CDATA[ξ 0,1 > -1.222e-06 Second-order torque term <![CDATA[ξ 0,2 > 1.473e-09 First-order hybrid type <![CDATA[ξ 1,1 > 5.05e-09 Second-order rotational speed term <![CDATA[ξ 2,0 > 6.49e-10

[0112] Considering that: ① The traffic light constraints are closely related to the location; ② The road information for speed planning is mainly given based on the vehicle location information. If a model is established in the time domain, the computational complexity will increase. Therefore, the optimal control problem is constructed as a distance-based discrete system. Using the vehicle driving time t (s) and speed v (s) as state variables, and the engine output torque T m as the control variable to establish the state transition matrix x(s) = [t(s) v(s)] T :

[0113]

[0114] Taking the comprehensive performance of energy consumption, driving time, and speed fluctuation as the optimization objective, establish the cost function of the optimal control problem for continuous intersection predictive cruise control:

[0115]

[0116]

[0117] In the formula, Q(s), t trip is the energy and time consumed by the vehicle during driving on the k-th section of the road s k interval, |v k (s) - v k-1 (s)| is the absolute value of the speed difference between the current stage and the previous stage, and λ1, λ2, λ3 are the weight factors of the corresponding cost items. Discretize the total road length with a distance step of Δs, divide the road into N - 1 equal parts, and the stage number k = 1, 2,..., N. is the distance from the starting and ending points of each section of the road to the initial position of the vehicle,

[0118] The dynamic programming solution algorithm 1131 is used to solve the optimal control problem and obtain the speed control sequence with the optimal performance index value of the cost function. Dynamic programming is proposed based on the Bellman optimization principle, decomposes the dynamic optimization decision problem into interconnected discrete multi-step decision problems, and is an effective method for solving the numerical solution of multi-variable and multi-constraint problems.

[0119] However, running the dynamic programming algorithm requires a large amount of computing resources. Due to the physical space and equipment cost of the vehicle terminal, it is unrealistic to install a server on each vehicle that can quickly complete the computing tasks. However, with the support of the cloud control system, the vehicle terminal only needs to send a request for speed planning to the regional cloud, and the regional cloud will dynamically optimize and schedule the computing resource usage of the planning task to multiple edge clouds. The powerful cloud computing resources can complete such high-real-time computing tasks. Therefore, in the environment supported by the cloud control system, the dynamic programming algorithm is selected to solve the continuous intersection predictive cruise control problem, and the design of the predictive cruise control method is specifically elaborated below.

[0120] Since dynamic programming must ensure the optimality of the subsequent sub-routes, it generally solves the problem by backward deduction starting from the terminal value, calculates the optimal cost values from each stage to the terminal value in turn, and obtains the optimal decision sequence accordingly. The expression of the cost function for solving dynamic programming at each stage is as follows:

[0121]

[0122] J k+1 (f(v k ,u k ) is the cumulative optimal cost of the subsequent sub-route. By storing the cumulative optimal cost, dynamic programming avoids the repeated calculation of many sub-problems. f(v k ,u k ) is the state transition equation, which characterizes the influence of the current state and decision results on the next state. The expression is as follows:

[0123]

[0124] On the basis of satisfying the constraints of the dynamic system, the solution process of dynamic programming also needs to satisfy the following constraints:

[0125]

[0126] k = i means that the current stage will reach the intersection, so the distance to the terminal value should be equal to the road section distance. And the time state variable t needs to be within the target time window obtained by the time pre-analysis sub-module 1121, and the queuing time prediction result obtained by solving the queuing dissipation time prediction module 111 is taken into account.

[0127] The algorithm first calculates the transfer cost to the feasible state points at the N - 1 stage. The feasible state points are determined by the vehicle dynamics constraints and the passing speed interval obtained by pre-analysis. Record the decisions of the optimal costs from each state point at the N - 1 stage to the N stage, and so on to solve the entire planning process of k = 1, 2,... N. An optimal vehicle speed sequence is generated by the backtracking method. Finally, starting from the initial value of k = 1, the speed sequence is smoothly transitioned through forward indexing. The vehicle only executes the optimal solution with h = 1 and repeats the optimization speed solution process after rolling a discrete distance of Δs.

