Global vehicle speed planning method, device, equipment, medium and product

Abstract

The invention provides a global vehicle speed planning method and device, equipment, a medium and a product, and belongs to the technical field of vehicle intelligent control, and the method comprises the steps: calculating the first historical vehicle speed distribution of a target route through the historical driving vehicle speed information of the target route; calculating passing time probability distribution of each road section on the target route according to the first historical vehicle speed distribution; and according to the passing time probability distribution of each road section and the current state of the vehicle, calculating a target average vehicle speed of each road section so as to obtain a global vehicle speed planning scheme of the vehicle running on the target route. According to the method, the historical driving speed information of the target route is considered, global speed planning is realized in combination with the current state of the vehicle, unnecessary acceleration and braking are reduced in the driving process, energy consumption is reduced, traffic smoothness is improved, driving stability and safety are improved, the influence caused by traffic flow fluctuation is effectively relieved, and the driving safety is improved. And smoother and energy-saving driving experience is provided for the user.

Description

Technical Field

[0001] This application relates to the field of automotive intelligent control technology, and in particular to a global vehicle speed planning method, device, equipment, medium, and product. Background Technology

[0002] With the increasing complexity of urban transportation networks and the continuous increase in the number of vehicles, optimizing vehicle speed planning during driving has become an important research direction for improving driving safety, saving energy consumption, and improving traffic efficiency.

[0003] Currently, most vehicle speed planning methods focus on real-time perception, that is, using sensors to obtain information about the vehicle's surrounding environment and traffic lights ahead to plan vehicle speed. However, these methods rely on sensor configuration and can only make suggestions for the current vehicle speed, and cannot plan vehicle speed for the entire road segment. This results in unnecessary acceleration and braking during driving, which increases energy consumption and also leads to poor driving stability and safety. Summary of the Invention

[0004] This application provides a global vehicle speed planning method, apparatus, device, medium, and product, aiming to solve the technical problems of existing vehicle speed planning methods that rely on sensor configuration, cannot perform global planning, resulting in high energy consumption, poor driving stability, and poor safety.

[0005] Firstly, this application provides a global vehicle speed planning method, including: The first historical speed distribution of the target route is calculated using the historical driving speed information of the target route. The first historical speed distribution is the probability distribution of historical speed with mileage. Calculate the probability distribution of travel time for each segment of the target route based on the first historical vehicle speed distribution; Based on the probability distribution of travel time for each road segment and the current state of the vehicle, the target average speed for each road segment is calculated to obtain a global speed planning scheme for the vehicle traveling on the target route; where the current state includes the current driving conditions and the current position.

[0006] As one example, the calculation of the first historical vehicle speed distribution of the target route using historical vehicle speed information specifically includes: The vehicle's driving information on the target route is collected at different times, including vehicle speed and mileage. A dataset is constructed using mileage as the feature vector and the mean and variance of historical vehicle speeds as predictors. Based on the dataset, predict the probability distribution of vehicle speed at each mileage on the target route.

[0007] As an example, the probability distribution of travel time for each segment of the target route is calculated based on the first historical vehicle speed distribution, specifically including: Based on the distribution of traffic light intersections, the target route is divided into multiple segments; The second historical vehicle speed distribution for each road segment is obtained based on the first historical vehicle speed distribution. Multiple travel times for each road segment are obtained based on the second historical vehicle speed distribution for each segment; The probability distribution of travel time for each road segment is fitted based on multiple travel times for each road segment.

[0008] As an example, based on the probability distribution of travel time for each road segment and the current state of the vehicles, the target average vehicle speed for each road segment is calculated, specifically including: Based on the probability distribution of travel time for each road segment and the current state of the vehicles, under the constraints of spatiotemporal coupling, with the goal of minimizing economic cost, the optimal travel time for each traffic light intersection on the target route is solved. The target average speed for each road segment is calculated based on the optimal passage time at each traffic light intersection and the distance between adjacent traffic light intersections.

[0009] As an example, the optimal travel time at each traffic light intersection on the target route is determined, specifically including: Based on the current state of the vehicle, calculate the node energy loss of the vehicle through each road segment on the target route according to the probability distribution of the travel time of each road segment. Optimization is performed based on node energy loss and the current position of the vehicle to obtain the optimal passage time for each traffic light intersection on the target route; Under the constraints of spatiotemporal coupling, an objective function is constructed with the goal of minimizing economic cost, and the optimal passage time is solved within the optimal passage period of each traffic light intersection.

[0010] As an example, calculating the nodal energy loss of a vehicle passing through each segment of the target route specifically includes: Based on the probability distribution of travel time for each road segment and the current state of the vehicle, calculate the first energy loss of the vehicle traveling from the first traffic light intersection to the second traffic light intersection and the second energy loss of the vehicle when passing the first traffic light intersection; wherein, the second traffic light intersection is the downstream traffic light intersection adjacent to the first traffic light intersection. The energy loss of the vehicle as it travels from upstream of the first traffic light intersection to upstream of the second traffic light intersection is calculated based on the first energy loss and the second energy loss.

[0011] As an example, the calculation of the first energy loss of the vehicle traveling from the first traffic light intersection to the second traffic light intersection and the second energy loss of the vehicle when passing the first traffic light intersection specifically includes: Based on the current state of the vehicle, the first passage probability at a certain moment in each green light time sequence segment of each traffic light intersection on the target route is determined according to the probability distribution of passage time for each road segment; wherein, each green light time sequence segment corresponds to a green light passage window period; The first probability density function is calculated based on the first traffic probability, corresponding to the time difference between a vehicle arriving at the second time in the second green light time segment of the first traffic light intersection from the first time in the first green light time segment, and the second probability density function is calculated based on the time difference between a vehicle arriving at the fourth time in the fourth green light time segment of the first traffic light intersection from the third time in the third green light time segment of the third traffic light intersection; wherein, the third traffic light intersection is an upstream traffic light intersection adjacent to the first traffic light intersection; The expected first speed of the vehicle from the first traffic light intersection to the second traffic light intersection and the expected second speed of the vehicle from the third traffic light intersection to the first traffic light intersection are calculated based on the first probability density function and the second probability density function, respectively. Calculate the first energy loss based on the expected first velocity; The second energy loss is calculated based on the expected first velocity and the expected second velocity.

[0012] As one example, calculating the nodal energy loss of a vehicle passing through each segment of the target route also includes: The second probability of a vehicle arriving at the second green light segment of the second traffic light intersection from the first moment within the first green light segment of the first traffic light intersection is calculated based on the first probability of passage. The node energy loss is calculated based on the first energy loss, the second energy loss, and the second passage probability.

[0013] As an example, determining the first probability of passage at a certain moment in each green light time sequence segment at each traffic light intersection on the target route specifically includes: Based on the current status of the vehicles, multiple green light windows are determined for each traffic light intersection according to the probability distribution of travel time for each road segment, thus forming the green light sequence of the traffic light intersection. The probability distribution of travel time for vehicles from the starting point of the target route to each traffic light intersection on the target route is determined based on the probability distribution of travel time for each road segment. The first probability of passage at a certain moment in each green light time segment of the traffic light intersection is determined based on the probability distribution of passage time at each traffic light intersection.

[0014] As one example, multiple green light windows are determined for each traffic light intersection to form the green light sequence at the traffic light intersection, specifically including: Based on the current status of the vehicle, the earliest and latest passage times at each traffic light intersection are determined according to the upper and lower speed limits. The earliest and latest passage times are revised to form the second earliest and second latest passage times for each traffic light intersection, thus forming the initial passage period for the traffic light intersection; wherein, the second earliest and second latest passage times are the start or end times of the green light passage window. Extract the green light window period within the initial traffic flow period of each traffic light intersection to form the green light sequence of the traffic light intersection.

[0015] As one example, the earliest and latest passage times are modified to form the second earliest and second latest passage times for each traffic light intersection, specifically including: If the first latest passage time is feasible, and the first earliest passage time or the first latest passage time is not a green light passage window, then the first earliest passage time or the first latest passage time is set as the start time of the next green light passage window or the last time of the previous green light passage window, thus forming the second earliest passage time or the second latest passage time.

