Multi-target pull-in trajectory planning method for port type stops of automatic driving bus

Abstract

The invention relates to a multi-target pull-in trajectory planning method for an automatic driving bus harbor type stop, and the method comprises the steps: S1, setting a control region, and building a plane coordinate system; s2, determining a basic operation rule of the bus; s3, determining a trajectory planning target and determining a trajectory planning constraint condition according to the multi-target pull-in trajectory planning model; step S31, selecting the minimum weighted values of the punctuality P, the energy consumption E and the comfort C as a target of bus pull-in track planning; step S32, determining constraint conditions of trajectory planning, and considering speed, acceleration, curvature, driving distance, starting and ending positions and driving obstacle avoidance constraints; s4, solving the planning model through a sequential quadratic optimization algorithm to obtain an optimal driving track of the bus; s5, executing the vehicle track according to the step S4; and S6, waiting for triggering of a next round of decision. The method can effectively achieve the decision-making of the whole automatic driving bus station entering process in a harbor type stop station scene.

Description

Technical Field

[0001] The present invention relates to the field of autonomous vehicle control, and more particularly, to a multi-objective in-station trajectory planning method for an autonomous bus bay-type stop. Background Art

[0002] In recent years, autonomous vehicles have achieved information sharing between vehicles and between vehicles and roads with the help of advanced sensing devices, showing great potential in improving driving safety and traffic efficiency. The behavioral decision-making and planning of autonomous vehicles have become a research hotspot. In the scenario of a bus bay-type stop, the bus in-station behavior is a typical high-frequency vehicle decision-making behavior. The core problem of the autonomous bus in-station system lies in trajectory planning. The vehicle collects information on its body position and obstacles in the approaching environment through sensors, and thus plans the optimal path from the initial position of the vehicle to the target parking space. Different from private cars, buses have an operating nature. During the bus in-station process, not only the enterprise operation cost but also the passenger experience should be considered. Therefore, in-station trajectory planning needs to consider factors such as arrival punctuality, energy consumption, and comfort, and the control range should not be limited to the local area of the bay-type stop. Existing research has not comprehensively considered the entire process of vehicle in-station, and the control objectives are relatively single. Based on this, on the basis of using autonomous driving technology, how to effectively control bus in-station while considering multiple factors is an urgent problem for those skilled in the art. Summary of the Invention

[0003] The purpose of the present invention is to overcome the above-mentioned defects in the prior art, and provide a multi-objective in-station trajectory planning method for an autonomous bus bay-type stop. This method involves the application of autonomous driving technology. On the basis of determining the control area, a multi-objective trajectory planning model is constructed, and the sequential quadratic programming algorithm is used for solution to obtain the optimal in-station driving trajectory of the bus vehicle.

[0004] To achieve the above object, the present invention provides a multi-objective in-station trajectory planning method for an autonomous bus bay-type stop, specifically including the following steps: Step S1: Set the control area and establish a plane coordinate system; The applicable scenario is a bay-type bus stop under the condition of a bus-only lane. The total length of the autonomous bus control area is , including the length of the road control area , the deceleration area length of the bay-type stop, and the parking area length . The lane width is , the width of the stopping area is , the angle between the platform and the deceleration area is , the length of the bus body , width , height , Wheelbase , Front overhang , Rear overhang , The four vertices of the bus are respectively , The angle between the vehicle body and the horizontal plane is the vehicle body direction angle , Establish a plane coordinate system, with the starting point of the horizontal axis being the starting point of the control area along the driving direction of the bus on the road, and the starting point of the vertical axis being the curbstone on the outer edge of the bus stop; Step S2: Determine the basic operation rules of the bus; Step S3: The multi-objective in-station trajectory planning model, including determining the trajectory planning objective and determining the trajectory planning constraint conditions; Step S4: Solve the planning model through the sequential quadratic optimization algorithm to obtain the optimal driving trajectory of the bus; Step S5: Execute the vehicle trajectory according to the trajectory output in Step S4; Step S6: Wait for the next round of decision trigger.