[0128] The on-vehicle platform 200 of at least one vehicle, and the on-vehicle platform 200 of at least one vehicle is communicatively connected to the cloud control platform 100, and is used to plan the target cruise vehicle speed of at least one vehicle based on the vehicle speed sequence that meets the preset optimal conditions and the actual state of at least one vehicle, so as to determine the vehicle speed trajectory of at least one vehicle that meets the preset optimal conditions based on the target cruise vehicle speed, and control at least one vehicle to travel according to the vehicle speed trajectory that meets the preset optimal conditions.

[0129] It can be understood that the vehicle-mounted platform 200 of at least one automobile in the present application can be a vehicle-mounted platform 200 .

[0130] In the actual implementation process, the vehicle-mounted platform 200 of at least one car in the embodiment of the present application is a key part of the vehicle's speed control, responsible for receiving the speed command issued by the cloud control platform 100, and performing optimal speed control in combination with the actual driving status of the vehicle. Real-time data interaction is carried out between the cloud control platform 100 and the vehicle-mounted platform 200 through a wireless communication system (such as 4G / 5G network). T-BOX (Telematics Box) is a key hub device for realizing cloud control and actual vehicle operation. T-BOX is not only responsible for the analysis and execution of instructions issued by the cloud control platform 100, but also for monitoring and adjusting the system status of the vehicle under various working conditions. Its functions cover the analysis algorithm of the recommended speed and gear, the transmission mechanism of the vehicle control command, and the switching logic of the system mode. T-BOX realizes the key operations of intelligent cruise control by communicating with CAN.

[0131] The embodiments of the present application can combine traffic information from multiple intersections and perform global speed planning based on the dynamic changes in queue dissipation time. By acquiring the status of intersection traffic lights and queue conditions in real time, the system can plan the optimal speed trajectory for the vehicle to avoid energy waste caused by frequent starts and stops. This speed planning method combined with queue dissipation time prediction can not only improve the traffic efficiency of urban trunk roads, but also provide vehicles with a more energy-saving driving strategy. In this process, a dynamic planning calculation method is used as an auxiliary module to achieve rolling adjustment of the speed trajectory to ensure accurate prediction and global optimization of queue dissipation time.

[0132] Optionally, in one embodiment of the present application, the on-board platform 200 of at least one automobile includes: a vehicle speed instruction parsing module, which is used to match and locate the real-time position of at least one automobile and the target waypoint to obtain recommended driving information of the target waypoint, and parse at least one vehicle speed instruction including cruising speed, gear information, acceleration instruction or deceleration instruction issued by the cloud control platform 100 according to the recommended driving information to generate a parsed vehicle speed instruction; a cruise state control module, which is used to control the speed of at least one automobile based on the parsed vehicle speed instruction and the changes in the traffic environment in front of at least one automobile according to the speed and distance difference between the front vehicle and the at least one automobile, so as to control the automobile to travel according to a speed trajectory that meets preset optimal conditions.

[0133] It is understandable that this application designs a vehicle global speed planning technology, combines the queue dissipation prediction results, and uses real-time roadside and cloud multi-source data to perform multi-intersection collaborative optimization. This application focuses on the overall technical framework and related implementation methods of achieving non-stop vehicle passing through multiple intersections and improving traffic efficiency through intelligent prediction and cloud computing.

