A vehicle lane-changing decision method and system for mixed passenger and freight traffic scenarios

Abstract

The present invention discloses a vehicle lane-changing decision method and system for mixed passenger and freight traffic. The method includes obtaining vehicle driving data through sensing equipment; constructing a truck longitudinal pressure state evaluation model, a bus longitudinal pressure state evaluation model and a lane line pressure state evaluation model, and calculating the truck longitudinal pressure degree, bus longitudinal pressure degree and lane line pressure degree suffered by the vehicle; constructing a vehicle lateral pressure state evaluation model obtained by converting the longitudinal pressure degree, calculating the lateral pressure degree suffered by the vehicle, constructing a lane-changing decision optimization model based on the pressure degree, and determining the vehicle lane-changing decision. The solution provided by the present invention is aimed at mixed passenger and freight traffic scenarios, fully considering the pressure effect of different types of vehicles such as trucks or buses on the vehicle, and proposes the lateral pressure degree, which is a fusion lane-changing index that characterizes the pressure effect of the fusion of passenger and freight vehicles, so that the lane-changing comfort of the vehicle lane-changing decision determined by the present application is high and not easily affected by trucks.

Description

Technical Field

[0001] The present invention relates to the technical field of vehicle lane-changing decision technology, and in particular to a vehicle lane-changing decision method and system for a mixed passenger and freight traffic scenario. Background Art

[0002] Due to the diversity of vehicle types and large differences in traffic speeds, there are many frequent and unsafe dangerous lane-changing behaviors in road traffic. In particular, the differentiated driving characteristics between buses and trucks result in potential pressure on the lane-changing of buses by surrounding trucks, resulting in low traffic flow and reduced driver comfort. In order to improve road operation efficiency, traffic flow, and driver comfort, it is necessary to optimize lane-changing decisions in mixed passenger and freight traffic environments.

[0003] The current inventions for lane change decision optimization mainly include rule models, discrete choice models, artificial intelligence models, Markov models, physiological-psychological models and survival models. The methods for realizing path planning for complex traffic scenes in the prior art are mainly implemented in the following ways:

[0004] 1. Consider the state changes of the vehicle before and after changing lanes in the model, including changes in acceleration, speed, and safety distance, and determine the optimal state moment of lane changing through the lane changing decision model. For example, Chinese patent CN110228473B discloses a lane changing decision method, device, storage medium, and smart car for smart vehicles. The patent collects lane changing environment information and determines the lane changing decision rule based on the vehicle state being better after lane changing.

[0005] 2. Training lane-changing decision models based on deep learning. For example, the unmanned vehicle lane-changing decision method and system based on adversarial imitation learning disclosed in Chinese patent CN111483468A. This patent describes the vehicle lane-changing decision task as a partially observable Markov decision process, and uses adversarial imitation learning to train from examples provided by professional driving demonstrations to obtain a vehicle lane-changing decision model.

[0006] At present, all the lane-changing decision models related to vehicle lane-changing decisions set the vehicle types to be homogenous, without distinguishing the differences between passenger and freight vehicles, and lack relevant research on the lane-changing driving behavior of trucks against passenger buses. Moreover, most of the current lane-changing decision models focus on directly analyzing the state information before and after the lane change to determine the vehicle's lane-changing decision, and lack a fusion lane-changing indicator that characterizes the truck oppression phenomenon. Therefore, the existing lane-changing decision models have the disadvantages of low actual lane-changing comfort and being easily affected by trucks. When the driver activates intelligent driving functions such as assisted driving, the driver's lane-changing experience is often poor. In summary, in the existing technology, it is crucial to add a vehicle lane-changing decision optimization method and system for passenger and freight mixed traffic scenarios. Summary of the invention

[0007] In order to solve the technical problems that the existing lane changing decision model lacks the difference between passenger and freight vehicles and lacks the integrated lane changing index to characterize the oppression phenomenon of trucks, resulting in low actual lane changing comfort and susceptibility to the influence of trucks, the embodiments of the present invention provide a vehicle lane changing decision method and system for passenger and freight mixed traffic scenarios.

[0008] The technical solution of the embodiment of the present invention is achieved as follows:

[0009] The embodiment of the present invention provides a vehicle lane-changing decision method for a mixed passenger-cargo traffic scenario, the method comprising: during the driving process of the vehicle, real-time detection of the vehicle and the surrounding road environment state, and calculation to obtain vehicle driving data; the vehicle driving data comprises characteristic parameters of the vehicle, characteristic parameters of surrounding trucks, and characteristic parameters of surrounding passenger cars; the characteristic parameters of the vehicle comprise the balance distance of the vehicle, the minimum vehicle spacing when the vehicle is parked, the vehicle speed of the vehicle, the minimum safe time headway of the vehicle, the maximum acceleration of the vehicle, the comfortable deceleration of the vehicle, and the quality of the vehicle. the surrounding truck characteristic parameters include the vehicle speed of the front vehicle or the rear vehicle when the front vehicle or the rear vehicle in the same lane as the vehicle is a truck, the vehicle speed difference between the front vehicle and the front vehicle or the rear vehicle when the front vehicle or the rear vehicle is a truck, and the headway between the front vehicle and the front vehicle or the rear vehicle when the front vehicle or the rear vehicle is a truck; the surrounding passenger car characteristic parameters include the vehicle speed of the front vehicle or the rear vehicle when the front vehicle or the rear vehicle in the same lane as the vehicle is a passenger car, the vehicle speed difference between the front vehicle and the front vehicle or the rear vehicle when the front vehicle or the rear vehicle is a passenger car, The head distance between the vehicle and the vehicle in front or behind when the vehicle in front or behind is a passenger car; the passenger car represents a vehicle type that mainly transports people and is less than 6 meters in length; the truck represents a vehicle type that mainly transports goods and is greater than or equal to 6 meters in length; according to the vehicle driving data, using the preset truck longitudinal pressure state evaluation model, bus longitudinal pressure state evaluation model and lane line pressure state evaluation model, respectively obtain the truck longitudinal pressure degree that characterizes the pressure effect of the front and rear trucks on the vehicle during driving, the bus longitudinal pressure degree that characterizes the pressure effect of the front and rear buses on the vehicle during driving, and the lane line pressure degree that characterizes the pressure effect of the surrounding lane lines on the vehicle during driving; according to the truck longitudinal pressure degree, the bus longitudinal pressure degree and the lane line pressure degree, using the preset lateral pressure state evaluation model, obtain the lateral pressure degree that characterizes the pressure effect of the surrounding passenger and freight vehicles when the vehicle changes lanes to the left or right during driving; using the lateral pressure degree and the lane line pressure degree, according to the preset lane change decision optimization model, determine the vehicle lane change decision of the vehicle considering the pressure effect of the surrounding passenger and freight vehicles.