[0016] As one embodiment, modifying the first earliest passage time and the first latest passage time to form the second earliest passage time and the second latest passage time for each traffic light intersection also includes: If the first latest passage time at the fourth traffic light intersection does not meet the requirements, the first latest passage time at the fourth traffic light intersection will be adjusted based on the vehicle speed limit and the second latest passage time at the fifth traffic light intersection downstream of the fourth traffic light intersection.

[0017] As one embodiment, modifying the first earliest passage time and the first latest passage time to form the second earliest passage time and the second latest passage time for each traffic light intersection also includes: If the revised first latest passage time of the fourth traffic light intersection is not the green light passage window, then the first latest passage time of the fourth traffic light intersection will be set to the last moment of the previous green light passage window, forming the second latest passage time of the fourth traffic light intersection.

[0018] Secondly, this application also provides a global vehicle speed planning device, including a first historical distribution calculation module, a road segment traffic probability distribution calculation module, and a target average vehicle speed calculation module. The first historical distribution calculation module is used to calculate the first historical speed distribution of the target route using the historical driving speed information of the target route. The first historical speed distribution is the probability distribution of historical speed with mileage. The road segment passage probability distribution calculation module is used to calculate the passage time probability distribution of each road segment on the target route based on the first historical vehicle speed distribution; The target average vehicle speed calculation module is used to calculate the target average vehicle speed for each road segment based on the probability distribution of travel time for each road segment and the current state of the vehicle, so as to obtain a global vehicle speed planning scheme for the vehicle to travel on the target route; wherein, the current state includes the current driving conditions and the current position.

[0019] Thirdly, this application also provides an electronic device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements any of the aforementioned global vehicle speed planning methods.

[0020] Fourthly, this application also provides a non-transitory computer-readable storage medium storing a computer program that, when executed by a processor, implements any of the aforementioned global vehicle speed planning methods.

[0021] Fifthly, this application also provides a computer program product, which includes a computer program that, when executed by a processor, implements any of the aforementioned global vehicle speed planning methods. Attached Figure Description

[0022] To more clearly illustrate the technical solutions in this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0023] Figure 1 This is one of the flowcharts illustrating the global vehicle speed planning method provided in this application; Figure 2 This is the second flowchart of the global vehicle speed planning method provided in this application; Figure 3 This is a flowchart illustrating the process of finding the optimal travel time at each traffic light intersection on the target route, as provided in this application. Figure 4 This is a flowchart of the calculation of the first energy loss and the second energy loss provided in this application; Figure 5 This is a flowchart illustrating the process of determining the green light sequence at each traffic light intersection, as provided in this application. Figure 6 This is the first historical vehicle speed distribution map obtained through simulation experiments, as provided in this application; Figures 7 to 9 This is a schematic diagram illustrating the verification of the energy consumption model provided in this application; Figures 10 to 11 This is a schematic diagram illustrating the verification of the vehicle dynamics model provided in this application; Figure 12 This is a schematic diagram of the optimal passage times at traffic light intersections provided in this application; Figures 13 to 14 This is a schematic diagram of the global vehicle speed planning results for green wave traffic provided in this application; Figure 15 This is a schematic diagram of the global vehicle speed planning device provided in this application; Figure 16 This is a schematic diagram of the solution module provided in this application; Figure 17 This is a schematic diagram of the structure of the electronic device provided in this application. Detailed Implementation

[0024] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0025] It should be noted that, in the description of this application, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0026] The terms "first," "second," etc., used in this application are used to distinguish similar objects and not to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that embodiments of this application can be implemented in orders other than those illustrated or described herein, and the objects distinguished by "first," "second," etc., are generally of the same class, without limiting the number of objects; for example, a first object can be one or more. Furthermore, "and / or" indicates at least one of the connected objects, and the character " / " generally indicates that the preceding and following objects have an "or" relationship.

[0027] The following is combined Figures 1 to 17 This application describes the global vehicle speed planning method, apparatus, equipment, medium, and product provided.

[0028] It should be noted that the global vehicle speed planning method provided in this application is implemented based on a global vehicle speed planning device. This method can determine the target average vehicle speed for each segment of the target route based on historical vehicle speed information and the current state of the vehicles. This ensures that the vehicle speed between traffic light intersections conforms to the historical speed probability distribution of that segment, adapting to complex time-varying conditions and achieving global vehicle speed planning for green wave traffic. This application implements global vehicle speed planning for target road segments and time periods. The planned speed conforms to the speed distribution of the vehicle group on the target route, mitigating the impact of traffic flow disturbances. By utilizing historical vehicle speed distribution information, it reduces reliance on real-time sensing systems and navigation information.

[0029] This application describes the global vehicle speed planning method using a global vehicle speed planning device as the execution subject as an example.

[0030] Figure 1 This is one of the flowcharts of the global vehicle speed planning method provided in this application. Figure 2 This is the second flowchart of the global vehicle speed planning method provided in this application.

[0031] like Figure 1 and 2 As shown, the global vehicle speed planning method provided in this application includes: S110: Calculate the first historical speed distribution of the target route using historical vehicle speed information. The first historical speed distribution is the probability distribution of historical speeds with respect to mileage.

[0032] S120: Calculate the probability distribution of travel time for each segment of the target route based on the first historical vehicle speed distribution.

[0033] S130: Based on the probability distribution of travel time for each road segment and the current state of the vehicle, calculate the target average speed for each road segment to obtain a global speed planning scheme for the vehicle traveling on the target route.

[0034] The current status includes the current driving conditions and the current location. Figure 2 As one possible implementation, the vehicle's current driving conditions include gradient values, speed limit information, traffic light information, etc., obtained through high-precision maps. The vehicle's current location can be obtained from the Global Positioning System (GPS).

[0035] Specifically, the global speed planning device analyzes the historical driving speed information of the target route, calculates the probability distribution of historical speeds at different mileages on the target route (i.e., the probability distribution of historical speeds with mileage), and obtains the first historical speed distribution.

[0036] Understandably, the target route includes multiple traffic light intersections, with adjacent intersections forming a road segment. Based on this, the global speed planning device calculates the travel time probability distribution for each road segment based on the first historical speed distribution. In this application, it is assumed that each road segment starts upstream of a traffic light intersection and ends upstream of the downstream traffic light intersection adjacent to that intersection. That is, when a vehicle passes through this road segment, it first crosses the traffic light intersection and then traverses the route between the two traffic light intersections. Furthermore, to achieve green wave traffic flow, it is assumed that vehicles travel at a constant speed on road segments between adjacent traffic light intersections; when the speeds of two adjacent road segments differ, vehicles transition by uniform acceleration or deceleration when crossing traffic light intersections.

[0037] Based on the analysis results of historical driving speed information, when a vehicle is about to pass through the target route, the global speed planning device calculates the target average speed of the vehicle passing through each road segment on the target route based on the vehicle's current state (including the vehicle's current driving conditions, current position, etc.) and the probability distribution of travel time for each road segment, thereby obtaining the global speed planning scheme for the vehicle to travel on the target route.

[0038] It should be noted that the target average speed for each road segment is determined by the assumption that the vehicle does not exceed the speed limit, maintains a constant speed on each road segment, does not stop at intersections, and reaches the destination of the target route at the specified final time. Therefore, this embodiment of the application takes into account the historical driving speed information of the target route and combines it with the current state of the vehicle to achieve global speed planning. This reduces unnecessary acceleration and braking during driving, lowers energy consumption, improves traffic flow, and enhances driving stability and safety. It also effectively mitigates the impact of traffic flow fluctuations and provides users with a smoother and more energy-efficient driving experience.

[0039] In one possible embodiment, step S110, calculating the first historical vehicle speed distribution of the target route using historical vehicle speed information of the target route, specifically includes: S1101: Collect vehicle driving information on the target route at different time periods. The driving information includes vehicle speed and mileage.

[0040] In one possible embodiment, under test conditions, an experiment is conducted using a combination of inertial navigation and vehicle speed sensors at a preset sampling frequency and at different time periods to collect vehicle speed and latitude / longitude information as the vehicle travels on the target route. All vehicle speed information is then compiled into vehicle speed data. The latitude and longitude information is converted into driving mileage to form mileage data. As shown below: (1) (2) Among them, subscript Indicates the first This experiment; for m A dimensional column vector, representing the 3rd column vector. The vehicle's various mileages during this experiment; for m A dimensional column vector, representing the 3rd column vector. The vehicle speed at each mileage point during this experiment.

