Autonomous driving bus trajectory optimization control method, device, equipment and medium
By obtaining the actual measurement data and constraints of energy consumption and emissions of buses, using VSP interval clustering method and MPC theory to establish an environmental benefit quantification model, solving the problem of large errors in bus trajectory optimization control, and achieving more efficient environmental benefits and Improved operational efficiency.
Patent Information
- Application Number
- CN202311733677.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2023-12-15
- Publication Date
- 2024-12-03
- Estimated Expiration
- 2043-12-15
Smart Images

Figure CN117930645B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of traffic planning, and in particular to a method, device, equipment and medium for optimizing the trajectory control of an autonomous driving bus. Background Art
[0002] As one of the main sources of energy consumption and emissions, how to effectively promote energy conservation and emission reduction in the transportation sector has become an important research issue in this field. Urban transportation accounts for up to 80% of energy consumption and emissions in the transportation sector, and with the development of urbanization, urban transportation energy consumption and emissions will continue to increase. Therefore, the issue of energy conservation and emission reduction in urban transportation has become a hot topic in transportation research at home and abroad.
[0003] Giving priority to the development of public transportation is one of the important measures to reduce urban transportation emissions. On the one hand, as an important means of public transportation, public buses (electric buses) occupy an important position in urban passenger transportation; on the other hand, public buses (electric buses) have a large body weight and volume, resulting in relatively high energy consumption and emissions per vehicle. Therefore, how to effectively improve the average environmental benefits per vehicle is of practical significance for promoting energy conservation and emission reduction in public transportation and enhancing the attractiveness of green travel.
[0004] In recent years, with the rapid development of computer, electronic communication and other technologies, the Connected-Automated Vehicle (CAV) technology has gradually matured, providing a feasible way to achieve micro-precise control of road traffic. Based on CAV technology, vehicles can perceive road traffic conditions in real time, optimize trajectories in real time according to the current operating status, and reasonably realize automatic control of vehicle speed and acceleration. By optimizing the optimal trajectory and reducing vehicle speed fluctuations, it can reduce vehicle energy consumption and emissions while ensuring traffic safety.
[0005] Furthermore, the current research field of trajectory optimization control for autonomous driving vehicles is relatively broad, but there is a relative lack of professional research on trajectory optimization control for specific vehicle types (such as buses), and most of them are oriented towards simple road driving scenarios. Considering the important position of buses in urban public transportation systems, especially in the context of the rapid development of autonomous driving technology, it is necessary to strengthen the research and application of bus trajectory optimization control to improve urban transportation efficiency and environmental sustainability. Summary of the invention
[0006] In view of this, the present invention provides a method, device, equipment and medium for optimizing the trajectory control of an autonomous driving bus to solve the problem of optimizing the trajectory control of the bus.
[0007] In a first aspect, the present invention provides a method for optimizing the trajectory of an autonomous driving bus, the method comprising:
[0008] Obtain a set of constraints; obtain the energy consumption and emission measured data set and the target operating route of the autonomous driving bus to be controlled; establish an environmental benefit quantification model based on the energy consumption and emission measured data set after processing by the VSP interval clustering method; establish an MPC-based autonomous driving bus trajectory target optimization control model based on the constraint set, the environmental benefit quantification model and the target operating route; use the MPC-based autonomous driving bus trajectory target optimization control model to optimize the operating trajectory of the autonomous driving bus to be controlled within the target operating route to obtain the target operating trajectory.
[0009] The automatic driving bus trajectory optimization control method provided by the present invention is based on the energy consumption and emission measured data set and the VSP interval clustering method to establish an environmental benefit quantification model, which can more accurately and objectively calculate the impact of the vehicle's driving trajectory on the environment. Then, according to the environmental benefit quantification model, an automatic driving bus trajectory target optimization control model based on MPC is established, which takes into account the impact of the bus's driving trajectory on environmental benefits and operating time. It can not only obtain a greater degree of environmental benefits, but also effectively improve the efficiency and comfort of bus operation. Furthermore, through the automatic driving bus trajectory target optimization control model based on MPC, real-time optimization control of the operating trajectory of the automatic driving bus to be controlled within the target operating route is achieved.
[0010] In an optional implementation, obtaining a constraint set includes:
[0011] Obtain an operation force data set, a driving mode, and an operation data set of the autonomous driving bus to be controlled; and determine a constraint condition set based on the operation force data set, the driving mode, and the operation data set.
[0012] The present invention determines the corresponding set of constraint conditions by comprehensively considering the force conditions, driving conditions and operating conditions of the autonomous driving bus to be controlled, thereby providing data support for the subsequent improvement of model accuracy.
[0013] In an optional implementation, based on the measured data set of energy consumption and emission, an environmental benefit quantification model is established after being processed by the VSP interval clustering method, including:
[0014] The operating environment of the autonomous bus to be controlled is obtained; a VSP-based energy consumption and emission model is established based on the operating environment; an environmental benefit quantification model is established based on the energy consumption and emission measured data set and the VSP-based energy consumption and emission model after processing using the VSP interval clustering method.
[0015] The present invention can calculate the environmental benefits more accurately and objectively through the energy consumption and emission model based on VSP.
[0016] In an optional implementation, based on the constraint set, the environmental benefit quantification model and the target operation route, an MPC-based autonomous driving bus trajectory target optimization control model is established, including:
[0017] Obtain the total operating time of the autonomous driving bus to be controlled; determine the environmental benefit of the autonomous driving bus to be controlled based on the environmental benefit quantification model; based on the constraint condition set and the environmental benefit quantification model, establish an MPC-based autonomous driving bus trajectory target optimization control model with the goal of minimizing the environmental benefit and the total operating time of the autonomous driving bus to be controlled within the target operating route.
[0018] The present invention further considers the impact of the bus driving trajectory on the environmental benefits on the basis of considering the running time.
[0019] In an optional implementation, based on a set of constraints, an MPC-based autonomous driving bus trajectory target optimization control model is established with the goal of minimizing the environmental benefits and total operating time of the autonomous driving bus to be controlled within the target operating route, including:
[0020] Based on the constraint condition set and the environmental benefit quantification model, an initial optimization control model of the trajectory of the autonomous driving bus based on MPC is established with the goal of minimizing the environmental benefits and the total operating time of the autonomous driving bus to be controlled within the target operating route. The initial optimization control model of the trajectory of the autonomous driving bus based on MPC is subjected to rolling optimization to obtain the target optimization control model of the trajectory of the autonomous driving bus based on MPC.
[0021] Through rolling optimization, the present invention can enable the MPC-based autonomous driving bus trajectory target optimization control model to obtain an optimal trajectory that is more in line with actual conditions.