[0010] An embodiment of the present invention also provides a vehicle lane changing decision system for mixed passenger and freight traffic scenarios, comprising: a processor and a memory for storing a computer program that can be run on the processor; wherein, when the processor is used to run the computer program, it executes the steps of any of the above methods.

[0011] An embodiment of the present invention further provides a storage medium, in which a computer program is stored. When the computer program is executed by a processor, the steps of any of the above methods are implemented.

[0012] This embodiment has the following advantages:

[0013] (1) This embodiment aims at the pressure effects of passenger and freight vehicles on the driving process of the vehicle in a mixed passenger and freight traffic scenario, constructs a truck longitudinal pressure state evaluation model and a bus longitudinal pressure state evaluation model, and realizes the distinction between passenger and freight vehicles in a mixed passenger and freight traffic scenario.

[0014] (2) Based on the longitudinal pressure degree, this embodiment proposes the lateral pressure degree, which is a fusion lane changing index that characterizes the fusion pressure effect of passenger and freight vehicles. This makes the lane changing decision of the vehicle determined by this application more comfortable and less susceptible to the influence of trucks. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 It is a flowchart of a vehicle lane-changing decision method for a mixed passenger and freight traffic scenario according to an embodiment of the present invention;

[0016] Figure 2 Schematic diagram of a lane-changing scenario K at a certain moment in an embodiment of the present invention;

[0017] Figure 3 A schematic diagram illustrating conversion between longitudinal compression degree and transverse compression degree according to an embodiment of the present invention;

[0018] Figure 4 1 is a diagram showing the internal structure of a computer device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0019] The present invention will be described in further detail below with reference to the accompanying drawings and embodiments.

[0020] The embodiment of the present invention provides a vehicle lane change decision method for a mixed passenger and freight traffic scenario. Figure 1 As shown, the method includes:

[0021] Step 101: During the driving process of the vehicle, the vehicle and the surrounding road environment are detected in real time, and the vehicle driving data is calculated;

[0022] The vehicle driving data includes characteristic parameters of the vehicle, characteristic parameters of surrounding trucks and characteristic parameters of surrounding passenger cars; the characteristic parameters of the vehicle include the balance distance of the vehicle, the minimum vehicle spacing when the vehicle is parked, the vehicle speed of the vehicle, the minimum safe time distance of the vehicle, the maximum acceleration of the vehicle, the comfortable deceleration of the vehicle, the mass of the vehicle, the lateral distance between the vehicle and the lane line, the headway of the vehicle, and the lane changing space of the vehicle; the characteristic parameters of surrounding trucks include the vehicle speed of the front vehicle or the rear vehicle when the front vehicle or the rear vehicle in the same lane as the vehicle is a truck, the vehicle speed difference between the vehicle and the front vehicle or the rear vehicle when the front vehicle or the rear vehicle is a truck, and the headway of the vehicle between the vehicle and the front vehicle or the rear vehicle when the front vehicle or the rear vehicle is a truck; the characteristic parameters of surrounding passenger cars include the vehicle speed of the front vehicle or the rear vehicle when the front vehicle or the rear vehicle in the same lane as the vehicle is a passenger car, the vehicle speed difference between the vehicle and the front vehicle or the rear vehicle when the front vehicle or the rear vehicle is a passenger car, and the headway of the vehicle between the vehicle and the front vehicle or the rear vehicle when the front vehicle or the rear vehicle is a passenger car;

[0023] Step 102: According to the vehicle driving data, using a preset truck longitudinal pressure state evaluation model, a bus longitudinal pressure state evaluation model, and a lane line pressure state evaluation model, respectively obtain a truck longitudinal pressure degree representing the pressure effect of front and rear trucks on the vehicle during driving, a bus longitudinal pressure degree representing the pressure effect of front and rear buses on the vehicle during driving, and a lane line pressure degree representing the pressure effect of surrounding lane lines on the vehicle during driving;

[0024] Step 103: According to the longitudinal compression degree of the truck, the longitudinal compression degree of the passenger car and the lane line compression degree, a preset lateral compression state evaluation model is used to obtain a lateral compression degree that represents the influence of the fusion compression of surrounding passenger and freight vehicles on the vehicle when the vehicle changes lanes to the left or right during driving;

[0025] Step 104: using the lateral pressure degree and the lane line pressure degree, according to a preset lane change decision optimization model, determine the vehicle lane change decision of the vehicle taking into account the impact of the fusion pressure of surrounding passenger and freight vehicles.

