Consider a predictive adaptive cruise control system of vehicle-cloud dual closed-loop control architecture

Abstract

The application relates to the technical field of vehicles, in particular to a predictive adaptive cruise control system considering a vehicle-cloud double closed-loop control architecture, which comprises the following steps: a cloud control platform receives driving state information, position information and a plurality of original route point information of a vehicle sent by a vehicle terminal platform, and calculates an economic vehicle speed sequence of the vehicle; the vehicle terminal platform receives the economic vehicle speed sequence, and constructs a following vehicle speed model of the vehicle in combination with a vehicle speed sequence of a preceding vehicle in a target time period, so as to calculate a target vehicle speed of the vehicle, and make the target vehicle speed meet expected requirements; the vehicle-cloud double closed-loop control architecture controls the vehicle to follow and drive by using the target vehicle speed, and updates the driving state information of the vehicle, generates a new following vehicle speed, and makes the vehicle follow and drive based on the predictive adaptive cruise of the vehicle-cloud double closed-loop control architecture. Therefore, the problems in the prior art, such as the use of a nonlinear solving model algorithm, complex solving, low calculation efficiency, the inability to update and iterate the following speed in time and the reduction of the driving performance of the vehicle, are solved.

Description

Technical Field

[0001] This application relates to the field of vehicle technology, and in particular to a predictive adaptive cruise control system that considers a vehicle-cloud dual closed-loop control architecture. Background Technology

[0002] With the continuous development of vehicle intelligence technology, driver assistance functions for commercial vehicles have been widely applied. Among them, ACC (Adaptive Cruise Control), which improves driving safety and reduces driver fatigue, and PCC (Predictive Cruise Control), which reduces vehicle energy consumption and improves driving efficiency, have been vigorously promoted. However, neither can simultaneously guarantee both vehicle safety and fuel economy. Therefore, combining the advantages of both and deeply integrating them is key to achieving safe and energy-efficient driving in commercial vehicles, and has become a current research hotspot and challenge.

[0003] In recent years, the development of cloud control platforms and intelligent connected vehicle technologies has provided new ideas for research on safe and energy-efficient driving of commercial vehicles. Cloud control platforms offer high-precision map services, can integrate perception information from intelligent connected vehicles and road infrastructure, and can achieve real-time multi-threaded rapid computation, providing rich road traffic information and powerful computing support for assisted driving applications. Some researchers have used time-varying road information (including gradient and speed limits) provided by cloud control platforms to solve the problem that existing non-connected vehicles struggle to obtain global road information and time-varying speed limit information, constructing predictive cruise control algorithms that achieve economical driving of vehicles within a global scope, achieving a fuel saving rate of 6.17% compared to constant speed cruise control. Other researchers have used cloud control platforms to enable vehicle platoons to acquire wide-area dynamic traffic environment information, giving the platoons beyond-line-of-sight perception capabilities and improving the safety, economy, efficiency, and smoothness of platoon driving. Still other researchers have proposed a cloud-based predictive cruise control method for platoons, fully considering the advantages of both the vehicle and cloud ends, achieving wide-area, long-term perception and rapid real-time planning computation, improving the economy and stability of platoon driving. The above studies are typical applications of connected cloud control technology to empower vehicle assisted driving, which significantly improves the safety, economy and traffic efficiency of assisted driving, and provides a reference for helping vehicles make safer and more energy-efficient driving strategies under the cloud control architecture.

[0004] In existing research, technologies that balance vehicle driving safety and economy mainly fall into two categories: Eco-ACC (Ecological Adaptive Cruise Control) and PACC (Predictive Adaptive Cruise Control). Researchers have improved upon traditional ACC by designing different cost functions to achieve safe and energy-efficient following. This method is called Eco-ACC. Current Eco-ACC energy-saving approaches mainly include three aspects: smoothing longitudinal acceleration, predicting the speed of the vehicle ahead, and considering the energy cost of following. Smoothing longitudinal acceleration saves fuel by reducing the extra fuel consumption caused by aggressive acceleration, but its effect is not significant in most driving conditions with sparse traffic flow and high speeds. Predicting the speed of the vehicle ahead involves predicting the speed of the vehicle ahead in advance, allowing the vehicle to make more reasonable driving strategies and achieve energy savings. The fuel-saving effect of this method is affected by the accuracy of speed prediction, and its essence is still to smooth the vehicle's speed based on the predicted speed fluctuations of the vehicle ahead, without directly considering the energy consumption aspect of following economy. Among them, the method that considers the energy consumption cost of following the vehicle achieves fuel saving by adding fuel consumption information or energy consumption information to the cost function, which can fundamentally represent the economic efficiency of vehicle driving. However, with the addition of the energy consumption term, the cost function is often nonlinear, making the solution calculation more complicated.

[0005] Most existing research combines the three methods mentioned above. These methods often use a smaller prediction time domain in a local range to reduce computational load, neglecting the global optimal solution. However, safety and energy-saving following control of commercial vehicles should extend the prediction time domain as much as possible to get as close as possible to the global optimal solution, which poses a challenge to computational efficiency.

[0006] The PACC system combines the advantages of PCC and ACC, fully utilizing information such as road gradient and speed limits to calculate the vehicle's optimal economic speed globally. This speed is then used as a reference speed for local following maneuvers. Simultaneously, it considers the dynamic information of the vehicle ahead to plan the local following speed, thereby achieving safe and energy-efficient following for commercial vehicles. Some researchers have adopted a hierarchical architecture, establishing a predictive model of the preceding vehicle's speed trajectory and designing a predictive adaptive cruise controller based on nonlinear model predictive control. The proposed PACC strategies have significantly reduced energy consumption during following maneuvers. Other researchers have planned predictive cruise economic speeds based on road gradient information and proposed a predictive adaptive cruise control strategy optimized using preceding vehicle information to address braking interference caused by the preceding vehicle during cruise, thereby reducing fuel consumption and alleviating driver fatigue.

[0007] However, PACC research in related technologies mostly adopts nonlinear solution model algorithms when planning safe and economical following speeds. This results in high computational resource consumption and long processing time, leading to complex algorithm solutions, low computational efficiency, and difficulty in ensuring the real-time performance of the algorithm planning. Consequently, the algorithm cannot update and iterate the following speed in a timely manner under actual conditions, reducing the vehicle's driving performance, which urgently needs to be addressed. Summary of the Invention

[0008] This application provides a predictive adaptive cruise control system that considers a vehicle-cloud dual closed-loop control architecture to solve the problems in related technologies, such as the use of nonlinear solution models and algorithms, which result in complex algorithm solutions, low computational efficiency, difficulty in ensuring the real-time performance of algorithm planning, inability to update and iterate following speed in a timely manner, and reduced vehicle driving performance.

[0009] The first aspect of this application provides a predictive adaptive cruise control system considering a vehicle-cloud dual closed-loop control architecture, comprising: a cloud control platform, configured to receive vehicle driving status information and location information sent by a vehicle-end platform, and obtain multiple original waypoint information of the vehicle on a target road segment from the vehicle-end platform based on the location information, and calculate an economic speed sequence of the vehicle at a first target distance based on the status information, the location information, and the multiple original waypoint information, and send the economic speed sequence to the vehicle-end platform; the vehicle-end platform, configured to collect the status information and the location information, send the status information and the location information to the cloud control platform, and receive the economic speed sequence from the cloud control platform. Based on the historical information of the preceding vehicle, the system predicts the speed sequence of the preceding vehicle within a target time period. Using the economic speed sequence and the speed sequence of the preceding vehicle within the target time period, it constructs a following speed model for the vehicle at a second target distance. Based on the calculation results of the following speed model, it adjusts the vehicle's target speed to meet the expected target requirements, wherein the second target distance is less than the first target distance. The vehicle-cloud dual-closed-loop control architecture uses the target speed to control the vehicle's following motion and updates the vehicle's driving status information. Based on the updated driving status information, it generates a new following speed for the vehicle, enabling the vehicle to drive based on predictive adaptive cruise control using the vehicle-cloud dual-closed-loop control architecture.

[0010] Optionally, in one embodiment of this application, the cloud control platform includes: a positioning module, used to parse the location information and obtain the current positioning information of the vehicle based on the location information; a high-precision map module, used to obtain multiple original waypoints corresponding to the map information of the target road segment ahead of the vehicle based on the current positioning information of the vehicle; a map reconstruction module, used to reconstruct the multiple original waypoints to obtain multiple target waypoints; and an economic speed sequence calculation module, used to plan the economic speed between the multiple target waypoints based on the current positioning information and the waypoint information of the road ahead when the vehicle is detected to have traveled to the target waypoint, so as to obtain the economic speed sequence of the vehicle for the first target distance.

[0011] Optionally, in one embodiment of this application, the high-precision map module is further configured to: acquire map information of the target road segment ahead of the vehicle; and use the map information to determine the plurality of original waypoints, wherein the plurality of original waypoints includes waypoint locations, slope information corresponding to the waypoint locations, and spacing information between adjacent waypoints.

[0012] Optionally, in one embodiment of this application, the map reconstruction module is further configured to: reconstruct the original waypoints according to a certain spacing or slope change rate based on the information contained in the multiple original waypoints, to obtain multiple target waypoints.

[0013] Optionally, in one embodiment of this application, the economic speed sequence calculation module is further configured to: detect whether the vehicle has reached the target road point; when the vehicle is detected to have reached the target road point, use the vehicle's location information, driving status information and target road point information to plan the economic speed sequence of the vehicle for the future first target distance; discretize the economic speed sequence according to the location of the original road point to obtain economic speed information, store the economic speed information in the original road point information, and send it to the vehicle-side platform.

[0014] Optionally, in one embodiment of this application, the vehicle-side platform includes: a preceding vehicle speed prediction module, configured to predict the speed sequence of the preceding vehicle in a target time period based on the original waypoint information sent by the cloud control platform and the historical information of the preceding vehicle; and a predictive adaptive cruise following speed planning module, configured to, when detecting that the vehicle has traveled to the desired original waypoint, construct a following speed planning model for the second target distance of the vehicle's target safety and target economy based on the original waypoint information sent by the cloud control platform and the speed sequence of the preceding vehicle in the target time period, and solve the following speed planning model.