[0022] In an optional implementation, the MPC-based autonomous driving bus trajectory target optimization control model is used to optimize the running trajectory of the autonomous driving bus to be controlled within the target running route to obtain the target running trajectory, including:
[0023] The initial running trajectory of the autonomous driving bus to be controlled within the target running route is obtained; based on the initial running trajectory, the MPC-based autonomous driving bus trajectory target optimization control model is solved using a nonlinear optimization algorithm to obtain the target running trajectory.
[0024] In an optional implementation, obtaining an initial running trajectory of the autonomous driving bus to be controlled within a target running route includes:
[0025] Based on the target operating route, a road infrastructure dataset, a bus network dataset and a historical operating trajectory dataset of the autonomous driving bus to be controlled are obtained; based on the road infrastructure dataset, the bus network dataset and the historical operating trajectory dataset, the initial operating trajectory of the autonomous driving bus to be controlled within the target operating route is obtained through vehicle following principle and improved Newell following model processing.
[0026] In a second aspect, the present invention provides a trajectory optimization control device for an autonomous driving bus, the device comprising:
[0027] The first acquisition module is used to obtain a set of constraint conditions; the second acquisition module is used to obtain the energy consumption and emission measured data set and the target operation route of the autonomous driving bus to be controlled; the processing and establishment module is used to establish an environmental benefit quantification model based on the energy consumption and emission measured data set after processing by the VSP interval clustering method; the establishment module is used to establish an MPC-based autonomous driving bus trajectory target optimization control model based on the constraint condition set, the environmental benefit quantification model and the target operation route; the control module is used to optimize the operation trajectory of the autonomous driving bus to be controlled within the target operation route using the MPC-based autonomous driving bus trajectory target optimization control model to obtain the target operation trajectory.
[0028] In a third aspect, the present invention provides a computer device, comprising: a memory and a processor, the memory and the processor being communicatively connected to each other, the memory storing computer instructions, and the processor executing the automatic driving bus trajectory optimization control method of the first aspect or any corresponding embodiment thereof by executing the computer instructions.
[0029] In a fourth aspect, the present invention provides a computer-readable storage medium having computer instructions stored thereon, the computer instructions being used to enable a computer to execute the autonomous driving bus trajectory optimization control method of the first aspect or any corresponding embodiment thereof. BRIEF DESCRIPTION OF THE DRAWINGS
[0030] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.
[0031] Figure 1 is a flow chart of a method for optimizing the trajectory of an autonomous driving bus according to an embodiment of the present invention;
[0032] Figure 2is a flow chart of another automatic driving bus trajectory optimization control method according to an embodiment of the present invention;
[0033] Figure 3 is a schematic diagram of the driving forces of an autonomous driving bus to be controlled according to an embodiment of the present invention;
[0034] Figure 4 is a driving mode cycle process of the autonomous driving bus to be controlled according to an embodiment of the present invention;
[0035] Figure 5 is a flow chart of another automatic driving bus trajectory optimization control method according to an embodiment of the present invention;
[0036] Figure 6 is a schematic diagram of a rolling optimization process according to an embodiment of the present invention;
[0037] Figure 7 is a schematic diagram of a car-following process according to an embodiment of the present invention;
[0038] Figure 8 is a flow chart of an automatic driving bus trajectory optimization control method considering environmental benefits according to an embodiment of the present invention;
[0039] Fig. 9 is a structural block diagram of a trajectory optimization control device for an autonomous driving bus according to an embodiment of the present invention;
[0040] Fig.10 It is a schematic diagram of the hardware structure of a computer device according to an embodiment of the present invention. DETAILED DESCRIPTION
[0041] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments 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 those skilled in the art without creative work are within the scope of protection of the present invention.
[0042] Currently, there are few trajectory optimization controls for autonomous driving vehicles that take environmental benefits into consideration. Most studies on the objectives of trajectory optimization control only consider time, fuel consumption costs, etc. It is extremely important to consider environmental benefits and ecological driving strategies in order to develop a sustainable and environmentally friendly transportation system.
[0043] However, the current existing methods generally simply apply the ecological driving model, without fully considering the particularities of specific vehicle types and driving environments, and then deeply analyzing the complex relationship between microscopic operating trajectories and energy consumption and emissions. The calculated energy consumption and emissions cause large errors in the microscopic trajectory optimization control process.
[0044] In addition, the current research field of trajectory optimization control for autonomous driving vehicles is relatively broad, but there is a relative lack of professional research on trajectory optimization control for specific vehicle types (such as buses), and most of them are aimed at simple road driving scenarios. Considering the important position of buses in urban public transportation systems, especially in the context of the rapid development of autonomous driving technology, it is necessary to strengthen the research and application of bus trajectory optimization control to improve urban transportation efficiency and environmental sustainability.
[0045] According to an embodiment of the present invention, an embodiment of a method for optimizing the trajectory of an autonomous bus is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in an order different from that shown here.
[0046] In this embodiment, a method for optimizing the trajectory of an autonomous driving bus is provided. Figure 1 is a flow chart of a trajectory optimization control method for an autonomous driving bus according to an embodiment of the present invention. Figure 1 As shown, the process includes the following steps:
[0047] Step S101, obtaining a set of constraint conditions.
[0048] Specifically, the constraint set may include multiple constraint conditions that limit the optimal control of the operating trajectory of the autonomous driving bus to be controlled, such as force constraints and driving constraints of the autonomous driving bus to be controlled during operation.
[0049] Step S102, obtaining a measured data set of energy consumption and emission and a target operating route of the autonomous driving bus to be controlled.
[0050] Specifically, the target operation route represents the route between the starting point and the end point of the autonomous driving bus to be controlled, that is, due to different planning settings, different autonomous driving buses to be controlled have different corresponding operation routes. For example, the target operation route of autonomous driving bus A to be controlled is from bus stop A to bus stop B, and the target operation route of autonomous driving bus B to be controlled is from bus stop C to bus stop D.
[0051] Furthermore, by combining the vehicle specific power (VSP) with the vehicle's microscopic operating parameters, the vehicle's energy consumption and emissions can be accurately measured from a microscopic perspective, that is, the corresponding energy consumption and emission measured data set can be obtained.
[0052] VSP refers to the instantaneous power per unit mass of a motor vehicle, that is, the power consumed by the motor vehicle engine for each ton (including its own weight) of objects moved, and its unit is kW / t. The expression covers a variety of motion parameters such as speed, acceleration, slope, and wind resistance, and comprehensively considers the engine's own kinetic energy and the work done to overcome the friction resistance of the ground, air resistance, and slope resistance. Its calculation expression is shown in the following relationship (1):
[0053] VSP=v×[a×(1+ε)+g×grade+g×C R ]+0.5×ρ a ×C D ×A×v 3 ÷m (1)
[0055] Where: m represents the mass of the vehicle and all people and objects inside it, in kg; v represents the vehicle speed, in m / s; a represents the acceleration, in m / s 2 ; ε represents the mass coefficient; grade represents the slope, unit is %; g: gravitational acceleration, unit is m / s 2 ; C R Indicates the rolling resistance coefficient; C D Indicates the drag coefficient; A indicates the vehicle's frontal area, in m 2 ρ a Indicates air density in kg / m 3 .