[0005] As a preference of the present invention, the following steps are further included in Step S2: Step S21: The moment when the bus arrives at the starting point of the control area is =0, and at this time the bus is already driving in the outermost lane, and the speed is , The safety distance between the vehicle body and the lane boundary before entering the station , The safety distance between the vehicle body and the platform boundary when docking , The distance from the front end of the vehicle to the front end of the platform when docking , The distance between the vehicle and the platform after docking , Take the trajectory of the center point of the front axle of the bus as the vehicle trajectory, and define The state of the bus at time as: (1); Wherein are respectively The horizontal and vertical coordinates of the bus at time are respectively The horizontal and vertical speeds of the bus at time and represent at time and The accelerations in the directions of

[0006] As a preference of the present invention, the following steps are further included in Step S21: Step S22: Within the control area, assume the driving distance of the autonomous bus is , Among them, the driving distance during the approach preparation stage , during the bus approach preparation stage, the bus experiences two driving states successively, which are divided into two parts. First, the first part is that the bus travels at a constant speed for a driving time of , and the driving distance is ; the second part is that the bus then decelerates at a deceleration of for a driving time of , and the driving distance . The final speed at this stage is set to . The parameter expressions for these two parts are as follows: The expression for the driving distance is as follows: (2); The expression for the driving distance is as follows: (3); The expression for the driving distance during the approach preparation stage is as follows: (4); The expression for the speed in the second part is as follows: (5); The expression for the acceleration in the second part is as follows: (6).

[0007] As an optimization of the present invention, step S22 further includes the following steps: Step S23: The driving distance for the bus to change lanes and drive into the bay stop, the driving time , the driving distance . In this stage, a fifth-degree polynomial trajectory planning model is selected to express the lane-changing trajectory, as follows: (7); , where are the coefficients of the fifth-degree polynomial. The first derivative and the second derivative are respectively calculated for the above formula: (9); The bus state at the end of the bus approach preparation stage is the starting point of the fifth-degree polynomial trajectory, expressed as: (10); The termination state after the bus stops at the station is: (11); When the initial moment of the bus changing lanes and entering the station and the end moment and its state are known, the trajectory coefficient of the vehicle is calculated, and then the optimal trajectory is selected through the in-station trajectory planning model.

[0008] As an optimization of the present invention, step S3 further includes the following steps: Step S31: Select the minimum weighted value of punctuality , energy consumption , and comfort as the goal of bus in-station trajectory planning. After normalization, the objective function expression is as follows: min (12); wherein, , , are the weight coefficients corresponding to each goal respectively, satisfying , , , are the reference values; In step S31, the expression of punctuality is as follows: (13); wherein, is the expected arrival and stop time of the bus, and the punctuality reference value is set.

[0009] As an optimization of the present invention, step S31 further includes the following steps: In step S31, the expression of energy consumption is as follows: (14); wherein, and are the energy consumptions of the bus during uniform motion and deceleration respectively; During the uniform motion stage, the energy consumption of the bus is calculated as: (15); Considering the efficiency loss, the motor output power during the uniform motion stage of the bus is: (16); wherein, is the mechanical transmission efficiency, is the motor efficiency, is the battery efficiency; The power Is the traction force And the speed The product of: (17).