[0015] Optionally, in one embodiment of this application, the preceding vehicle speed prediction module is further configured to: predict the preceding vehicle's speed in the target time period based on the road slope information in the original waypoint information and the historical speed information of the preceding vehicle using a preset Gaussian process regression algorithm, thereby obtaining predicted driving speed information; convert the predicted driving speed information from the time domain to the spatial domain, and discretize it into the original waypoint information within the second target distance, thereby obtaining the discretized original waypoint information.

[0016] Optionally, in one embodiment of this application, the predictive adaptive cruise following speed planning module is further configured to: based on the discrete original waypoint information, starting from the current location of the vehicle, set a preset number of desired original waypoints at preset intervals of the original waypoints, and detect whether the vehicle has traveled to the set desired original waypoints; when the vehicle is detected to have traveled to the set desired original waypoints, construct a following speed planning model for the vehicle following target safety and target economy using the economic speed information in the original waypoint information sent by the cloud control platform and the speed sequence of the preceding vehicle in the target time period, and solve the model based on a preset dynamic programming algorithm to obtain the following speed of the vehicle within the second target distance.

[0017] Optionally, in one embodiment of this application, the following speed planning model for the vehicle following target safety and target economy is as follows:

[0018]

[0019] subject to

[0020]

[0021] k = 1, 2, 3, 4, 5, v (k) >0

[0022]

[0023] Among them, w1, w2, w3, w4, and w5 represent the weights of fuel consumption, long-distance economical speed, following distance error, relative speed between the lead vehicle and the vehicle in front, and driving efficiency, respectively. Let v be the fuel consumption in stage k. (k) Let Δd be the speed of the main vehicle in stage k. k Let be the relative distance between the main vehicle and the vehicle in front during stage k. Let t be the speed of the vehicle in front during stage k. k Let v be the vehicle's travel time in stage k. (k+1) Let Δs be the speed of the main vehicle in stage k+1. (k)Let δ be the distance between the k-th and (k+1)-th original waypoints, δ be the vehicle rotational mass conversion factor, m be the vehicle mass, r be the wheel radius, and i be the distance between the k-th and (k+1)-th original waypoints. g Where i is the gearbox transmission ratio, i0 is the main reducer transmission ratio, η is the transmission efficiency, and T is the transmission efficiency. (k) For the engine torque in stage k, C D Where A is the air resistance coefficient, g is the frontal area, f is the gravitational acceleration, and θ is the rolling resistance coefficient. (k) Let ω be the road gradient for stage k. (k) For the engine speed in stage k, a (k) For the vehicle acceleration in stage k, T min With T max v is the boundary between minimum and maximum torque. min With v max ω represents the boundary between the minimum and maximum vehicle speeds. min With ω max For the minimum and maximum speed boundaries, a min With a max For the minimum and maximum acceleration boundaries, d min With d max These are the minimum and maximum following distances.

[0024] Optionally, in one embodiment of this application, the predictive adaptive cruise following speed planning module is further configured to: solve the following speed planning model based on the vehicle following target safety and target economy using a preset forward dynamic programming algorithm to obtain the following speed of the vehicle within the second target distance; and send the following speed within the second target distance to the vehicle chassis to perform corresponding throttle or brake control actions on the vehicle.

[0025] A second aspect of this application provides a predictive adaptive cruise control method considering a vehicle-cloud dual-closed-loop control architecture. The method employs the predictive adaptive cruise control system described above, and includes the following steps: obtaining multiple original waypoint information of the vehicle on a target road segment based on the vehicle's location information; calculating an economic speed sequence for the vehicle at a first target distance based on the state information, the location information, and the multiple original waypoint information; receiving the economic speed sequence and predicting the speed sequence of the preceding vehicle in a target time period based on historical information of the preceding vehicle; constructing a following speed model for the vehicle at a second target distance using the economic speed sequence and the speed sequence of the preceding vehicle in the target time period; adjusting the target speed of the vehicle based on the calculation results of the following speed model, so that the target speed meets the expected target requirements, wherein the second target distance is less than the first target distance; controlling the vehicle to follow other vehicles using the target speed and updating the vehicle's driving state information to generate a new following speed based on the updated driving state information, so that the vehicle drives based on the predictive adaptive cruise control of the vehicle-cloud dual-closed-loop control architecture.

[0026] Optionally, in one embodiment of this application, controlling the vehicle to follow another vehicle using the target vehicle speed and updating the vehicle's driving status information to generate a new following speed based on the updated driving status information, so that the vehicle drives based on predictive adaptive cruise control using a vehicle-cloud dual closed-loop control architecture, includes: when the vehicle reaches the desired original waypoint, triggering the following speed planning module of the vehicle-side platform, then the following speed planning module of the vehicle-side platform recalculates the following speed of the vehicle again using the economic speed sequence information of the cloud control platform and the speed sequence of the preceding vehicle in the target time period, to obtain a new following speed for the vehicle. The vehicle speed is recorded and sent to the vehicle chassis to execute corresponding throttle or brake control actions; and / or, when the vehicle reaches the next target road point, the economic speed sequence calculation module of the cloud control platform is triggered to replan the economic speed of the vehicle to obtain a new economic speed sequence for the vehicle, and update the economic speed information in the road point information. The updated economic speed information is then sent back to the vehicle-side platform, and the following speed planning module in the vehicle-side platform plans again to achieve dual closed-loop control between the vehicle-side platform and the cloud control platform, enabling the vehicle to achieve predictive adaptive cruise driving based on the vehicle-cloud dual closed-loop control architecture.

[0027] A third aspect of this application provides a vehicle, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement a predictive adaptive cruise control method considering a vehicle-cloud dual closed-loop control architecture as described in the above embodiments.

[0028] A fourth aspect of this application provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the predictive adaptive cruise control method considering a vehicle-cloud dual-closed-loop control architecture as described above.

[0029] A fifth aspect of this application provides a computer program product, including a computer program that, when executed, is used to implement the predictive adaptive cruise control method considering the vehicle-cloud dual closed-loop control architecture described above.

[0030] This application embodiment can obtain the economic speed sequence of the vehicle at the first target distance, predict the speed sequence of the preceding vehicle in the target time period based on the historical information of the preceding vehicle, and determine the following speed of the vehicle at the second target distance by comparing it with the economic speed sequence. The following speed is used to control the vehicle's following motion and update the vehicle's driving status information. A new following speed is generated based on the updated driving status information, enabling the vehicle to drive based on predictive adaptive cruise control using a vehicle-cloud dual closed-loop control architecture. This effectively reduces the algorithm's solution complexity, improves computational efficiency, and enhances vehicle safety and economy. Therefore, it solves the problems in related technologies where most use nonlinear solution models and algorithms, resulting in complex solutions, low computational efficiency, difficulty in ensuring real-time algorithm planning, inability to update the following speed in a timely manner, and reduced vehicle driving performance.

[0031] Additional aspects and advantages of this application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of this application. Attached Figure Description

[0032] The above and / or additional aspects and advantages of this application will become apparent and readily understood from the following description of the embodiments taken in conjunction with the accompanying drawings, wherein:

[0033] Figure 1 This is a schematic diagram of a predictive adaptive cruise control system based on a vehicle-cloud dual closed-loop control architecture, according to an embodiment of this application.

[0034] Figure 2 This is a schematic diagram illustrating a specific operating scenario at high speed, representing a particular embodiment of this application.

[0035] Figure 3 This is a diagram of a vehicle-cloud dual-closed-loop control architecture according to a specific embodiment of this application;

[0036] Figure 4 A schematic diagram illustrating the specific algorithm framework and technical principle of a predictive adaptive cruise control system considering a vehicle-cloud dual closed-loop control architecture, as a specific embodiment of this application;

[0037] Figure 5 This is a waypoint diagram of a specific embodiment of this application;

[0038] Figure 6 This is a schematic diagram of vehicle-side following safety and economical vehicle speed rolling planning according to a specific embodiment of this application;

[0039] Figure 7 This is a schematic diagram of vehicle speed rolling planning when the number of minor road points between two major road points is odd, according to a specific embodiment of this application.

[0040] Figure 8 This is a schematic diagram of vehicle speed rolling planning when the number of minor road points between two major road points is even, according to a specific embodiment of this application.

[0041] Figure 9 This is a schematic diagram of the longitudinal dynamics force analysis of a vehicle according to a specific embodiment of this application;

[0042] Figure 10 This is a schematic diagram of a fitted vehicle engine fuel consumption model according to a specific embodiment of this application;

[0043] Figure 11 This is a schematic diagram illustrating the discrete speed of the vehicle in front according to a specific embodiment of this application;

[0044] Figure 12 This is a schematic diagram of the state space on a short-distance waypoint according to a specific embodiment of this application;

[0045] Figure 13 This is a schematic diagram illustrating the cost calculation at a distance waypoint according to a specific embodiment of this application;

[0046] Figure 14 This is a flowchart of a predictive adaptive cruise control method considering a vehicle-cloud dual closed-loop control architecture according to an embodiment of this application;

[0047] Figure 15 This is a structural schematic diagram of a vehicle provided according to an embodiment of this application. Detailed Implementation

[0048] The embodiments of this application are described in detail below. Examples of these embodiments are shown in the accompanying drawings, wherein 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 intended to explain this application, and should not be construed as limiting this application.

[0049] The following description, with reference to the accompanying drawings, describes a predictive adaptive cruise control system based on a vehicle-cloud dual closed-loop control architecture proposed in accordance with embodiments of this application. Figure 1 This is a schematic diagram of the predictive adaptive cruise control system based on the vehicle-cloud dual closed-loop control architecture of this application embodiment.

[0050] Before introducing the predictive adaptive cruise control system considering the vehicle-cloud dual closed-loop control architecture proposed in the embodiments of this application, let's briefly introduce the working principle of the predictive adaptive cruise control system considering the vehicle-cloud dual closed-loop control architecture involved in this method. Figure 2 For trucks operating on highways. Figure 3 This is the control architecture for a vehicle-cloud dual closed-loop system, which includes a cloud control system and a vehicle-side platform.