[0134] In the actual execution process, the embodiments of the present application can be as Figure 8As shown, it is a sub-module deployed on the vehicle platform 200 in a specific example of the intelligent vehicle urban arterial cloud-controlled energy-saving cruise system based on high-precision maps in the embodiment of the present application. The vehicle speed command parsing module 21 and the cruise state control module 22 in the T-BOX are the core of the vehicle platform 200. The cloud control platform 100 issues specific control commands to the vehicle-mounted T-BOX based on the predicted queue dissipation time and the generated speed sequence. The command content received by the T-BOX usually includes the recommended cruise vehicle speed, gear information, acceleration or deceleration commands, etc. The parsing algorithm for the recommended vehicle speed and gear parses these commands and converts them into operation parameters that the vehicle can execute. The specific working process of the parsing algorithm is as follows: First, the control commands issued by the cloud are transmitted to the T-BOX in the form of communication data packets through the vehicle-mounted communication system (such as LTE or 5G network). Then, the parsing algorithm extracts relevant control parameters from the data packet, such as at what speed the vehicle should cruise and when to shift gears. Due to the differences in the vehicle's power transmission system and electronic control system, the parsing algorithm adjusts the recommended vehicle speed and gear according to the current operating state of the vehicle (such as engine speed, gear, vehicle speed, etc.) to ensure seamless execution of the commands. The parsed commands are not directly sent to the vehicle's actuators, but first transmitted to each electronic control unit (ECU) and transmission control unit (TCU) of the vehicle through the vehicle-mounted control network, such as the CAN (Controller Area Network) bus. The CAN bus is an efficient and stable vehicle-mounted communication protocol, widely used for information transmission between various subsystems inside the vehicle. The T-BOX communicates with the ECU and TCU through the CAN bus to ensure that the recommended vehicle speed and gear can be applied to vehicle control in a timely and accurate manner. After the parsing algorithm completes the parsing of the cloud commands, the T-BOX sends specific control commands to each control unit of the vehicle through the CAN line. The transmission of the control commands involves two key modules: the ECU and the TCU. The ECU is responsible for receiving the recommended vehicle speed information sent by the T-BOX and adjusting parameters such as the throttle opening and engine speed according to the current driving conditions of the vehicle to achieve the predetermined vehicle speed control target. In terms of vehicle control, the TCU controls the shifting action according to the gear recommendation command sent by the T-BOX. Since the vehicle requires different gears under different speed and load conditions, the TCU combines the vehicle's real-time dynamics state, such as vehicle speed, engine speed, and load conditions, for shifting control to ensure that the vehicle can maintain the best power transmission efficiency and the most economical energy consumption during cruising. The entire control command transmission process has high real-time performance and accuracy. The high bandwidth and low latency characteristics of the CAN line ensure that the commands parsed from the T-BOX can be quickly transmitted to the ECU and TCU and obtain real-time responses inside the vehicle.This process plays a crucial role in the intelligent cruise control of vehicles, enabling the vehicle to operate precisely according to the planned vehicle speed and gear of the cloud control platform 100 in a complex urban traffic environment, thus achieving an energy-saving and efficient driving experience. The in-vehicle platform 200 ensures the switching of system modes and the safety adjustment function. During the actual operation of the vehicle, the T-BOX is not only responsible for parsing and transmitting cloud control instructions but also needs to monitor the running state of the vehicle in real time to ensure the safety and stability of the system. A complete system mode switching logic is designed in the T-BOX to handle various emergencies or abnormal states, such as signal interruption, emergency braking, etc. This logic monitors the running data and communication status of the vehicle to ensure that the system can switch to the safety mode in a timely manner under any adverse conditions, avoiding accidents.

[0135] The switching logic of the system mode depends on the continuous monitoring of the vehicle state by the T-BOX. When the T-BOX detects that the vehicle is in an abnormal state, such as signal failure, abnormal sensor data, or the vehicle needs to perform emergency braking, the system will immediately enter the preset safety mode. In this mode, the T-BOX will automatically stop sending recommended vehicle speed and gear instructions to the ECU and TCU and let the vehicle's autonomous control system take over the operation of the vehicle. This mode switching ensures that when cloud control cannot be carried out normally, the vehicle can still drive safely according to the local control strategy. In case of an emergency, the safety adjustment mechanism in the T-BOX also includes intervention in the vehicle's braking system and power system. For example, when the T-BOX detects an emergency ahead, it will immediately trigger the vehicle's braking system to ensure the vehicle stops safely first. This automated safety adjustment process, through the close integration of the T-BOX with various internal systems of the vehicle, enables the vehicle to flexibly handle various complex situations in a changing traffic environment.

[0136] In the embodiment of the present application, the vehicle speed command parsing module 21 is used to perform matching and positioning according to the real-time position of the vehicle and the target waypoints divided by the cloud to obtain the recommended driving information of the target waypoints, supporting the controlled vehicle to execute the economic vehicle speed command.