[0026] This embodiment is mainly a vehicle lane change decision method proposed for mixed passenger and freight traffic scenarios. In actual lane change scenarios, vehicles may face a variety of complex lane change scenarios, such as a passenger car or a truck in front and behind the current lane, or a passenger car or a truck in front and behind the adjacent lane. By distinguishing the types of vehicles in the scenario, the vehicle lane change decision of this application can better meet the needs of current complex scenarios.

[0027] Specifically, see Figure 2 This embodiment will use a specific scenario to explain the solution of this embodiment in detail.

[0028] like Figure 2 As shown, at a certain time K, the vehicle (i.e. Figure 2 The target vehicle in the current lane is a large truck, there is no vehicle behind the current lane, there is no vehicle ahead in the left adjacent lane, and the vehicle behind the left adjacent lane is a car. Based on this scenario, the process of calculating the vehicle lane change decision in this embodiment may specifically include the following contents:

[0029] S01, for a mixed passenger and freight traffic scenario, obtain vehicle driving data.

[0030] In this embodiment, the Figure 2 The vehicle-mounted device in the vehicle obtains the trajectory data of the vehicle (also called the current vehicle), other vehicle data and environmental data, etc., and then obtains the vehicle driving data by calculating the above data.

[0031] The current vehicle trajectory data, other vehicle data and environmental data may specifically include the following contents: the current vehicle's position coordinates, lane, instantaneous speed, acceleration, vehicle type, vehicle length, vehicle mass, vehicle comfortable deceleration, vehicle maximum acceleration, headway, lane line type, the spacing between lane lines at the current vehicle's position, the number of lanes, the distance between the front and rear vehicles in the same lane as the current vehicle, the speed of the front and rear vehicles, and the type of front and rear vehicles, the distance between the front and rear vehicles in the left and right lanes of the current vehicle, the speed of the front and rear vehicles, and the type of front and rear vehicles, etc.

[0032] The vehicle driving data may specifically include the following contents: characteristic parameters of the vehicle, characteristic parameters of surrounding trucks and characteristic parameters of surrounding passenger cars; wherein the characteristic parameters of the vehicle include the balance distance of the vehicle, the minimum vehicle spacing when the vehicle stops, the vehicle speed of the vehicle, the minimum safe time distance of the vehicle, the maximum acceleration of the vehicle, the comfortable deceleration of the vehicle, the mass of the vehicle, the lateral distance between the vehicle and the lane line, the headway of the vehicle, the lane changing space of the vehicle, etc. The characteristic parameters of surrounding trucks include the vehicle speed of the preceding vehicle or the following vehicle when the preceding vehicle or the following vehicle in the same lane as the vehicle is a truck, the vehicle speed difference between the preceding vehicle and the preceding vehicle or the following vehicle when the preceding vehicle or the following vehicle is a truck, and the headway of the preceding vehicle and the preceding vehicle when the preceding vehicle or the following vehicle is a truck, etc. The characteristic parameters of surrounding passenger vehicles include the vehicle speed of the preceding vehicle or the following vehicle when the preceding vehicle or the following vehicle in the same lane as the vehicle is a passenger car, the vehicle speed difference between the preceding vehicle and the preceding vehicle or the following vehicle when the preceding vehicle or the following vehicle is a passenger car, and the head distance between the preceding vehicle and the preceding vehicle or the following vehicle when the preceding vehicle or the following vehicle is a passenger car.

[0033] In this embodiment, data is collected and acquired through vehicle-mounted equipment. In actual application, the above data can also be acquired through other equipment, such as collection devices or monitoring devices set on both sides of the road. This embodiment does not limit the data collection method.

[0034] The vehicle-mounted equipment may include sensing equipment and computing units. The sensing equipment includes radar, camera, integrated radar and vision detector, etc., which can sense the vehicle movement position, speed, traffic flow and other traffic elements at the sub-second level in real time, and the sensing interval can be 0.1 seconds. The computing unit includes an on-board computer, etc., which pre-processes the data sensed by the sensing equipment, extracts the sensed environmental data and vehicle movement trajectory with an accuracy higher than 90%, and stores such data at each time step as historical data.

[0035] In actual applications, after data is collected, there are often missing values, abnormal values, and duplicate values. In order to ensure data quality and improve calculation accuracy, this embodiment can fill missing values ​​in the data through interpolation, process abnormal values ​​through the Loess smoothing method, and process duplicate values ​​through de-duplication and merging. Through the above cleaning and preprocessing, high-quality data can be obtained for subsequent calculations.

[0036] S02, based on the MORSE potential function, a longitudinal oppression state evaluation model is used (in this embodiment, in order to distinguish the difference between passenger and freight vehicles in the scene, the longitudinal oppression state evaluation model is further divided into a truck longitudinal oppression state evaluation model and a bus longitudinal oppression state evaluation model) and a lane oppression state evaluation model to calculate the bus longitudinal vehicle oppression degree of the vehicle at time t Longitudinal vehicle pressure of truck and lane pressure The calculation formula is as follows:

[0037] The calculation formula of the evaluation model of the longitudinal compression state of trucks is:

[0038]