[0041] S1102: Construct a dataset using mileage as the feature vector and the mean and variance of historical vehicle speeds as predictors. (i.e., historical vehicle speed information): (3) The total number of samples in the dataset is N×m.

[0042] S1103: Based on dataset Predict the probability distribution of vehicle speed at each mileage along the target route.

[0043] In one possible implementation, prediction is based on a Gaussian process regression model. Vehicle speed probability distribution at location: (4) (5) in, For mileage Average vehicle speed at the location; For mileage Average vehicle speed at the location; Representing the vehicle speed matrix The Columns, vehicle speed matrix It is based on vehicle speed data Transformed into a vehicle speed matrix Each column corresponds to the vehicle speed data at a discrete mileage s; Represent a 3D identity matrix; Indicates the measured noise at the first The variance of the dimension; Representing an N×m dimensional row vector, through The vector is calculated to obtain each element. Represent a real number obtained through a kernel function: Where Z represents the mileage feature data within dataset D, and Different mileage samples in mileage feature data Z This indicates different mileage positions on the target route. Representing feature data Z Thej OK, and These are hyperparameters in the kernel function; Let be a real number. = ; Represent a A symmetric matrix, through calculate, Representing mileage feature data Z The i OK; for The transpose of .

[0044] Using a Gaussian process regression model, with the input being... At that time, the corresponding vehicle speed distribution is obtained as follows: .

[0045] For each mileage, the maximum likelihood estimation method is first used to estimate the hyperparameters in the Gaussian process regression model. , Calculations are performed to obtain an estimation model of the historical vehicle speed distribution corresponding to each mileage.

[0046] Specifically, the global vehicle speed planning device receives vehicle driving information collected at different times on the target route, and constructs a dataset with mileage as the feature vector and the mean and variance of historical vehicle speeds as the prediction quantities based on the driving information. Based on the dataset, it predicts the probability distribution of vehicle speed at each mileage on the target route.

[0047] Understandably, the first historical vehicle speed distribution can also be calculated based on other probability distribution prediction models.

[0048] This application embodiment transforms discrete driving information into vehicle speed distribution information that reflects a probability distribution, providing basic data for global vehicle speed planning.

[0049] In one possible embodiment, step S120, calculating the probability distribution of travel time for each segment of the target route based on the first historical vehicle speed distribution, specifically includes: S1201: Based on the distribution of traffic light intersections, the target route is divided into multiple segments, and the travel time for each sub-segment is marked as follows: .

[0050] S1202: Obtain the second historical vehicle speed distribution for each road segment based on the first historical vehicle speed distribution.

[0051] Understandably, each road segment corresponds to a mileage range on the target route, and this mileage range corresponds to the second historical vehicle speed distribution. For each mileage within this mileage range, then: (6) S1203: Based on the second historical vehicle speed distribution of each road segment, multiple travel times for that road segment are obtained, where different travel times for that road segment correspond to different speed combinations at multiple mileage points within the corresponding mileage range. For each speed combination, the corresponding travel time is... for: (7) in, Indicates the first The first section of the road The corresponding travel time for each speed combination Indicates the first i The total mileage within each road segment For the first route to the target i Mileage at each traffic light intersection For the first route to the target i - Mileage at 1 traffic light intersection Indicates the first The mileage difference at each mileage point.

[0052] This yields a set of multiple travel times for that road segment. .

[0053] S1204: Fit the probability distribution of travel time for each road segment based on multiple travel times for that road segment.

[0054] In one possible implementation, Gaussian distribution theory is used to fit the set of each road segment to obtain the probability distribution of travel time for each road segment. .

[0055] Specifically, the global vehicle speed planning device obtains the second historical vehicle speed distribution for each road segment based on the first historical vehicle speed distribution, and extracts different combinations of vehicle speeds at multiple mileages within the mileage range of each road segment based on the second historical vehicle speed distribution of each road segment to obtain multiple travel times, and fits the travel time probability distribution of each road segment based on the multiple travel times.

[0056] This application embodiment determines the probability distribution of travel time for each road segment based on the historical vehicle speed distribution of the target road segment, and converts vehicle speed information into travel time information, providing a data foundation for accurately determining the target average vehicle speed in each road segment.

[0057] In one possible embodiment, step S130 involves calculating the target average vehicle speed for each road segment based on the probability distribution of travel time for each road segment and the current state of the vehicle. Specifically, this includes: S1301: Based on the probability distribution of travel time for each road segment and the current state of the vehicles, under the spatiotemporal coupling constraint, with the goal of minimizing economic cost, solve for the optimal travel time at each traffic light intersection on the target route.

[0058] S1302: Calculate the target average speed for each road segment based on the optimal passage time at each traffic light intersection and the distance between adjacent traffic light intersections. (8) in, For the first route to the target i The target average vehicle speed for each road segment For the first route to the target i +1 traffic light intersection's mileage, For the first route to the target i The best time to travel at +1 traffic light intersection For the first route to the target i The best time to travel at a traffic light intersection.

[0059] In this embodiment, the global vehicle speed planning device solves for the optimal passage time at each traffic light intersection based on the current state of the vehicle, with the goal of satisfying the spatiotemporal coupling constraints and minimizing economic costs, and determines the target average vehicle speed for each road segment based on this.

[0060] This application embodiment obtains the optimal passage time for each traffic light intersection through condition constraints and objective optimization, thereby obtaining the target average speed for each road segment, achieving the goal of not exceeding the speed limit, not stopping at intersections, and reaching the destination of the target route at the specified final time.

[0061] In one possible embodiment, such as Figure 3 As shown, step 1301 involves determining the optimal travel time at each traffic light intersection on the target route, specifically including: S310: Based on the vehicle's current state, calculate the nodal energy loss of the vehicle on each road segment along the target route according to the probability distribution of travel time for each road segment. .in, Indicates that the vehicle passed the first i Energy loss at each node of each road segment.

[0062] S320: Based on node energy loss The optimal travel time for each traffic light intersection on the target route is determined by optimizing the vehicle's current position. This optimal travel time minimizes the energy loss at each intersection when the vehicle passes through that intersection. Minimum.

[0063] In one possible implementation, Dijkstra's algorithm is used to find the node energy loss when a vehicle passes through the road segment, starting from the current position and based on the current traffic light state. The shortest green light period is considered the optimal green light period at the traffic light intersections on that road segment. ,in To pass the first The optimal green light start time for a traffic light intersection. To pass the first The optimal green light period at a traffic light intersection, including the end time of the green light.

[0064] S330: Construct an objective function under spatiotemporal coupling constraints with the goal of minimizing economic cost, and solve for the optimal passage time within the optimal passage period of each traffic light intersection.

[0065] The spatiotemporal coupling constraint is as follows: (9) in, This refers to the torque of the vehicle's actuator motor. and These are the minimum and maximum torques of the actuator motor, respectively. and These are the maximum and minimum speed limits for the road sections where the traffic light intersections are located. For vehicles to pass the i The best time to cross a traffic light intersection. For vehicles to pass the i The best time to travel at +1 traffic light intersection.

[0066] The objective function is to minimize the total energy loss of all nodes along the entire target route, i.e. (10) in, This represents the total number of road segments on the target route.

[0067] By solving the above optimization problem, we can obtain the first... The best time to travel at a traffic light intersection Best time to pass through .

[0068] This application's embodiments determine the optimal passage time for each traffic light intersection by minimizing the node energy loss of each road segment, and determine the optimal passage time within the optimal passage time for each traffic light intersection by minimizing the total node energy loss of the entire route, ensuring that the vehicle's energy consumption is minimized in the global speed planning scheme of this application.

[0069] Based on the above, in one possible embodiment, step S310, calculating the nodal energy loss of the vehicle as it passes through each segment of the target route, specifically includes: P1: Based on the probability distribution of travel time for each road segment Calculate the first energy loss of the vehicle as it travels from the first traffic light intersection to the second traffic light intersection (i.e., the route within the road segment to which the first traffic light intersection belongs) based on the vehicle's current state. The second energy loss when the vehicle passes through the first traffic light intersection. The second traffic light intersection is the downstream traffic light intersection adjacent to the first traffic light intersection.