[0056] Step S103: Based on the energy consumption and emission measured data set, an environmental benefit quantification model is established by processing it using the VSP interval clustering method.
[0057] Among them, the principle of the VSP interval clustering method is that the instantaneous energy consumption and emission rate corresponding to each VSP in a certain range of VSP intervals are relatively close. Therefore, the average value of the energy consumption and emission rate corresponding to each VSP value in this interval is used as the energy consumption and emission rate corresponding to all VSP values in this interval.
[0058] Furthermore, the environmental benefit quantification model is used to reflect the impact of the vehicle's driving trajectory on the environment, that is, the environmental benefit corresponding to the vehicle's driving trajectory. The environmental benefit may include the total energy consumption and emissions of the autonomous bus to be controlled.
[0059] Specifically, based on the measured data set of energy consumption and emissions, the corresponding environmental benefit quantification model can be constructed through the VSP interval clustering method.
[0060] Step S104, based on the constraint condition set, the environmental benefit quantification model and the target operation route, an MPC-based autonomous driving bus trajectory target optimization control model is established.
[0061] Specifically, combining the obtained environmental benefit quantification model and the target operating route, under the constraints of the constraint condition set, the corresponding MPC-based autonomous driving bus trajectory target optimization control model can be constructed.
[0062] Step S105, using the MPC-based autonomous driving bus trajectory target optimization control model to optimize the running trajectory of the autonomous driving bus to be controlled within the target running route to obtain the target running trajectory.
[0063] Specifically, the obtained MPC-based autonomous driving bus trajectory target optimization control model can realize real-time optimization control of the operating trajectory of the autonomous driving bus to be controlled within the target operating route, and obtain the corresponding target operating trajectory.
[0064] The automated driving bus trajectory optimization control method provided in this embodiment is based on the energy consumption and emission measured data set and the VSP interval clustering method to establish an environmental benefit quantification model, which can more accurately and objectively calculate the impact of the vehicle's driving trajectory on the environment. Then, according to the environmental benefit quantification model, an MPC-based automated driving bus trajectory target optimization control model is established, which takes into account the impact of the bus's driving trajectory on environmental benefits and operating time. It can not only obtain a greater degree of environmental benefits, but also effectively improve the efficiency and comfort of bus operation. Furthermore, the MPC-based automated driving bus trajectory target optimization control model is used to achieve real-time optimization control of the operating trajectory of the automated driving bus to be controlled within the target operating route.
[0065] In this embodiment, a method for optimizing the trajectory of an autonomous driving bus is provided. Figure 2 is a flow chart of a trajectory optimization control method for an autonomous driving bus according to an embodiment of the present invention. Figure 2 As shown, the process includes the following steps:
[0066] Step S201, obtaining a set of constraint conditions.
[0067] Specifically, the above step S201 includes:
[0068] Step S2011, obtaining the operating force data set, driving mode and operating data set of the autonomous driving bus to be controlled.
[0069] Specifically, the operating force data set is used to reflect the force conditions of the autonomous driving bus to be controlled during the actual operation process, such as Figure 3As shown, the autonomous driving bus to be controlled is mainly affected by engine traction, driving ground resistance, air resistance and slope resistance.
[0070] Further, the driving mode may include an acceleration mode, a cruising mode, a deceleration process, and a parking mode.
[0071] Furthermore, the operating data set may include the acceleration, speed, and total operating distance of the autonomous bus to be controlled.
[0072] Step S2012, determining a constraint condition set based on the operating force data set, the driving mode and the operating data set.
[0073] Specifically, according to the operating force data set, combined with Newton's second law, the corresponding dynamic model can be obtained, as shown in the following equations (2) and (3):
[0074] Ma=F e -f d (2)
[0075]
[0076] Where: M represents the mass of the autonomous bus; F e Indicates driving force; f d Indicates the resistance of the car during driving, which can include slope resistance F S , rolling resistance F r and air resistance F a ; θ represents the road inclination, C r represents the rolling resistance coefficient; ρ represents the air mass density; A represents the cross-sectional area of the vehicle; C a Represents the aerodynamic drag coefficient.
[0077] Furthermore, according to the driving process of the autonomous driving bus to be controlled along the cycle of "stop-accelerate-cruise-decelerate-stop", a corresponding kinematic model can be constructed. The specific switching process is as follows:
[0078] (1) Acceleration mode: The vehicle accelerates to leave the station, which can be expressed as shown in the following relations (4) to (7):
[0079] x(t+1)=x(t)+T·v(t) (4)
[0080] v(t+1)=v(t)+T·a(t) (5)
[0081] a(t+1)=a(t)a(t)>0 (6)
[0082]
[0083] Where: x(t), v(t), a(t) represent distance, speed, and acceleration respectively. In this embodiment, it is considered that a(t)>0.16m / s 2 It is an acceleration process, and in order to ensure the comfort of the driving process, it is determined that a(t) < 3m / s 2 , t represents the time, and T represents the update time step (1s).
[0084] Furthermore, the above equation (4) represents the vehicle position update; equation (5) represents the vehicle speed update; and equations (6) and (7) represent the acceleration update and calculation.
[0085] (2) Cruising mode: When the bus moves from the acceleration mode to the desired speed, it runs at a constant speed and enters the cruising mode. The acceleration is 0, and the cruising distance and time are determined by subtracting the acceleration and deceleration distance from the station distance, as shown in the following equations (8) to (10), which represent the vehicle position update, vehicle speed update, and acceleration update, respectively:
[0086] x(t+1)=x(t)+T·v(t) (8)
[0087] v(t+1)=v(t)=v0#(10) (9)
[0089] a(t+1)=a(t)=0 (10)
[0090] Where: v0 is the expected speed of the autonomous bus traveling on this road section.
[0091] (3) Deceleration process: The same as the acceleration process, except that the vehicle speed must be exactly 0 when it decelerates to the platform.
[0092] (4) Parking mode: The vehicle arrives at the station and passengers get on and off. represents the position coordinate of the i-th station, and ξ(t) records the parking time, as shown in the following relationships (11) to (13), which respectively represent the vehicle position update, vehicle speed update, and recorded parking time update:
[0093]
[0094] v(t+1)=v(t)=0 (12)
[0096] ξ(t+1)=ξ(t)+1 (13)
[0097] Furthermore, the entire driving mode cycle process can be Figure 4 As shown. The formula on the arrow represents the connection between each cycle. The whole cycle process is described as:
[0098] When the vehicle departs from the i-th station, it starts to accelerate until the speed changes to the desired speed and enters the cruise mode, that is, v(t) = v0.