[0010] As an optimization of the present invention, step S31 further includes the following steps: During the constant-speed driving stage, the traction force of the pure electric bus moving longitudinally overcomes the rolling resistance, the gradient resistance, and the air resistance. The traction force calculation formula is as follows: (18); (19); In the formula: Is the traction force, Is the rolling resistance, Is the gradient resistance, Is the air resistance, Is the angle between the vehicle body and the horizontal plane, Is the air resistance coefficient, Is the speed, Is the frontal area, Is the speed, Is the total mass of the vehicle and passengers, Is the acceleration due to gravity, Is the rolling resistance coefficient; Therefore, the energy consumption of the bus during the constant-speed driving stage The calculation formula is: (20); During the deceleration driving stage, the pure electric bus has energy recovery. A part of the kinetic energy is used to offset the driving resistance, and the other part is converted into electrical energy by the drive motor to charge the power battery, and the remaining part is dissipated as heat; according to the kinematic relationship, the braking energy Of the pure electric bus during the deceleration time is expressed as: (21); The kinetic energy reduced to offset the driving resistance Is expressed as: (22); The energy recovered by the pure electric bus during deceleration Is expressed as: (23); In the formula: Is the brake distribution ratio; The braking energy recovery efficiency coefficient Can be expressed as: (24); During the deceleration stage, the braking energy of the pure electric bus is expressed as (25); Let the energy consumption reference value be the energy consumed by the bus when traveling a distance at the initial speed .

[0011] As a preference of the present invention, the following steps are further included in step S31: In step S31, the comfort is expressed by the following formula: (26); wherein means dividing the carriage into areas, the number of standing and sitting passengers in area are and respectively, and the comfort levels are and respectively; The comfort of standing passengers is calculated by the following formula: (27); wherein the comprehensive weighted acceleration of the standing passengers at is expressed as: (28); wherein and respectively represent at the acceleration in the axis and the comfort of sitting passengers is calculated by the following formula: (29); The comprehensive weighted acceleration of the sitting passengers at is expressed as: (30); Let the comfort reference value be the comfort value calculated by decelerating the bus at the maximum acceleration .

[0012] As a preference of the present invention, the following steps are further included in step S3: Step S32: Determine the constraint conditions for trajectory planning, considering the speed 、Acceleration 、Jerk 、Curvature 、Travel distance, start and end positions, travel obstacle avoidance constraints; Among them, the speed constraint is expressed as: (31); The acceleration constraint is expressed as: (32); The jerk constraint is expressed as: (33); Among them, 、 、 are the maximum speed, maximum acceleration, and maximum jerk values respectively; The curvature The calculation formula is expressed as: (34); The curvature constraint is expressed as: (35); is the minimum turning radius of the bus, with a value range of 8m - 12m; When the bus is in the straight - line driving stage, that is, at the end moment of changing lanes and entering the bay - side stop, there is no wheel steering, that is: (36).

[0013] As an optimization of the present invention, step S32 further includes the following steps: The horizontal and vertical coordinates of the four vertices of the bus at moment are respectively expressed as ([[]] , ), ([[]] , ), ([[]] , ), ([[]] , ). According to the Ackermann steering model, the real - time coordinate positions of the four vertices are obtained; during the bus's approach to the station, there is a safety distance between the outer edge of the vehicle and the road and platform boundary, and the obstacle avoidance constraint is expressed as: (1) Control safety, the vehicle travels within the controllable range; the straight - line uniform - speed travel distance constraint , the straight - line deceleration travel distance constraint ; (3) The rear of the vehicle has not entered the bay, and the front of the vehicle has not entered the bay, that is, when , it satisfies , , , ; (4) The rear of the bus has not entered the bay and the front is in the deceleration area, that is, when , , it satisfies , , , , ; Among them, is the steering angle of the bus, and its expression is as follows: (37); Among them, is the relationship between the longitudinal running trajectory of the bus and time, is the relationship between the lateral running trajectory of the bus and time; (5) The rear of the bus has not entered the bay and the front is in the docking area, that is, when , , it satisfies , , , , ; (6) The rear is in the deceleration area and the front is in the deceleration area. When , , it satisfies , , , ; (7) The rear is in the deceleration area and the front is in the docking area, that is, when , , it satisfies , , , ; (8) The rear is in the docking area and the front is in the docking area, that is, when , , it satisfies , , , ; In addition, the state constraints at the bus starting and ending points are expressed as: (1) The starting state of the bus is ; (2) The ending state of the bus is .