[0051] First, the implementation of the PACC system requires a reasonable analysis of the functions of both the cloud and the vehicle to ensure that each can fully leverage its advantages and achieve efficient and safe operation. The PACC system mainly includes three algorithm modules: long-distance economic speed planning algorithm (PCC algorithm), preceding vehicle speed prediction algorithm, and short-distance following speed planning algorithm. The PCC algorithm can plan the optimal economic speed for the vehicle over a relatively long distance; therefore, it is highly dependent on road map information and speed limit information. The relevant support platform in the cloud control platform can provide static road map information and dynamic traffic information during vehicle movement, which are essential for long-distance economic speed planning. Furthermore, the PCC algorithm does not have high real-time requirements; therefore, it can be deployed on the cloud control application platform. In the following scenario, the driving information of both the lead vehicle and the preceding vehicle is constantly changing. Both the preceding vehicle speed prediction algorithm and the short-distance following speed planning algorithm need to obtain the vehicle's driving information in real time. Therefore, both of these algorithms can be deployed in the vehicle's computing unit to ensure that real-time requirements are met.

[0052] like Figure 3 The diagram shows a predictive adaptive cruise control system based on a vehicle-cloud dual-closed-loop control architecture. In this system architecture, the driving status information of the main vehicle is continuously uploaded to the cloud. The cloud uses a dynamic programming algorithm with rolling iteration in the long-distance domain to solve for the long-distance economic speed sequence based on future road information. Meanwhile, the vehicle uses the predicted information of the vehicle in front and the long-distance economic speed sequence to solve for the short-distance following speed in real time in the short-distance domain. Finally, the main vehicle drives at the desired following speed and continuously updates and iterates the vehicle status information, thus realizing the vehicle-cloud dual-closed-loop control.

[0053] For example, combining Figure 2 and Figure 4 As shown, Figure 4This is a truck predictive adaptive cruise control system based on a cloud control platform, mainly composed of three algorithm modules: a long-distance economic speed planning module, a preceding vehicle speed prediction module, and a short-distance following speed planning module. During following, the long-distance economic speed planning module and the preceding vehicle speed prediction module provide the short-distance following speed planning module with a long-distance economic speed sequence and the predicted speed of the preceding vehicle over a future period, respectively, thereby calculating the final desired speed of the main vehicle in the following speed planning module. This application mainly focuses on the design of the short-distance following speed planning algorithm; therefore, it is assumed that the long-distance economic speed planning and preceding vehicle speed prediction models have been completed. Considering the low market penetration rate of existing connected vehicles, it is assumed that the preceding vehicle is still a traditional human-driven vehicle. The main vehicle obtains the driving information of the preceding vehicle through sensor fusion perception and inputs it into the preceding vehicle speed prediction model based on road slope information to achieve short-term preceding vehicle speed prediction. The calculation of predictive adaptive cruise control algorithms depends on the waypoint spacing in the cloud-based road map. Especially for long-distance economic speed planning, if the waypoint spacing in the original map library is too small, it will affect the computational complexity. The following will take the working principle of a predictive adaptive cruise control system considering the vehicle-cloud dual closed-loop control architecture as an example to explain in detail.

[0054] like Figure 1 As shown, the predictive adaptive cruise control system 10 considering the vehicle-cloud dual closed-loop control architecture includes: a cloud control platform 100, a vehicle-end platform 200, and a vehicle-cloud dual closed-loop control architecture 300.

[0055] Specifically, the cloud control platform 100 is used to receive the vehicle's driving status information and location information sent by the vehicle-end platform 200, and obtain multiple original waypoint information of the vehicle on the target road segment based on the location information. Based on the status information, location information and multiple original waypoint information, the platform calculates the economic speed sequence of the vehicle at the first target distance, and sends the economic speed sequence to the vehicle-end platform 200.

[0056] In actual implementation, the cloud control platform 100 in this application embodiment can receive the vehicle's driving status information and location information sent by the vehicle-end platform 200, and obtain multiple original waypoint information of the vehicle on the target road segment based on the location information. Based on the status information, location information and multiple original waypoint information, it calculates the economic speed sequence of the vehicle at the first target distance, such as the economic speed sequence in the long-distance domain, and sends the economic speed sequence to the vehicle-end platform 200, effectively improving the executability of cloud predictive cruise control.

[0057] For example, embodiments of this application can obtain map information of a certain road segment ahead of the vehicle, use the map information to determine multiple original road points, i.e. small road points, and reconstruct multiple original road points to obtain multiple target road points, i.e. large road points. When the vehicle is detected to have traveled to a large road point, the economic speed between multiple large road points is planned to obtain the economic speed sequence of the vehicle's first target distance, which effectively improves the accuracy of calculating long-distance economic speed and reduces the computational complexity.

[0058] Optionally, in one embodiment of this application, the cloud control platform 100 includes: a positioning module, a high-precision map module, a map reconstruction module, and an economic vehicle speed sequence calculation module.

[0059] The positioning module is used to parse location information and obtain the vehicle's current location information based on the location information.

[0060] In some embodiments, the positioning module in the cloud control platform 100 can parse the vehicle's location information and obtain the vehicle's current location information based on the location information, effectively improving the accuracy of the vehicle's location.

[0061] The high-precision map module is used to obtain multiple original waypoints corresponding to the map information of the target road segment ahead of the vehicle based on the vehicle's current location information.

[0062] In some embodiments, the high-precision map module in the cloud control platform 100 can obtain multiple original waypoints corresponding to the map information of a certain road segment ahead of the vehicle based on the vehicle's current positioning information, effectively improving the reliability of the vehicle's economical driving.

[0063] Optionally, in one embodiment of this application, the high-precision map module is further used to: acquire map information of the target road segment ahead of the vehicle; and use the map information to determine multiple original waypoints, wherein the multiple original waypoints include waypoint locations, slope information corresponding to the waypoint locations, and spacing information between adjacent waypoints.

[0064] In some embodiments, the high-precision map module in the cloud control platform 100 can also obtain map information of a certain road segment ahead of the vehicle and use the map information to determine multiple original waypoints, i.e., small waypoints. The multiple original waypoints include the waypoint location, the slope information corresponding to the waypoint location, and the distance information between adjacent waypoints, which effectively improves the accuracy of calculating long-distance economic speed.

[0065] The map reconstruction module is used to reconstruct multiple original waypoints to obtain multiple target waypoints.

[0066] As one possible approach, the map reconstruction module in the cloud control platform 100 can reconstruct multiple original waypoints to obtain multiple target waypoints. For example, it can use map information to determine multiple corresponding original waypoints, i.e., small waypoints, and reconstruct these multiple original waypoints to obtain multiple target waypoints, i.e. large waypoints. This allows for the generation of a smaller number of target waypoints without losing the road features represented by the original waypoints, thus reducing the computational load of the economic speed sequence calculation module.

[0067] For example, in this embodiment of the application, map information of the road segment 2000m ahead of the vehicle can be obtained, and multiple original waypoints can be determined using the map information. That is, the interval between the original waypoint data in the cloud is about 20m. When performing long-distance predictive cruise economic speed planning, if the prediction range is set to 2000m, then about 100 original waypoints are needed, which is 100 stages, i.e., N=100.

[0068] Optionally, in one embodiment of this application, the map reconstruction module is further configured to: reconstruct the original waypoints according to a certain spacing or slope change rate based on the information contained in the multiple original waypoints, to obtain multiple target waypoints.

[0069] In some embodiments, the map reconstruction module in the cloud control platform 100 can also reconstruct the original waypoints according to the information contained in the original waypoints, according to a certain spacing or slope change rate. For example, multiple original waypoints, i.e. small waypoints, are determined using map information, and the multiple original waypoints are reconstructed according to a certain spacing or slope change rate to obtain multiple target waypoints, i.e. large waypoints, which effectively improves the accuracy of vehicle position.

[0070] For example, in the embodiments of this application, multiple original waypoints can be reconstructed. Under the premise of ensuring that the road feature information is not lost, multiple original waypoints, i.e. small waypoints, are divided into new large waypoints according to certain rules. For example, if the large waypoints are spaced about 200m apart, then predicting a 2000m road only requires 10 large waypoints, i.e. 10 stages, to calculate the long-distance predictive cruise economic speed. This greatly reduces the computational complexity of DP (Dynamic Programming) in solving long-distance economic speed from the perspective of waypoint preprocessing.

[0071] The economic speed sequence calculation module is used to plan the economic speed between multiple target road points based on the current positioning information and the road point information of the road ahead when the vehicle is detected to be traveling to a target road point, so as to obtain the economic speed sequence of the vehicle's first target distance.

[0072] In actual execution, the economic speed sequence calculation module in the cloud control platform 100 can plan the economic speed between multiple major road points when the vehicle is detected to be traveling to the target road point, for example, when the vehicle is detected to be traveling to a major road point, in order to obtain the economic speed sequence of the vehicle's first target distance. This effectively improves the accuracy of calculating the economic speed over long distances and reduces the complexity of the calculation.

[0073] Optionally, in one embodiment of this application, the economic speed sequence calculation module is further configured to: detect whether the vehicle has reached the target road point; when the vehicle is detected to have reached the target road point, use the vehicle's location information, driving status information and target road point information to plan the economic speed sequence of the vehicle at the first target distance in the future; discretize the economic speed sequence according to the location of the original road point to obtain economic speed information, store the economic speed information in the original road point information, and send it to the vehicle-side platform.

[0074] In some embodiments, the economic speed sequence calculation module in the cloud control platform 100 can detect whether the vehicle has reached the target road point, i.e., the major road point. For example, when the vehicle is detected to have reached the major road point, the module uses the vehicle's location information, driving status information and target road point information to plan the economic speed between multiple major road points, and obtains the economic speed sequence for the first target distance of the vehicle. The economic speed sequence is then discretized according to the location of the original road point to obtain the economic speed information. The economic speed information is stored in the original road point information and sent to the vehicle-side platform 200, which effectively improves the accuracy of calculating long-distance economic speed and reduces the computational complexity.