[0137] In an embodiment, the controlled vehicle requests a cloud control predictive cruise control application service request and interacts with the cloud control platform 100 at a certain frequency. For example, in this embodiment, the on-vehicle platform 200 interacts with the cloud control platform 100 at a frequency of 10 hz. Due to the characteristics of the rapidly changing traffic situation in urban conditions, in this embodiment, the cloud control platform 100 divides each waypoint on the target driving path at an equal distance step of 20 m. At the same time, the target waypoint representing the intersection should be divided based on the intersection stop line. Therefore, the cruise state control module 22 needs to match the target waypoint of the vehicle's real-time position from the waypoints sent by the cloud control platform 100, so as to determine the economic vehicle speed that should be traveled currently according to the recommended driving information included in the sent waypoints.

[0138] The vehicle speed command parsing module 21 is used to parse the economic speed command that the current vehicle should travel according to the recommended driving information included in the target waypoint. In this embodiment, the economic vehicle speed sequence sent by the cloud control platform 100 is stored in the queue linear list in the order from near to far according to the distance between each target waypoint and the initial position of the vehicle. The elements in the space follow the principle of first in first out and are output at the end of the queue in turn.

[0139] The cruise state control module 22 uses an on-vehicle radar to detect changes in the traffic environment in front of the vehicle, and automatically adjusts the driving vehicle speed according to the speed and distance differences between the vehicle in front and the self-vehicle through the control of the drive and braking systems, so as to maintain a safe driving distance between the self-vehicle and the vehicle in front. At the same time, this module controls the error of the safe following distance between the controlled vehicle and the vehicle in front. The cruise state control module 22 takes the relative speed Δv between the self-vehicle and the vehicle in front and the target following distance error Δd as inputs and the safe following vehicle speed control of the self-vehicle as the output:

[0140] v safe =K v Δv+K d Δd

[0141] In the formula, K v and K d are the driver control gains.

[0142] The vehicle urban arterial cloud-controlled energy-saving cruise system based on high-precision maps proposed according to the embodiments of the present application can utilize the vehicle-end, roadside device, and high-precision map data collected by the cloud control platform, combine the driving behavior of the vehicle and traffic signal constraints, construct a vehicle driving state prediction model from a global perspective, and through dynamic analysis and real-time update algorithms, can accurately predict the queue dissipation time of vehicles at each intersection, effectively improving the traffic flow passing efficiency in complex urban environments; by constructing a queue dissipation time prediction model based on XGBoost, deeply mining large-scale traffic data, and automatically learning traffic flow laws, this technology can flexibly respond to the time-varying traffic characteristics of different road sections and signal cycles, dynamically update the queue dissipation time prediction, significantly improving the accuracy and stability of the queue dissipation time prediction, especially having obvious advantages in complex scenarios with long time, multiple road sections, and multiple lanes; combining the queue dissipation prediction results, using multi-source data from real-time roadside and cloud to perform multi-intersection collaborative optimization, and achieving seamless passing of vehicles through multiple intersections through intelligent prediction and cloud computing, the overall technical framework for improving passing efficiency and its related implementation methods. Thus, it solves the problems in the related technologies. First, the traditional queue dissipation time prediction module is based on idealized assumptions and fails to fully consider the vehicle differences in heterogeneous traffic flows, resulting in insufficient prediction accuracy; second, the existing cruise control methods fail to effectively combine the dynamic characteristics of queue dissipation, making the planned vehicle speed commands difficult to execute in the actual traffic environment; in addition, the distributed control method of deploying processing units on the vehicle side is limited by hardware costs and computing capabilities and cannot perform real-time and efficient speed planning in complex traffic scenarios at multiple intersections.

[0143] Next, a vehicle urban arterial cloud-controlled energy-saving cruise method based on high-precision maps proposed according to the embodiments of the present application is described with reference to the accompanying drawings.

[0144] Figure 9 It is a flowchart of the vehicle urban arterial cloud-controlled energy-saving cruise method based on high-precision maps according to the embodiments of the present application.