[0070] P2: Based on the first energy loss Second energy loss Calculate the nodal energy loss of a vehicle traveling from upstream of the first traffic light intersection to upstream of the second traffic light intersection (i.e., the complete road segment to which the first traffic light intersection belongs). E : (11) In this embodiment of the application, based on the vehicle speed control scheme of smooth intersection and uniform route, the node energy loss is divided into two parts: the vehicle passing through the traffic light intersection and the vehicle traveling on the route between the traffic light intersections. This is to ensure the accuracy of the optimal passage time (step S320) and the optimal passage time (step S330) of the traffic light intersection by accurately calculating the energy loss.

[0071] In one possible embodiment, in step P1, as Figure 4 As shown, calculate the first energy loss of the vehicle traveling from the first traffic light intersection to the second traffic light intersection. And the second energy loss when the vehicle passes through the first traffic light intersection. Specifically, it includes: S410: Based on the vehicle's current state, and according to the probability distribution of travel time for each road segment. Determine the first probability of passage at a certain moment within each green light time segment at each traffic light intersection on the target route. Each green light time segment corresponds to a green light passage window.

[0072] S420: Calculate the time difference between when a vehicle arrives at the second time within the second green light segment of the second traffic light intersection, based on the first traffic probability, from the first moment within the first green light segment of the first traffic light intersection. The corresponding first probability density function The time difference between the third moment in the third green light sequence segment at the third traffic light intersection and the fourth moment in the fourth green light sequence segment at the first traffic light intersection. The corresponding second probability density function .

[0073] The third traffic light intersection is the upstream traffic light intersection adjacent to the first traffic light intersection.

[0074] in, (12) (13) (14) (15) in, Indicates the vehicle's position on the target route. The first traffic light intersection At a certain moment in a green light sequence segment The first probability of passage, Indicates the vehicle's position on the target route. The first traffic light intersection At a certain moment in a green light sequence segment The first probability of passage, Indicates the vehicle's position on the target route. The first traffic light intersection At a certain moment in a green light sequence segment The first probability of passage, Indicates the vehicle's position on the target route. The first traffic light intersection The end time of each green light sequence segment Indicates the vehicle's position on the target route. The first traffic light intersection The start time of each green light sequence segment.

[0075] S430: Based on the first probability density function respectively Second probability density function Calculate the expected first speed of the vehicle from the first traffic light intersection to the second traffic light intersection. And the expected second speed of vehicles from the third traffic light intersection to the first traffic light intersection. .

[0076] in: (16) (17) in, and Indicates time difference The maximum and minimum values, and Indicates time difference The maximum and minimum values.

[0077] S440: Calculate the first energy loss based on the expected first velocity. .

[0078] In this application, the calculation of energy loss is based on a vehicle dynamics model and an energy consumption calculation model. The vehicle dynamics model is as follows: (18) (19) The energy consumption calculation model is as follows: (20) in, For driving torque, For vehicle speed, It is the air drag coefficient. It refers to the vehicle's frontal area. It is air density. The rolling resistance coefficient, The slope angle, It is the acceleration due to gravity. For vehicle quality, The rotational mass conversion factor is . For the wheel radius, This indicates the rotational speed of the vehicle's actuator motor. This indicates the torque of the vehicle's actuator motor. for and The determined power of the actuator motor, These are the fitting coefficients.

[0079] First energy loss The calculation is as follows: (twenty one) (twenty two) (twenty three) (twenty four) (25) in, This represents the average speed of vehicles from downstream of the first traffic light intersection to upstream of the second traffic light intersection. The main reduction ratio.

[0080] S450: Based on First Speed ​​Expectation Second speed expectation Calculate the second energy loss : (26) (27) (28) (29) (30) (31) in, This represents the average speed of vehicles from downstream of the third traffic light intersection to upstream of the first traffic light intersection. This represents the absolute value of the maximum acceleration of a vehicle from downstream of the third traffic light intersection to upstream of the first traffic light intersection.

[0081] In this embodiment, the probability density of a vehicle passing between two adjacent traffic light intersections at different times is calculated by using the first passage probability at a certain moment in each green light time sequence segment of each traffic light intersection. Then, the speed expectation of each road segment is calculated, and the two parts of energy loss are calculated based on the speed expectation. The energy loss is calculated at the time granularity, which provides accuracy guarantee for more accurately calculating the best time for a vehicle to pass through each traffic light intersection.

[0082] In actual operation, the vehicle starts from the... The first traffic light intersection Departing at different times within a green light sequence segment, in the... The first traffic light intersection The probability of arrival at different times within a green light time segment is not the same. Based on this consideration, in a preferred embodiment, calculating the nodal energy loss of a vehicle passing through each segment of the target route further includes: In step S420, while calculating the first probability density function, a second probability of passage is also calculated based on the first passage probability: the vehicle arrives at the second green light segment of the second traffic light intersection from the first moment within the first green light time segment of the first traffic light intersection. .

[0083] Furthermore, in S450, the node energy loss is calculated based on the first energy loss, the second energy loss, and the second passage probability, i.e.: (32) In this embodiment, the impact of the probability of a vehicle passing through a road segment at different times on energy loss is taken into account, which further improves the calculation accuracy of energy loss and makes the intersection passage time as close as possible to the probability distribution of the road segment, thereby reducing the impact of the speed fluctuation of the target route on the green wave passage of the vehicle.

[0084] In one possible embodiment, step S410, determining the first probability of passage at a certain moment in each green light time sequence segment of each traffic light intersection on the target route, specifically includes: S4101: Based on the vehicle's current state, and according to the probability distribution of travel time for each road segment. Multiple green light windows are determined for each traffic light intersection to form the green light sequence of the intersection, where each green light window is considered a segment of the green light sequence for that traffic light intersection. ,in, and Indicates the first The first traffic light intersection The start and end times of the green light sequence segment.

[0085] S4102: Based on the probability distribution of travel time for each road segment Determine the probability distribution of travel time for vehicles from the starting point of the target route to each traffic light intersection along the target route. .

[0086] Assuming that the travel times of each road segment are independent, the probability distribution of the travel time for a vehicle to arrive at the nth traffic light intersection from the starting point can be obtained as follows: (33) (34) (35) Where, in the formula, This represents the average time it takes for a vehicle to travel from the starting point to the nth traffic light intersection. This represents the time variance of a vehicle traveling from the starting point to the nth traffic light intersection. This indicates that the vehicle departs from the starting point and arrives at the destination. A sample at a traffic light intersection at a specific time; This represents the average travel time for the road segment at the nth traffic light intersection; This represents the variance of travel time for the road segment to which the nth traffic light intersection belongs.

[0087] Based on this, in step S420 above, the second passage probability ,in, This represents the probability that a vehicle will be able to proceed from the first moment within the first green light time sequence of the first traffic light intersection to a certain moment within the second green light time sequence of the second traffic light intersection. Indicates the vehicle's position on the target route. The first traffic light intersection The end time of each green light sequence segment Indicates the vehicle's position on the target route. The first traffic light intersection The start time of each green light sequence segment.

[0088] S4103: Probability distribution of travel time at each traffic light intersection Determine the first probability of passage at a certain moment in each green light sequence segment at a traffic light intersection.

[0089] in, (36) in, Indicates the vehicle's position on the target route. The first traffic light intersection The probability of first passage at a certain moment in a green light sequence segment; and They represent the first The first traffic light intersection The start and end times of the green light within a single green light sequence segment; This represents the average time it takes for a vehicle to travel from the starting point to the nth traffic light intersection. This represents the time variance of a vehicle traveling from the starting point to the nth traffic light intersection. Indicates the vehicle is in The first traffic light intersection The first green light timing segment passes through the first The probability of a traffic light intersection; Indicates the vehicle is in The first traffic light intersection Within a green light sequence segment Time through the first The probability of a traffic light intersection.

[0090] Similarly, (37) (38) In this embodiment, the probability distribution of the travel time of a vehicle from the starting point to the traffic light intersection is determined based on the green light sequence of each traffic light intersection. This determines the first travel probability at a certain moment in each green light sequence segment of each traffic light intersection. The first travel probability at a certain moment in each green light sequence segment is calculated from the perspective of the overall target route, thereby improving the accuracy of the speed expectation of each road segment calculated based on the first travel probability.

