Fusion type predictive lane changing cruise control method and device

Abstract

The invention provides a fusion type predictive lane changing cruise control method and device, and relates to the technical field of vehicles. The method comprises the steps of planning an energy-saving vehicle speed sequence of a self-driving vehicle based on static road information; determining a prediction state of the obstacle vehicle according to the current state of the obstacle vehicle within a preset distance range; according to the energy-saving vehicle speed sequence, a discretization behavior state space of the self-driving vehicle in the road section is constructed; determining a lane changing state point of the self-driving vehicle from the discretized behavior state space based on the energy-saving vehicle speed sequence and the predicted state of the obstacle vehicle; and according to the energy-saving vehicle speed sequence and the lane changing state point, a future optimal suggested state sequence of the self-driving vehicle is obtained, fusion type predictive lane changing cruise control is carried out on the self-driving vehicle, and the energy-saving effect of the vehicle can be enhanced.

Description

Technical Field

[0001] The present invention relates to the field of vehicle technology, and in particular to a fusion predictive lane-changing cruise control method and device. Background Art

[0002] With the rapid development of my country's economy, the volume of transportation has increased year by year. In order to achieve the goal of low-carbon transportation, energy-saving driving technologies such as predictive cruise control are now mainly used to reduce the driving energy consumption of self-driving vehicles and achieve low-carbon transportation energy conservation and emission reduction.

[0003] In a complex and ever-changing traffic environment, a vehicle may frequently change its speed due to the influence of an obstacle vehicle in front of the current lane, which increases the vehicle's energy consumption and reduces the vehicle's driving efficiency. At present, the lane change decision and control technology is mainly used to control the vehicle's lane change by calculating the acceleration gain of the vehicle before and after the lane change to reduce the negative impact of the obstacle vehicle in front. This lane change decision and control technology is mainly based on the dynamic information of the surrounding vehicles from the vehicle's perspective to control the vehicle's lane change, without considering the road slope characteristics and the surrounding vehicle status information under the beyond-visual-range range, resulting in a large gap between the actual vehicle state of the lane change and the ideal vehicle state under the current road characteristics, which in turn leads to poor energy-saving effects of the vehicle. Summary of the invention

[0004] In view of the problems existing in the prior art, the present invention provides a fusion predictive lane change cruise control method and device.

[0005] The present invention provides a fusion predictive lane change cruise control method, comprising: Based on static road information, plan the energy-saving speed sequence of the self-driving vehicle; Determine the predicted state of the obstacle vehicle according to the current state of the obstacle vehicle within a preset distance range; construct a discretized behavior state space of the self-driving vehicle in the road section according to the energy-saving vehicle speed sequence; Determining a lane change state point of the self-driving vehicle from the discretized behavior state space based on the energy-saving vehicle speed sequence and the predicted state of the obstacle vehicle; A state sequence of the self-driving vehicle is obtained according to the energy-saving vehicle speed sequence and the lane-changing state point, so as to perform fusion predictive lane-changing cruise control on the self-driving vehicle.

[0006] According to a fusion predictive lane change cruise control method provided by the present invention, the lane change state point of the self-driving vehicle is determined from the discretized behavior state space based on the energy-saving vehicle speed sequence and the predicted state of the obstacle vehicle, specifically comprising: Expanding the energy-saving vehicle speed sequence to obtain a set of simulated vehicle speed space points centered on the energy-saving vehicle speed; The lane changing state point of the self-driving vehicle is determined from the discretized behavior state space based on the simulated vehicle speed space point and the predicted state of the obstacle vehicle.

[0007] According to a fusion predictive lane change cruise control method provided by the present invention, a self-driving vehicle state sequence is obtained according to the energy-saving vehicle speed sequence and the lane change state point, specifically comprising: Determining each lane change state point and the driving cost corresponding to the simulated vehicle speed; forwardly simulate different lane change state points and simulated vehicle speeds to obtain multiple simulated state sequences, and determine the driving cost of each simulated state sequence; The driving costs of each of the simulated state sequences are compared to obtain the self-driving vehicle state sequence with the minimum cost; the self-driving vehicle state sequence includes a vehicle speed sequence and a behavior sequence.

[0008] According to a fusion predictive lane change cruise control method provided by the present invention, before determining each lane change state point and the driving cost corresponding to the simulated vehicle speed, the method further includes: Establishing a cost model based on the fuel consumption, driving efficiency and speed deviation between the simulated vehicle speed and the energy-saving vehicle speed of the self-driving vehicle at the lane change state point; Determining each lane change state point and the driving cost corresponding to the simulated vehicle speed specifically includes: The driving cost of each lane change state point and the corresponding simulated vehicle speed is determined based on the cost model.

[0009] According to a fusion predictive lane change cruise control method provided by the present invention, the lane change state point of the self-driving vehicle is determined from the discretized behavior state space based on the simulated vehicle speed and the predicted state of the obstacle vehicle, specifically comprising: Based on the simulated vehicle speed and the predicted state of the obstacle vehicle, a behavior state point that meets a preset lane-changing safety standard is determined from the discretized behavior state space as the lane-changing state point of the self-driving vehicle.

[0010] According to a fusion predictive lane change cruise control method provided by the present invention, based on static road information, an energy-saving speed sequence of a self-driving vehicle is planned, which specifically includes: Determine a planned distance domain of the energy-saving speed sequence of the self-driving vehicle, divide the planned distance domain into at least two stages based on road information, and plan the energy-saving speed sequence of the self-driving vehicle for each stage; When the self-driving vehicle reaches the second stage, the step of planning the energy-saving speed sequence of the self-driving vehicle is repeated to dynamically plan the energy-saving speed sequence of the self-driving vehicle; The discretized behavior state space corresponding to the energy-saving vehicle speed sequence according to lane planning specifically includes: The discretized behavior state space corresponding to the energy-saving vehicle speed sequence in the first stage in the distance domain is planned according to the lane and the discrete step number.

[0011] According to a fusion predictive lane change cruise control method provided by the present invention, the current state includes a state quantity set and a control quantity set, and the predicted state of the obstacle vehicle is determined according to the current state of the obstacle vehicle within a preset distance range, specifically including: Obtaining a discrete state space of the obstacle vehicle according to the state quantity set and control quantity set of the obstacle vehicle within a preset distance range; The predicted state of the obstacle vehicle is determined based on a preset microscopic traffic model and the discrete state space.