[0099] Keep cruising at a constant speed until there is a deceleration distance left to the i+1th station, that is Entering deceleration mode, is the position of the i+1th station, is the deceleration distance from the i-th station to the i+1-th station.
[0100] When the vehicle slows down to the i+1th station, Enter parking mode.
[0101] In parking mode, passengers can get on and off the bus, so the parking time is related to the number of people getting on and off the bus. Let d i represents the time that the autonomous driving vehicle should stay at station i, n i represents the number of people getting on and off at station i, h i In order to ensure a reasonable distance between buses and to prevent passengers from missing the bus due to not reaching the platform, the parking time d i In addition to considering the time for passengers to get on and off the bus, the minimum parking time h of the vehicle must also be met. i , that is, d i =0.7n i +h i . When all passengers are on board, ξ(t)>d i , the vehicle will start and enter acceleration mode again.
[0102] Furthermore, according to the above loop structure, it can be known that the distance between stations should be equal to the sum of the acceleration process, the cruising process, and the deceleration process, as shown in the following relationship (14):
[0103]
[0104] Where: a acc 、a dec Respectively represent the acceleration of the acceleration and deceleration process; t cru Indicates the cruising process time.
[0105] Furthermore, the hybrid dynamics and kinematics model of the autonomous bus system, i.e., the above equations (2) to (14), as well as the acceleration, speed and total running distance of the vehicle are used as the corresponding constraint condition set.
[0106] Step S202: Obtain the energy consumption and emission measured data set and target operation route of the autonomous driving bus to be controlled. Figure 1 Step S102 of the illustrated embodiment will not be described in detail here.
[0107] Step S203: Based on the energy consumption and emission measured data set, an environmental benefit quantification model is established by processing it using the VSP interval clustering method.
[0108] Specifically, the above step S203 includes:
[0109] Step S2031, obtaining the operating environment of the autonomous driving bus to be controlled.
[0110] Step S2032: Establish a VSP-based energy consumption and emission model based on the operating environment.
[0111] Specifically, considering the operating environment of the autonomous bus to be controlled, the above equation (1) is modified to obtain the corresponding VSP-based energy consumption and emission model, as shown in the following equation (15):
[0112] VSP=v[a+9.807×sin(grade)+0.09199]+0.000169×v 3 (15)
[0114] Step S2033: Based on the energy consumption and emission measured data set and the VSP-based energy consumption and emission model, an environmental benefit quantification model is established after being processed by the VSP interval clustering method.
[0115] Specifically, according to the principle of the VSP interval clustering method described in step S103, the VSP is divided into different intervals (Bin) at certain intervals. The VSP interval can be expressed as the following relation (16):
[0116]
[0117] Where n is an integer; l takes an appropriate value according to the vehicle type, energy type, operating environment, speed limit, etc. of the research object.
[0118] In one example, the VSP intervals corresponding to the urban bus driving scene facing the controlled autonomous bus were divided. Since the bus speed of the urban rapid transit system generally does not exceed 50km / h, the VSP of the corresponding range is distributed between, and the corresponding intervals have different discrete degrees. On this basis, the VSP is divided into deceleration, idling [-20.5,0), [0, 0.5), [0.5, 1), [1, 1.5), [1.5, 2), [2, 3), [3, 6), [6, 9), [9, 20.5) with reference to the MOVES non-uniform scale division method, a total of 11 interval groups.
[0119] Furthermore, the VSP interval clustering method is used to calculate the energy consumption and emission rate of traditional buses and autonomous buses in each VSP interval, as shown in the following equation (17):
[0120] ER i,k =EF i,k ÷N k (17)
[0121] Where: ER i,k EF represents the emission rate or energy consumption rate of vehicle i in the kth VSP interval, in g / s; i,k represents the total emission or total energy consumption of vehicle i in the kth VSP interval, in g; N k Represents the total time the vehicle spends in the kth VSP interval, in seconds.
[0122] Furthermore, the current VSP value is calculated through the micro-operation data of the bus, and the current energy consumption and emission rate are found in the corresponding interval, as shown in the following relationship (18):
[0123] ER t =δ(VSPbin) (18)
[0124] Where: ER t represents the emission rate at time t; function δ(·) represents the corresponding function between VSP and energy consumption and emission rate.
[0125] Furthermore, the corresponding total energy consumption and emissions can be calculated through the following relationship (19):
[0126] ES=∑(ER tk ×D k ) (19)
[0127] Where: ES represents the total energy consumption or emission of public transport vehicles in the study section, unit: g; ER tk represents the energy consumption and emission rate of the vehicle in the kth VSP interval at time t, in g / s; D k Represents the total time of the kth VSP interval, in seconds.
[0128] Finally, through the above-mentioned equations (16) to (19), an environmental benefit quantification model can be established to reflect the environmental benefits of the total energy consumption and emissions of the autonomous driving bus to be controlled.
[0129] Step S204: Based on the constraint set, the environmental benefit quantification model and the target operation route, an MPC-based autonomous driving bus trajectory target optimization control model is established. Figure 1 Step S104 of the illustrated embodiment will not be described in detail here.
[0130] Step S105, using the MPC-based autonomous driving bus trajectory target optimization control model to optimize the running trajectory of the autonomous driving bus to be controlled within the target running route, and obtain the target running trajectory. Figure 1 Step S105 of the illustrated embodiment will not be described in detail here.
[0131] The automated driving bus trajectory optimization control method provided in this embodiment establishes an environmental benefit quantification model based on the VSP energy consumption and emission model, and can more accurately and objectively calculate the impact of the vehicle's driving trajectory on the environment. Furthermore, the corresponding set of constraints is determined by comprehensively considering the stress conditions, driving conditions, and operating conditions of the automated driving bus to be controlled, and an MPC-based automated driving bus trajectory target optimization control model is established based on the constraint condition set and the environmental benefit quantification model, which takes into account the impact of the bus's driving trajectory on environmental benefits. This can not only achieve a greater degree of environmental benefits, but also effectively improve the efficiency and comfort of bus operation. Furthermore, the MPC-based automated driving bus trajectory target optimization control model realizes real-time optimization control of the operating trajectory of the automated driving bus to be controlled within the target operating route.
[0132] In this embodiment, a method for optimizing the trajectory of an autonomous driving bus is provided. Figure 5 is a flow chart of a trajectory optimization control method for an autonomous driving bus according to an embodiment of the present invention. Figure 5 As shown, the process includes the following steps:
[0133] Step S501, obtain a set of constraint conditions. For details, see Figure 2 Step S201 of the illustrated embodiment will not be described in detail here.
[0134] Step S502: Obtain the energy consumption and emission measured data set and target operation route of the autonomous driving bus to be controlled. Figure 1 Step S102 of the illustrated embodiment will not be described in detail here.