[0039] Among them, r e represents the equilibrium distance of the vehicle, s0 represents the minimum vehicle spacing when the vehicle stops, v0 represents the vehicle speed of the vehicle in front of or behind the vehicle, v represents the vehicle speed of the vehicle, Δv represents the vehicle speed difference between the vehicle and the vehicle in front of or behind the vehicle, T is the minimum safe time distance of the vehicle, a max 、b com They represent the maximum acceleration and comfortable deceleration of the vehicle respectively. It indicates the longitudinal pressure of the bus when the front or rear vehicle is a bus, r is the distance between the vehicle and the front or rear vehicle, a C , D C , is the model coefficient, e represents the base of the natural logarithm;

[0040] The calculation formula of the evaluation model of the longitudinal compression state of buses is:

[0041]

[0042] Among them, r e represents the equilibrium distance of the vehicle, s0 represents the minimum vehicle spacing when the vehicle stops, v0 represents the vehicle speed of the vehicle in front of or behind the vehicle, v represents the vehicle speed of the vehicle, Δv represents the vehicle speed difference between the vehicle and the vehicle in front of or behind the vehicle, T is the minimum safe time distance of the vehicle, a max 、b com They represent the maximum acceleration and comfortable deceleration of the vehicle respectively. It indicates the longitudinal pressure of the truck when the front or rear vehicle is a truck, r is the distance between the vehicle and the front or rear vehicle, a T , D T , is the model coefficient, and e represents the base of the natural logarithm.

[0043] The calculation formula of the lane line pressure state evaluation model is:

[0044]

[0045] in, is the lane line pressure when the lane line is a dotted line, When x is equal to L or R, it represents the lane line pressure degree with the left dotted lane line and the lane line pressure degree with the right dotted lane line respectively, m is the mass of the vehicle, v is the vehicle speed of the vehicle, d is the lateral distance between the vehicle and the lane line, α, β, σ are model coefficients; when the lane line is a solid line, the lane line pressure degree is infinite, and e represents the base of the natural logarithm.

[0046] The lane line pressure state evaluation model in this embodiment is obtained by improving the Gaussian potential function to describe the pressure effect of the lane line on the vehicle. The lane line pressure degree can make the vehicle still drive straight in the lane when there are no other vehicles around.

[0047] The longitudinal compression state evaluation model is obtained by improving the MORSE potential function. The model is used to describe the compression phenomenon generated when a vehicle and a passenger truck are running closely together. This embodiment mainly divides the longitudinal compression state evaluation model into a truck longitudinal compression state evaluation model and a passenger truck longitudinal compression state evaluation model according to the front and rear vehicle types. In actual application, in order to further distinguish the difference in vehicle types in the scene, the longitudinal compression state evaluation model can also be divided into the following 4 types of longitudinal compression state evaluation models based on the front and rear vehicle types and according to the vehicle type.

[0048] The four types of longitudinal compression status evaluation models are divided as follows:

[0049] 1) CT model for evaluating the longitudinal compression state of a car when it is compressed by large trucks in front and behind;

[0050] 2) The longitudinal compression state evaluation model CC when a car is compressed by the car in front;

[0051] 3) The longitudinal compression state evaluation model TC of a large truck when it is compressed by a car in front;

[0052] 4) The longitudinal compression state evaluation model TT of a large truck when it is compressed by the large truck in front;

[0053] The calculation formulas of the longitudinal compression state evaluation model CT, CC, TC and TT are as follows:

[0054]

[0055]

[0056] in, Indicates the balance distance when the current vehicle is a car and when the current vehicle is a truck. They represent the longitudinal pressure of the front and rear cars and the longitudinal pressure of the front and rear trucks at the current moment, respectively. v0, v, and Δv are the speeds of the front car, the current car, and the speed difference between the two cars, respectively. They represent the maximum acceleration and comfortable deceleration when the current vehicle is a car. They represent the maximum acceleration and comfortable deceleration when the current vehicle is a truck. They represent the minimum parking distance when the current vehicle is a car and when the current vehicle is a truck, T is the minimum safe time distance between vehicles, r is the distance between the current vehicle and the front vehicle, and a C , D C , a T , D T , are the unknown coefficients of the model, and e represents the base of the natural logarithm.

[0057] Before applying the truck longitudinal pressure state evaluation model, bus longitudinal pressure state evaluation model and lane line pressure state evaluation model of this embodiment, a particle swarm algorithm based on a chaotic inertia weight strategy can be used to classify and calibrate the model to determine the model parameters in the model, and then the calibrated truck longitudinal pressure state evaluation model, bus longitudinal pressure state evaluation model and lane line pressure state evaluation model can be used for calculation.

[0058] Here, the calibration may be performed by calibrating 10 times and taking an average value of the parameter calibration results. The calibration results of this embodiment are shown in Table 1 and Table 2 below.

[0059] Table 1

[0060]

[0061] Table 2

[0062] Lane line parameters Parameter Description bus truck α Lane pressure coefficient 0.57 0.81 β Lane speed discount factor 1.72 2.37 σ Lane line coefficient to be determined 1.51 0.96

[0063] S03, constructing a lateral pressure state evaluation model (including a single lane lateral pressure state evaluation model and a fusion lane lateral pressure state evaluation model), performing dimensionality conversion on the longitudinal pressure degree, and calculating the lateral vehicle pressure degree of the current vehicle at time t.

[0064] The single-lane lateral pressure state evaluation model is used to obtain the single-lane lateral pressure degree that characterizes the impact of the integrated pressure of the front and rear passenger and freight vehicles on the vehicle during its driving process based on the longitudinal pressure degree of the truck, the longitudinal pressure degree of the bus and the pressure degree of the lane line; the integrated lane lateral pressure state evaluation model is used to obtain the lateral pressure degree that characterizes the impact of the integrated pressure of the surrounding passenger and freight vehicles when the vehicle changes lanes to the left or right during its driving process based on the single-lane lateral pressure degree.