[0012] According to a fusion predictive lane change cruise control method provided by the present invention, the predicted state of the obstacle vehicle is determined according to the current state of the obstacle vehicle within a preset distance range; after the discretized behavior state space of the self-driving vehicle in the road section corresponding to the energy-saving vehicle speed sequence is planned according to the lane, the method further includes: When the state sequence of the self-driving vehicle is not obtained, a prompt message indicating that lane change is not possible is sent to the vehicle end, so as to perform single-lane preset cruise control on the self-driving vehicle.

[0013] The present invention also provides a fusion predictive lane-changing cruise control device, comprising: an energy-saving vehicle speed planning module, for planning an energy-saving vehicle speed sequence of a self-driving vehicle based on static road information; A behavior state discretization module is used to determine the predicted state of the obstacle vehicle according to the current state of the obstacle vehicle within a preset distance range; and to construct a discretized behavior state space of the self-driving vehicle in the road section according to the energy-saving vehicle speed sequence; a lane-changing state determination module, configured to determine a lane-changing state point of the self-driving vehicle from the discretized behavior state space based on the energy-saving vehicle speed sequence and the predicted state of the obstacle vehicle; A state sequence determination module is used to obtain the state sequence of the self-driving vehicle according to the energy-saving vehicle speed sequence and the lane change state point, so as to perform fusion predictive lane change cruise control on the self-driving vehicle.

[0014] The present invention also provides a vehicle, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the fused predictive lane change cruise control method as described above is implemented.

[0015] The integrated predictive lane-changing cruise control method and device provided by the present invention plans the energy-saving speed sequence of the self-driving vehicle through static road information, combines the predicted state of obstacle vehicles within a preset distance range, determines the lane-changing state point of the self-driving vehicle in the discrete behavior state space of the self-driving vehicle in the road section corresponding to the energy-saving speed, and obtains the state sequence of the self-driving vehicle according to the energy-saving speed and the lane-changing state point, so as to control the self-driving vehicle to change lanes at the energy-saving speed, narrow the gap between the actual self-driving vehicle state of the lane change and the ideal self-driving vehicle state under the current road characteristics, and increase the energy-saving effect of the self-driving vehicle. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0017] Figure 1 It is a flow chart of the integrated predictive lane-changing cruise control method provided by the present invention.

[0018] Figure 2 It is a schematic diagram of a preset distance range in the fusion predictive lane-changing cruise control method provided by the present invention.

[0019] Figure 3 It is a schematic diagram of the discretized behavior state space in the fusion predictive lane change cruise control method provided by the present invention.

[0020] Figure 4 It is a forward simulation schematic diagram of the fusion predictive lane-changing cruise control method provided by the present invention.

[0021] Figure 5 It is a schematic diagram of lane change judgment in the fusion predictive lane change cruise control method provided by the present invention.

[0022] Figure 6 It is one of the framework schematic diagrams of the fusion predictive lane change cruise control method provided by the present invention.

[0023] Figure 7 This is the second framework schematic diagram of the fusion predictive lane change cruise control method provided by the present invention.

[0024] Figure 8 This is the third framework schematic diagram of the integrated predictive lane change cruise control method provided by the present invention.

[0025] Fig. 9 It is a schematic diagram of engine fuel consumption of the integrated predictive lane change cruise control method provided by the present invention.

[0026] Fig.10 This is the fourth framework schematic diagram of the fusion predictive lane change cruise control method provided by the present invention.

[0027] Fig.11 It is a structural schematic diagram of the fusion predictive lane-changing cruise control device provided by the present invention.

[0028] Fig.12 It is a structural schematic diagram of a vehicle provided by the present invention. DETAILED DESCRIPTION

[0029] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0030] Combine the following Figure 1-Figure 11 The present invention describes a fusion predictive lane change cruise control method and device.

[0031] Figure 1 is one of the flow charts of the fusion predictive lane change cruise control method provided by the present invention, such as Figure 1 As shown, the method includes: Step 101: Plan an energy-saving speed sequence for a self-driving vehicle based on static road information.

[0032] Road information refers to information describing the road status, such as slope, speed limit, etc. The road status may include road shapes such as road width, curves, road slope, etc., the connection relationship between roads such as intersections and tunnels, and road elevation, etc. Among them, the road information can be obtained from the remote end, or it can be preset in the execution body of this method, etc. In this embodiment, the road information can be three-dimensional road information.

[0033] For example, a preset power system and vehicle speed coordinated optimization strategy may be used based on static road information to plan a gear sequence with the lowest driving cost for the self-driving vehicle in a target road section, and the vehicle speed under the gear sequence.

[0034] Step 102: determining a predicted state of the obstacle vehicle according to the current state of the obstacle vehicle within a preset distance range; and constructing a discretized behavior state space of the self-driving vehicle in the road section according to the energy-saving vehicle speed sequence.

[0035] Obstacle vehicles refer to vehicles around the vehicle within a preset distance range, including vehicles in front, behind, and to the side. The preset distance range can be set according to actual needs, and this embodiment does not make any further restrictions on this. For example, Figure 2 As shown, the preset distance range may be 1000 meters in front of the vehicle and 200 meters behind the vehicle, so as to comply with existing traffic practices, obtain sudden traffic conditions in front of the vehicle, and adjust cruise control.

[0036] like Figure 3 As shown, for example, the number of discrete steps can be determined based on the time and discrete step length of the self-driving vehicle from the current stage to the first stage of the planned path at the energy-saving speed, and the behavior state space corresponding to the energy-saving speed is discretized according to the lane with the discrete step number to obtain the discretized behavior state space. Among them, the discrete step length can be 0.5s, the discrete steps can be , The energy-saving vehicle speed is the time from the current stage to the first stage of the planned path. The formula can be used to obtain s1, s2, ..., sk, ..., LC=0 indicates the left lane, LC=1 indicates the middle lane, LC=2 indicates the right lane, and the end point may indicate the end point of the road section corresponding to the energy-saving speed.

[0037] The state of the obstacle vehicle refers to the state of the obstacle vehicle related to the lane change of the self-driving vehicle. The current state can be the state of the obstacle vehicle at the current behavior state point in the discretized behavior state space, and the predicted state can be the state of the obstacle vehicle at the subsequent behavior state point in the discretized behavior state space.