[0145] As Figure 9 shown, the vehicle urban arterial cloud-controlled energy-saving cruise method based on high-precision maps includes the following steps:

[0146] In step S901, based on the target high-precision map and the corresponding road traffic information, predict the queue dissipation time of at least one vehicle to generate a vehicle speed sequence that meets preset optimal conditions.

[0147] In step S902, based on the vehicle speed sequence that meets the preset optimal conditions and the actual state of at least one vehicle, plan the target cruise vehicle speed of at least one vehicle, determine the vehicle speed trajectory of at least one vehicle that meets the preset optimal conditions based on the target cruise vehicle speed, and control at least one vehicle to travel according to the vehicle speed trajectory that meets the preset optimal conditions.

[0148] Optionally, in an embodiment of the present application, based on the target high-precision map and the corresponding road traffic information, the queuing dissipation time of at least one vehicle is predicted to generate a vehicle speed sequence that meets the preset optimal conditions, including: based on the real-time position information of at least one vehicle, generating at least one of static road information and dynamic traffic information including lane lines, intersections, stop lines, and crosswalks; based on at least one of static road information and dynamic traffic information, predicting the queuing dissipation time of at least one vehicle at the intersection according to a preset model; analyzing the queuing dissipation time to determine the time window and speed range that meet the preset optimal conditions for at least one vehicle to pass through each section of the road; and according to the preset dynamic programming algorithm, determining the vehicle speed sequence that meets the preset optimal conditions.

[0149] Optionally, in an embodiment of the present application, based on at least one of static road information and dynamic traffic information, predicting the queuing dissipation time of at least one vehicle at the intersection according to a preset model includes: based on real-time traffic data, constructing a traffic data set, and performing data cleaning on the data in the traffic data set to remove abnormal data and generate a cleaned data set; and using the cleaned data set to train the preset model to predict the queuing dissipation time of at least one vehicle at the intersection.

[0150] Optionally, in an embodiment of the present application, analyzing the queuing dissipation time to determine the time window and speed range that meet the preset optimal conditions for at least one vehicle to pass through each section of the road includes: a time pre-analysis unit for calculating the target passing time window for passing through consecutive intersections to determine the time for at least one vehicle to pass through consecutive intersections with a green light within the target passing time window; and a speed pre-analysis unit for calculating the target passing speed range for at least one vehicle to pass through consecutive intersections based on the time.

[0151] Optionally, in an embodiment of the present application, the calculation formula for the target passing time window is:

[0152]

[0153] where are the times when the j-th phase of the i-th intersection switches to green and red respectively;

[0154] The calculation formula for the target passing speed range is:

[0155]

[0156] where are the earliest and latest times to reach the i-th intersection respectively, L i is the length of the i-th section of the road, v max 、vmin are the upper and lower limit values of the driving speed of at least one vehicle.

[0157] Optionally, in an embodiment of the present application, for the time window and speed range that meet the preset optimal conditions, a vehicle speed sequence that meets the preset optimal conditions is determined according to the preset dynamic programming algorithm, including: aiming at the energy consumption, driving time, and speed fluctuation of at least one vehicle, establishing a cost function of the control problem for the predictive cruise control at consecutive intersections that meets the preset optimal conditions, and generating a speed control sequence that meets the preset optimal conditions according to the control problem cost function.

[0158] Optionally, in an embodiment of the present application, controlling at least one vehicle to travel along a vehicle speed trajectory that meets the preset optimal conditions includes: matching and positioning according to the real-time position of at least one vehicle and the target waypoint to obtain the recommended driving information of the target waypoint, and parsing at least one vehicle speed instruction including cruise vehicle speed, gear information, acceleration instruction, or deceleration instruction sent by the cloud control platform 100 according to the recommended driving information to generate a parsed vehicle speed instruction; based on the parsed vehicle speed instruction and the traffic environment change in front of at least one vehicle, performing speed control on at least one vehicle according to the speed and distance difference between the vehicle in front and at least one vehicle to control the vehicle to travel along a vehicle speed trajectory that meets the preset optimal conditions.