[0135] Step S503: Based on the measured data set of energy consumption and emission, a quantitative model of environmental benefits is established after processing by VSP interval clustering method. Figure 2 Step S203 of the illustrated embodiment will not be described in detail here.
[0136] Step S504, based on the constraint condition set, the environmental benefit quantification model and the target operation route, an MPC-based autonomous driving bus trajectory target optimization control model is established.
[0137] Specifically, the above step S504 includes:
[0138] Step S5041, obtaining the total running time of the autonomous driving bus to be controlled;
[0139] Specifically, the total operating time refers to the total time required for the autonomous driving bus to be controlled to operate within the target operating route.
[0140] Step S5042: determining the environmental benefit of the autonomous driving bus to be controlled based on the environmental benefit quantification model.
[0141] Specifically, according to the description of step S203, the total energy consumption and emissions of the corresponding autonomous driving bus to be controlled, that is, the environmental benefit, can be calculated through the environmental benefit quantification model.
[0142] Step S5043, based on the constraint condition set and the environmental benefit quantification model, an MPC-based autonomous driving bus trajectory target optimization control model is established with the goal of minimizing the environmental benefit and total operating time of the autonomous driving bus to be controlled within the target operating route.
[0143] Specifically, with the goal of minimizing the environmental benefits and total operating time of the autonomous driving bus to be controlled within the target operating route, and under the condition of satisfying a set of constraints, a corresponding MPC-based autonomous driving bus trajectory target optimization control model can be established.
[0144] In some optional implementations, the above step S5043 includes:
[0145] Step a1, based on the constraint set and the environmental benefit quantification model, with the goal of minimizing the environmental benefit and total operating time of the autonomous driving bus to be controlled within the target operating route, establish an initial optimization control model of the autonomous driving bus trajectory based on MPC.
[0146] Step a2, performing rolling optimization on the initial optimization control model of the MPC-based autonomous driving bus trajectory to obtain the MPC-based autonomous driving bus trajectory target optimization control model.
[0147] Specifically, assuming that the vehicle departs from the i-th station to the i+1-th station, the total energy consumption and emissions under the environmental benefit quantification model can be calculated, as shown in the following equations (20) to (23):
[0148]
[0149]
[0150]
[0151]
[0152] Where: Represent the total energy consumption and emissions in acceleration mode, deceleration mode, cruising mode and parking mode respectively.
[0153] Furthermore, the total energy consumption and emission index J of the entire route are set based on the hybrid dynamics and kinematics model formulas of the autonomous bus system and the vehicle's acceleration, speed and total running distance as constraints. total and the total running time t in the specified running line [0, x f ] within the smallest (x f is the distance to the terminal station), and the constraints are satisfied. Finally, the optimization problem can be written as the following relations (24) to (28):
[0154]
[0155] stvehicledynamics (25)
[0157] v min ≤v≤v max (26)
[0158] a min ≤a≤a max (27)
[0159] 0≤x≤x f (28)
[0160] Among them, γ represents the weight coefficient.
[0161] Furthermore, the idea of rolling optimization is adopted, and feedback correction is performed while repeatedly optimizing. After optimization at each moment, the state quantity obtained through optimization at the next moment is assigned, and only the first element of the prediction is retained, and the subsequent moments are re-predicted.
[0162] Specifically, the autonomous driving bus departs from the i-th station to the i+1-th station as an optimization step length. Assume that there are N stations in total and the location information of the stations is known.
[0163] like Figure 6 As shown, first, the vehicle departs from the first platform;
[0164] Step 1: Enter all required parameters and ensure they are within a reasonable range;
[0165] Step 2: Dynamically input the waiting time d of the vehicle arriving at the station over time i ;
[0166] Step 3: Optimize But only keep The obtained running trajectory state parameters are used for the next optimization calculation;
[0167] Step 4: Set i+1 and return to step 2 until i=N-1;
[0168] Step 5: Finally get And the running trajectory status parameters of the entire line.
[0169] Furthermore, through the above-mentioned rolling optimization process, the final trajectory optimization control model can be established, that is, the MPC-based autonomous driving bus trajectory target optimization control model.
[0170] Step S505, using the MPC-based autonomous driving bus trajectory target optimization control model to optimize the running trajectory of the autonomous driving bus to be controlled within the target running route to obtain the target running trajectory.
[0171] Specifically, the above step S505 includes:
[0172] Step S5051, obtaining the initial running trajectory of the autonomous driving bus to be controlled within the target running route.
[0173] Among them, the initial operation trajectory represents the unoptimized driving trajectory of the autonomous driving bus to be controlled within the target operation route.
[0174] In some optional implementations, the above step S5051 includes:
[0175] Step b1, based on the target operating route, obtain a road infrastructure dataset, a bus network dataset, and historical operating trajectory data of the autonomous driving bus to be controlled.
[0176] Step b2, based on the road infrastructure dataset, the bus network dataset and the historical operation trajectory dataset, the initial operation trajectory of the autonomous bus to be controlled within the target operation route is obtained through processing using the vehicle following principle and the improved Newell following model.
[0177] Specifically, through the investigation, we can obtain the road infrastructure dataset corresponding to the target operation route, the bus network dataset and the historical operation trajectory data of the autonomous driving bus to be controlled.
[0178] In one example, the operating road scenario, operating conditions, vehicles to be optimized, and operating data are obtained through investigation, as shown in Table 1 below:
[0179] Table 1
[0180]
[0181] Furthermore, combined with the vehicle following characteristics, the initial running trajectory of the autonomous driving bus to be controlled within the target running route can be generated.
[0182] Specifically, the process of the autonomous bus following the car in the longitudinal direction is as follows: the bus needs to determine whether there is a vehicle ahead of it second by second. If the distance to the vehicle ahead is greater than 300m, the bus is not in the following state and the leading vehicle drives in the optimal operating state. Figure 7 shown.
[0183] Furthermore, an improved Newell following model is introduced and calibrated: Based on the driving characteristics of the following vehicle and the leading vehicle, the function is optimized by adding a speed difference term to compensate for the deficiency of the traditional Newell model that does not consider the influence of the leading vehicle and the vehicle speed difference. The specific model is shown in the following relation (29):
[0184]
[0185] Where: λ represents the weight coefficient of the undetermined speed difference; Δx i (t) represents the distance difference between the front and rear vehicles of the i-th vehicle; Δv i (t) represents the speed difference between the front and rear vehicles of the i-th vehicle; V1[Δx i (t)] and V2[Δv i (t)] represent the functions of the vehicle spacing and speed difference, respectively, as shown in the following equations (30) and (31):
[0186]
[0187] V2[Δv i (t)] = μtanh[Δv i (t)] (31)
[0188] Where: v max Indicates the set maximum speed, in m / s; μ is a dimensionless constant to be determined.