[0065] Specifically, the single lane lateral pressure state evaluation model is:

[0066]

[0067] in, Indicates the lateral pressure of a single lane. Indicates the longitudinal pressure of a bus when the front or rear vehicle is a bus. Indicates the longitudinal pressure of a truck when the front or rear vehicle is a truck.

[0068] The evaluation model of fusion lane lateral pressure state is:

[0069]

[0070] Among them, Y e L , Y e R They respectively represent the lateral pressure degree of the surrounding passenger and freight vehicles when the vehicle changes lanes to the left and the lateral pressure degree of the surrounding passenger and freight vehicles when the vehicle changes lanes to the right. They are the lane pressure between the left dashed lane line and the right dashed lane line when the vehicle has not started to change lanes to the left, and the lane pressure between the right dashed lane line and the right dashed lane line when the vehicle has not started to change lanes to the right. They are respectively the single-lane lateral pressure degree of the vehicles in front and behind the current lane on the vehicle, the single-lane lateral pressure degree of the vehicles in front and behind the adjacent left lane on the vehicle, and the single-lane lateral pressure degree of the vehicles in front and behind the adjacent right lane on the vehicle.

[0071] The single lane lateral pressure state evaluation model in this embodiment mainly obtains a virtual pressure degree that represents the lateral pressure of the single lane on the vehicle by fusing and converting the longitudinal pressure degrees of the front and rear vehicles on a single lane. The fused lane lateral pressure state evaluation model calculates the total virtual pressure degree of multiple lanes involved in the vehicle's lateral pressure state when the vehicle changes lanes to the left or right based on the single lane lateral pressure state evaluation model.

[0072] In the single lane lateral pressure state evaluation model of this embodiment, in addition to summing up the longitudinal pressure degrees of the vehicles in front and behind the single lane to obtain the summed fused longitudinal pressure degree, the conversion coefficient T is used on this basis. map Convert a compression degree in the longitudinal direction to a compression degree in the transverse direction. Here, the conversion coefficient T map The determination of can be performed based on historical data by fitting the inverse function curve in the nonlinear fitting method. Specifically, the conversion coefficient T map The result of multiplying the sum of the longitudinal compression degrees is fitted with THW, and the goodness of fit is 0.639. The fitting result is,

[0073]

[0074] in, is the lane line pressure when the lane line is a dotted line, and THW is the headway time.

[0075] See also Figure 3 In the scenario of this embodiment, when the vehicle changes lanes to the left, it will mainly involve the lateral pressure of the vehicle from the lane and the adjacent left lane.

[0076] Specifically, first, according to the single lane lateral pressure state evaluation model, the conversion coefficient T map Convert the longitudinal pressure of the truck in front of the lane to the vehicle in the longitudinal direction into the lateral pressure of the lane to the vehicle in the lateral direction ( Figure 3 At the same time, according to the single lane lateral pressure state evaluation model, the conversion coefficient T map Convert the longitudinal pressure degree of the rear passenger car in the adjacent left lane to the vehicle in the longitudinal direction into the lateral pressure degree of the adjacent left lane to the vehicle in the lateral direction ( Figure 3 Then the lane exerts a lateral pressure on the vehicle in the lateral direction ( Figure 3 In ), the lateral pressure of the adjacent left lane on the vehicle in the lateral direction ( Figure 3 In ) and the lane pressure between the vehicle and the left dashed lane line ( Figure 3 In ) performs a vector sum in the lateral direction to obtain the lateral pressure degree of the vehicle when changing lanes to the left due to the fusion pressure of the surrounding passenger and freight vehicles.

[0077] S04, constructing a lane-changing decision optimization model based on vehicle pressure, and calculating the lane-changing decision of each vehicle at time t.

[0078] In this embodiment, the minimum lane-changing distance d of vehicles without lane-changing collision is defined as s , so that the model outputs lane-changing decisions that meet the lane-changing safety conditions. When the lane-changing space of the vehicle is greater than the minimum lane-changing distance, the vehicle is conditionally able to change lanes, otherwise the vehicle is not conditionally able to change lanes. The calculation method for the minimum lane-changing distance of the vehicle is as follows:

[0079]

[0080] Where, d s is the lane-changing safety distance, t s represents a time step; v n (t) represents the vehicle speed at that moment, b com Decelerate the vehicle comfortably.

[0081] According to the vehicle pressure state in a passenger-cargo mixed traffic environment, when the vehicle lateral pressure is greater than the negative value of the lane line pressure, the vehicle is in a forced lane change state. A vehicle lane change decision calculation method in a passenger-cargo mixed traffic environment is constructed. The specific calculation method is as follows:

[0082]

[0083] Where D is the vehicle lane change decision. When D is 0, 1, and -1, it means the vehicle keeps the current lane, changes lanes to the left, and changes lanes to the right. lc Indicates the vehicle's intention to change lanes, D lc When it is 0, 1, or -1, it indicates the vehicle's lane-changing intentions: keeping the current lane, changing lanes to the left, or changing lanes to the right. lc Indicates the lane-changing space of the vehicle; d s Y is the safe distance for lane change; e L , Y e R They respectively represent the lateral pressure degree of the surrounding passenger and freight vehicles when the vehicle changes lanes to the left and the lateral pressure degree of the surrounding passenger and freight vehicles when the vehicle changes lanes to the right;

[0084] S05, when optimizing the lane-changing decision, calculate the time to collision (TTC) after the vehicle changes lanes, and use the TTC value to estimate the driving comfort of the driver after the lane change. The TTC value is calculated as follows:

[0085]

[0086] Where TTC is the distance to collision time after the vehicle changes lanes, d is the distance between the vehicle and the preceding vehicle after the lane change, Δv is the speed difference between the vehicle and the preceding vehicle after the lane change, and D l , L l 、V l are the center point of the vehicle l in front of the vehicle after the lane change, the vehicle length of the vehicle l in front of the vehicle l and the vehicle speed of the vehicle l in front of the vehicle l, respectively. f , L f 、V f They are the center point, vehicle length and vehicle speed of the vehicle after lane changing.