[0075] For example, such as Figure 5 The diagram shown is a waypoint illustration, where the red points {R0, R1, R2, ... R} are... N-1 R N} represents the reconstructed major road points, with the blue point r. i，j (i represents the i-th stage, and j represents the j-th minor waypoint in the i-th stage excluding the two major waypoints) are the original waypoints in the cloud map data, i.e. minor waypoints. Each minor waypoint contains three pieces of information: the location of the current waypoint, the road slope corresponding to the location of the current waypoint, and the distance between the current waypoint and the previous waypoint.

[0076] Secondly, the waypoint segmentation algorithm used in this embodiment does not alter the position of the reconstructed waypoints when reconstructing the original waypoints; it only changes the road slope information contained in the reconstructed waypoints. Therefore... Figure 5 The red waypoints in the diagram can be considered either major waypoints or minor waypoints, when R... i When (i = 1, 2, ..., N) is considered a waypoint, the distance between that waypoint and the previous waypoint is R.i-1 With R i The distance between them is approximately 200m; when R i When (i = 1, 2, ..., N) is considered a waypoint, the distance between this waypoint and the previous waypoint is r. i，j (j is R) i-1 With R i The number of path points between them) and R i The spacing between them is approximately 20m. The major waypoints calculated by the waypoint segmentation algorithm are used to construct the optimal control problem for long-range predictive cruise in the cloud. Based on a dynamic programming algorithm, the long-range economic speed for the next 10 stages (approximately 2000m) is predicted. The long-range economic speed information contained at each major waypoint can be discretized to each minor waypoint by distance, so each waypoint on the road contains four pieces of information at this point. When the vehicle reaches the next major waypoint, the planning of the long-range economic speed for the next 10 stages begins. Each time the vehicle reaches the next major waypoint, a new round of long-range predictive cruise economic speed planning is triggered, thus realizing the rolling planning control of long-range predictive cruise economic speed in the cloud.

[0077] The vehicle-side platform 200 is used to collect status information and location information, and send the status information and location information to the cloud control platform 100. It also receives the economic speed sequence from the cloud control platform 100, and predicts the speed sequence of the preceding vehicle in the target time period based on the historical information of the preceding vehicle. It uses the economic speed sequence and the speed sequence of the preceding vehicle in the target time period to construct a following speed model for the second target distance of the vehicle. Based on the calculation results of the following speed model, it adjusts the target speed of the vehicle so that the target speed meets the expected target requirements. The second target distance is less than the first target distance.

[0078] In actual implementation, the vehicle-side platform 200 in this embodiment can collect vehicle status information and location information, and send the status information and location information to the cloud control platform 100. It also receives the economic speed sequence sent to the vehicle-side platform 200 by the cloud control platform 100 through vehicle-cloud communication. Based on the historical information of the preceding vehicle, it predicts the speed sequence of the preceding vehicle in the future. Using the economic speed sequence and the speed sequence of the preceding vehicle in the future, it constructs a following speed model for the second target distance of the vehicle. Based on the calculation results of the following speed model, it adjusts the target speed of the vehicle, that is, it further calculates the expected short-distance following speed, so that the target speed meets the expected target requirements, and realizes safe and economical predictive adaptive cruise control. In addition, when there is no preceding vehicle within the following range of the main vehicle, the economic speed sent by the cloud will be directly used as the expected short-distance following speed of the main vehicle to control the vehicle speed and realize economical predictive cruise control.

[0079] Optionally, in one embodiment of this application, the vehicle-side platform 200 includes: a forward vehicle speed prediction module and a predictive adaptive cruise following speed planning module.

[0080] Among them, the preceding vehicle speed prediction module is used to predict the speed sequence of the preceding vehicle in the target time period based on the original waypoint information sent by the cloud control platform 100 and the historical information of the preceding vehicle.

[0081] In some embodiments, the vehicle speed prediction module in the vehicle platform 200 can predict the speed sequence of the vehicle in the future based on multiple original waypoint information sent by the cloud control platform 100 and the historical information of the vehicle in front, such as the historical driving information of the vehicle in front, effectively improving the safety of predictive adaptive cruise control.

[0082] Optionally, in one embodiment of this application, the preceding vehicle speed prediction module is further configured to: predict the preceding vehicle's speed in the target time period based on the road slope information and the historical speed information of the preceding vehicle in the original waypoint information, and obtain the predicted driving speed information; convert the predicted driving speed information from the time domain to the spatial domain, and discretize it into the original waypoint information within the second target distance, to obtain the discretized original waypoint information.

[0083] As one possible approach, the vehicle speed prediction module in the vehicle platform 200 can predict the speed of the vehicle in the future based on road gradient information and the historical speed information of the vehicle in front from multiple original waypoint information. This prediction results in the predicted speed information of the vehicle in front. Furthermore, the predicted speed information of the vehicle in front is transformed from the time domain to the spatial domain and further discretized into the original waypoint information within the second target distance to obtain the discretized original waypoint information, effectively improving the economy of predictive cruise of the vehicle.

[0084] The predictive adaptive cruise following speed planning module is used to construct a following speed planning model for the second target distance that balances vehicle target safety and target economy when the vehicle is detected to be traveling to the desired original waypoint. This model is based on the original waypoint information sent by the cloud control platform 100 and the speed sequence of the preceding vehicle in the target time period. The following speed planning model is then solved.

[0085] In some embodiments, the predictive adaptive cruise following speed planning module in the vehicle platform 200 can construct a following speed planning model for the second target distance of vehicle safety and economy based on the original waypoint information sent by the cloud control platform 100 and the speed sequence of the preceding vehicle in the future when the vehicle is detected to be traveling to the desired original waypoint. The following speed planning model is then solved to determine the short-distance following speed of the vehicle, thereby improving the economy and safety of the vehicle's predictive cruise.

[0086] In one embodiment of this application, the predictive adaptive cruise following speed planning module is further configured to: based on the discrete original waypoint information, starting from the current location of the vehicle, set a preset number of desired original waypoints at preset intervals, and detect whether the vehicle has traveled to the set desired original waypoints; when the vehicle is detected to have traveled to the set desired original waypoints, construct a following speed planning model for the safety and economy of following the vehicle target using the economic speed information in the original waypoint information sent by the cloud control platform 100 and the speed sequence of the preceding vehicle in the target time period, and solve the model based on a preset dynamic programming algorithm to obtain the following speed of the vehicle within the second target distance.

[0087] In actual implementation, the predictive adaptive cruise following speed planning module in the vehicle platform 200 can set a desired original road point based on the discrete original road point information, starting from the vehicle's current location, and every two original road points, and detect whether the vehicle has traveled to the set desired original road point; when the vehicle is detected to have traveled to the set desired original road point, it uses the economic speed information in the original road point information sent by the cloud control platform 100 and the speed sequence of the preceding vehicle in the future to construct a following speed planning model for vehicle following safety and economy, and solves it based on dynamic programming algorithm to obtain the following speed of the vehicle within the second target distance, thereby improving the economy and safety of the vehicle's predictive cruise.

[0088] In one embodiment of this application, the following speed planning model for vehicle following target safety and target economy is as follows:

[0089]

[0090] subject to

[0091]

[0092] k = 1, 2, 3, 4, 5, v (k) >0

[0093]

[0094] Among them, w1, w2, w3, w4, and w5 represent the weights of fuel consumption, long-distance economical speed, following distance error, relative speed between the lead vehicle and the vehicle in front, and driving efficiency, respectively. Let v be the fuel consumption in stage k. (k) Let Δd be the speed of the main vehicle in stage k. k Let be the relative distance between the main vehicle and the vehicle in front during stage k. Let t be the speed of the vehicle in front during stage k. k v represents the vehicle's travel time in stage k; (k+1)Let Δs be the speed of the main vehicle in stage k+1. (k) Let δ be the distance between the k-th and (k+1)-th original waypoints, δ be the vehicle rotational mass conversion factor, m be the vehicle mass, r be the wheel radius, and i be the distance between the k-th and (k+1)-th original waypoints. g Where i is the gearbox transmission ratio, i0 is the main reducer transmission ratio, η is the transmission efficiency, and T is the transmission efficiency. (k) For the engine torque in stage k, C D Where A is the air resistance coefficient, g is the frontal area, f is the gravitational acceleration, and θ is the rolling resistance coefficient. (k) Let ω be the road gradient for stage k. (k) For the engine speed in stage k, a (k) For the vehicle acceleration in stage k, T min With T max v is the boundary between minimum and maximum torque. min With v max ω represents the boundary between the minimum and maximum vehicle speeds. min With ω max For the minimum and maximum speed boundaries, a min With a max For the minimum and maximum acceleration boundaries, d min With d max These are the minimum and maximum following distances.

[0095] Optionally, in one embodiment of this application, the predictive adaptive cruise following speed planning module is further used to: solve a following speed planning model based on the vehicle following target safety and target economy using a preset forward dynamic programming algorithm to obtain the following speed of the vehicle within a second target distance; and send the following speed within the second target distance to the vehicle chassis to perform corresponding throttle or brake control actions on the vehicle.

[0096] As one possible approach, the predictive adaptive cruise following speed planning module in the vehicle platform 200 can use a forward dynamic programming algorithm to solve a following speed planning model based on vehicle following safety and economy, obtain the following speed of the vehicle within a second target distance, and send the following speed within the second target distance to the vehicle chassis to execute corresponding throttle or brake control actions on the vehicle, thereby achieving economical predictive cruise.

[0097] The vehicle-cloud dual closed-loop control architecture 300 is used to control the vehicle to follow the target vehicle speed and update the vehicle's driving status information. Based on the updated driving status information, a new following speed is generated for the vehicle, enabling the vehicle to drive based on the predictive adaptive cruise control of the vehicle-cloud dual closed-loop control architecture 300.