[0189] Furthermore, the model parameters are calibrated based on the existing historical operation trajectory data set. The parameter calibration process refers to the function parameter fitting method and uses the least squares method to fit the parameters.
[0190] In one example, the parameter calibration results are shown in Table 2 below:
[0191] Table 2. Parameter calibration results
[0192] <![CDATA[v0(m / s)]]> <![CDATA[v max (m / s)]]> <![CDATA[h c (m)]]> <![CDATA[T f (s)]]> λ μ Self-driving buses 8.33 13.80 4.74 - 4.586 0.438
[0193] Furthermore, a corresponding initial running trajectory can be generated based on the improved car-following model and the test data.
[0194] Step S5052: Based on the initial operation trajectory, a nonlinear optimization algorithm is used to solve the MPC-based automatic driving bus trajectory target optimization control model to obtain the target operation trajectory.
[0195] Specifically, based on the idea of priority diagram and game theory, weight analysis is performed based on the relative size of values. First, the approximate distribution of weights is determined, and then slight changes are made to analyze the cost increase.
[0196] In one example, γ=0.97 is determined as the weight coefficient of the objective function.
[0197] Furthermore, since the MPC-based autonomous driving bus trajectory target optimization control model contains nonlinear constraints and is a nonlinear hybrid optimization problem, the fmincon function of MATLAB is used to optimize and solve the trajectory optimization model based on the interior point method, and then the corresponding target operation trajectory can be obtained.
[0198] The automated driving bus trajectory optimization control method provided in this embodiment is based on the energy consumption and emission measured data set and the VSP interval clustering method to establish an environmental benefit quantification model, which can more accurately and objectively calculate the impact of the vehicle's driving trajectory on the environment. Then, according to the environmental benefit quantification model, an automated driving bus trajectory target optimization control model based on MPC is established. On the basis of considering the running time, the impact of the bus's driving trajectory on the environmental benefits is further considered, which can not only obtain a greater degree of environmental benefits, but also effectively improve the efficiency and comfort of bus operation. Furthermore, the automated driving bus trajectory target optimization control model based on MPC is used to achieve real-time optimization control of the running trajectory of the automated driving bus to be controlled within the target running route.
[0199] In one example, a method for optimizing the trajectory of an autonomous bus taking environmental benefits into consideration is provided. Figure 8 As shown in the figure, it is mainly divided into two parts: the establishment of the trajectory optimization control model of the autonomous driving bus and the application of the model. The model establishment includes the environmental benefit quantification model and the trajectory optimization control model. First, based on the VSP definition and the measured data of the energy consumption and emission of the autonomous driving bus, a unified environmental benefit quantification model is established. Then, based on the MPC theory and establishment steps, considering the typical application scenarios of the autonomous driving bus and the operating characteristics of the autonomous driving bus, the hybrid dynamics and kinematics model of the autonomous driving bus operation is analyzed, and then the microscopic operation trajectory optimization model for the autonomous driving bus is constructed with the maximization of the environmental benefits and operating efficiency of the bus as the objective function. In the model application, it is first necessary to generate the initial trajectory based on the actual scenario survey data and certain trajectory generation rules, use MATLAB and other tools for numerical simulation, and use the nonlinear optimization algorithm interior point method to solve the model, so as to obtain the optimal control trajectory.
[0200] This example provides an optimization control method for autonomous buses with environmental benefits. Based on the concept of MPC theory, it considers typical scenarios of autonomous buses entering and exiting stations and the operating characteristics of autonomous buses. It combines hybrid dynamics and kinematics models of autonomous buses to establish an optimization control model for autonomous buses. This model can be optimized in real time to obtain the optimal trajectory that is more in line with the actual microscopic operation of the vehicle. In the objective function of the optimization model, not only the vehicle's fuel consumption and energy consumption as well as comfortable acceleration are considered, but also the consideration of energy conservation and emission reduction environmental benefits is added in response to sustainable development of transportation.
[0201] Furthermore, in the past, when considering environmental benefits, reasonable eco-driving models were not fully utilized to calculate the benefit value, nor were these benefits converted into specific performance in terms of energy consumption and emissions. In contrast, the energy consumption and emission model based on VSP in this study can more accurately and objectively calculate the impact of vehicle driving trajectories on the environment.
[0202] In this embodiment, a device for optimizing the trajectory of an autonomous driving bus is also provided, which is used to implement the above-mentioned embodiments and preferred implementation modes, and will not be repeated hereafter. As used below, the term "module" may be a combination of software and / or hardware that implements a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.
[0203] This embodiment provides a trajectory optimization control device for an autonomous driving bus, such as Fig. 9 As shown, including:
[0204] The first acquisition module 901 is used to acquire a constraint condition set.
[0205] The second acquisition module 902 is used to obtain the energy consumption and emission measured data set and the target operation route of the autonomous driving bus to be controlled.
[0206] The processing and establishing module 903 is used to establish an environmental benefit quantification model based on the energy consumption and emission measured data set after processing by the VSP interval clustering method.
[0207] A module 904 is established to establish an MPC-based automatic driving bus trajectory target optimization control model based on a constraint condition set, an environmental benefit quantification model, and a target operation route.
[0208] The control module 905 is used to optimize the running trajectory of the autonomous driving bus to be controlled within the target running route by using the MPC-based autonomous driving bus trajectory target optimization control model to obtain the target running trajectory.
[0209] In some optional implementations, the first acquisition module 901 includes:
[0210] The first acquisition submodule is used to obtain the operating force data set, driving mode and operating data set of the autonomous driving bus to be controlled.
[0211] The first determination submodule is used to determine a constraint condition set based on an operation force data set, a driving mode and an operation data set.
[0212] In some optional implementations, the processing and establishing module 903 includes:
[0213] The second acquisition submodule is used to obtain the operating environment of the autonomous driving bus to be controlled.
[0214] The first submodule is used to establish an energy consumption and emission model based on the VSP based on the operating environment.
[0215] The processing and establishment submodule is used to establish an environmental benefit quantification model based on the energy consumption and emission measured data set and the VSP-based energy consumption and emission model after processing by the VSP interval clustering method.
[0216] In some optional implementations, the establishing module 904 includes:
[0217] The third acquisition submodule is used to obtain the total running time of the autonomous driving bus to be controlled;
[0218] The second determination submodule is used to determine the environmental benefit of the autonomous driving bus to be controlled based on the environmental benefit quantification model.
[0219] The second submodule is used to establish an MPC-based autonomous driving bus trajectory target optimization control model based on a constraint set and an environmental benefit quantification model, with the goal of minimizing the environmental benefits and total operating time of the autonomous driving bus to be controlled within the target operating route.