[0091] In one possible embodiment, in step S4101, as Figure 5 As shown, multiple green light windows are determined for each traffic light intersection, forming the green light sequence of the intersection. Each green light window is considered a segment of the green light sequence for that traffic light intersection, specifically including: S510: Based on the current state of the vehicle, determine the earliest and latest passage times at each traffic light intersection according to the upper and lower speed limits, denoted as... and ,in, and They represent the first The earliest and latest times to proceed at each traffic light intersection: (39) (40) S520: Correct the first earliest and first latest passage times to form the second earliest and second latest passage times for each traffic light intersection, thus establishing the initial passage period for the traffic light intersection. Among them, the second earliest passage time and the second latest passage time are the start or end time of the green light passage window period.

[0092] S530: Extract the initial traffic period for each traffic light intersection. The green light window period within the intersection forms the green light sequence of the traffic light intersection, with each green light window period serving as a segment of the green light sequence for that traffic light intersection.

[0093] The initial passage period at each traffic light intersection. It often includes multiple complete green light windows. ,Right now This refers to a period within the permitted traffic hours when there are multiple green light windows for vehicles to pass, marked as... ,in and Marked as the first The first traffic light intersection The start and end times of the green light sequence segment 。

[0094] In this embodiment, after determining the passage time of vehicles at traffic light intersections through speed limit information, the start and end times are corrected to the start or end time of the green light passage window, and the green light timing segment is determined accordingly to provide conditions for green wave passage and prepare for non-stop passage at intersections.

[0095] In one possible embodiment, step S520 employs a pruning algorithm for correction. Specifically, the first earliest passage time and the first latest passage time are corrected to form the second earliest passage time and the second latest passage time for each traffic light intersection, which specifically includes: First latest passage time Where feasible, if the earliest passage time Or the first and latest passage time If it is not within the green light window, then the earliest passage time will be [the first time to proceed]. Or the first and latest passage time Set the start time of the next green light window or the end time of the previous green light window to form the second earliest passage time. Or the second latest passage time .

[0096] Specifically, if it is possible to reach the destination of the target route at the maximum speed within the remaining time of the target route, then a determination is made. It is feasible.

[0097] In this embodiment of the application, the first earliest passage time or the first latest passage time is modified to the start time of the next green light passage window or the last time of the previous green light passage window, so that the time when the vehicle passes through the intersection is aligned with the start or end time of the green light passage window.

[0098] Based on the above, step S520 further includes: checking each traffic light intersection one by one, and if the first latest passage time of the fourth traffic light intersection is... Not in compliance with requirements (e.g.) or Leading to the If the speed of vehicles on a particular road segment exceeds the speed limit, then the speed limit will be used as the benchmark. The second latest passage time for the fifth traffic light intersection, which is adjacent to the fourth traffic light intersection downstream. Revise the first latest passage time at the fourth traffic light intersection. The revised first latest passage time for the fourth traffic light intersection was obtained. : .

[0099] In this embodiment, each traffic light intersection is checked one by one to ensure that vehicles can pass through as many intersections as possible without exceeding the speed limit.

[0100] Based on the above, step S520 further includes: if the revised first latest passage time of the fourth traffic light intersection... If it is not within the green light window, then the latest passage time at the fourth traffic light intersection will be... Set as the last moment of the previous green light travel window to form the second latest travel time at the fourth traffic light intersection. .

[0101] In this embodiment of the application, by aligning the modified first latest passage time with the last moment of the previous green light passage window, vehicles can pass through the intersection at the last moment of the previous green light passage window, thus achieving non-stop passage at the intersection.

[0102] The technical solution of this application is verified by simulation test as follows.

[0103] The global vehicle speed planning method proposed in this application will be simulated and verified on a target route in a certain city, and the simulation results will be compared with those of the global vehicle speed planning method for green wave traffic, which does not consider historical vehicle speed distribution. The only difference between the different methods and the system of this application is in the control system of global vehicle speed planning, but the perception and execution systems are the same.

[0104] To better simulate the dynamic characteristics of an autonomous vehicle driven by a four-wheel hub motor, the simulation environment for this application was built in CarSim. The green wave traffic global speed planning device integrated in this application, which considers historical vehicle speed distribution, was implemented in Simulink. The selected vehicle parameters are those of a mass-produced model from a certain company, the traffic light timings are real-world timings collected from a certain location, and the historical vehicle speed data used are experimentally collected data. The resulting probability distribution map of historical vehicle speed changes with mileage (i.e., the aforementioned first historical vehicle speed distribution) is shown below. Figure 6 As shown.

[0105] In addition, this application designs three metrics to evaluate the performance of the global vehicle speed planning method: 1. Probability density of travel time at each traffic intersection under the historical travel time distribution.

[0106] (41) In the formula For the first Traffic time at each traffic intersection The probability density under the historical common distribution.

[0107] 2. The probability density of the planned average vehicle speed between adjacent traffic intersections under the historical average vehicle speed distribution.

[0108] (42) In the formula The average speed (i.e., speed expectation) planned between adjacent traffic intersections. The probability density of the average vehicle speed under the historical traffic distribution. To pass the first Average speed of each road segment To pass the first The average speed variance of each road segment.

[0109] 3. Energy consumption indicators.

[0110] (43) In the formula This represents the total energy loss at each node along the target route.

[0111] First, this application validated the energy consumption model and the vehicle dynamics model, and the validation results are as follows: Figures 7 to 11 As shown. The simulation test model was validated. First, the energy consumption model was validated using data collected from the vehicle's CAN bus (including motor speed, motor torque, vehicle speed, etc.) as input, and compared with the actual battery energy consumption. The results are as follows: Figures 7 to 9 The diagram shows the model verification. Under the simulated conditions using real vehicle data, the total driving distance reached 15.78km, the actual battery energy consumption was 16.0106kWh / 100km, the initial battery state of charge (SOC) was 100%, and the battery SOC at the end of the experiment was 95.8%. The simulation set the initial battery SOC to 100%, and the battery SOC at the end of the simulation was 96.1%.

[0112] Secondly, the vehicle dynamics model was verified by using data collected from the vehicle's CAN bus (including gradient, motor torque, etc.) as input and comparing it with actual vehicle speed changes. This yielded the following results: Figures 10 to 11 The diagram shown illustrates the verification of the vehicle dynamics model. The selected data segment from the real vehicle data collection simulates a 33-second driving condition.

[0113] To illustrate the impact of global speed planning systems based on different green wave traffic global speed planning algorithms on the method proposed in this application, in addition to the green wave traffic global speed planning method that considers historical vehicle speed distribution, this application also establishes a green wave traffic global speed planning method that does not consider historical vehicle speed distribution. The resulting green wave traffic global speed planning system was verified under test conditions, and the verification results are as follows: Figures 12 to 14 As shown. By Figure 12 It can be seen that the probability density of the calculated green light passage segments at each traffic intersection is relatively high under the historical passage time distribution, and the passage time at each traffic intersection is within three standard deviations of the historical passage time distribution. Figures 13 to 14 It can be observed that this application considers the influence of historical vehicle speed distribution when performing global vehicle speed planning, and the planned global vehicle speed is closer to the historical vehicle speed distribution, satisfying the vehicle speed distribution of the target route's vehicle group. In addition, the planned average vehicle speed between adjacent traffic intersections has a high probability density under the historical average vehicle speed distribution, which is basically close to the mean of the historical average vehicle speed distribution.

[0114] Therefore, the following conclusions can be drawn: The green wave speed planned in this application fully considers the impact of historical traffic flow. In practical applications, it can reduce the impact of target route vehicle speed fluctuations on the green wave passage of the vehicle itself, and also verify the rationality of the basis of this application for planning the global speed of green wave passage by considering historical vehicle speed distribution.

[0115] In summary, the simulation results show that this application achieves green wave traffic speed planning that conforms to the vehicle speed distribution within the target route by considering historical vehicle speed distribution for global green wave traffic planning. This alleviates the impact of vehicle speed fluctuations on the green wave traffic of the vehicle itself. In particular, the development of a green wave traffic global speed planning system that adapts to traffic conditions is of great significance.

[0116] Based on the above, this application also provides a global vehicle speed planning device. The global vehicle speed planning device and the global vehicle speed planning method described above can be referred to each other accordingly.