[0087] According to the distance-to-collision time and the preset threshold, the lane-changing comfort of the vehicle after changing lanes is calculated using the following calculation formula:

[0088]

[0089] Among them, TTC is the distance to collision time after the vehicle changes lanes. * is the preset threshold.

[0090] Specifically, in the scenario of this embodiment, TTC* can be determined as 1.5. If the TTC value is less than TTC*, the lane changing comfort level is within a good range, and the system's working mode is in the optimization completion state, and the vehicle changes lanes according to the current decision; if the TTC value is greater than or equal to TTC*, the lane changing comfort level is within the range to be optimized, and the system's working mode is in the re-optimization state, further collecting on-board equipment data and starting to calculate the vehicle's pressure level, and re-optimizing the lane changing decision; after re-optimization, when the optimization model and the system's working mode become the optimization completion state, the vehicle changes lanes according to the current decision again.

[0091] S06: If the driver turns on an intelligent driving function such as automatic driving, the optimized lane changing decision will be sent to the vehicle control system through the on-board information sending device to start changing lanes. If the driver does not turn on an intelligent driving function such as automatic driving, the optimized lane changing decision will be provided to the driver as lane changing information induction.

[0092] In this embodiment, by comparing the traffic flow operation status 3600 seconds before and after the implementation of the scheme of this embodiment, it can be shown that the optimization effect of the scheme of this embodiment is significant. Here, the comparison results are shown in Table 3 below.

[0093] Table 3

[0094]

[0095] It can be seen from the above table that after applying the scheme of this embodiment, the average speed of passenger cars in road traffic increased from 27.3m / s to 30.8m / s, the headway time increased from 2.4s to 3.1s, and the lane change success rate increased from 68.6% to 87.4%. At the same time, the average speed of trucks increased from 19.6m / s to 23.2m / s, the headway time increased from 2.2s to 3.7s, and the lane change success rate increased from 54.9% to 61.9%. Therefore, the scheme of this embodiment can significantly improve traffic fluency and road operation efficiency, and the optimization effect is significant for mixed passenger and freight traffic scenarios.

[0096] Compared with the prior art, this embodiment has the following beneficial effects:

[0097] 1. Different from only considering the impact of physical indicators such as acceleration, speed and safe distance on vehicle lane changing, this embodiment takes into account the pressure exerted on the vehicle by other vehicles and lane lines, and innovatively adopts the lateral and longitudinal vehicle pressure degrees to quantify the impact of surrounding vehicles faced by the vehicle in the lane changing decision-making process. On this basis, a vehicle lane changing decision model for a mixed passenger and freight traffic environment is established, reflecting the changing trend of the vehicle lane changing intention in a mixed passenger and freight traffic scenario.

[0098] 2. Different from the model that only considers traffic safety indicators such as TTC and THW, the model of this embodiment not only uses TTC as a comfort indicator, but also integrates the truck oppression phenomenon as a basis for optimizing lane change decisions, and can handle vehicle lane change scenarios of multiple types of vehicles.

[0099] 3. Different from the open-loop lane-changing decision optimization process, this embodiment indirectly divides the vehicle driving comfort based on the TTC value, and then judges the lane-changing decision optimization model and the working status of the system, realizes the cyclic optimization control process, can make real-time decisions, and improves the safety and comfort of lane changing.

[0100] In order to implement the method of an embodiment of the present invention, an embodiment of the present invention also provides a vehicle lane changing decision system for mixed passenger and freight traffic scenarios, including: a processor and a memory for storing a computer program that can be run on the processor; wherein, when the processor is used to run the computer program, the steps of any one of the above methods are executed.

[0101] The above-mentioned system provided in this embodiment belongs to the same concept as the above-mentioned method embodiment. The specific implementation process thereof is detailed in the method embodiment and will not be repeated here.

[0102] In order to implement the method of the embodiment of the present invention, the embodiment of the present invention also provides a computer program product, which includes computer instructions, and the computer instructions are stored in a computer-readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device performs the steps of the above method.

[0103] Based on the hardware implementation of the above program modules, and in order to implement the method of the embodiment of the present invention, the embodiment of the present invention also provides an electronic device (computer device). Specifically, in one embodiment, the computer device can be a terminal, and its internal structure diagram can be as follows: Figure 4 As shown. The computer device includes a processor A01, a network interface A02, a display screen A04, an input device A05 and a memory (not shown in the figure) connected through a system bus. Among them, the processor A01 of the computer device is used to provide computing and control capabilities. The memory of the computer device includes an internal memory A03 and a non-volatile storage medium A06. The non-volatile storage medium A06 stores an operating system B01 and a computer program B02. The internal memory A03 provides an environment for the operation of the operating system B01 and the computer program B02 in the non-volatile storage medium A06. The network interface A02 of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor A01, the method of any one of the above embodiments is implemented. The display screen A04 of the computer device can be a liquid crystal display or an electronic ink display, and the input device A05 of the computer device can be a touch layer covered on the display screen, or a button, trackball or touchpad set on the computer device housing, or an external keyboard, touchpad or mouse, etc.