[0014] The beneficial effects of the present invention are as follows: 1. A multi-objective approach for the inbound trajectory planning of an autonomous bus at a bay-side stop according to the present invention relates to the innovative application of autonomous driving technology and can effectively achieve the whole-process decision-making of an autonomous bus entering the station in a bay-side stop scenario.

[0015] 2. By constructing a trajectory planning model, the present invention divides the entire inbound process into a constant-speed stage, a variable deceleration stage, and a lane-changing and inbound stage. Considering the characteristics of bus operation, it defines the operating states of each stage and pays attention to the front-back correlation and mutual influence of each driving stage, so that the trajectory planning result can reach the global optimum.

[0016] 3. The trajectory planning model constructed by the present invention fully considers the enterprise operation cost and the passenger riding experience, and proposes a multi-objective optimization function including punctuality, energy consumption, and comfort. In terms of constraints, it fully considers the characteristics of bus vehicles, operating characteristics, and safety factors, so that the trajectory planning result can reach the optimum of comprehensive factors.

[0017] 4. The energy consumption sub-objective proposed by the present invention considers the energy consumption characteristics of pure electric buses, and the kinetic energy recovery is considered in the deceleration stage; the comfort sub-objective proposed considers the comfort values of passengers in different areas of the carriage and in different standing and sitting states, and the obtained inbound trajectory is more in line with the actual decision-making scenario. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the following drawings are some embodiments of the present invention.

[0019] Figure 1 is the flow schematic diagram of the multi-objective inbound trajectory planning method for an autonomous bus at a bay-side stop provided by the present invention; Figure 2 is the plan view of the control area for the multi-objective inbound trajectory planning of an autonomous bus at a bay-side stop provided by the present invention; Figure 3 is the flow chart of the sequential quadratic programming algorithm provided by the present invention; Figure 4 is the schematic diagram of the full-course planned trajectory provided by the present invention; Figure 5 is the schematic diagram of the trajectory of a bus changing lanes and entering the bay-side stop provided by the present invention; Figure 6 is one of the diagrams related to the simulation parameters of the experimental data provided by the present invention; Figure 7 is the second diagram related to the simulation parameters of the experimental data provided by the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0020] Example 1