[0038] A lane is a specific area that guides vehicles to travel in a fixed direction. Discrete steps refer to the number of discrete behavior state points into which the behavior state is divided, which can be used to describe the number of times the behavior state is updated or calculated within a specified range.

[0039] The discretized behavior state space includes a plurality of behavior state points. Exemplarily, the number of behavior state points under each discrete step may correspond to the number of lanes.

[0040] Step 103: Determine a lane-changing state point of the self-driving vehicle from the discretized behavior state space based on the energy-saving vehicle speed sequence and the predicted state of the obstacle vehicle.

[0041] The lane-changing state point refers to the behavior state point at which the self-driving vehicle can safely change lanes at an energy-saving speed under the corresponding obstacle vehicle prediction state. The lane-changing state point includes discrete steps and lane-changing behaviors, and the lane-changing behaviors include changing lanes to the left or to the right.

[0042] Step 104: Obtain a state sequence of the self-driving vehicle according to the energy-saving vehicle speed sequence and the lane-changing state point, so as to perform fusion predictive lane-changing cruise control on the self-driving vehicle.

[0043] The state sequence includes the energy-saving vehicle speed sequence and the behavior state at each discrete step, and the behavior state includes lane changing behavior and no lane changing. It can be understood that the behavior state point corresponding to the discrete steps other than the discrete steps corresponding to the lane changing state point is no lane changing, thereby obtaining the state sequence completed by the self-driving vehicle.

[0044] The integrated predictive lane-changing cruise control method provided by the embodiment of the present invention plans the energy-saving speed sequence of the self-driving vehicle based on road information, combines the predicted state of the obstacle vehicle within the preset distance range, determines the lane-changing state point of the self-driving vehicle in the discretized behavior state space of the self-driving vehicle in the road section corresponding to the energy-saving speed sequence, and obtains the state sequence of the self-driving vehicle according to the energy-saving speed sequence and the lane-changing state point, so as to control the self-driving vehicle to change lanes at the energy-saving speed, narrow the gap between the actual self-driving vehicle state of the lane change and the ideal self-driving vehicle state under the current road characteristics, and increase the energy-saving effect of the self-driving vehicle.

[0045] It is understandable that the energy-saving speed sequence of self-driving vehicles planned based on static road information is mainly aimed at reducing energy consumption such as power consumption and fuel consumption. In the complex situation of vehicle interaction in multi-lane traffic flow in actual traffic, changing lanes directly based on the energy-saving speed sequence may cause the self-driving vehicle to miss the opportunity to change lanes, thereby increasing the vehicle's energy consumption as a whole and reducing the energy-saving effect of the self-driving vehicle.

[0046] To solve this technical problem, based on the above embodiment, the lane change state point of the self-driving vehicle is determined from the discretized behavior state space based on the energy-saving vehicle speed sequence and the predicted state of the obstacle vehicle, specifically including: Expanding the energy-saving vehicle speed sequence to obtain a set of simulated vehicle speed space points centered on the energy-saving vehicle speed; The lane changing state point of the self-driving vehicle is determined from the discretized behavior state space based on the simulated vehicle speed space point and the predicted state of the obstacle vehicle.

[0047] Exemplarily, the energy-saving speed sequence can be further discretized by the following formula to obtain the speed state space of the simulated vehicle speed space points, so as to improve the feasible solution space for the lane changing problem of the self-driving vehicle at a speed as close to the energy-saving speed as possible.

[0048] in, To simulate the speed state space of the vehicle speed space point, Energy-saving speed sequence for self-driving vehicles.

[0049] The vehicle speed threshold between adjacent simulated vehicle speeds in the speed state space of the simulated vehicle speed space point can be set according to the actual working conditions, and is not further limited in this embodiment.

[0050] The working principle and technical effect of determining the lane changing state point of the self-driving vehicle from the discretized behavior state space based on the simulated vehicle speed and the predicted state of the obstacle vehicle are basically the same as the working principle and technical effect of determining the lane changing state point of the self-driving vehicle from the discretized behavior state space based on the energy-saving vehicle speed sequence and the predicted state of the obstacle vehicle, and they will not be repeated here. The difference is that multiple simulated vehicle speeds are included under the same discrete step number, and it is necessary to judge whether the behavior state point is a lane changing state point based on the predicted state of the obstacle vehicle and each simulated vehicle speed of each behavior state point.

[0051] In this embodiment, the energy-saving vehicle speed sequence is expanded so that the vehicle speed at each behavior state point can be one of at least two simulated vehicle speeds, so that the self-driving vehicle can choose the best lane change time within a wider speed range and better adapt to the complex changes in the dynamic traffic environment.

[0052] Frequent lane changes can easily lead to vehicle instability, increasing the risk of rollover or loss of control, and frequent lane changes will make it difficult for surrounding vehicles to predict the vehicle's driving intention, increasing the risk of collision. To reduce traffic risks, in one embodiment, before determining the lane change state point from the discretized behavior state space based on the simulated vehicle speed and the state of the obstacle vehicle within the preset distance range, the method also includes: determining that the state point interval between the previous lane change state point and the target behavior state point is within the allowable lane change interval range.

[0053] The target behavior state point refers to the behavior state point to be judged as a lane change state point. For example, the lane change interval range may be greater than 6 behavior state points. When it is determined that the lane change interval between the target behavior state point and the previous lane change state point is 5 behavior state points, the behavior state point is directly determined as a non-lane change state point.

[0054] Crossing two lanes at once requires greater steering force and longer distance, which can easily cause the vehicle to lose control or roll over. Crossing two lanes at once will increase the driver's blind spot and increase the risk of collision with other vehicles. To reduce traffic risks, in one embodiment, the lane changing behavior in the lane changing state point is that the self-driving vehicle turns from the current lane to the adjacent lane.

[0055] like Figure 4 As shown, based on any of the above embodiments, the self-driving vehicle state sequence is obtained according to the energy-saving vehicle speed sequence and the lane change state point, specifically including: Determining each lane change state point and the driving cost corresponding to the simulated vehicle speed; forwardly simulate different lane change state points and simulated vehicle speeds to obtain multiple simulated state sequences, and determine the driving cost of each simulated state sequence; The driving costs of each of the simulated state sequences are compared to obtain the self-driving vehicle state sequence with the minimum cost; the self-driving vehicle state sequence includes a vehicle speed sequence and a behavior sequence.