[0098] In some embodiments, the vehicle-cloud dual-closed-loop control architecture 300 in this application embodiment can use the target vehicle speed to control the vehicle to follow the vehicle and update the vehicle's driving status information to generate a new following speed based on the updated driving status information. This allows the vehicle to drive based on the predictive adaptive cruise control of the vehicle-cloud dual-closed-loop control architecture. For example, when the vehicle reaches the next target waypoint, the vehicle's economic speed is replanned to obtain a new economic speed sequence. Alternatively, when the vehicle reaches the next original waypoint, the following speed is recalculated using the new economic speed sequence and the speed sequence of the preceding vehicle in the target time period to obtain a new following speed. Thus, the vehicle can be controlled based on the predictive adaptive cruise control of the vehicle-cloud dual-closed-loop control architecture.

[0099] For example, since the relative distance between the lead vehicle and the vehicle in front is generally no more than 100m in actual following situations, it is not necessary to reconstruct the road points when using the forward dynamic programming algorithm to solve for the speed of vehicles following short distances. Figure 5 As shown, taking stage K1 as an example, the rolling planning process of the vehicle's following speed is illustrated. Road point R0 is the starting point for the entire predictive adaptive cruise control algorithm, at which point the vehicle's initial position is 0 and its initial speed is v0. Considering that the stable following distance is within 100m in actual driving, when calculating the following speed in the short-distance domain, the speed of five small road points is planned sequentially from the starting point R0, continuing until... Figure 6 r in (a) 15 Position; the planned following speed is then executed based on the actual position of the master vehicle, and the control sequence is executed from the starting position R0 of the speed planning to the next small waypoint r. 12 The distance between them is the vehicle's roll control distance. For example... Figure 6 As shown in (b), when the vehicle travels at the planned speed to the small road point r 12 At that time, a new round of short-distance following speed planning was triggered. Figures 6-8 The red areas represent the actual rolling control area of ​​the vehicle, while the yellow areas represent the parts that were planned but not executed.

[0100] In other words, when a vehicle passes a major road point, this embodiment of the application can first plan the economic speed between the next 10 major road points using a long-distance domain economic speed planning algorithm. When the vehicle travels to the next major road point, the calculation of the long-distance domain economic speed will be triggered again. The calculated long-distance economic speed is discretized by distance and the recommended information is stored on each minor road point. The short-distance domain following speed planning algorithm calculates and plans the following speed between the next 5 minor road points each time, that is, plans the following speed for the next 5 short road segments, while actually controlling the distance of the vehicle traveling two short road segments. When the vehicle passes the next minor road point, a new round of short-distance domain following speed planning will be triggered. That is, the long-distance domain economic speed planning algorithm is replanned every 200m, and the short-distance domain following speed is replanned every 40m.

[0101] At this point, taking stage K1 as an example, when the number of minor paths between major path point R0 and R1 is odd, that is... In this context, n1 is an odd number, and the number of road segments consisting of minor road points between major road points R0 and R1 is an even number, such as... Figure 7 As shown in (a), in stage K1, the last short-distance following speed planning should be performed at the small road point. At, where v0′ represents the vehicle traveling on a small road point. The actual speed at this point. Since the main road point R1 has not yet been passed, the speed at the minor road point... At this point, only short-distance following speed planning is performed. Following the previously designed rolling planning control strategy, the algorithm then plans the following speed for 5 short road segments and controls the vehicle to travel 2 short road segments. Under these conditions, the vehicle can be controlled to reach the main road point R1. After the vehicle reaches the main road point R1, if... Figure 7 As shown in (b), a new round of cloud-based long-distance predictive cruise economic speed planning is triggered, followed by vehicle-side short-distance following speed planning.

[0102] Conversely, when the number of minor paths between major path points R0 and R1 is even, that is... In this context, n1 is an even number, and the number of road segments consisting of minor road points between major road points R0 and R1 is an odd number, such as... Figure 8 As shown in (a), at this point in stage K1, the last short-distance following speed planning should be performed at the small road point. At this point, the algorithm starts from this point, using the vehicle speed v0′ at this point as the initial speed, and begins planning the following speed for the next 5 short road segments, controlling the vehicle's movement. However, when the vehicle reaches the main road point R1, due to the triggering of long-range predictive cruise economic speed planning, the reference economic speeds for all minor road points within the next approximately 2000m are updated. Therefore, at this point, it is necessary to re-plan the vehicle's short-range following speed at point R1. During the final short-range following speed planning in the first stage K1, the PACC algorithm only controls the vehicle to travel a short distance, i.e. Figure 8 (a) The area indicated by red. After the vehicle reaches the main road point R1, if... Figure 8 As shown in (b), a new round of cloud-based long-distance predictive cruise economic speed planning is triggered, followed by vehicle-side short-distance following speed planning.

[0103] In summary, when a vehicle passes a major road point, the PACC system first triggers the long-range predictive cruise economic speed planning algorithm in the cloud. At this time, the recommended economic speed information of all minor road points within the next 2000m will be updated. Therefore, it is necessary to further trigger the short-range following speed planning algorithm on the vehicle to calculate the following speed of the vehicle within the next 5 minor road points, i.e., within a range of about 100m. When the vehicle passes the second minor road point, i.e., after traveling about 40m, the short-range following speed planning algorithm is triggered again to perform rolling planning of the algorithm. This realizes the vehicle-cloud collaborative closed-loop rolling control based on road point triggering, which effectively improves the safety and economy of cloud predictive cruise control.

[0104] In some embodiments, since the longitudinal dynamics model and fuel consumption model of the vehicle are used when planning the economic speed in the long-distance domain of the cloud and the following speed in the short-distance domain of the vehicle, the embodiments of this application need to design the longitudinal dynamics and fuel consumption models of the vehicle. The PACC system is mainly used in highway scenarios. The entire system combines the motion information of the preceding vehicle with the motion state of the vehicle itself to reasonably plan the following cruise speed, ensuring that the vehicle can improve the fuel economy of the vehicle by utilizing road gradient information while driving safely. Since the system does not include lane changing and steering control issues, the embodiments of this application only need to model the longitudinal dynamics characteristics of the vehicle.

[0105] By performing force analysis on the vehicle's motion, information such as the required driving speed for the longitudinal dynamics model can be calculated. Figure 9 As shown, during the process of a vehicle climbing a hill, it is subjected to multiple forces in the longitudinal direction, including rolling resistance F. f air resistance F w , ramp resistance F i and the driving force F that drives the vehiclet To facilitate controller design, the following assumptions are made:

[0106] (1) Ignore dynamics such as tire slippage and half-shaft torsion.

[0107] (2) The clutch is not engaged / disengaged and gear shifting is not performed, that is, the vehicle is driven in a fixed gear.

[0108] According to Newton's second law, the longitudinal dynamic model of the vehicle can be obtained from the force analysis:

[0109]

[0110] Among them, T tq Where is the engine torque (N·m), and g is the acceleration due to gravity (m / s²). 2 f is the rolling resistance coefficient, θ is the road gradient (rad), and C D Where A is the air resistance coefficient and A is the frontal area (m²). 2 ), v is the vehicle's speed (km / h), F t The driving force is N, and m is the vehicle mass (kg).

[0111] It should be noted that when the engine torque T tq When the value is positive, the driving force is the traction force that propels the vehicle. Conversely, when the value is negative, the driving force is the drag force that hinders the vehicle's movement.

[0112] To accurately calculate fuel consumption during vehicle operation, a polynomial fuel consumption model for the engine can be established, specifically as follows: Figure 10 As shown, the polynomial fuel consumption model fits the fuel consumption model to a value related to the vehicle speed n and engine torque T. tq The quadratic polynomial function, where the fuel consumption model is:

[0113]

[0114] Where, ξ i，j Here are the fitting coefficients, n is the vehicle speed, and T is the speed of rotation. tq This refers to engine torque.

[0115] This application embodiment can solve the optimal control problem of predictive adaptive cruise control by combining the predicted speed of the vehicle in front, the road waypoints provided by the cloud, and the economic speed sequence in the long-distance domain, and by taking into account factors such as following safety, fuel economy and driving efficiency, and comprehensively considering the relevant constraints of vehicle driving and road conditions.

[0116] As one possible implementation, embodiments of this application can determine the actual position of the vehicle, i.e., the main vehicle, based on its current driving status information, and determine the actual road gradient based on the road points corresponding to the actual position. In this process, a long-distance economic speed sequence is calculated based on a long-distance predictive cruise economic speed planning algorithm in the cloud. The long-distance predictive cruise economic speed planning algorithm can extract the actual road gradient and establish a functional relationship between vehicle driving and the actual road gradient based on the vehicle dynamics model and fuel consumption model. It can also construct a predictive cruise optimization control problem using the relevant constraints of the vehicle and the road.

[0117] For example, in this embodiment of the application, a dynamic programming algorithm can be used to calculate the long-distance economical vehicle speed at all major road points within a future range of approximately 2km, denoted as... Where v0 is the initial speed of the main vehicle when the long-distance economic speed planning begins; v_cc represents the long-distance economic speed at the second-to-last major road point; v_cc represents the long-distance economic speed at the last major road point, which is the target speed set by the driver. Then, the calculated long-distance economic speeds at the major road points can be discretized according to the locations of the minor road points.

[0118]

[0119] Among them, v_pcc (i，j) v_pcc represents the economic speed at the j-th road point in the i-th stage, in m / s. i Let x be the economical speed at the i-th major road point, in m / s; denominator x i -x i-1 x is the distance between the i-th waypoint and the (i-1)-th waypoint, in meters; i This represents the location of the i-th major point, in meters (m); x (i，j) This represents the position of the j-th waypoint in the i-th stage, in meters.

[0120] like Figure 11 As shown, at this time, all the minor road points within about 2km ahead of the main vehicle (i.e., 10 major road points) contain the long-distance economic speed calculated by the cloud, which effectively improves the economy and efficiency of cloud predictive cruise control.

[0121] In actual implementation, when the lead vehicle is following another vehicle, the speed and position information of the vehicle in front is crucial for the lead vehicle. This embodiment of the application can use a Gaussian process regression algorithm, combined with the road gradient, to predict the speed sequence of the vehicle in front over a certain period, i.e., the speed of the vehicle in front over a future period, as detailed below:

[0122] (1) Select input and output quantities according to the actual problem requirements, and establish training and test sets; use time, cloud road slope information, and front vehicle speed data as training data for Gaussian process learning;

[0123] (2) Select an appropriate kernel function based on the data's distribution, variation patterns, noise, and other characteristics;

[0124] (3) Determine the prior model of Gaussian process regression and train the model to optimize hyperparameters;

[0125] (4) Determine the posterior GPR model and input the test set data into the regression prediction model for prediction.