[0021] This example provides a multi-objective approach for planning the approach trajectory of an autonomous bus at a bay-type bus stop, which specifically includes the following steps: Step S1: Set the control area and establish a plane coordinate system; The applicable scenario is a bay-type bus stop under the condition of a bus-only lane. The total length of the control area for the autonomous bus is , including the length of the road control area and the deceleration area length of the bay-type bus stop and the parking area length , the lane width is , the width of the stopping area is , the angle between the platform and the deceleration area is , the length of the bus body , width , height , wheelbase , front overhang , rear overhang , the four vertices of the bus are respectively , the angle between the bus body and the horizontal plane is the body direction angle , establish a plane coordinate system, the starting point of the horizontal axis is the starting point of the control area where the bus travels along the road, and the starting point of the vertical axis is the curbstone on the outer edge of the bus platform; Step S2: Determine the basic operating rules of the bus; Step S21: The moment when the bus arrives at the starting point of the control area is =0, and at this time the bus is already traveling in the outermost lane, with a speed of , the safety distance between the bus body and the lane boundary before entering the station is , the safety distance between the bus body and the platform boundary when stopping is , the distance from the front end of the vehicle to the frontmost end of the platform when stopping is , the distance between the vehicle and the platform after stopping is , taking the trajectory of the center point of the front axle of the bus as the vehicle trajectory, define the state of the bus at time as: (1); where are respectively the horizontal and vertical coordinates of the bus at time are respectively the horizontal and vertical speeds of the bus at time and represent the and direction accelerations at time Within the control area, let the driving distance of the autonomous bus be , where the driving distance during the approach preparation stage is . During the approach preparation stage, the bus goes through two driving states and is divided into two parts. First, in the first part, the bus travels at a constant speed of for a driving time of , and the driving distance is . Second, in the second part, the bus then decelerates at a deceleration of for a driving time of (controlled by a trigonometric speed curve), and the driving distance is . The final speed at this stage is set to . The parameter expressions for these two parts are as follows: The expression for the driving distance is as follows: (2); The expression for the driving distance is as follows: (3); The expression for the driving distance during the approach preparation stage is as follows: (4); The expression for the speed in the second part is as follows: (5); The expression for the acceleration in the second part is as follows: (6); The driving distance for the bus to change lanes and drive into the bay stop, the driving time is , and the driving distance is . In this stage, a fifth-degree polynomial trajectory planning model is selected for the lane-changing trajectory expression, as follows: (7); , where are the coefficients of the fifth-degree polynomial. The first derivative and second derivative of the above formula are obtained respectively: (8); The state of the bus at the end of the approach preparation stage is the starting point of the fifth-degree polynomial trajectory, expressed as: (10); The termination state after the bus stops at the station is: (11); When the initial time and the end time of the bus lane-changing and approaching the station and its state are known, the trajectory coefficient of the vehicle can be obtained, and the optimal trajectory can be selected through the approaching-station trajectory planning model; Step S3: The multi-objective approaching-station trajectory planning model, including determining the trajectory planning objective and determining the trajectory planning constraint conditions; Step S31: Select the weighted value of punctuality , energy consumption , comfort to be the minimum as the objective of the bus approaching-station trajectory planning. After normalization, the objective function expression is as follows: min (12); wherein, , , , are the weight coefficients corresponding to each objective respectively, satisfying , , , are the reference values; In the step S31, the expression of punctuality is as follows: (13); wherein, is the expected arrival and stop time of the bus. Let the punctuality reference value ; In the step S31, the expression of energy consumption is as follows: (14); wherein, and are the energy consumptions of the bus running at a constant speed and decelerating respectively; In the constant-speed driving stage, the energy consumption of the bus is calculated as: (15); Considering the efficiency loss, the motor output power in the constant-speed driving stage of the bus is: (16); wherein, is the mechanical transmission efficiency, is the motor efficiency, is the battery efficiency; The power of the bus running at a constant speed is the traction force Product: (17); During the constant-speed driving stage, the