[0056] Forward simulation refers to simulating the possible driving states of the self-driving vehicle starting from the current state. A tree search can be performed in the driving space to realize a cyclic forward simulation of the driving cost of the self-driving vehicle under different behaviors and speeds. For example, after the self-driving vehicle starts from the current state and drives at an energy-saving speed for 3 behavior state points, it changes lanes to the right at the first simulated speed at the fourth behavior state point, and obtains the speed sequence in the first simulation state sequence: energy-saving speed, energy-saving speed, energy-saving speed, first simulated speed; behavior sequence: no lane change, no lane change, no lane change, change lane to the right.

[0057] In this embodiment, by simulating the driving cost of the main vehicle under different behaviors and speeds, the driving strategy can be adjusted in real time according to the dynamic traffic environment, reducing the risk of increased energy consumption due to frequent and drastic changes in vehicle speed under complex traffic conditions.

[0058] Based on any of the above embodiments, before determining each lane change state point and the driving cost corresponding to the simulated vehicle speed, the method further includes: Establishing a cost model based on the fuel consumption, driving efficiency and speed deviation between the simulated vehicle speed and the energy-saving vehicle speed of the self-driving vehicle at the lane change state point; Determining each lane change state point and the driving cost corresponding to the simulated vehicle speed specifically includes: The driving cost of each lane change state point and the corresponding simulated vehicle speed is determined based on the cost model.

[0059] Among them, driving efficiency refers to a parameter that measures the amount of resources consumed by a vehicle, such as electricity and fuel, in the process of completing a driving task. The driving efficiency of a vehicle can be measured by the distance traveled by the vehicle in the same time, or by the fluctuation rate of the vehicle speed.

[0060] For example, the fuel consumption of a self-driving vehicle can be calculated by the following formula: in, For self-driving vehicle fuel consumption, is the instantaneous fuel consumption of the engine, is the engine speed, is the engine torque.

[0061] The driving efficiency can be calculated by the following formula: in, For driving efficiency, for, for The speed deviation between the simulated vehicle speed and the energy-saving vehicle speed can be calculated by the following formula: in, is the speed deviation, To save energy, To simulate the vehicle speed.

[0062] In one embodiment, the fuel consumption, driving efficiency and speed deviation of the self-driving vehicle can be weighted to establish a cost model. The specific weighting method can be determined according to actual needs and is not further limited in this embodiment.

[0063] For example, the cost model can be established by weighting the fuel consumption, driving efficiency and speed deviation of the self-driving vehicle based on the following formula: in, , i=1,2,3,4 are weight factors, and is the standardization constant used to standardize the three utility functions; and They are respectively the fuel consumption of the self-driving vehicle at the corresponding slope when the vehicle is driving at the upper and lower bounds of the discrete speed.

[0064] In this embodiment, by combining the fuel consumption, driving efficiency and speed deviation of the self-driving vehicle, a comprehensive optimization of the vehicle driving cost is achieved, so as to balance the vehicle's driving performance in different dimensions, improve the vehicle's energy-saving effect while ensuring driving efficiency, and improve user experience.

[0065] Based on the above embodiments, the predictive optimal traffic problem can be constructed based on the state matrix, constraints and driving cost function, and then the self-driving vehicle state sequence with the minimum cost can be found through forward behavior tree search, as shown in the following formula: like Figure 5As shown, in order to reduce the collision risk when the vehicle changes lanes, based on any of the above embodiments, the lane change state point of the self-driving vehicle is determined from the discretized behavior state space based on the simulated vehicle speed and the predicted state of the obstacle vehicle, specifically including: Based on the simulated vehicle speed and the predicted state of the obstacle vehicle, a behavior state point that meets a preset lane-changing safety standard is determined from the discretized behavior state space as the lane-changing state point of the self-driving vehicle.

[0066] The specific lane change safety standard can be set according to the needs, and this embodiment does not make any further restrictions on this. For example, it can be based on the relative distance between the self-driving vehicle and the vehicle in the adjacent lane. Safe lane change distance OK, if If the lane is the same as the lane you are in, you cannot change lanes. Otherwise, you can change lanes. It can be determined based on the following formula: in, For the self-driving car in the fusion stage The simulated vehicle speed selected in the state space, is the set following distance.

[0067] Can be taken , where the current lane is lane 1, the lane on one side of the current lane is lane 0, and the lane on the other side of the current lane is lane 2. is the distance between the self-driving vehicle and the front vehicle in lane 0, is the distance between the self-driving vehicle and the vehicle behind in lane 0, is the distance between the self-driving vehicle and the front vehicle in the current lane, is the distance between the self-driving vehicle and the front vehicle in lane 2, is the distance between the self-driving vehicle and the vehicle behind it in lane 2. Figure 5 In the figure, lane 0 is the lane with i=0, lane 1 is the lane with i=1, and lane 2 is the lane with i=2.

[0068] Based on any of the above embodiments, planning an energy-saving speed sequence of a self-driving vehicle based on static road information specifically includes: Determine a planned distance domain of the energy-saving speed sequence of the self-driving vehicle, divide the planned distance domain into at least two stages based on road information, and plan the energy-saving speed sequence of the self-driving vehicle for each stage; When the self-driving vehicle reaches the second stage, the energy-saving speed planning steps of the self-driving vehicle are repeated, and the energy-saving speed sequence of the self-driving vehicle is dynamically planned.

[0069] The planning distance domain refers to the distance ahead of the self-driving vehicle at which the energy-saving speed is planned. For example, the planning distance domain can be 1 km ahead of the self-driving vehicle, or 1.5 km ahead of the self-driving vehicle, etc.

[0070] Exemplarily, the planned distance domain for energy-saving vehicle speed may be determined to be 1 km ahead of the vehicle, and the planned distance domain may be divided into at least two stages according to road information such as tunnels, speed limits and slopes within 1 km ahead of the vehicle.

[0071] The discretized behavior state space corresponding to the energy-saving vehicle speed sequence according to lane planning specifically includes: The discretized behavior state space corresponding to the energy-saving vehicle speed sequence in the first stage in the planning distance domain is planned according to the lane and the discrete step number.