[0220] In some optional implementations, the second establishing submodule includes:
[0221] A unit is established for establishing an initial optimization control model of the trajectory of an autonomous bus based on MPC based on a constraint set and an environmental benefit quantification model, with the environmental benefit and the total operating time of the autonomous bus to be controlled being minimized within a target operating route.
[0222] The optimization unit is used to perform rolling optimization on the initial optimization control model of the MPC-based autonomous driving bus trajectory to obtain the MPC-based autonomous driving bus trajectory target optimization control model.
[0223] In some optional implementations, the control module 905 includes:
[0224] The third acquisition submodule is used to obtain the initial running trajectory of the autonomous driving bus to be controlled within the target running route.
[0225] The solving submodule is used to solve the MPC-based autonomous driving bus trajectory target optimization control model based on the initial operation trajectory using a nonlinear optimization algorithm to obtain the target operation trajectory.
[0226] In some optional implementations, the third acquisition submodule includes:
[0227] The first acquisition unit is used to acquire a road infrastructure dataset, a bus network dataset, and a historical operation trajectory dataset of the autonomous driving bus to be controlled based on the target operation route.
[0228] The second acquisition unit is used to obtain the initial operation trajectory of the autonomous driving bus to be controlled within the target operation route based on the road infrastructure dataset, the bus network dataset and the historical operation trajectory dataset, after processing by the vehicle following principle and the improved Newell following model.
[0229] The further functional description of each of the above modules and units is the same as that of the above corresponding embodiments and will not be repeated here.
[0230] The autonomous driving bus trajectory optimization control device in this embodiment is presented in the form of a functional unit, where the unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and memory that executes one or more software or fixed programs, and / or other devices that can provide the above functions.
[0231] The embodiment of the present invention also provides a computer device having the above Fig. 9 The trajectory optimization control device of the autonomous driving bus is shown.
[0232] See also Fig.10 , Fig.10 is a schematic diagram of the structure of a computer device provided by an optional embodiment of the present invention, such as Fig.10As shown, the computer device includes: one or more processors 10, a memory 20, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. Various components are connected to each other using different buses for communication, and can be installed on a common mainboard or installed in other ways as needed. The processor can process the instructions executed in the computer device, including instructions stored in or on the memory to display the graphical information of the GUI on an external input / output device (such as, a display device coupled to the interface). In some optional embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Similarly, multiple computer devices can be connected, and each device provides some necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system). Fig.10 A processor 10 is taken as an example.
[0233] The processor 10 may be a central processing unit, a network processor or a combination thereof. The processor 10 may further include a hardware chip. The hardware chip may be a dedicated integrated circuit, a programmable logic device or a combination thereof. The programmable logic device may be a complex programmable logic device, a field programmable gate array, a general purpose array logic or any combination thereof.
[0234] The memory 20 stores instructions executable by at least one processor 10, so that at least one processor 10 executes the method shown in the above embodiment.
[0235] The memory 20 may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function; the data storage area may store data created according to the use of the computer device, etc. In addition, the memory 20 may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some optional embodiments, the memory 20 may optionally include a memory remotely arranged relative to the processor 10, and these remote memories may be connected to the computer device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.
[0236] The memory 20 may include a volatile memory, such as a random access memory; the memory may also include a non-volatile memory, such as a flash memory, a hard disk or a solid state drive; the memory 20 may also include a combination of the above types of memory.
[0237] The computer device further comprises a communication interface 30 for the computer device to communicate with other devices or a communication network.
[0238] The embodiment of the present invention also provides a computer-readable storage medium. The method according to the embodiment of the present invention can be implemented in hardware, firmware, or can be implemented as a computer code that can be recorded in a storage medium, or can be implemented as a computer code that is originally stored in a remote storage medium or a non-temporary machine-readable storage medium and will be stored in a local storage medium through a network download, so that the method described herein can be stored in such software processing on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only storage memory, a random access memory, a flash memory, a hard disk or a solid-state hard disk, etc.; further, the storage medium can also include a combination of the above types of memories. It can be understood that a computer, a processor, a microprocessor controller, or programmable hardware includes a storage component that can store or receive software or computer code. When the software or computer code is accessed and executed by a computer, a processor, or hardware, the method shown in the above embodiment is implemented.
[0239] Although the embodiments of the present invention have been described in conjunction with the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present invention, and such modifications and variations are all within the scope defined by the appended claims.
Claims
1. A trajectory optimization control method for an autonomous driving bus, characterized in that: The method comprises: Get the constraint set; Obtain the measured data set of energy consumption and emission and the target operation route of the autonomous bus to be controlled; Based on the energy consumption and emission measured data set, an environmental benefit quantification model is established after being processed by the VSP interval clustering method; Based on the constraint condition set, the environmental benefit quantification model and the target operation route, an MPC-based autonomous driving bus trajectory target optimization control model is established; Using the MPC-based autonomous driving bus trajectory target optimization control model to optimize the running trajectory of the autonomous driving bus to be controlled within the target running route, to obtain a target running trajectory; Obtaining the constraint set includes: Obtaining an operation force data set, a driving mode, and an operation data set of the autonomous driving bus to be controlled; Determining the constraint condition set based on the operation force data set, the driving mode and the operation data set; Among them, based on the energy consumption and emission measured data set, after being processed by the VSP interval clustering method, an environmental benefit quantification model is established, including: Acquiring the operating environment of the autonomous driving bus to be controlled; Establishing a VSP-based energy consumption and emission model based on the operating environment; Based on the energy consumption and emission measured data set and the VSP-based energy consumption and emission model, the environmental benefit quantification model is established after being processed by the VSP interval clustering method; The VSP-based energy consumption and emission model is represented by the following relational expression: VSP=v[a+9.807×sin(grade)+0.09199]+0.000169×v 3 Where: VSP represents the instantaneous power per unit mass of the motor vehicle, in kW / t; v represents the vehicle speed, in m / s; a represents the acceleration, in m / s 2 ;grade indicates slope, unit: %; Wherein, based on the energy consumption and emission measured data set and the VSP-based energy consumption and emission model, the environmental benefit quantification model is established after being processed by the VSP interval clustering method, including: Using the VSP interval clustering method, VSP is divided into different intervals at certain intervals, which can be expressed as the following first relation: Where: bin represents interval; n represents an integer; l is determined according to the vehicle type, energy type, operating environment, and speed limit of the research object; Using the VSP interval clustering method, the energy consumption and emission rates of traditional buses and autonomous buses in each VSP interval are calculated, which can be expressed as the following second relationship: IS i,k =EU i,k ÷N k Where: ER i,k EF represents the emission rate or energy consumption rate of vehicle i in the kth VSP interval, in g / s; i,k represents the total emission or total energy consumption of vehicle i in the kth VSP interval, in g; N k represents the total time of the vehicle in the kth VSP interval, in seconds; The current VSP value is calculated through the micro-operation data of the bus, and the current energy consumption and emission rate are found in the corresponding interval, which is expressed as the following third relationship: IS t =δ(VSPbin) Where: ER t represents the emission rate at time t; the function δ(·) represents the corresponding function between VSP and energy consumption and emission rate; The corresponding total energy consumption and emissions are calculated by the following fourth relationship: ES=∑(ER tk ×D k ) Where: ES represents the total energy consumption or emission of public transport vehicles in the study section, unit: g; ER tk represents the energy consumption and emission rate of the vehicle in the kth VSP interval at time t, in g / s; D k represents the total time of the kth VSP interval, in seconds; An environmental benefit quantification model that reflects the environmental benefits including the total energy consumption and emissions of the autonomous driving bus to be controlled is established through the first, second, third and fourth relationships.