traction force for the longitudinal driving of a pure electric bus must overcome the rolling resistance, gradient resistance, and air resistance. The traction force calculation formula is as follows: (18); (19); Where: is the traction force, is the rolling resistance, is the gradient resistance, is the air resistance, is the angle between the vehicle body and the horizontal plane, is the air resistance coefficient, is the speed, is the vehicle mass, and the passenger mass sum, is the acceleration due to gravity; Therefore, the energy consumption of the bus during the constant-speed driving stage The calculation formula is: During the deceleration driving stage, the pure electric bus has energy recovery. Part of the kinetic energy is used to offset various driving resistances, another part is converted into electrical energy by the drive motor for charging the power battery, and the remaining part is dissipated as heat; According to the kinematic relationship, the braking energy of the pure electric bus during the deceleration time is expressed as: The kinetic energy reduced for offsetting various driving resistances is expressed as: (22); The energy recovered by the pure electric bus during deceleration is expressed as: (23); Where: is the brake distribution ratio; The braking energy recovery efficiency coefficient can be expressed as: (24); During the deceleration driving stage, the braking energy of the pure electric bus is expressed as: Let the energy consumption reference value The energy consumed by the bus traveling a distance at an initial speed; In the step S31, the comfort expression is as follows: Expression is as follows: (26); wherein, represents dividing the carriage into areas, the number of standing and sitting passengers in area are and respectively, and the comfort levels are and respectively; The comfort level of standing passengers is calculated as follows: (27); wherein, the combined weighted acceleration of standing passengers at time is expressed as: (28); wherein, and respectively represent at time, the accelerations in the axis and axis directions; The comfort level of sitting passengers is calculated as follows: The combined weighted acceleration of sitting passengers at time is expressed as: (30); Let the comfort reference value be the comfort value calculated by the bus decelerating at the maximum acceleration ; Step S32: Determine the constraint conditions for trajectory planning, considering speed , acceleration , jerk , curvature , travel distance, start and end positions, and travel obstacle avoidance constraints; Among them, the speed constraint is expressed as: (31); The acceleration constraint is expressed as: (32); The jerk constraint is expressed as: (33); Wherein, , , are the maximum speed, maximum acceleration, and maximum jerk values respectively; The curvature is calculated as: (34); The curvature constraint is expressed as: (35); is the minimum turning radius of the bus, with a value range of 8m - 12m; When the bus is driving in a straight line, that is, at the end moment of changing lanes and entering the bay stop, there is no wheel steering, that is: (36); The horizontal and vertical coordinates of the four vertices of the bus at are respectively expressed as ( , ), ( , ), ( , ), ( , ). According to the Ackermann steering model, the real-time coordinate positions of the four vertices are obtained; during the bus's approach to the station, the outer edge of the vehicle should maintain a certain safety distance from the road and platform boundaries. The obstacle avoidance constraint is expressed as: (1) Control safety, and the vehicle drives within the controllable range; the straight-line uniform driving distance constraint , the straight-line decelerating driving distance constraint ; (3) The rear of the vehicle has not entered the bay, and the front of the vehicle has not entered the bay. That is, when , it satisfies , , , ; (4) The rear of the vehicle has not entered the bay, and the front of the vehicle is in the deceleration zone. That is, when , , it satisfies , , , , ; Wherein, is the steering angle of the bus, and its expression is as follows: (37); Among them, is the relationship between the longitudinal running trajectory of the bus and time, is the relationship between the lateral running trajectory of the bus and time; (5) The rear of the vehicle has not entered the bay, and the front of the vehicle is in the parking area, that is, when , , it satisfies , , , , ; (6) The rear of the vehicle is in the deceleration area, and the front of the vehicle is in the deceleration area. When , , it satisfies , , , ; (7) The rear of the vehicle is in the deceleration area, and the front of the vehicle is in the parking area, that is, when , , it satisfies , , , ; (8) The rear of the vehicle is in the parking area, and the front of the vehicle is in the parking area, that is, when , , it satisfies , , , ; In addition, the state constraints at the bus starting and ending points are expressed as: (1) The starting state of the bus is ; (2) The ending state of the bus is ; Step S4: Solve the planning model through the sequential quadratic programming algorithm to obtain the optimal driving trajectory of the bus; Step S5: Execute the vehicle trajectory according to the trajectory output in Step S4; Step S6: Wait for the next round of decision trigger.