[0072] For example, the discrete step length may be The discrete steps obtained in 0.5s are , ,……, ,in , the behavior state of the self-driving vehicle in the first stage of the planning distance domain can be planned based on the lane and the discrete number of steps to obtain a discretized behavior state space. When the self-driving vehicle reaches the second stage, the first stage in the new planning distance domain is planned according to the energy-saving speed steps of the self-driving vehicle, and the discretized behavior state space corresponding to the behavior state of the first stage in the new planning distance domain is obtained.

[0073] In this embodiment, by making the discretized behavior state space used for dynamically controlling lane changing behavior correspond to the first stage of statically planning the energy-saving vehicle speed, the influence of the energy-saving vehicle speed can be fully considered during the lane changing process, so that in the process of controlling the lane changing of the self-driving vehicle based on the energy-saving vehicle speed, a more energy-saving behavior state can be selected to reduce the energy consumption of the self-driving vehicle.

[0074] Based on any of the above embodiments, the current state includes a state quantity set and a control quantity set, and the predicted state of the obstacle vehicle is determined according to the current state of the obstacle vehicle within a preset distance range, specifically including: Obtaining a discrete state space of the obstacle vehicle according to the state quantity set and control quantity set of the obstacle vehicle within a preset distance range; The predicted state of the obstacle vehicle is determined based on a preset microscopic traffic model and the discrete state space.

[0075] The state quantity set refers to the variable set that represents the vehicle state at a certain moment. For example, the state quantity set can be expressed by the following formula: in, express The longitudinal position of the vehicle at time express The vehicle speed at the time, express The current lane number of the vehicle at the moment, , when the vehicle is in the middle lane , when in the right lane , when in the left lane , Self-driving vehicles, Indicates the first car in the middle lane. Indicates the second car in the middle lane. represents the nth vehicle in the middle lane, Indicates the first car in the left lane. Indicates the second car in the left lane. represents the pth vehicle in the left lane, Indicates the first car in the right lane. Indicates the second car in the right lane. represents the qth vehicle in the right lane.

[0076] The control quantity set refers to the set of variables that characterize the change of vehicle state at a moment. For example, the control quantity set can be expressed by the following formula: in, express The vehicle's acceleration at that moment, express The vehicle's left lane change decision at time , 0 means no lane change, 1 means change lane to the left. express The vehicle's right lane change decision at time t is determined in the same way as the left lane change decision. SV is the self-driving vehicle.

[0077] Exemplarily, the discrete state space of the obstacle vehicle can be expressed by the following formula: Among them, the discrete time step is ΔT, A and B are the coefficient matrices of the state space equation, as shown below: In the state set The longitudinal position of the vehicle at the time can be calculated by the vehicle following model. For example, the acceleration of the traffic vehicle following can be calculated by the Intelligent Driver Model (IDM) model as shown below: in, represents the maximum acceleration of the vehicle, represents the desired speed of the vehicle, express The speed of any vehicle at time, express The longitudinal relative speed of any vehicle and its preceding vehicle at time , Represents the acceleration index, usually taken as , express The actual following distance of any vehicle at time, express The expected following distance of any vehicle at time, Indicates the minimum vehicle spacing when stationary. represents the expected headway, Indicates the comfortable deceleration set for the vehicle.

[0078] In order to avoid lane changing operations in an unknown state and reduce potential risks, based on any of the above embodiments, the predicted state of the obstacle vehicle is determined according to the current state of the obstacle vehicle within a preset distance range; after the discretized behavior state space of the self-driving vehicle in the road section corresponding to the energy-saving speed is planned according to the lane, the method also includes: if the state sequence of the self-driving vehicle is not obtained, a prompt message indicating that lane change is not possible is sent to the vehicle end, so as to perform preset cruise control of a single lane on the self-driving vehicle.

[0079] like Figure 6 As shown, exemplarily, the upper layer in the cloud removes the infeasible state transfer points under the power system constraints based on the power system constraints, speed limit constraints, static slope information, road speed limit, energy consumption model and vehicle dynamics model to perform dynamic planning and solve. After completing the coordinated planning of vehicle gear and speed, the energy-saving vehicle speed can be sent to the lower layer to build the forward traffic drivable space based on IDM prediction and search the forward behavior tree based on the driving space to perform lane change fusion processing. By judging whether the lane change fusion processing has a solution, different prompt information can be sent to the vehicle end. If there is a solution, the first prompt information can be sent to the vehicle end to control the vehicle through mode 1 based on predictive adaptive cruise control. If there is no solution, the second prompt information can be sent to the vehicle end to control the vehicle through mode 2 based on lane change safety judgment and lane change path planning and tracking control.

[0080] In one embodiment, when there is no solution, the energy-saving vehicle speed of the upper layer can be sent to the vehicle end so as to control the vehicle based on the energy-saving vehicle speed.

[0081] In order to specifically illustrate the functions of the fused predictive lane change cruise control method provided by this embodiment, a specific example is provided below.

[0082] The cloud-controlled system can also be called a cloud-controlled digital twin system. It has the typical characteristics of a cyber-physical system (CPS) and is a new generation of transportation system for real-time collaborative computing of large-scale networked applications.

[0083] like Figure 7 As shown in the figure, the cloud control system includes physical space and information space. The physical space may include the physical layer, which can also be called the physical system layer, the traffic physical layer, etc., and the information space may be the edge cloud. The physical space includes basic elements such as intelligent connected cars, human drivers, pedestrians, roadside equipment, communication facilities, and traffic elements (such as speed limits, slope curvature, and traffic lights) in mixed road traffic scenarios. Roadside perception equipment collects the status information of vehicles on the road in real time through cross-domain collaborative perception algorithms and uploads the data to the edge cloud.

[0084] The information space includes the Cloud Control Base Platform (CCBP) and the Cloud Control Application Platform (CCAP). The Cloud Control Base Platform can also be called the Cloud Control Base Layer or the Twin State Layer, and the Cloud Control Application Platform can also be called the Cloud Control Application Platform Layer or the Twin Application Layer.