[0126] Based on the above steps, the problem of predicting the speed of a vehicle ahead using high-precision cloud-based map information is solved through calculation, and the predicted speed sequence f(X) is obtained. * This can be used to adjust the vehicle's control method to improve its driving performance. Repeating this process at the next moment, and continuing in a loop, allows for stable prediction of the speed of the vehicle ahead.

[0127] For example, a vehicle-side algorithm for predicting the speed of a preceding vehicle can predict its speed sequence over the next 3 seconds. Due to the design of the planning method, when the master vehicle is following another vehicle within a local range, the algorithm needs to iterate based on the location of road points within the prediction range. Therefore, the algorithm design requires obtaining the actual position and speed of the preceding vehicle when the master vehicle reaches any road point within the prediction range. However, the predicted speed sequence still retains information in the time dimension, making it impossible to retrieve the actual speed and position of the preceding vehicle at each road point. Therefore, this embodiment of the application needs to convert the speed sequence into spatial information based on the location of road points, that is, to transform the predicted speed sequence from the time domain to the spatial domain.

[0128] Next, as Figure 12 As shown, starting from the initial position of the vehicles, the initial speed of the main vehicle is v0, the speed of the vehicle in front is v_p0, and the relative distance between the vehicles is d0. The speed sequence of the vehicle in front predicted by the main vehicle in the next 3 seconds is {v_pre}. i |i=1,2,…,15}, as shown in Table 1. Table 1 is a table of predicted vehicle speeds ahead, as detailed below:

[0129] Table 1

[0130]

[0131] Furthermore, when planning vehicle speed for short-distance following, the planning range is approximately 100m, meaning the planning speed for the following vehicle at the next 5 road points. Assume the speed planning result for the next 5 road points is {v_pacc}. iIf |i=1, 2, 3, 4, 5}, then the travel time t between each pair of waypoints can be calculated. i ,Right now:

[0132]

[0133] Among them, t i The travel time between any two waypoints, s i v_pacc is the distance between the i-th waypoint and the (i-1)-th waypoint. i The following vehicle speed is planned for the main vehicle at the next 5 road points. When i = 0, v_pacc0 is the initial speed v0 of the main vehicle.

[0134] Secondly, after calculating the travel time of the main vehicle in each segment, it is necessary to calculate the speed and position of the preceding vehicle when the main vehicle reaches each small waypoint, from the initial position R0 to the future fifth waypoint r. 1_5 The distance between them is about 100m, which means it takes the main vehicle more than 4 seconds to travel. At this time, the predicted speed sequence of the preceding vehicle is only 3 seconds. Therefore, it is assumed that the preceding vehicle maintains uniform speed for the first 3 seconds. After the travel time exceeds 3 seconds, the preceding vehicle will travel at the speed of the 3rd second.

[0135] When the vehicle reaches the i-th road point, the total time consumed by the main vehicle is:

[0136]

[0137] Among them, t all_i This is the total time consumed by the main vehicle during travel.

[0138] When t all_i When the time is ≤3s, the speed of the preceding vehicle at the i-th minor road point can be interpolated based on the travel time of the main vehicle and Table 1. Let t be the time. all_i If the value is between index j and index j+1 in Table 1, and j = 0, 1, ... 14, then the speed of the vehicle in front is:

[0139]

[0140] Among them, t j v_pre represents the time corresponding to serial number j in Table 1. j The speed sequence of the vehicle in front is preset within a certain time period.

[0141] The distance traveled by the vehicle in front at this time is:

[0142]

[0143] in, This represents the speed of the vehicle in front.

[0144] The location of the vehicle in front is:

[0145] x_p i =d0+Δx_p i (12)

[0146] Where d0 is the relative vehicle spacing, Δx_p i This represents the distance traveled by the vehicle in front.

[0147] The relative distance between the vehicle in front and the main vehicle is:

[0148] Δd i =x_p i -x i (13)

[0149] Among them, x_p i Let Δd be the position of the vehicle in front. i x represents the relative distance between the vehicle in front and the vehicle in front. i The location of the main vehicle.

[0150] When t all_i If the time is greater than 3 seconds, then at the i-th minor road point, the speed of the vehicle in front is v_pre. 15 Furthermore, the distance traveled by the vehicle in front at this time consists of two parts: the first part travels at a uniform speed within 3 seconds, and the part exceeding 3 seconds travels at a speed according to v_pre. 15 Moving at a constant speed, the distance traveled by the vehicle in front is:

[0151]

[0152] Then the formulas for calculating the position of the vehicle in front and the relative distance between the main vehicle and the vehicle in front are formulas (12) and (13).

[0153] In summary, the predicted speed of the preceding vehicle in this embodiment can be converted from the time domain to the spatial domain. It can also predict the position of the preceding vehicle when the main vehicle reaches a certain road point, which can reduce unnecessary fluctuations in the main vehicle's speed and make the final planned following speed of the main vehicle more reasonable. Thus, the preparation work for the short-distance following speed planning algorithm has been completed. As can be seen from the above, the control variable of the preceding vehicle speed prediction algorithm is the following speed v_pacc at each road point.

[0154] Furthermore, the embodiments of this application can construct the optimal control problem for predictive adaptive cruise control. Since the slope of the road map in the predictive adaptive cruise control system designed in this application is given according to certain waypoint discretizations, that is, the slope of a road segment is a discrete function of GPS (Global Positioning System) position. In addition, during actual vehicle operation, the VCU (Vehicle Control Unit) re-plans the algorithm at a certain frequency. Therefore, the system studied in the embodiments of this application is a typical discrete control system.

[0155] In this embodiment, when planning following speed within a short distance, the planning is performed within a range of approximately 100m, i.e., within the next 5 road points. The optimization problem constructed needs to simultaneously consider economical speed, fuel consumption, driving efficiency, the speed of the vehicle in front, and relative distance between vehicles in the long distance domain, thereby planning an optimal following speed that is both safe and energy-efficient. Since the optimization problem involved in this embodiment highly depends on high-precision map information provided by the cloud, and this information is given in the form of road points, the algorithm needs to be redesigned according to the road point triggering strategy during the design process. In summary, the optimization problem to be constructed in this embodiment is a typical multi-stage optimal decision problem, and dynamic programming algorithm is an effective method for solving multi-stage decision problems, capable of efficiently calculating the optimal decision sequence.

[0156] Therefore, in this embodiment, vehicle speed can be selected as the state and control variables for short-distance following vehicle speed planning, and the vehicle speed can be discretized at certain intervals to form a state space for short-distance road points, such as... Figure 13 As shown, the state space consists of 6 waypoints, including the starting point where the main vehicle is located.

[0157] Therefore, the optimization problem constructed in the embodiments of this application is:

[0158]

[0159] Among them, w1, w2, w3, w4, and w5 represent the weights of fuel consumption, long-distance economical speed, following distance error, relative speed between the lead vehicle and the vehicle in front, and driving efficiency, respectively. Let v be the fuel consumption in stage k. (k) Let Δd be the speed of the main vehicle in stage k. k Let be the relative distance between the main vehicle and the vehicle in front during stage k. Let t be the speed of the vehicle in front during stage k. k This represents the actual driving situation of the vehicle in stage k.

[0160] The fuel consumption for stage k is calculated using the following formula:

[0161]

[0162] in, This refers to engine torque. Where is the engine speed, δ is the vehicle rotational mass conversion factor, and a is the vehicle acceleration.

[0163] d (desire，k) When the main vehicle reaches the kth waypoint in the future, the expected following distance between the main vehicle and the vehicle in front is:

[0164] d (desire，k) =t s *v (k) +d s (19)

[0165] Among them, t s The headway is typically between 0.5s and 3.5s; d s The minimum fixed vehicle spacing generally includes one vehicle length and the minimum distance between vehicles.

[0166] To prevent the vehicle speed from deviating too much from the reference speed, the speed boundary of the state space is set as follows:

[0167] v min ≤v (k) ≤v max (20)

[0168] Based on the actual conditions of a vehicle on a highway, the effective operating range of an engine is often within a certain range of engine speed and torque. Engine speed is related to vehicle speed, while torque is constrained by the engine's external characteristic curve. Therefore, the following constraints exist:

[0169]

[0170] Where, ω (k) Let T be the vehicle speed at the kth waypoint. (k) Let be the vehicle torque at the kth road point.

[0171] According to the principles of economical driving, rapid acceleration and deceleration have a significant impact on fuel consumption, therefore, there is an acceleration constraint:

[0172] a min ≤a (k) ≤a max (twenty two)

[0173] In summary, the optimization problem of following speed planning within the short-range domain has been completed, that is, the optimal control problem of predictive adaptive cruise control on the vehicle side has been completed. By using a forward dynamic programming algorithm, a safe, efficient, and economical following speed within the short-range domain can be solved. Based on the waypoint-triggered planning strategy, when the vehicle reaches the second future waypoint, the algorithm will re-plan the short-range following speed according to the vehicle's real-time status information, realizing the rolling iterative update of the following speed within the short-range domain, effectively achieving vehicle safety and energy efficiency.

[0174] This application combines a cloud-based long-range domain economic speed planning algorithm with a vehicle-side short-range domain following safety speed planning algorithm. It comprehensively considers the economy, safety, and driving efficiency of the vehicle, and combines a forward dynamic programming algorithm to solve for the optimal speed. It takes into account the dynamic characteristics of the vehicle during driving and solves for the optimal speed, avoiding the problem of large computational load in solving nonlinear cost functions. At the same time, it realizes safe, energy-saving, and efficient driving of the vehicle.