[0104] Those skilled in the art will understand that Figure 4 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0105] The device provided by the embodiment of the present invention includes a processor, a memory, and a program stored in the memory and executable on the processor. When the processor executes the program, the method of any one of the above embodiments is implemented.

[0106] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0107] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0108] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0109] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0110] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0111] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0112] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0113] It can be understood that the memory of the embodiment of the present invention can be a volatile memory or a non-volatile memory, and can also include both volatile and non-volatile memories. Among them, the non-volatile memory can be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), a magnetic random access memory (FRAM), a flash memory, a magnetic surface memory, an optical disc, or a compact disc read-only memory (CD-ROM); the magnetic surface memory can be a disk memory or a tape memory. The volatile memory can be a random access memory (RAM), which is used as an external cache. By way of example and not limitation, many forms of RAM are available, such as static random access memory (SRAM), synchronous static random access memory (SSRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDRSDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM, SyncLink Dynamic Random Access Memory), and direct RAM bus random access memory (DRRAM, Direct Rambus Random Access Memory).The memories described in the embodiments of the present invention are intended to include, but are not limited to, these and any other suitable types of memories.

[0114] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0115] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included within the scope of the claims of the present application.

Claims

1. A vehicle lane-changing decision method for mixed passenger and freight traffic, characterized in that: The method comprises: During the driving process of the vehicle, the state of the vehicle and the surrounding road environment is detected in real time, and the vehicle driving data is calculated; the vehicle driving data includes characteristic parameters of the vehicle, characteristic parameters of surrounding trucks and characteristic parameters of surrounding buses; the characteristic parameters of the vehicle include the balance distance of the vehicle, the minimum vehicle spacing when the vehicle is parked, the vehicle speed of the vehicle, the minimum safe time headway of the vehicle, the maximum acceleration of the vehicle, the comfortable deceleration of the vehicle, the mass of the vehicle, the lateral distance between the vehicle and the lane line, the head headway of the vehicle, and the lane changing space of the vehicle; the characteristic parameters of surrounding trucks include the preceding vehicle or The vehicle speed of the front vehicle or rear vehicle when the rear vehicle is a truck, the vehicle speed difference between the vehicle and the front vehicle or rear vehicle when the front vehicle or rear vehicle is a truck, and the head distance between the vehicle and the front vehicle or rear vehicle when the front vehicle or rear vehicle is a truck; the surrounding passenger vehicle characteristic parameters include the vehicle speed of the front vehicle or rear vehicle when the front vehicle or rear vehicle in the same lane as the vehicle is a passenger car, the vehicle speed difference between the vehicle and the front vehicle or rear vehicle when the front vehicle or rear vehicle is a passenger car, and the head distance between the vehicle and the front vehicle or rear vehicle when the front vehicle or rear vehicle is a passenger car; the passenger car represents a vehicle type that mainly transports people and is less than 6 meters in length; the truck represents a vehicle type that mainly transports goods and is greater than or equal to 6 meters in length; According to the vehicle driving data, using a preset truck longitudinal pressure state evaluation model, a bus longitudinal pressure state evaluation model, and a lane line pressure state evaluation model, respectively obtain a truck longitudinal pressure degree representing the pressure effect of front and rear trucks on the vehicle during driving, a bus longitudinal pressure degree representing the pressure effect of front and rear buses on the vehicle during driving, and a lane line pressure degree representing the pressure effect of surrounding lane lines on the vehicle during driving; According to the longitudinal compression degree of the truck, the longitudinal compression degree of the passenger car and the lane line compression degree, a preset lateral compression state evaluation model is used to obtain a lateral compression degree that characterizes the influence of the fusion compression of surrounding passenger and freight vehicles on the vehicle when the vehicle changes lanes to the left or right during driving; By using the lateral pressure degree and the lane line pressure degree, according to a preset lane change decision optimization model, a vehicle lane change decision of the vehicle is determined taking into account the influence of the fusion pressure of surrounding passenger and freight vehicles; The passenger car longitudinal compression state evaluation model includes: in, represents the balance distance of the vehicle, Indicates the minimum distance between vehicles when the vehicle is parked. Indicates the vehicle speed of the preceding or following vehicle when the preceding or following vehicle is a passenger car. Indicates the vehicle speed of the host vehicle, Indicates the speed difference between the vehicle in front of or behind the vehicle when the vehicle in front of or behind the vehicle is a passenger car. is the minimum safe time distance of this vehicle, , They represent the maximum acceleration and comfortable deceleration of the vehicle respectively. Indicates the longitudinal pressure of a bus when the front or rear vehicle is a bus. The distance between the front and rear vehicles of the vehicle when the front or rear vehicle is a passenger car. is the model coefficient, represents the base of natural logarithms; The truck longitudinal compression state evaluation model includes: in, represents the balance distance of the vehicle, Indicates the minimum distance between vehicles when the vehicle is parked. Indicates the vehicle speed of the vehicle in front of or behind the vehicle when the vehicle in front of or behind the vehicle is a truck. Indicates the vehicle speed of the host vehicle, Indicates the speed difference between the vehicle in front of or behind the vehicle when the vehicle in front of or behind the vehicle is a truck. is the minimum safe time distance of this vehicle, , They represent the maximum acceleration and comfortable deceleration of the vehicle respectively. Indicates the longitudinal pressure of a truck when the front or rear vehicle is a truck. is the distance between the front and rear vehicles of the vehicle when the vehicle in front or behind is a truck. is the model coefficient, represents the base of natural logarithms; The lane line pressure state evaluation model includes: in, is the lane line pressure when the lane line is a dotted line, In When it is equal to L or R, it indicates the lane pressure degree with the left dotted lane line and the lane pressure degree with the right dotted lane line respectively. For the quality of this vehicle, is the vehicle speed of the host vehicle, is the lateral distance between the vehicle and the lane line, , , is the model coefficient; when the lane line is a solid line, the lane line pressure is infinite. represents the base of natural logarithms; The lateral pressure state evaluation model includes a single-lane lateral pressure state evaluation model and a fused lane lateral pressure state evaluation model; according to the longitudinal pressure degree of the truck, the longitudinal pressure degree of the bus and the lane line pressure degree, a preset lateral pressure state evaluation model is used to obtain a lateral pressure degree that characterizes the influence of the fusion pressure of surrounding passenger and freight vehicles on the vehicle when changing lanes to the left or right during driving, including: according to the longitudinal pressure degree of the truck, the longitudinal pressure degree of the bus and the lane line pressure degree, the single-lane lateral pressure state evaluation model is used to obtain a single-lane lateral pressure degree that characterizes the influence of the fusion pressure of front and rear passenger and freight vehicles on the vehicle during driving; according to the single-lane lateral pressure degree, the fused lane lateral pressure state evaluation model is used to obtain a lateral pressure degree that characterizes the influence of the fusion pressure of surrounding passenger and freight vehicles on the vehicle when changing lanes to the left or right during driving; The single lane lateral pressure state evaluation model includes: in, Indicates the lateral pressure of a single lane. Indicates the longitudinal pressure of a bus when the front or rear vehicle is a bus. Indicates the longitudinal pressure of a truck when the front or rear vehicle is a truck. in, is the conversion factor, in, is the lane line pressure when the lane line is a dotted line, is the headway time; The fusion lane lateral pressure state evaluation model includes: in, , They respectively represent the lateral pressure degree of the surrounding passenger and freight vehicles when the vehicle changes lanes to the left and the lateral pressure degree of the surrounding passenger and freight vehicles when the vehicle changes lanes to the right. , They are the lane pressure between the left dashed lane line and the right dashed lane line when the vehicle has not started to change lanes to the left, and the lane pressure between the right dashed lane line and the right dashed lane line when the vehicle has not started to change lanes to the right. 、 They are the single-lane lateral pressure degree of the vehicle in front and behind the current lane, the single-lane lateral pressure degree of the vehicle in front and behind the adjacent left lane, and the single-lane lateral pressure degree of the vehicle in front and behind the adjacent right lane; The preset lane-changing decision optimization model includes: in, in, For vehicle lane change decision, When it is 0, 1, or -1, it indicates three lane-changing decisions: the vehicle keeps the current lane, changes lanes to the left, or changes lanes to the right. Indicates the vehicle's intention to change lanes. When it is 0, 1, or -1, it indicates the vehicle's lane-changing intentions: keeping the current lane, changing lanes to the left, or changing lanes to the right. Indicates the lane-changing space of the vehicle; The safe distance for lane change; , They respectively represent the lateral pressure degree of the surrounding passenger and freight vehicles when the vehicle changes lanes to the left and the lateral pressure degree of the surrounding passenger and freight vehicles when the vehicle changes lanes to the right; Indicates the vehicle speed at the current moment, represents a time step, Decelerate the vehicle comfortably.