[0085] The physical system layer can send information such as elements of the physical space to the cloud control basic platform layer through real-time data collection. The cloud control basic platform layer can obtain twin data by integrating information through standardized communications, and conduct real-time digital mapping of the physical space. It can also further perform future reasoning on the status information of traffic participants, such as behavior recognition and intention estimation, vehicle speed prediction and trajectory prediction, etc. to obtain basic data, and send the basic data to the cloud control application platform layer. The cloud control application platform layer can deeply mine and utilize static road information and dynamic traffic reasoning information, perform control calculations through vehicle safety collaborative application 1, energy-saving collaborative application 2, and efficient collaborative application n, and send the optimization results as application outputs to the cloud control basic platform layer. The cloud control basic platform layer generates instructions for fusion control and sends the instructions to the physical space, thereby realizing the fusion application of digital twin technology in the cloud control system.

[0086] like Figure 8As shown, in this embodiment, the cloud control application platform of the cloud control system can execute a fusion predictive lane change cruise method. The upper cloud layer combines the speed limit, slope, weather and other information provided by the static road map, removes the infeasible state transfer points under the power system constraints, and performs energy-saving speed planning for the self-driving vehicle. In the fusion process, only the first stage in the planned energy-saving speed distance domain is used, which can be called the first stage fusion; the road information can be sent to the edge cloud through roadside perception and vehicle-road perception fusion through multiple roadside collaborative base stations, so that the twin state layer of the edge cloud can perform twin mapping of road objects such as position, size, type and road surface, weather and other environments, and digital reasoning of the behavior, speed and trajectory prediction of traffic participants to obtain twin data, and then send dynamic traffic participant prediction information to the twin application layer to perform hierarchical fusion of dynamic and static information, and send the results to the traffic physical layer.

[0087] Specifically, the optimal energy-saving speed and gear sequence of the self-driving vehicle can be planned based on road information. The lane changing behavior and speed can be further integrated based on the energy-saving speed of the upper cloud layer in the lower layer of the cloud. The speed of the forward traffic vehicle is predicted by using a microscopic traffic model to construct the drivable space of the self-driving vehicle. Then, with the goal of minimizing driving cost, forward simulation is performed using tree search and other methods to obtain the speed sequence and behavior sequence of the self-driving vehicle with the lowest cost, which is then sent to the vehicle end to perform integrated predictive lane change cruise control on the self-driving vehicle.

[0088] Furthermore, if the self-driving vehicle state sequence is not obtained, a prompt message indicating that lane change is impossible can be sent to the vehicle end, that is, there is no optimal lane change speed fusion sequence, and the system can enter preset control modes such as Predictive Adaptive Cruise Control (PACC) / Predictive Cruise Control (PCC) to perform single-lane energy-saving driving control.

[0089] Specifically, according to the vehicle dynamics model and the high-efficiency range of the engine, static slope information plays an important role in the vehicle's power system control. In order to improve the vehicle's energy-saving driving effect, the road slope information ahead of the vehicle can be obtained in the upper layer of the cloud to predictively plan the vehicle's speed and power system.

[0090] Exemplarily, the vehicle driving equation is discretized in the distance domain by the forward Euler method to obtain the vehicle state transfer equation shown below.

[0091] in, for k The speed of the stage, fork+ The speed of the vehicle in stage 1, is the distance between two adjacent stages; For stage k The total transmission ratio of the transmission system; For stage k of engine torque; For stage k The road slope angle; is the rotation mass conversion factor; is the mass of the car (kg); Acceleration (m / s 2 ); is the transmission gear ratio; is the mechanical efficiency of the transmission system; is the tire radius; is the main reducer transmission ratio; is the air resistance coefficient; is the windward area; is the acceleration due to gravity; is the rolling resistance coefficient.

[0092] In the vehicle state transfer equation, the vehicle speed v is the state quantity, gear position ge and torque e For control quantities, through reasonable planning of these control quantities, effective control of the vehicle state can be achieved and the goal of energy-saving driving can be achieved.

[0093] The objective function for calculating the driving cost based on the instantaneous fuel consumption of the engine and the driving efficiency of the vehicle is as follows: in, is the instantaneous fuel consumption model of the engine when the vehicle is moving. and is the weighting coefficient; The corresponding engine fuel consumption model is as follows: Fig. 9 As shown, it can be expressed by the following formula: is the instantaneous fuel consumption of the engine, in kg / s; are the coefficients of each polynomial; is the engine speed in rpm, is the engine torque, in N·m.

[0094] Therefore, on the basis of minimizing the driving cost, the energy-saving speed model of the self-driving vehicle can be obtained by combining the constraints of the vehicle power system and the traffic speed limit as follows: in, , is the minimum and maximum torque boundary; , is the minimum and maximum vehicle speed boundary; , are the minimum and maximum acceleration boundaries; , is the minimum and maximum speed boundary; , The minimum and maximum gear boundaries.

[0095] like Fig.10 As shown, according to the calculation principle of the dynamic programming algorithm, the construction phase and the gear ge and vehicle speed v The three-dimensional state space is then removed based on the road speed limit and the infeasible state points under the constraints of the state transition equation. Then, according to the reverse calculation and forward solution process, the optimal vehicle speed and gear sequence state points are calculated to plan the energy-saving speed of the self-driving vehicle. The stage can be the future distance.

[0096] After obtaining the energy-saving speed of the self-driving vehicle, the speed of the traffic vehicle on the road ahead can be predicted based on the IDM model to obtain the drivable space for the self-driving vehicle at each moment in the future without colliding with other vehicles; the discretized behavior state space of the self-driving vehicle in the road section corresponding to the energy-saving speed is planned according to the lane; the energy-saving speed is expanded to obtain at least two simulated speeds; based on the simulated speed and the predicted state of the obstacle vehicle, the behavior state point that meets the preset lane change safety standard is determined from the discretized behavior state space as the lane change state point of the self-driving vehicle; based on the fuel consumption, driving speed and other factors of the self-driving vehicle at the lane change state point, the self-driving vehicle is automatically predicted. A cost model is established based on the driving efficiency and the speed deviation between the simulated vehicle speed and the energy-saving vehicle speed; based on the cost model, the driving cost of each lane change state point and the corresponding simulated vehicle speed is determined; the driving cost of each lane change state point and the corresponding simulated vehicle speed is determined; forward simulation is performed on different lane change state points and the simulated vehicle speeds to obtain multiple simulated state sequences, and the driving cost of each simulated state sequence is determined; the driving costs of each simulated state sequence are compared to obtain the speed sequence and behavior sequence of the self-driving vehicle with the minimum cost, so as to perform fusion predictive lane change cruise control on the self-driving vehicle.