[0117] As an example, such as Figure 15 As shown, the global vehicle speed planning device includes a first historical distribution calculation module 1510, a road segment traffic probability distribution calculation module 1520, and a target average vehicle speed calculation module 1530.

[0118] The first historical distribution calculation module 1510 is used to calculate the first historical speed distribution of the target route using the historical driving speed information of the target route. The first historical speed distribution is the probability distribution of historical speed with mileage. The road segment passage probability distribution calculation module 1520 is used to calculate the passage time probability distribution of each road segment on the target route based on the first historical vehicle speed distribution; The target average vehicle speed calculation module 1530 is used to calculate the target average vehicle speed of each road segment based on the probability distribution of travel time of each road segment and the current state of the vehicle, so as to obtain a global vehicle speed planning scheme for the vehicle to travel on the target route; wherein, the current state includes the current driving conditions and the current position.

[0119] In one possible embodiment, the first historical distribution calculation module 1510 is further configured to: The vehicle's driving information on the target route is collected at different times, including vehicle speed and mileage. A dataset is constructed using mileage as the feature vector and the mean and variance of historical vehicle speeds as predictors. Based on the dataset, predict the probability distribution of vehicle speed at each mileage on the target route.

[0120] In one possible embodiment, the road segment traffic probability distribution calculation module 1520 is further used for: Based on the distribution of traffic light intersections, the target route is divided into multiple segments; The second historical vehicle speed distribution for each road segment is obtained based on the first historical vehicle speed distribution. Multiple travel times for each road segment are obtained based on the second historical vehicle speed distribution for each segment; The probability distribution of travel time for each road segment is fitted based on multiple travel times for each road segment.

[0121] In one possible embodiment, such as Figure 15 As shown, the target average vehicle speed calculation module 1530 includes a solution module 15301 and an averaging module 15302; The solver module 15301 is used to solve the optimal travel time at each traffic light intersection on the target route based on the probability distribution of travel time for each road segment and the current state of the vehicles, under the constraints of spatiotemporal coupling, with the goal of minimizing economic cost. The averaging module 15302 is used to calculate the target average speed of each road segment based on the optimal passage time of each traffic light intersection and the distance between adjacent traffic light intersections.

[0122] In one possible embodiment, such as Figure 16 As shown, the solution module 15301 includes a node loss calculation module 1610, an optimal passage period acquisition module 1620, and an optimal passage time acquisition module 1630.

[0123] The node loss calculation module 1610 is used to calculate the node energy loss of the vehicle on each road segment of the target route based on the vehicle's current state and the probability distribution of the travel time of each road segment. The optimal travel time acquisition module 1620 is used to optimize based on node energy loss and the current position of the vehicle to obtain the optimal travel time for each traffic light intersection on the target route. The optimal passage time acquisition module 1630 is used to construct an objective function with the goal of minimizing economic cost under spatiotemporal coupling constraints, and solve for the corresponding optimal passage time within the optimal passage period of each traffic light intersection.

[0124] In one possible embodiment, the node loss calculation module 1610 includes a first loss calculation module 16101 and a second loss calculation module 16102.

[0125] The first loss calculation module 16101 is used to calculate the first energy loss of a vehicle traveling from the first traffic light intersection to the second traffic light intersection and the second energy loss of a vehicle when passing through the first traffic light intersection, based on the probability distribution of travel time for each road segment and the current state of the vehicle; wherein, the second traffic light intersection is the downstream traffic light intersection adjacent to the first traffic light intersection. The second loss calculation module 16102 is used to calculate the node energy loss of a vehicle traveling from upstream of the first traffic light intersection to upstream of the second traffic light intersection based on the first energy loss and the second energy loss.

[0126] In one possible embodiment, the first loss calculation module 16101 includes a first passage probability determination module, a probability density function calculation module, a speed expectation calculation module, a third loss calculation module, and a fourth loss calculation module: The first passage probability determination module is used to determine the first passage probability at a certain moment in each green light time sequence segment of each traffic light intersection on the target route based on the current state of the vehicle and the probability distribution of passage time for each road segment; wherein, each green light time sequence segment corresponds to a green light passage window period; The probability density function calculation module is used to calculate, based on the first traffic probability, the first probability density function corresponding to the time difference between a vehicle arriving at the second time in the second green light time segment of the first traffic light intersection from the first time in the first green light time segment, and the second probability density function corresponding to the time difference between a vehicle arriving at the fourth time in the fourth green light time segment of the first traffic light intersection from the third time in the third green light time segment of the third traffic light intersection; wherein, the third traffic light intersection is an upstream traffic light intersection adjacent to the first traffic light intersection; The speed expectation calculation module is used to calculate the first speed expectation of a vehicle from the first traffic light intersection to the second traffic light intersection and the second speed expectation of a vehicle from the third traffic light intersection to the first traffic light intersection, respectively, based on the first probability density function and the second probability density function. The third loss calculation module is used to calculate the first energy loss based on the expected first velocity. The fourth loss calculation module is used to calculate the second energy loss based on the first velocity expectation and the second velocity expectation.

[0127] In a preferred embodiment, the first loss calculation module 16101 further includes a second passage probability determination module, which is used to calculate the second passage probability of a vehicle arriving at the second green light time segment of the second traffic light intersection from the first time segment of the first traffic light intersection based on the first passage probability, and the second loss calculation module 16102 is used to calculate the node energy loss based on the first energy loss, the second energy loss and the second passage probability.

[0128] In one possible embodiment, the first passage probability determination module includes a green light timing determination module, a passage time probability distribution determination module, and a passage probability calculation module. The green light sequence determination module is used to determine multiple green light passage windows for each traffic light intersection based on the current state of the vehicle and the probability distribution of passage time for each road segment, thus forming the green light sequence of the traffic light intersection. The travel time probability distribution determination module is used to determine the travel time probability distribution of a vehicle from the starting point of the target route to each traffic light intersection on the target route based on the travel time probability distribution of each road segment. The passage probability calculation module is used to determine the first passage probability at a certain moment in each green light time sequence segment of the traffic light intersection based on the passage time probability distribution of each traffic light intersection.

[0129] In one possible embodiment, the green light timing determination module includes a passage time determination module, a correction module, and an extraction module: The passage time determination module is used to determine the earliest and latest passage time at each traffic light intersection based on the current state of the vehicle and according to the upper and lower speed limits. The modification module is used to correct the first earliest passage time and the first latest passage time to form the second earliest passage time and the second latest passage time for each traffic light intersection, thus forming the initial passage period for the traffic light intersection; wherein, the second earliest passage time and the second latest passage time are the start or end time of the green light passage window period; The extraction module is used to extract the green light window period within the initial traffic flow period of each traffic light intersection, forming the green light sequence of the traffic light intersection.

[0130] In one possible embodiment, the correction module is further configured to: If the first latest passage time is feasible, and the first earliest passage time or the first latest passage time is not a green light passage window, then the first earliest passage time or the first latest passage time is set as the start time of the next green light passage window or the last time of the previous green light passage window, thus forming the second earliest passage time or the second latest passage time.

[0131] In one possible embodiment, the correction module is further configured to: If the first latest passage time at the fourth traffic light intersection does not meet the requirements, the first latest passage time at the fourth traffic light intersection will be adjusted based on the vehicle speed limit and the second latest passage time at the fifth traffic light intersection downstream of the fourth traffic light intersection.

[0132] In one possible embodiment, the correction module is further configured to: If the revised first latest passage time of the fourth traffic light intersection is not the green light passage window, then the first latest passage time of the fourth traffic light intersection will be set to the last moment of the previous green light passage window, forming the second latest passage time of the fourth traffic light intersection.

[0133] Figure 17 This is a schematic diagram of the structure of the electronic device provided in this application, such as... Figure 17As shown, the electronic device may include: a processor 1710, a communications interface 1720, a memory 1730, and a communication bus 1740. The processor 1710, communications interface 1720, and memory 1730 communicate with each other via the communication bus 1740. The processor 1710 can call logical instructions in the memory 1730 to execute a global vehicle speed planning method. This method includes: calculating a first historical vehicle speed distribution for the target route using historical driving speed information, where the first historical vehicle speed distribution is a probability distribution of historical vehicle speed with mileage; calculating the probability distribution of travel time for each segment on the target route based on the first historical vehicle speed distribution; and calculating the target average vehicle speed for each segment based on the probability distribution of travel time for each segment and the current state of the vehicle, to obtain a global vehicle speed planning scheme for the vehicle traveling on the target route. The current state includes the current driving condition and the current position.