[0159] It should be noted that the foregoing explanation of the embodiment of the cloud control energy-saving cruise system for vehicles on urban arterial roads based on high-precision maps also applies to the cloud control energy-saving cruise method for vehicles on urban arterial roads based on high-precision maps in this embodiment, which will not be elaborated here.

[0160] The vehicle urban arterial cloud-controlled energy-saving cruise method based on high-precision maps proposed in the embodiments of the present application can utilize the vehicle-end, roadside device, and high-precision map data collected by the cloud control platform, combine the driving behavior of the vehicle and traffic signal constraints, construct a vehicle driving state prediction model from a global perspective, and through dynamic analysis and real-time update algorithms, can accurately predict the queue dissipation time of vehicles at each intersection, effectively improving the traffic flow passing efficiency in complex urban environments; by constructing a queue dissipation time prediction model based on XGBoost, deeply mining large-scale traffic data, and automatically learning traffic flow rules, this technology can flexibly cope with the time-varying traffic characteristics of different road sections and signal cycles, dynamically update the queue dissipation time prediction, significantly improving the accuracy and stability of the queue dissipation time prediction, especially having obvious advantages in complex scenarios with long time, multiple road sections, and multiple lanes; combining the queue dissipation prediction results, using multi-source data from real-time roadside and cloud to perform multi-intersection collaborative optimization, and achieving seamless passing of vehicles through multiple intersections through intelligent prediction and cloud computing, the overall technical framework for improving passing efficiency and its related implementation methods. Thus, it solves the problems in the related technologies. First, the traditional queue dissipation time prediction module is based on idealized assumptions and fails to fully consider the vehicle differences in heterogeneous traffic flows, resulting in insufficient prediction accuracy; second, the existing cruise control methods fail to effectively combine the dynamic characteristics of queue dissipation, making the planned vehicle speed commands difficult to execute in the actual traffic environment; in addition, the distributed control method of deploying processing units on the vehicle side is limited by hardware costs and computing capabilities and cannot perform real-time and efficient speed planning in complex multi-intersection traffic scenarios, and the problems of inaccurate queue dissipation time prediction and low energy efficiency during the cruise of urban vehicles in the current technology.

[0161] Figure 10 The following is a schematic structural diagram of an electronic device provided by an embodiment of the present application. The electronic device may include:

[0162] A memory 1001, a processor 1002, and a computer program stored on the memory 1001 and executable on the processor 1002.

[0163] When the processor 1002 executes the program, it implements the vehicle urban arterial cloud-controlled energy-saving cruise method based on high-precision maps provided in the above embodiments.

[0164] Further, the electronic device further includes:

[0165] A communication interface 1003 for communication between the memory 1001 and the processor 1002.

[0166] The memory 1001 is used to store a computer program executable on the processor 1002.

[0167] The memory 1001 may include high-speed RAM memory and may also include non-volatile memory, such as at least one disk memory.

[0168] If the memory 1001, the processor 1002, and the communication interface 1003 are implemented independently, the communication interface 1003, the memory 1001, and the processor 1002 can be interconnected via a bus and communicate with each other. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, an Extended Industry Standard Architecture (EISA) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For the sake of simplicity in representation, Figure 10 only a thick line is used in the figure, but it does not mean that there is only one bus or one type of bus.

[0169] Optionally, in a specific implementation, if the memory 1001, the processor 1002, and the communication interface 1003 are integrated on a single chip, the memory 1001, the processor 1002, and the communication interface 1003 can communicate with each other via an internal interface.

[0170] The processor 1002 may be a Central Processing Unit (CPU), or an Application Specific Integrated Circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present application.

[0171] This embodiment also provides a computer-readable storage medium, on which a computer program is stored. When the program is executed by a processor, the above-described method for energy-saving cruise control of an automobile on an urban arterial road based on a high-precision map is implemented.

[0172] The embodiments of the present application also provide a computer program product, on which a computer program is stored. When the program is executed by a processor, the above-described method for energy-saving cruise control of an automobile on an urban arterial road based on a high-precision map is implemented.