[0097] The fused predictive lane changing cruise control device provided by the present invention is described below. The fused predictive lane changing cruise control device described below and the fused predictive lane changing cruise control method described above can be referenced to each other.

[0098] Fig.11 A structural schematic diagram of a fusion predictive lane change cruise control device is shown as an example. Fig.11 As shown, the device comprises: The energy-saving vehicle speed planning module 1101 is used to plan the energy-saving vehicle speed sequence of the self-driving vehicle based on static road information; The behavior state discretization module 1102 is used to determine the predicted state of the obstacle vehicle according to the current state of the obstacle vehicle within a preset distance range; and to construct a discretized behavior state space of the self-driving vehicle in the road section according to the energy-saving vehicle speed sequence; A lane-changing state determination module 1103, configured to determine a lane-changing state point of the self-driving vehicle from the discretized behavior state space based on the energy-saving vehicle sequence speed and the predicted state of the obstacle vehicle; The state sequence determination module 1104 is used to obtain the state sequence of the self-driving vehicle according to the energy-saving vehicle speed sequence and the lane change state point, so as to perform fusion predictive lane change cruise control on the self-driving vehicle.

[0099] Based on any of the above embodiments, the lane change state determination module 1103 is specifically configured to: Expanding the energy-saving vehicle speed sequence to obtain a set of simulated vehicle speed space points centered on the energy-saving vehicle speed point; The lane changing state point of the self-driving vehicle is determined from the discretized behavior state space based on the simulated vehicle speed space point and the predicted state of the obstacle vehicle.

[0100] Based on any of the above embodiments, the state sequence determination module 1104 is specifically configured to: Determining each lane change state point and the driving cost corresponding to the simulated vehicle speed; forwardly simulate different lane change state points and simulated vehicle speeds to obtain multiple simulated state sequences, and determine the driving cost of each simulated state sequence; The driving costs of each of the simulated state sequences are compared to obtain the self-driving vehicle state sequence with the minimum cost; the self-driving vehicle state sequence includes a vehicle speed sequence and a behavior sequence.

[0101] Based on any of the above embodiments, the fusion predictive lane change cruise control device further includes a driving cost determination module, which is used to: Establishing a cost model based on the fuel consumption, driving efficiency and speed deviation between the simulated vehicle speed and the energy-saving vehicle speed of the self-driving vehicle at the lane change state point; Determining each lane change state point and the driving cost corresponding to the simulated vehicle speed specifically includes: The driving cost of each lane change state point and the corresponding simulated vehicle speed is determined based on the cost model.

[0102] Based on any of the above embodiments, the lane changing state determination module 1103 is specifically used to determine the behavior state point that meets the preset lane changing safety standard from the discretized behavior state space based on the simulated vehicle speed and the predicted state of the obstacle vehicle as the lane changing state point of the self-driving vehicle.

[0103] Based on any of the above embodiments, the energy-saving vehicle speed planning module 1101 is specifically used to: determine a planning distance domain of the energy-saving vehicle speed sequence of the self-driving vehicle, divide the planning distance domain into at least two stages based on road information, and plan the energy-saving vehicle speed sequence of the self-driving vehicle for each stage; When the self-driving vehicle reaches the second stage, the step of planning the energy-saving speed of the self-driving vehicle is repeated to dynamically plan the energy-saving speed of the self-driving vehicle; The discretized behavior state space corresponding to the energy-saving vehicle speed sequence according to lane planning specifically includes: The discretized behavior state space corresponding to the energy-saving vehicle speed sequence in the first stage in the distance domain is planned according to the lane and the discrete step number.

[0104] Based on any of the above embodiments, the current state includes a state quantity set and a control quantity set; the behavior state discrete module 1102 is specifically used for: Obtaining a discrete state space of the obstacle vehicle according to the state quantity set and control quantity set of the obstacle vehicle within a preset distance range; The predicted state of the obstacle vehicle is determined based on a preset microscopic traffic model and the discrete state space.

[0105] Based on any of the above embodiments, the integrated predictive lane change cruise control device also includes a prompt information sending module, which is used to send a prompt information that the lane cannot be changed to the vehicle end when the state sequence of the self-driving vehicle is not obtained, so as to perform a preset cruise control of a single lane for the self-driving vehicle.

[0106] Fig.12 A schematic diagram of the structure of a vehicle is shown as an example. Fig.12As shown, the vehicle may include: a processor 1210, a communication interface 1220, a memory 1230 and a communication bus 1240, wherein the processor 1210, the communication interface 1220 and the memory 1230 communicate with each other through the communication bus 1240. The processor 1210 may call the logic instructions in the memory 1230 to execute a fusion predictive lane change cruise control method, the method comprising: planning an energy-saving speed sequence of the self-driving vehicle based on static road information; determining the predicted state of the obstacle vehicle according to the current state of the obstacle vehicle within a preset distance range; constructing a discretized behavior state space of the self-driving vehicle in the road section according to the energy-saving speed sequence; determining the lane change state point of the self-driving vehicle from the discretized behavior state space based on the energy-saving speed sequence and the predicted state of the obstacle vehicle; obtaining the state sequence of the self-driving vehicle according to the energy-saving speed sequence and the lane change state point, so as to perform fusion predictive lane change cruise control on the self-driving vehicle.

[0107] In addition, the logic instructions in the above-mentioned memory 1230 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on such an understanding, the technical solution of the present invention can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium, including several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0108] On the other hand, the present invention also provides a computer program product, which includes a computer program. The computer program can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the fused predictive lane change cruise control method provided by the above methods, which includes: planning an energy-saving speed sequence of a self-driving vehicle based on static road information; determining a predicted state of an obstacle vehicle within a preset distance range based on a current state of the obstacle vehicle; constructing a discrete behavior state space of the self-driving vehicle in a road section based on the energy-saving speed sequence; determining a lane change state point of the self-driving vehicle from the discrete behavior state space based on the energy-saving speed sequence and the predicted state of the obstacle vehicle; and obtaining a state sequence of the self-driving vehicle based on the energy-saving speed sequence and the lane change state point to perform fused predictive lane change cruise control on the self-driving vehicle.