[0022] Embodiment 2

[0023] Refer to Figure 1-7 This embodiment provides a multi-objective approach for planning the approach trajectory of an autonomous bus at a bay-type stop, which includes the following steps: Step S1: Set the control area and establish a plane coordinate system; Among them, please refer to Figure 1, the relevant information on the experimental data simulation parameters of this embodiment can be found in Figure 6 and Figure 7 .

[0024] Step S2: Perform model solving; Refer to Figure 3 , the model established in this embodiment is a multi-objective optimization model with the uniform driving time , deceleration driving time , the final speed in the deceleration section , lane-changing and parking driving time as control variables. In this embodiment, the function in MATLAB is used to solve the global minimum of a non-linear multi-variable model with constraints; Refer to Figure 4 , Step S3: Execute the vehicle trajectory according to the trajectory output in Step S2, The punctuality index is 6, the energy consumption is 2,438,000 joules, the comfort index is 701.25, and the total consumption time is 31 seconds; Step S4: Wait for the next round of decision trigger.

[0025] The above is only the specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention can easily think of changes or substitutions, which should all be covered within the protection scope of the present invention. Therefore, the protection scope of the present invention should be subject to the protection scope of the claims.

Claims

1. A multi-target entry trajectory planning method for an autonomous bus bay stop, characterized in that: The following steps are involved: Step S1: Set the control area and establish a plane coordinate system; The applicable scenario is a bay-type bus stop under the condition of a bus lane. The total length of the autonomous driving bus control area is , including the length of the road control area , Length of deceleration zone at bay-type stops and parking area length , lane width is , the width of the parking area is , the angle between the platform and the deceleration zone is , bus body length ,width ,high , wheelbase 、Front overhang 、Rear suspension The four vertices of the bus are , the angle between the vehicle body and the horizontal plane is the vehicle body direction angle , establish a plane coordinate system, the starting point of the horizontal axis is the starting point of the control area along the road direction of the bus, and the starting point of the vertical axis is the curbstone at the outer edge of the bus platform; Step S2: Determine the basic operation rules of the bus; Step S3: a multi-objective entry trajectory planning model, including determining trajectory planning objectives and determining trajectory planning constraints; Step S4: Solve the planning model through a sequential quadratic optimization algorithm to obtain the optimal driving trajectory of the bus; Step S5: executing the vehicle trajectory according to the trajectory output in step S4; Step S6: Wait for the next round of decision triggering.

2. According to claim 1, a multi-target entry trajectory planning method for an autonomous driving bus bay stop is characterized in that: Step S2 also includes the following steps: Step S21: The bus arrives at the starting point of the control area at =0, and the bus is already in the outermost lane at this time, with a speed of , safe distance between the vehicle body and lane boundary before entering the station , safe distance between the vehicle body and the platform boundary when stopping , the distance from the front end of the vehicle to the front end of the platform when stopping , the distance between the vehicle and the platform after it stops , taking the center point trajectory of the bus front axle as the vehicle trajectory, define Bus status for: （1）； in They are The horizontal and vertical coordinates of the bus time. They are The horizontal and vertical speed of the bus at that moment, and express Moment and Direction of acceleration.

3. The multi-target entry trajectory planning method for an autonomous driving bus bay stop according to claim 2 is characterized in that: Step S21 also includes the following steps: Step S22: Within the control area, the driving distance of the autonomous driving bus is , where the driving distance in the preparation phase is The bus goes through two driving states in the preparation stage of entering the station, which are divided into two parts. First, the first part is that the bus The driving time is constant speed. , the driving distance is ; The second part is that the bus decelerates Slow down and the driving time is , driving distance The final speed of this stage is set to , the parameter expression of these two parts is as follows: Driving distance The expression is as follows: （2）； Driving distance The expression is as follows: （3）； Distance travelled during the pit stop preparation phase The expression is as follows: （4）； The second part of the speed is expressed as follows: （5）； The second part of the acceleration is expressed as follows: （6）。 4. The multi-target entry trajectory planning method for an autonomous driving bus bay stop according to claim 3 is characterized in that: Step S22 also includes the following steps: Step S23: The distance traveled by the bus when changing lanes and entering the harbor stop , driving time , driving distance In this stage, the quintic polynomial trajectory planning model is selected to express the lane change trajectory as follows: （7）； , Are the coefficients of the fifth-order polynomial, and calculate the first-order derivative and the second-order derivative of the above formula respectively: （8）； （9）； The bus state at the end of the bus station preparation phase is the starting point of the quintic polynomial trajectory, expressed as: （10）； The final status of the bus after it stops at the station is: （11）； When the bus changes lanes and enters the station, the initial moment and end time and its state are known, the trajectory coefficient of the vehicle is calculated, and then the optimal trajectory is selected through the entry trajectory planning model.