[0173] In the description of this specification, the descriptions with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples", etc., mean that the specific features, structures, materials, or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of this application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described may be combined in any one or N embodiments or examples in a suitable manner. In addition, without contradiction, those skilled in the art can combine and combine the different embodiments or examples described in this specification and the features of different embodiments or examples.

[0174] In addition, the terms "first" and "second" are used only for descriptive purposes and cannot be construed as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include at least one of such features. In the description of this application, the meaning of "N" is at least two, such as two, three, etc., unless otherwise specifically defined.

[0175] Any process or method description, whether in a flowchart or described in other ways, can be understood to represent a module, segment, or portion of code including one or N executable instructions for implementing a customized logical function or process, and the scope of the preferred embodiments of this application includes additional implementations, where the functions may be executed in a manner that is not in the order shown or discussed, including in a substantially simultaneous manner according to the functions involved or in the reverse order, which should be understood by those skilled in the art to which the embodiments of this application pertain.

[0176] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a definable sequence list of executable instructions for implementing logical functions, and can be specifically implemented in any computer-readable medium for use by an instruction execution system, apparatus, or device (such as a computer-based system, a system including a processor, or other systems that can fetch and execute instructions from the instruction execution system, apparatus, or device), or used in combination with these instruction execution systems, apparatus, or devices. For the purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. More specific examples (non-exhaustive list) of computer-readable media include the following: an electrical connection part (electronic device) having one or N wirings, a portable computer disk cartridge (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). Additionally, the computer-readable medium can even be paper or other suitable media on which the program can be printed, because the program can be obtained electronically by optically scanning the paper or other media, followed by editing, interpretation, or otherwise processing as appropriate, and then stored in a computer memory.

[0177] It should be understood that various parts of the present application can be implemented by hardware, software, firmware, or a combination thereof. In the above embodiments, the N 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 in hardware, as in another embodiment, any one or a combination of the following techniques well known in the art can be used: discrete logic circuits having logic gate circuits for implementing logical functions on data signals, application-specific integrated circuits having appropriate combinational logic gate circuits, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0178] Those of ordinary skill in the art of this technology can understand that all or part of the steps carried by the method of implementing the above embodiments can be completed by instructing relevant hardware through a program, and the said program can be stored in a computer-readable storage medium. When the program is executed, it includes one or a combination of the steps of the method embodiments.

[0179] In addition, in each embodiment of the present application, each functional unit can be integrated into one processing module, or each unit can exist physically alone, or two or more units can be integrated into one module. The above-mentioned integrated module can be implemented in the form of hardware or in the form of a software functional module. When the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium.

[0180] The above-mentioned storage medium can be a read-only memory, a magnetic disk or an optical disc, etc. Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and should not be construed as limiting the present application. Those of ordinary skill in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of the present application.

Claims

1. An energy-saving cruise control system for automobiles on urban arterial roads based on high-precision maps, characterized in that, Including: A cloud control platform, which is used to predict the queue dissipation time of at least one vehicle based on a target high-precision map and the corresponding road traffic information, so as to generate a vehicle speed sequence that meets preset optimal conditions; The in-vehicle platforms of the at least one vehicle, the in-vehicle platforms of the at least one vehicle are communicatively connected to the cloud control platform, and are used to plan the target cruise vehicle speed of the at least one vehicle based on the vehicle speed sequence that meets the preset optimal conditions and the actual states of the at least one vehicle, so as to determine the vehicle speed trajectory of the at least one vehicle that meets the preset optimal conditions based on the target cruise vehicle speed, and control the at least one vehicle to travel according to the vehicle speed trajectory that meets the preset optimal conditions.

2. The vehicle urban arterial cloud-controlled energy-saving cruise system based on a high-precision map according to claim 1, wherein The cloud control platform includes: A high-precision map module, which is used to generate at least one piece of static road information and dynamic traffic information including lane lines, intersections, stop lines, and crosswalks based on the real-time position information of the at least one vehicle; A queue dissipation time prediction module, which is used to predict the queue dissipation time of the at least one vehicle at the intersection according to a preset model based on the at least one piece of static road information and the dynamic traffic information; A scenario pre-analysis module, which is used to analyze the queue dissipation time to determine the time window and speed range that meet the preset best conditions for the at least one vehicle to pass through each section of the road; A vehicle speed planning module, which determines the vehicle speed sequence that meets the preset optimal conditions based on the time window and the speed range that meet the preset best conditions according to a preset dynamic programming algorithm.