2. The method according to claim 1, characterized in that: Based on the constraint condition set, the environmental benefit quantification model and the target operation route, an MPC-based automatic driving bus trajectory target optimization control model is established, including: Obtaining the total running time of the autonomous driving bus to be controlled; Determining the environmental benefit of the autonomous driving bus to be controlled based on the environmental benefit quantification model; Based on the constraint condition set and the environmental benefit quantification model, the MPC-based autonomous driving bus trajectory target optimization control model is established with the goal of minimizing the environmental benefit and the total operating time of the to-be-controlled autonomous driving bus within the target operating route.
3. The method according to claim 2, characterized in that Based on the constraint condition set, the MPC-based autonomous driving bus trajectory target optimization control model is established with the goal of minimizing the environmental benefits of the autonomous driving bus to be controlled and the total operating time within the target operating route, including: Based on the constraint condition set and the environmental benefit quantification model, an initial optimization control model of the autonomous driving bus trajectory based on MPC is established with the goal of minimizing the environmental benefit and the total operating time of the autonomous driving bus to be controlled within the target operating route; The MPC-based automatic driving bus trajectory initial optimization control model is subjected to rolling optimization to obtain the MPC-based automatic driving bus trajectory target optimization control model.
4. The method according to claim 1, characterized in that: The MPC-based autonomous driving bus trajectory target optimization control model is used to optimize the running trajectory of the autonomous driving bus to be controlled within the target running route to obtain the target running trajectory, including: Obtaining an initial running trajectory of the to-be-controlled autonomous driving bus within the target running route; Based on the initial operation trajectory, the MPC-based autonomous driving bus trajectory target optimization control model is solved using a nonlinear optimization algorithm to obtain the target operation trajectory.
5. The method according to claim 1, characterized in that Obtaining the initial running trajectory of the to-be-controlled autonomous driving bus within the target running route includes: Acquire a road infrastructure dataset, a bus network dataset, and a historical running trajectory dataset of the autonomous driving bus to be controlled based on the target running route; Based on the road infrastructure dataset, the bus network dataset and the historical operation trajectory dataset, the initial operation trajectory of the autonomous driving bus to be controlled within the target operation route is obtained through vehicle following principle and improved Newell following model processing.
6. An automatic driving bus trajectory optimization control device, characterized in that: The device comprises: A first acquisition module is used to acquire a constraint condition set; The second acquisition module is used to obtain the energy consumption and emission measured data set and the target operation route of the autonomous driving bus to be controlled; A processing and establishment module, used to establish an environmental benefit quantification model based on the energy consumption and emission measured data set after being processed by the VSP interval clustering method; Establishing a module for establishing an MPC-based automatic driving bus trajectory target optimization control model based on the constraint condition set, the environmental benefit quantification model and the target operation route; A control module, configured to optimize the running trajectory of the autonomous driving bus to be controlled within the target running route by using the MPC-based autonomous driving bus trajectory target optimization control model to obtain a target running trajectory; Wherein, the first acquisition module includes: The first acquisition submodule is used to acquire an operation force data set, a driving mode and an operation data set of the autonomous driving bus to be controlled; A first determination submodule, configured to determine the constraint condition set based on the operation force data set, the driving mode and the operation data set; Wherein, the processing and establishing module includes: The second acquisition submodule is used to acquire the operating environment of the autonomous driving bus to be controlled; A first establishment submodule is used to establish an energy consumption and emission model based on the VSP based on the operating environment; A processing and establishing submodule, for establishing the environmental benefit quantification model based on the energy consumption and emission measured data set and the VSP-based energy consumption and emission model after processing by a VSP interval clustering method; The VSP-based energy consumption emission model in the first establishment submodule is identified by the following relational expression: VSP=v[a+9.807×sin(grade)+0.09199]+0.000169×v 3 Where: VSP represents the instantaneous power per unit mass of the motor vehicle, in kW / t; v represents the vehicle speed, in m / s; a represents the acceleration, in m / s 2 ;grade indicates slope, unit: %; The processing and establishing submodule is specifically used for: Using the VSP interval clustering method, VSP is divided into different intervals at certain intervals, which can be expressed as the following first relation: Where: bin represents interval; n represents an integer; l is determined according to the vehicle type, energy type, operating environment, and speed limit of the research object; Using the VSP interval clustering method, the energy consumption and emission rates of traditional buses and autonomous buses in each VSP interval are calculated, which can be expressed as the following second relationship: IS i,k =EU i,k ÷N k Where: ER i,k EF represents the emission rate or energy consumption rate of vehicle i in the kth VSP interval, in g / s; i,k represents the total emission or total energy consumption of vehicle i in the kth VSP interval, in g; N k represents the total time of the vehicle in the kth VSP interval, in seconds; The current VSP value is calculated through the micro-operation data of the bus, and the current energy consumption and emission rate are found in the corresponding interval, which is expressed as the following third relationship: IS t =δ(VSPbin) Where: ER t represents the emission rate at time t; the function δ(·) represents the corresponding function between VSP and energy consumption and emission rate; The corresponding total energy consumption and emissions are calculated by the following fourth relationship: ES=∑(ER tk ×D k ) Where: ES represents the total energy consumption or emission of public transport vehicles in the study section, unit: g; ER tk represents the energy consumption and emission rate of the vehicle in the kth VSP interval at time t, in g / s; D k represents the total time of the kth VSP interval, in seconds; An environmental benefit quantification model that reflects the environmental benefits including the total energy consumption and emissions of the autonomous driving bus to be controlled is established through the first, second, third and fourth relationships.
7. A computer device, characterized in that: include: A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the automatic driving bus trajectory optimization control method according to any one of claims 1 to 5 by executing the computer instructions.
8. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a computer to execute the autonomous driving bus trajectory optimization control method according to any one of claims 1 to 5.
Citation Information
Patent Citations
Traveling-track-based ecological driving optimization method and system
CN104778851A
Automated Driving Integrated Control Apparatus, Automated Driving Integrated Control System, and Vehicle Control Apparatus
US20190302797A1