2. The vehicle lane-changing decision method for mixed passenger and freight traffic according to claim 1 is characterized in that: After determining the vehicle lane change decision of the vehicle taking into account the pressure effect of the surrounding passenger and freight vehicle integration, the method further includes: Calculating the lane-changing comfort of the vehicle after the lane-changing decision; When the lane-changing comfort is good, deploying the vehicle lane-changing decision to the autonomous driving vehicle so that the autonomous driving vehicle changes lanes according to the vehicle lane-changing decision, or sending the vehicle lane-changing decision to a manually driven vehicle so as to induce the manually driven vehicle to change lanes; When the lane-changing comfort level is to be optimized, the vehicle lane-changing decision is recalculated until the lane-changing comfort level is good.

3. The vehicle lane-changing decision method for mixed passenger and freight traffic according to claim 2 is characterized in that: According to the lane-changing decision of the vehicle, the lane-changing comfort of the vehicle after the lane-changing is calculated, including: According to the lane-changing decision of the vehicle, the distance-to-collision time after the lane-changing of the vehicle is calculated using the following calculation formula: in, is the distance to collision time after the vehicle changes lanes, is the distance between the vehicle in front after changing lanes, is the speed difference between the vehicle after lane change and the vehicle in front, , , The vehicle in front of the vehicle after changing lanes l The center point of the front vehicle The length of the vehicle and the vehicle ahead l The vehicle speed, , , They are the center point, vehicle length and vehicle speed of the vehicle after lane change; According to the distance-to-collision time and the preset threshold, the lane-changing comfort of the vehicle after changing lanes is calculated using the following calculation formula: in, is the distance to collision time after the vehicle changes lanes, is the preset threshold. Value less than When the vehicle changes lanes, the comfort level is good. Value greater than When the threshold is reached, the lane changing comfort of the vehicle after changing lanes is to be optimized.

4. A vehicle lane-changing decision system for mixed passenger and freight traffic, characterized in that: include: A processor and a memory for storing a computer program that can be run on the processor; wherein, when the processor is used to run the computer program, the steps of the method according to any one of claims 1 to 3 are executed.

5. A storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 3 are implemented.

Images