[0175] The predictive adaptive cruise control system based on the vehicle-cloud dual-closed-loop control architecture proposed in this application can, when the vehicle is detected to be in predictive cruise control mode, obtain the economic speed sequence of the vehicle at the first target distance, predict the speed sequence of the preceding vehicle in the target time period based on the historical information of the preceding vehicle, and determine the following speed of the vehicle at the second target distance with the economic speed sequence. The following speed is used to control the vehicle's following movement and update the vehicle's driving state information. A new following speed is generated based on the updated driving state information, enabling the vehicle to drive based on the predictive adaptive cruise control of the vehicle-cloud dual-closed-loop control architecture. This effectively reduces the algorithm's solution complexity, improves computational efficiency, and enhances vehicle safety and economy. Therefore, it solves the problems in related technologies where most use nonlinear solution models and algorithms, resulting in complex solutions, low computational efficiency, difficulty in ensuring real-time algorithm planning, inability to update the following speed in a timely manner, and reduced vehicle driving performance.

[0176] in, Figure 14 This is a flowchart illustrating a predictive adaptive cruise control method considering a vehicle-cloud dual closed-loop control architecture, as provided in an embodiment of this application.

[0177] like Figure 14 As shown, the predictive adaptive cruise control method considering the vehicle-cloud dual closed-loop control architecture includes the following steps:

[0178] In step S1401, multiple original waypoint information of the vehicle on the target road segment is obtained based on the vehicle's location information, and the economic speed sequence of the vehicle at the first target distance is calculated based on the status information, location information and multiple original waypoint information.

[0179] It is understood that the embodiments of this application can obtain multiple original waypoint information of the vehicle on the target road segment based on the vehicle's location information. For example, the embodiments of this application can obtain map information of a certain road segment ahead of the vehicle, use the map information to determine multiple corresponding original waypoints, i.e., small waypoints, and reconstruct multiple original waypoints to obtain multiple target waypoints, i.e. large waypoints. When the vehicle is detected to have traveled to a large waypoint, the economic speed between multiple large waypoints is planned to obtain the economic speed sequence of the vehicle's first target distance, which effectively improves the accuracy of calculating long-distance economic speed and reduces the complexity of calculation.

[0180] In step S1402, an economic speed sequence is received, and the speed sequence of the preceding vehicle in the target time period is predicted based on the historical information of the preceding vehicle. A following speed model for the second target distance of the vehicle is constructed using the economic speed sequence and the speed sequence of the preceding vehicle in the target time period. The target speed of the vehicle is adjusted based on the calculation results of the following speed model so that the target speed meets the expected target requirements. The second target distance is less than the first target distance.

[0181] It is understood that the embodiments of this application can receive the economic vehicle speed sequence sent by the cloud through vehicle-to-cloud communication, and predict the speed sequence of the preceding vehicle in the future based on the historical information of the preceding vehicle. The following speed model of the vehicle at the second target distance is constructed using the economic vehicle speed sequence and the speed sequence of the preceding vehicle in the future. The target speed of the vehicle is adjusted based on the calculation result of the following speed model, that is, the expected short-distance following speed is further calculated so that the target speed meets the expected target requirements, thereby realizing safe and economical predictive adaptive cruise control. In addition, when there is no preceding vehicle within the following range of the main vehicle, the economic vehicle speed sent by the cloud will be directly used as the expected short-distance following speed of the main vehicle to control the vehicle speed and realize economical predictive cruise control.

[0182] In step S1403, the target vehicle speed is used to control the vehicle to follow the vehicle, and the vehicle's driving status information is updated to generate a new following speed based on the updated driving status information, so that the vehicle can drive based on the predictive adaptive cruise control architecture of the vehicle-cloud dual closed loop control architecture.

[0183] It is understood that the embodiments of this application can use the target vehicle speed to control the vehicle to follow the vehicle and update the vehicle's driving status information to generate a new following speed based on the updated driving status information. For example, when the vehicle travels to the next target road point, the vehicle's economic speed is replanned to obtain a new economic speed sequence. Alternatively, when the vehicle travels to the next original road point, the vehicle's following speed is recalculated using the new economic speed sequence and the speed sequence of the preceding vehicle in the target time period to obtain a new following speed. Thus, the vehicle can be controlled by predictive adaptive cruise control based on the vehicle-cloud dual closed-loop control architecture.

[0184] In one embodiment of this application, the vehicle is controlled to follow another vehicle using a target speed, and the vehicle's driving status information is updated. A new following speed is generated based on the updated driving status information, enabling the vehicle to drive using predictive adaptive cruise control based on a vehicle-cloud dual-closed-loop control architecture. This includes: when the vehicle reaches the desired original waypoint, triggering the following speed planning module on the vehicle-side platform, the following speed planning module on the vehicle-side platform recalculates the vehicle's following speed again using the economic speed sequence information from the cloud control platform and the speed sequence of the preceding vehicle during the target time period, to obtain the new following speed, and then sending it. The system moves to the vehicle chassis to perform corresponding throttle or brake control actions; and / or, when the vehicle reaches the next target road point, the cloud control platform's economic speed sequence calculation module is triggered to replan the vehicle's economic speed to obtain a new economic speed sequence, and update the economic speed information in the road point information. The updated economic speed information is then sent back to the vehicle-side platform, and the vehicle-side platform's following speed planning module plans again to achieve dual closed-loop control between the vehicle-side platform and the cloud control platform, enabling the vehicle to achieve predictive adaptive cruise driving based on the vehicle-cloud dual closed-loop control architecture.

[0185] For example, in this embodiment of the application, when the vehicle travels to the desired original road point, i.e. a small road point, the following speed planning module on the vehicle side is triggered. Then, the following speed planning module on the vehicle side recalculates the following speed of the vehicle by using the economic speed sequence information and the speed sequence of the preceding vehicle in the target time period to obtain the new following speed of the vehicle and send it to the vehicle chassis to perform corresponding throttle or brake control actions on the vehicle.

[0186] For example, when the vehicle reaches the next target road point, i.e., a major road point, the economic speed sequence calculation module of the cloud control platform is triggered to replan the vehicle's economic speed to obtain a new economic speed sequence and update the economic speed information in the road point information. The updated economic speed information is then sent back to the vehicle, and the following speed planning module in the vehicle plans the speed again to achieve dual closed-loop control between the vehicle platform and the cloud control platform. This enables the vehicle to achieve predictive adaptive cruise driving based on the vehicle-cloud dual closed-loop control architecture.

[0187] The predictive adaptive cruise control method based on the vehicle-cloud dual-closed-loop control architecture proposed in this application can, when the vehicle is detected to be in predictive cruise control mode, obtain the economic speed sequence of the vehicle at the first target distance, predict the speed sequence of the preceding vehicle in the target time period based on the historical information of the preceding vehicle, and determine the following speed of the vehicle at the second target distance with the economic speed sequence. The following speed is used to control the vehicle's following movement and update the vehicle's driving state information. A new following speed is generated based on the updated driving state information, enabling the vehicle to drive based on the predictive adaptive cruise control of the vehicle-cloud dual-closed-loop control architecture. This effectively reduces the algorithm's solution complexity, improves computational efficiency, and enhances vehicle safety and economy. Therefore, it solves the problems in related technologies where most use nonlinear solution models and algorithms, resulting in complex solutions, low computational efficiency, difficulty in ensuring real-time algorithm planning, inability to update the following speed in a timely manner, and reduced vehicle driving performance.

[0188] Figure 15 A schematic diagram of the structure of a vehicle provided in an embodiment of this application. The vehicle may include:

[0189] The memory 1501, the processor 1502, and the computer program stored on the memory 1501 and executable on the processor 1502.

[0190] When the processor 1502 executes the program, it implements the predictive adaptive cruise control method considering the vehicle-cloud dual closed-loop control architecture provided in the above embodiments.

[0191] Furthermore, the vehicle also includes:

[0192] Communication interface 1503 is used for communication between memory 1501 and processor 1502.

[0193] The memory 1501 is used to store computer programs that can run on the processor 1502.

[0194] The memory 1501 may include high-speed RAM memory, and may also include non-volatile memory, such as at least one disk storage device.

[0195] If the memory 1501, processor 1502, and communication interface 1503 are implemented independently, then the communication interface 1503, memory 1501, and processor 1502 can be interconnected via a bus to complete communication between them. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. The bus can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 15 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0196] Optionally, in a specific implementation, if the memory 1501, processor 1502, and communication interface 1503 are integrated on a single chip, then the memory 1501, processor 1502, and communication interface 1503 can communicate with each other through an internal interface.

[0197] The processor 1502 may be a central processing unit (CPU), an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of this application.

[0198] This embodiment also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the predictive adaptive cruise control method considering the vehicle-cloud dual closed-loop control architecture described above.

[0199] This embodiment also provides a computer program product, including a computer program that, when executed, is used to implement the predictive adaptive cruise control method considering the vehicle-cloud dual closed-loop control architecture as described above.

[0200] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0201] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this application, "N" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0202] Any process or method described in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or N executable instructions for implementing custom logic functions or processes, and the scope of the preferred embodiments of this application includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as should be understood by those skilled in the art to which embodiments of this application pertain.

[0203] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include: an electrical connection having one or more wires (electronic device), a portable computer disk drive (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Alternatively, the computer-readable medium may be paper or other suitable media on which the program can be printed, since the program can be obtained electronically by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in a computer memory.

[0204] It should be understood that the various parts of this application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, the N steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0205] Those skilled in the art will understand that all or part of the steps of the methods in the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, the program includes one or a combination of the steps of the method embodiments.

[0206] Furthermore, the functional units in the various embodiments of this application can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into a module. The integrated module can be implemented in hardware or as a software functional module. If the integrated module is implemented as a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium.

[0207] The storage medium mentioned above can be a read-only memory, a disk, or an optical disk, etc. Although embodiments of this application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting this application. Those skilled in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of this application.