[0134] Furthermore, the logical instructions in the aforementioned memory 1730 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0135] On the other hand, this application also provides a computer program product, which includes a computer program stored on a non-transitory computer-readable storage medium. The computer program includes program instructions, and when the program instructions are executed by a computer, the computer can execute the global vehicle speed planning method provided in the above embodiments. The method includes: calculating a first historical vehicle speed distribution of the target route using historical driving speed information of the target route, wherein the first historical vehicle speed distribution is a probability distribution of historical vehicle speed with mileage; calculating the travel time probability distribution of each road segment on the target route based on the first historical vehicle speed distribution; and calculating the target average vehicle speed of each road segment based on the travel time probability distribution of each road segment and the current state of the vehicle, so as to obtain a global vehicle speed planning scheme for the vehicle to travel on the target route; wherein the current state includes the current driving condition and the current position.

[0136] In another aspect, this application also provides a non-transitory computer-readable storage medium storing a computer program thereon. When executed by a processor, the computer program is implemented to perform the global vehicle speed planning method provided in the above embodiments. The method includes: calculating a first historical vehicle speed distribution of the target route using historical driving speed information of the target route, wherein the first historical vehicle speed distribution is a probability distribution of historical vehicle speed with mileage; calculating the travel time probability distribution of each road segment on the target route based on the first historical vehicle speed distribution; and calculating the target average vehicle speed of each road segment based on the travel time probability distribution of each road segment and the current state of the vehicle, so as to obtain a global vehicle speed planning scheme for the vehicle to travel on the target route; wherein the current state includes the current driving condition and the current position.

[0137] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0138] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0139] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application.

Claims

1. A global vehicle speed planning method, characterized by, The method comprises the following steps: calculating a first historical speed distribution of the target route by using historical driving speed information of the target route, the first historical speed distribution being a probability distribution of historical speed with respect to mileage; calculating a passing time probability distribution of each road section on the target route according to the first historical speed distribution; calculating a target average speed of each road section according to the passing time probability distribution of each road section and a current state of the vehicle, so as to obtain a global speed planning scheme for the vehicle driving on the target route; wherein the current state comprises a current driving condition and a current position.

2. The global vehicle speed planning method of claim 1, wherein, The method for calculating the first historical speed distribution of the target route by using historical driving speed information of the target route comprises the following steps: collecting driving information of the vehicle on the target route at different time periods, the driving information comprising speed and driving mileage; constructing a data set by taking mileage as a feature vector and taking mean value and variance of historical speed as prediction quantities; predicting a speed probability distribution at each mileage on the target route based on the data set.

3. The global vehicle speed planning method of claim 1, wherein, The method for calculating the passing time probability distribution of each road section on the target route according to the first historical speed distribution comprises the following steps: dividing the target route into a plurality of road sections according to distribution of traffic lights; obtaining a second historical speed distribution of each road section based on the first historical speed distribution; obtaining a plurality of passing times of each road section based on the second historical speed distribution of each road section; fitting a passing time probability distribution of each road section based on the plurality of passing times of each road section.

4. The global vehicle speed planning method of claim 1, wherein, The method for calculating the target average speed of each road section according to the passing time probability distribution of each road section and the current state of the vehicle comprises the following steps: solving optimal passing time of each traffic light on the target route under a spatiotemporal coupling constraint, with the objective of minimizing economic cost, according to the passing time probability distribution of each road section and the current state of the vehicle; calculating the target average speed of each road section according to the optimal passing time of each traffic light and distance between adjacent traffic lights.

5. The global vehicle speed planning method of claim 4, wherein, The method for solving the optimal passing time of each traffic light on the target route comprises the following steps: calculating node energy loss of the vehicle passing through each road section on the target route according to the passing time probability distribution of each road section based on the current state of the vehicle; obtaining the optimal passing time period of each traffic light on the target route by optimization based on the node energy loss and the current position of the vehicle; constructing an objective function with the objective of minimizing economic cost under a spatiotemporal coupling constraint, and solving the corresponding optimal passing time within the optimal passing time period of each traffic light.

6. The global vehicle speed planning method of claim 5, wherein, The method for calculating the node energy loss of the vehicle passing through each road section on the target route comprises the following steps: calculating first energy loss of the vehicle driving from a first traffic light to a second traffic light and second energy loss of the vehicle passing through the first traffic light according to the passing time probability distribution of each road section and the current state of the vehicle; wherein the second traffic light is a downstream traffic light adjacent to the first traffic light. calculating a first energy loss of the vehicle from the first traffic light intersection to the second traffic light intersection and a second energy loss of the vehicle when passing the first traffic light intersection, specifically comprising:

7. The global vehicle speed planning method of claim 6, wherein, calculating a first energy loss of the vehicle from the first traffic light intersection to the second traffic light intersection and a second energy loss of the vehicle when passing the first traffic light intersection, specifically comprising: calculating a first energy loss of the vehicle from the first traffic light intersection to the second traffic light intersection and a second energy loss of the vehicle when passing the first traffic light intersection, specifically comprising: calculating a first energy loss of the vehicle from the first traffic light intersection to the second traffic light intersection and a second energy loss of the vehicle when passing the first traffic light intersection, specifically comprising: calculating a first energy loss of the vehicle from the first traffic light intersection to the second traffic light intersection and a second energy loss of the vehicle when passing the first traffic light intersection, specifically comprising: calculating a first energy loss of the vehicle from the first traffic light intersection to the second traffic light intersection and a second energy loss of the vehicle when passing the first traffic light intersection, specifically comprising: calculating a first energy loss of the vehicle from the first traffic light intersection to the second traffic light intersection and a second energy loss of the vehicle when passing the first traffic light intersection, specifically comprising:

8. The global vehicle speed planning method of claim 7, wherein, calculating a first energy loss of the vehicle from the first traffic light intersection to the second traffic light intersection and a second energy loss of the vehicle when passing the first traffic light intersection, specifically comprising: calculating a first energy loss of the vehicle from the first traffic light intersection to the second traffic light intersection and a second energy loss of the vehicle when passing the first traffic light intersection, specifically comprising: calculating a first energy loss of the vehicle from the first traffic light intersection to the second traffic light intersection and a second energy loss of the vehicle when passing the first traffic light intersection, specifically comprising:

9. The global vehicle speed planning method of claim 7, wherein, calculating a first energy loss of the vehicle from the first traffic light intersection to the second traffic light intersection and a second energy loss of the vehicle when passing the first traffic light intersection, specifically comprising: calculating a first energy loss of the vehicle from the first traffic light intersection to the second traffic light intersection and a second energy loss of the vehicle when passing the first traffic light intersection, specifically comprising: calculating a first energy loss of the vehicle from the first traffic light intersection to the second traffic light intersection and a second energy loss of the vehicle when passing the first traffic light intersection, specifically comprising: calculating a first energy loss of the vehicle from the first traffic light intersection to the second traffic light intersection and a second energy loss of the vehicle when passing the first traffic light intersection, specifically comprising:

10. The global vehicle speed planning method of claim 9, wherein, calculating a first energy loss of the vehicle from the first traffic light intersection to the second traffic light intersection and a second energy loss of the vehicle when passing the first traffic light intersection, specifically comprising: calculating a first energy loss of the vehicle from the first traffic light intersection to the second traffic light intersection and a second energy loss of the vehicle when passing the first traffic light intersection, specifically comprising: calculating a first energy loss of the vehicle from the first traffic light intersection to the second traffic light intersection and a second energy loss of the vehicle when passing the first traffic light intersection, specifically comprising: calculating a first energy loss of the vehicle from the first traffic light intersection to the second traffic light intersection and a second energy loss of the vehicle when passing the first traffic light intersection, specifically comprising: calculating a first energy loss of the vehicle from the first traffic light intersection to the second traffic light intersection and a second energy loss of the vehicle when passing the first traffic light intersection, specifically comprising: calculating a first energy loss of the vehicle from the first traffic light intersection to the second traffic light intersection and a second energy loss of the vehicle when passing the first traffic light intersection, specifically comprising: calculating a first energy loss of the vehicle from the first traffic light intersection to the second traffic light intersection and a second energy loss of the vehicle when passing the first traffic light intersection, specifically comprising: calculating a first energy loss of the vehicle from the first traffic light intersection to the second traffic light intersection and a second energy loss of the vehicle when passing the first traffic light intersection, specifically comprising: calculating a first energy loss of the vehicle from the first traffic light intersection to the second traffic light intersection and a second energy loss of the vehicle when passing the first traffic light intersection, specifically comprising: calculating a first energy loss of the vehicle from the first traffic light intersection to the second traffic light intersection and a second energy loss of the vehicle when passing the first traffic light intersection, specifically comprising: calculating a first energy loss of the vehicle from the first traffic light intersection to the second traffic light intersection and a second energy loss of the vehicle when passing the first traffic light intersection, specifically comprising: calculating a first energy loss of the vehicle from the first traffic light intersection to the second traffic light intersection and a second energy loss of the vehicle when passing the first traffic light intersection, specifically comprising: calculating a first energy loss of the vehicle from the first traffic light intersection to the second traffic light intersection and a second energy loss of the vehicle when passing the first traffic light intersection, specifically comprising: calculating a first energy loss of the vehicle from the first traffic light intersection to the second traffic light intersection and a second energy loss of the vehicle when passing the first traffic light intersection, specifically comprising: calculating a first energy loss of the vehicle from the first traffic light intersection to the second traffic light intersection and a second energy loss of the vehicle when passing the first traffic light intersection, specifically comprising: calculating a first energy loss of the vehicle from the first traffic light intersection to the second traffic light intersection and a second energy loss of the vehicle when passing the first traffic light intersection, specifically comprising: calculating a first energy loss of the vehicle from the first traffic light intersection to the second traffic light intersection and a second energy loss of the vehicle when passing the first traffic light intersection, specifically comprising: calculating a first energy loss of the vehicle from the first traffic light intersection to the second traffic light intersection and a second energy loss of the vehicle when passing the first traffic light intersection, specifically comprising: calculating a first energy loss of the vehicle from the first traffic light intersection to the second traffic light intersection and a second energy loss of the vehicle when passing the first traffic light intersection, specifically comprising: calculating a first energy loss of the vehicle from the first traffic light intersection to the second traffic light intersection and a second energy loss of the vehicle when passing the first traffic light intersection, specifically comprising: calculating a first energy loss of the vehicle from the first traffic light intersection to the second traffic light intersection and a second energy loss of the vehicle when passing the first traffic light intersection, specifically comprising: calculating a first energy loss of the vehicle from the first traffic light intersection to the second traffic light intersection and a second energy loss of the vehicle when passing the first traffic light intersection, specifically comprising: calculating a first energy loss of the vehicle from the first traffic light intersection to the second traffic light intersection and a second energy loss of the vehicle when passing the first traffic light intersection, specifically comprising: calculating a first energy loss of the vehicle from the first traffic light intersection to the second traffic light intersection and a second energy loss of the vehicle when passing the first traffic light intersection, specifically comprising: calculating a first energy loss of the vehicle from the first traffic light intersection to the second traffic light intersection and a second energy loss of the vehicle when passing the first traffic light intersection, specifically comprising: calculating a first energy loss of the vehicle from the first traffic light intersection to the second traffic light intersection and a second energy loss of the vehicle when passing the first traffic light intersection, specifically comprising: calculating a first energy loss of the vehicle from the first traffic light intersection to the second traffic light intersection and a second energy loss of the vehicle when passing the first traffic light intersection, specifically comprising: calculating a first energy loss of the vehicle from the first traffic light intersection to the second traffic light intersection and a second energy loss of the vehicle when passing the first traffic light intersection, specifically comprising: calculating a first energy loss of the vehicle from the first traffic light intersection to the second traffic light intersection and a second energy loss of the vehicle when passing the first traffic light intersection, specifically comprising: calculating a first energy loss of the vehicle from the first traffic light intersection to the second traffic light intersection and a second energy loss of the vehicle when passing the first traffic light intersection, specifically comprising: calculating a first energy loss of the vehicle from the first traffic light intersection to the second traffic light intersection and a second energy loss of the vehicle when passing the first traffic light intersection, specifically comprising: calculating a first energy loss of the vehicle from the first traffic light intersection to the second traffic light intersection and a second energy loss of the vehicle when passing the first traffic light intersection, specifically comprising: calculating a first energy loss of the vehicle from the first traffic light intersection to the second traffic light intersection and a second energy loss of the vehicle when passing the first traffic light intersection, specifically comprising: calculating a first energy loss of the vehicle from the first traffic light intersection to the second traffic light intersection and a second energy loss of the vehicle when passing the first traffic light intersection, specifically comprising: calculating a first energy loss of the vehicle from the first traffic light intersection to the second traffic light intersection and a second energy loss of the vehicle when passing the first traffic light intersection, specifically comprising: calculating a first energy loss of the vehicle from the first traffic light intersection to the second traffic light intersection and a second energy loss of the vehicle when passing the first traffic light intersection, specifically comprising: calculating a first energy loss of the vehicle from the first traffic light intersection to the second traffic light intersection and a second energy loss of the vehicle when passing the first traffic light intersection, specifically comprising: calculating a first energy loss of the correcting the first earliest passing time and the first latest passing time to form a second earliest passing time and a second latest passing time of each traffic light intersection, and forming an initial passing period of the traffic light intersection; wherein the second earliest passing time and the second latest passing time are start time or end time of a green light passing window period; extracting a green light passing window period in the initial passing period of each traffic light intersection to form a green light timing of the traffic light intersection.

11. The global vehicle speed planning method of claim 10, wherein, correcting the first earliest passing time and the first latest passing time to form a second earliest passing time and a second latest passing time of each traffic light intersection, and forming an initial passing period of the traffic light intersection; wherein the second earliest passing time and the second latest passing time are start time or end time of a green light passing window period; correcting the first earliest passing time and the first latest passing time to form a second earliest passing time and a second latest passing time of each traffic light intersection, and forming an initial passing period of the traffic light intersection; wherein the second earliest passing time and the second latest passing time are start time or end time of a green light passing window period; 12. The global vehicle speed planning method of claim 11, wherein, correcting the first earliest passing time and the first latest passing time to form a second earliest passing time and a second latest passing time of each traffic light intersection, and forming an initial passing period of the traffic light intersection; wherein the second earliest passing time and the second latest passing time are start time or end time of a green light passing window period; correcting the first earliest passing time and the first latest passing time to form a second earliest passing time and a second latest passing time of each traffic light intersection, and forming an initial passing period of the traffic light intersection; wherein the second earliest passing time and the second latest passing time are start time or end time of a green light passing window period; 13. The global vehicle speed planning method of claim 12, wherein, correcting the first earliest passing time and the first latest passing time to form a second earliest passing time and a second latest passing time of each traffic light intersection, and forming an initial passing period of the traffic light intersection; wherein the second earliest passing time and the second latest passing time are start time or end time of a green light passing window period; comprising a first historical distribution calculation module, a road section passing probability distribution calculation module, and a target average speed calculation module; 14. A global vehicle speed planning device characterized by comprising: the first historical distribution calculation module is configured to calculate a first historical speed distribution of a target route by using historical driving speed information of the target route, the first historical speed distribution being a probability distribution of historical speed with respect to mileage; the road section passing probability distribution calculation module is configured to calculate a passing time probability distribution of each road section on the target route according to the first historical speed distribution; the target average speed calculation module is configured to calculate a target average speed of each road section according to the passing time probability distribution of each road section and a current state of the vehicle, so as to obtain a global speed planning scheme for driving of the vehicle on the target route; wherein the current state comprises a current driving condition and a current position. The processor executes the computer program to implement the global speed planning method according to any one of claims 1 to 13.

15. An electronic device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein, The computer program is executed by the processor to implement the global speed planning method according to any one of claims 1 to 13. 16.A non-transitory computer-readable storage medium having stored thereon a computer program, wherein, ​ 17. A computer program product comprising a computer program, characterized in that, The computer program, when executed by a processor, implements the global vehicle speed planning method according to any one of claims 1 to 13.

Images