[0109] On the other hand, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to execute the fused predictive lane change cruise control method provided by the above-mentioned methods, the method comprising: planning an energy-saving speed sequence of a self-driving vehicle based on static road information; determining a predicted state of an obstacle vehicle within a preset distance range based on a current state of the obstacle vehicle; constructing a discrete behavior state space of the self-driving vehicle in a road section based on the energy-saving speed sequence; determining a lane change state point of the self-driving vehicle from the discrete behavior state space based on the energy-saving speed sequence and the predicted state of the obstacle vehicle; and obtaining a state sequence of the self-driving vehicle based on the energy-saving speed sequence and the lane change state point to perform fused predictive lane change cruise control on the self-driving vehicle.

[0110] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0111] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0112] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A fusion predictive lane change cruise control method, characterized in that: include: Based on static road information, plan the energy-saving speed sequence of the self-driving vehicle; Determine the predicted state of the obstacle vehicle according to the current state of the obstacle vehicle within a preset distance range; construct a discretized behavior state space of the self-driving vehicle in the road section according to the energy-saving vehicle speed sequence; Determining a lane change state point of the self-driving vehicle from the discretized behavior state space based on the energy-saving vehicle speed sequence and the predicted state of the obstacle vehicle; A state sequence of the self-driving vehicle is obtained according to the energy-saving vehicle speed sequence and the lane-changing state point, so as to perform fusion predictive lane-changing cruise control on the self-driving vehicle.

2. The fusion predictive lane change cruise control method according to claim 1, characterized in that: Determining a lane change state point of the self-driving vehicle from the discretized behavior state space based on the energy-saving vehicle speed sequence and the predicted state of the obstacle vehicle specifically includes: Expanding the energy-saving vehicle speed sequence to obtain a set of simulated vehicle speed space points centered on the energy-saving vehicle speed point; The lane changing state point of the self-driving vehicle is determined from the discretized behavior state space based on the simulated vehicle speed space point and the predicted state of the obstacle vehicle.

3. The fusion predictive lane change cruise control method according to claim 2, characterized in that: Obtaining a self-driving vehicle state sequence according to the energy-saving vehicle speed sequence and the lane change state point specifically includes: Determining each lane change state point and the driving cost corresponding to the simulated vehicle speed; forwardly simulate different lane change state points and simulated vehicle speeds to obtain multiple simulated state sequences, and determine the driving cost of each simulated state sequence; The driving costs of the simulated state sequences are compared to obtain the self-driving vehicle state sequence with the minimum cost; the self-driving vehicle state sequence includes a vehicle speed sequence and a behavior sequence.

4. The fusion predictive lane change cruise control method according to claim 3, characterized in that: Before determining each lane change state point and the driving cost corresponding to the simulated vehicle speed, the method further includes: Establishing a cost model based on the fuel consumption, driving efficiency and speed deviation between the simulated vehicle speed and the energy-saving vehicle speed of the self-driving vehicle at the lane change state point; Determining each lane change state point and the driving cost corresponding to the simulated vehicle speed specifically includes: The driving cost of each lane change state point and the corresponding simulated vehicle speed is determined based on the cost model.

5. The fusion predictive lane change cruise control method according to claim 2, characterized in that: Determining a lane change state point of the self-driving vehicle from the discretized behavior state space based on the simulated vehicle speed and the predicted state of the obstacle vehicle specifically includes: Based on the simulated vehicle speed and the predicted state of the obstacle vehicle, a behavior state point that meets a preset lane-changing safety standard is determined from the discretized behavior state space as the lane-changing state point of the self-driving vehicle.

6. The fusion predictive lane change cruise control method according to claim 1, characterized in that: Based on static road information, plan the energy-saving speed sequence of the self-driving vehicle, including: Determine a planned distance domain of the energy-saving speed sequence of the self-driving vehicle, divide the planned distance domain into at least two stages based on road information, and plan the energy-saving speed sequence of the self-driving vehicle for each stage; When the self-driving vehicle reaches the second stage, the step of planning the energy-saving speed sequence of the self-driving vehicle is repeated to dynamically plan the energy-saving speed sequence of the self-driving vehicle; The discretized behavior state space corresponding to the energy-saving vehicle speed sequence according to lane planning specifically includes: The discretized behavior state space corresponding to the energy-saving vehicle speed sequence in the first stage in the distance domain is planned according to the lane and the discrete step number.

7. The fusion predictive lane change cruise control method according to claim 1, characterized in that: The current state includes a state quantity set and a control quantity set. The predicted state of the obstacle vehicle is determined according to the current state of the obstacle vehicle within a preset distance range, specifically including: Obtaining a discrete state space of the obstacle vehicle according to the state quantity set and control quantity set of the obstacle vehicle within a preset distance range; The predicted state of the obstacle vehicle is determined based on a preset microscopic traffic model and the discrete state space.

8. The fusion predictive lane change cruise control method according to claim 1, characterized in that: Determining a predicted state of the obstacle vehicle according to a current state of the obstacle vehicle within a preset distance range; After planning the discretized behavior state space of the self-driving vehicle in the road section corresponding to the energy-saving vehicle speed sequence according to the lane, the method further includes: When the state sequence of the self-driving vehicle is not obtained, a prompt message indicating that lane change is not possible is sent to the vehicle end, so as to perform single-lane preset cruise control on the self-driving vehicle.

9. A fusion predictive lane change cruise control device, characterized in that: include: Energy-saving vehicle speed planning module, used to plan the energy-saving vehicle speed sequence of the self-driving vehicle based on static road information; A behavior state discretization module is used to determine the predicted state of the obstacle vehicle according to the current state of the obstacle vehicle within a preset distance range; and to construct a discretized behavior state space of the self-driving vehicle in the road section according to the energy-saving vehicle speed sequence; a lane-changing state determination module, configured to determine a lane-changing state point of the self-driving vehicle from the discretized behavior state space based on the energy-saving vehicle speed sequence and the predicted state of the obstacle vehicle; A state sequence determination module is used to obtain the state sequence of the self-driving vehicle according to the energy-saving vehicle speed sequence and the lane change state point, so as to perform fusion predictive lane change cruise control on the self-driving vehicle.

10. A self-driving vehicle, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When the processor executes the computer program, the fused predictive lane change cruise control method as described in any one of claims 1 to 8 is implemented.

Images