Claims

1. A predictive adaptive cruise control system considering a vehicle-cloud dual closed-loop control architecture, characterized in that, This includes a cloud control platform, a vehicle-side platform, and a dual closed-loop control architecture between the vehicle and the cloud. The cloud control platform is used to receive the vehicle's driving status information and location information sent by the vehicle-end platform, and obtain multiple original waypoint information of the vehicle on the target road segment based on the location information. Based on the status information, the location information and the multiple original waypoint information, the platform calculates the economic speed sequence of the vehicle at the first target distance, and sends the economic speed sequence to the vehicle-end platform. The vehicle-side platform is used to collect the status information and the location information, and send the status information and the location information to the cloud control platform. It also receives the economic speed sequence from the cloud control platform, predicts the speed sequence of the preceding vehicle in the target time period based on the historical information of the preceding vehicle, and constructs a following speed model for the second target distance of the vehicle using the economic speed sequence and the speed sequence of the preceding vehicle in the target time period. The platform adjusts the target speed of the vehicle based on the calculation results of the following speed model so that the target speed meets the expected target requirements. The second target distance is less than the first target distance. The vehicle-cloud dual closed-loop control architecture is used to control the vehicle to follow the target vehicle speed and update the vehicle's driving status information. Based on the updated driving status information, a new following speed is generated for the vehicle, enabling the vehicle to drive based on the predictive adaptive cruise control of the vehicle-cloud dual closed-loop control architecture.

2. The predictive adaptive cruise control system considering a vehicle-cloud dual closed-loop control architecture according to claim 1, characterized in that, The cloud control platform includes: A positioning module is used to parse the location information and obtain the current positioning information of the vehicle based on the location information; The high-precision map module is used to obtain multiple original waypoints corresponding to the map information of the target road segment ahead of the vehicle based on the vehicle's current positioning information; The map reconstruction module is used to reconstruct the multiple original waypoints to obtain multiple target waypoints; The economic speed sequence calculation module is used to plan the economic speed between multiple target road points based on the current positioning information and the road point information of the road ahead when the vehicle is detected to be traveling to a target road point, so as to obtain the economic speed sequence of the vehicle for the first target distance.

3. The predictive adaptive cruise control system considering a vehicle-cloud dual closed-loop control architecture according to claim 2, characterized in that, The high-precision map module is further used for: Obtain map information of the target road segment ahead of the vehicle; The map information is used to determine the plurality of original waypoints, wherein the plurality of original waypoints include waypoint locations, slope information corresponding to the waypoint locations, and spacing information between adjacent waypoints.

4. The predictive adaptive cruise control system considering a vehicle-cloud dual closed-loop control architecture according to claim 2, characterized in that, The map reconstruction module is further used for: Based on the information contained in the multiple original waypoints, the original waypoints are reconstructed according to a certain spacing or slope change rate to obtain multiple target waypoints.

5. The predictive adaptive cruise control system considering a vehicle-cloud dual closed-loop control architecture according to claim 2, characterized in that, The economic vehicle speed sequence calculation module is further used for: Detect whether the vehicle has reached the target road point; When the vehicle is detected to be traveling to the target waypoint, the vehicle's location information, driving status information and target waypoint information are used to plan the economic speed sequence of the vehicle for the first target distance in the future. The economic speed sequence is discretized according to the location of the original waypoints to obtain economic speed information, which is then stored in the original waypoint information and sent to the vehicle-side platform.

6. The predictive adaptive cruise control system considering a vehicle-cloud dual closed-loop control architecture according to claim 1, characterized in that, The vehicle-side platform includes: The preceding vehicle speed prediction module is used to predict the speed sequence of the preceding vehicle in a target time period based on the multiple original waypoint information sent by the cloud control platform and the historical information of the preceding vehicle. The predictive adaptive cruise following speed planning module is used to construct a following speed planning model for the second target distance of the vehicle's target safety and target economy based on the original waypoint information sent by the cloud control platform and the speed sequence of the preceding vehicle in the target time period when the vehicle is detected to be traveling to the desired original waypoint, and to solve the following speed planning model.

7. The predictive adaptive cruise control system considering a vehicle-cloud dual closed-loop control architecture according to claim 6, characterized in that, The preceding vehicle speed prediction module is further used for: Based on the road slope information in the multiple original waypoint information and the historical speed information of the preceding vehicle, a preset Gaussian process regression algorithm is used to predict the driving speed of the preceding vehicle in the target time period, thereby obtaining the predicted driving speed information. The predicted driving speed information is transformed from the time domain to the spatial domain and discretized into the original waypoint information within the second target distance to obtain the discretized original waypoint information.

8. The predictive adaptive cruise control system considering a vehicle-cloud dual closed-loop control architecture according to claim 7, characterized in that, The predictive adaptive cruise following speed planning module is further used for: Based on the discrete original waypoint information, starting from the current location of the vehicle, a preset number of desired original waypoints are set at each preset interval of the original waypoints, and it is detected whether the vehicle has traveled to the set desired original waypoints. When the vehicle is detected to have traveled to the set desired original waypoint, the following speed planning model for the vehicle following target safety and target economy is constructed using the economic speed information in the multiple original waypoint information and the speed sequence of the preceding vehicle in the target time period, and solved based on a preset dynamic programming algorithm to obtain the following speed of the vehicle within the second target distance.

9. The predictive adaptive cruise control system considering a vehicle-cloud dual closed-loop control architecture according to claim 8, characterized in that, The following vehicle speed planning model, which considers both the safety and economy of the vehicle following target, is as follows: k=1,2,3,4,5,v (k) >0 Among them, w1, w2, w3, w4, and w5 represent the weights of fuel consumption, long-distance economical speed, following distance error, relative speed between the lead vehicle and the vehicle in front, and driving efficiency, respectively. Let v be the fuel consumption in stage k. (k) Let Δd be the speed of the main vehicle in stage k. k Let be the relative distance between the main vehicle and the vehicle in front during stage k. Let t be the speed of the vehicle in front during stage k. k Let v be the vehicle's travel time in stage k. (k+1) Let Δs be the speed of the main vehicle in stage k+1. (k) Let δ be the distance between the k-th and (k+1)-th original waypoints, δ be the vehicle rotational mass conversion factor, m be the vehicle mass, r be the wheel radius, and i be the distance between the k-th and (k+1)-th original waypoints. g Where i is the gearbox transmission ratio, i0 is the main reducer transmission ratio, η is the transmission efficiency, and T is the transmission efficiency. (k) For the engine torque in stage k, C D Where A is the air resistance coefficient, g is the frontal area, f is the gravitational acceleration, and θ is the rolling resistance coefficient. (k) Let ω be the road gradient for stage k. (k) For the engine speed in stage k, a (k) For the vehicle acceleration in stage k, T min With T max v is the boundary between minimum and maximum torque. min With v max ω represents the boundary between the minimum and maximum vehicle speeds. min With ω max For the minimum and maximum speed boundaries, a min With a max For the minimum and maximum acceleration boundaries, d min With d max These are the minimum and maximum following distances.

10. The predictive adaptive cruise control system considering a vehicle-cloud dual closed-loop control architecture according to claim 8, characterized in that, The predictive adaptive cruise following speed planning module is further used for: Based on the following speed planning model that combines the safety and economy of the vehicle following target, a preset positive dynamic programming algorithm is used to solve the problem and obtain the following speed of the vehicle within the second target distance. The following vehicle speed within the second target distance is sent to the vehicle chassis to execute corresponding throttle or brake control actions on the vehicle.

11. A predictive adaptive cruise control method considering a vehicle-cloud dual closed-loop control architecture, characterized in that, A predictive adaptive cruise control system considering a vehicle-cloud dual-closed-loop control architecture as described in any one of claims 1-10, wherein the method includes the following steps: Based on the vehicle's location information, obtain multiple original waypoint information of the vehicle on the target road segment, and calculate the vehicle's economic speed sequence at the first target distance based on the status information, the location information, and the multiple original waypoint information; The system receives the economic speed sequence and predicts the speed sequence of the preceding vehicle in the target time period based on the historical information of the preceding vehicle. It then constructs a following speed model for the second target distance of the vehicle using the economic speed sequence and the speed sequence of the preceding vehicle in the target time period. Based on the calculation results of the following speed model, the system adjusts the target speed of the vehicle to meet the expected target requirements, wherein the second target distance is less than the first target distance. The vehicle is controlled to follow the vehicle using the target vehicle speed, and the vehicle's driving status information is updated. A new following speed is generated based on the updated driving status information, enabling the vehicle to drive based on predictive adaptive cruise control using a vehicle-cloud dual closed-loop control architecture.

12. The predictive adaptive cruise control method considering a vehicle-cloud dual closed-loop control architecture according to claim 11, characterized in that, The step of controlling the vehicle to follow the target vehicle speed and updating the vehicle's driving status information to generate a new following speed based on the updated driving status information, enabling the vehicle to drive based on predictive adaptive cruise control using a vehicle-cloud dual closed-loop control architecture, includes: When the vehicle reaches the desired original road point, the following speed planning module of the vehicle platform is triggered. The following speed planning module of the vehicle platform then uses the economic speed sequence information of the cloud control platform and the speed sequence of the preceding vehicle in the target time period to recalculate the following speed of the vehicle to obtain the new following speed of the vehicle and send it to the vehicle chassis to perform corresponding throttle or brake control actions on the vehicle. And / or, when the vehicle reaches the next target waypoint, the economic speed sequence calculation module of the cloud control platform is triggered to replan the economic speed of the vehicle to obtain a new economic speed sequence for the vehicle, and update the economic speed information in the waypoint information. The updated economic speed information is then sent back to the vehicle-side platform, and the following speed planning module in the vehicle-side platform plans again to achieve dual closed-loop control between the vehicle-side platform and the cloud control platform, enabling the vehicle to achieve predictive adaptive cruise driving based on the vehicle-cloud dual closed-loop control architecture.

13. A vehicle, characterized in that, include: The system includes a memory, a processor, and a computer program stored in the memory and executable on the processor, the processor executing the program to implement the predictive adaptive cruise control method considering a vehicle-cloud dual closed-loop control architecture as described in any one of claims 11-12.

14. A computer-readable storage medium having a computer program stored thereon, characterized in that, The program is executed by the processor to implement the predictive adaptive cruise control method considering the vehicle-cloud dual closed-loop control architecture as described in any one of claims 11-12.

15. A computer program product, comprising a computer program, characterized in that, The computer program is executed by a processor to implement the predictive adaptive cruise control method considering the vehicle-cloud dual closed-loop control architecture as described in any one of claims 11-12.

Images