3. The vehicle urban arterial cloud-controlled energy-saving cruise system based on a high-precision map according to claim 2, characterized in that, The queue dissipation time prediction module includes: A data set construction and cleaning unit, which is used to construct a traffic data set based on real-time traffic data, and clean the data in the traffic data set to remove abnormal data and generate a cleaned data set; A model training unit, which is used to train the preset model with the cleaned data set to predict the queue dissipation time of the at least one vehicle at the intersection.

4. The vehicle urban arterial cloud-controlled energy-saving cruise system based on a high-precision map according to claim 3, characterized in that, The scenario pre-analysis module includes: A time pre-analysis unit, which is used to calculate the target passing time window for passing through consecutive intersections, so as to determine the time for the at least one vehicle to pass through the consecutive intersections with a green light within the target passing time window; A speed pre-analysis unit, which is used to calculate the target passing speed range for the at least one vehicle to pass through the consecutive intersections based on the time.

5. The vehicle urban arterial cloud-controlled energy-saving cruise system based on a high-precision map according to claim 4, wherein The calculation formula for the target passing time window is: Among them, are respectively the times when the j-th phase at the i-th intersection switches to green and red lights; The calculation formula for the target passing speed range is: Among them, are respectively the fastest time and the slowest time to reach the i-th intersection, L i is the length of the i-th road segment, v max , v min are the upper and lower limits of the at least one vehicle driving speed.

6. The vehicle urban arterial cloud-controlled energy-saving cruise system based on a high-precision map according to claim 1, wherein, The vehicle speed planning module includes: A dynamic programming solving unit, which is used to establish a cost function of a control problem that meets the preset optimal conditions for predictive cruise control of consecutive intersections with the energy consumption, driving time, and speed fluctuation of the at least one vehicle as the goals, and generate a speed control sequence that meets the preset optimal conditions according to the control problem cost function.

7. The vehicle urban arterial cloud-controlled energy-saving cruise system based on a high-precision map according to claim 1, characterized in that, The in-vehicle platforms of the at least one vehicle include: A vehicle speed command parsing module, configured to perform matching and positioning based on the real-time positions of the at least one vehicle and the target waypoint, so as to obtain recommended driving information of the target waypoint, and parse at least one vehicle speed command including a cruise vehicle speed, a gear information, an acceleration command or a deceleration command sent by the cloud control platform according to the recommended driving information, so as to generate a parsed vehicle speed command; A cruise state control module, configured to perform speed control on the at least one vehicle based on the parsed vehicle speed command and changes in the traffic environment in front of the at least one vehicle, and control the vehicle to travel along the vehicle speed trajectory that meets the preset optimal conditions according to the speed and distance differences between the vehicle in front and the at least one vehicle.

8. A method for energy-saving cruise control of an automobile on urban arterial roads based on a high-precision map, characterized in that, It includes the following steps: Based on the target high-precision map and the corresponding road traffic information, predicting the queue dissipation time of at least one vehicle, so as to generate a vehicle speed sequence that meets the preset optimal conditions; Based on the vehicle speed sequence that meets the preset optimal conditions and the actual state of the at least one vehicle, planning the target cruise vehicle speed of the at least one vehicle, so as to determine the vehicle speed trajectory of the at least one vehicle that meets the preset optimal conditions based on the target cruise vehicle speed, and control the at least one vehicle to travel along the vehicle speed trajectory that meets the preset optimal conditions.

9. An electronic device, characterized in that, It includes: A memory, a processor, and a computer program stored on the memory and executable on the processor, and the processor executes the program to implement the vehicle cloud control energy-saving cruise method on urban arterial roads based on a high-precision map as claimed in claim 8.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, The program is executed by the processor to be used to implement the vehicle cloud control energy-saving cruise method on urban arterial roads based on a high-precision map as claimed in claim 8.

Images