5. The multi-target entry trajectory planning method for an autonomous driving bus bay stop according to claim 1 is characterized in that: Step S3 also includes the following steps: Step S31: Select punctuality , Energy consumption , Comfort The minimum weighted value of is taken as the goal of bus entry trajectory planning. The normalized objective function expression is as follows: min (12); in, , , are the weight coefficients corresponding to each target, satisfying , , , is the base value; In step S31, the punctuality The expression is as follows: （13）； in, Set the on-time benchmark value for the expected arrival time of the bus .

6. The multi-target entry trajectory planning method for an autonomous driving bus bay stop according to claim 5 is characterized in that: Step S31 also includes the following steps: In step S31, energy consumption The expression is as follows: （14）； in, and are the energy consumption of the bus running at a constant speed and at a reduced speed respectively; During the uniform speed driving stage, the energy consumption of the bus The calculation formula is: （15）； Considering the efficiency loss, the motor output power of the bus during the uniform speed driving stage is for: （16）； in, Mechanical transmission efficiency, Motor efficiency, Battery efficiency; Bus constant speed power For traction and speed The product of: （17）。 7. The multi-target entry trajectory planning method for an autonomous driving bus bay stop according to claim 5 is characterized in that: Step S31 also includes the following steps: During the constant speed driving stage, the traction force calculation formula is as follows: （18）； （19）； Where: For traction, is the rolling resistance, is the slope resistance, is the air resistance, is the angle between the vehicle body and the horizontal plane, is the air resistance coefficient, is the windward area, For speed, is the total mass of the vehicle and passengers, is the acceleration due to gravity, is the rolling resistance coefficient; Therefore, the energy consumption of buses during the uniform speed driving stage is The calculation formula is: （20）； During the deceleration phase, pure electric buses have energy recovery; according to the kinematic relationship, the braking energy of the pure electric bus during the deceleration time is It is expressed as: （21）； Used to offset the kinetic energy reduced by driving resistance It is expressed as: （22）； Energy recovered during deceleration of pure electric buses It is expressed as: （23）； Where: is the brake distribution ratio; Braking energy recovery efficiency coefficient It is expressed as: （24）； The braking energy of a pure electric bus during deceleration express （25）； Set energy consumption benchmark The bus has an initial speed Driving distance The energy consumed.

8. The method for planning multi-target entry trajectories for an autonomous bus bay stop according to claim 5, characterized in that: Step S31 also includes the following steps: In step S31, comfort The expression is as follows: （26）； in, Indicates that the carriage is divided into Regions, areas The number of standing and sitting passengers are and The comfort is and ; Standing passenger comfort The calculation formula is as follows: （27）； Among them, standing passengers The comprehensive weighted acceleration at the moment Expressed as: （28）； in, and Respectively time, Axis and Acceleration in the axis direction; Comfort for seated and standing passengers The calculation formula is as follows: （29）； Seated passengers The comprehensive weighted acceleration at the moment Expressed as: （30）； Set comfort level The bus has the maximum acceleration Comfort value calculated for deceleration driving.

9. The multi-target entry trajectory planning method for an autonomous driving bus bay stop according to claim 1 is characterized in that: Step S3 also includes the following steps: Step S32: Determine the constraints of trajectory planning, taking into account the speed , acceleration , jerk , curvature , driving distance, starting and ending positions, and driving obstacle avoidance constraints; The speed constraint is expressed as: （31）； The acceleration constraint is expressed as: （32）； The jerk constraint is expressed as: （33）； in, , , They are the maximum speed, maximum acceleration, and maximum jerk values ​​respectively; Curvature The calculation formula is expressed as: （34）； The curvature constraint is expressed as: （35）； It is the minimum turning radius of the bus, ranging from 8m to 12m; When the bus is in the straight-line driving stage, that is, at the end of the lane change to enter the harbor stop, there is no wheel turning, that is: （36）。 10. The multi-target entry trajectory planning method for an autonomous driving bus bay stop according to claim 9 is characterized in that: Step S32 also includes the following steps: The four vertices of the bus are The horizontal and vertical coordinates of the time are represented as ( , )、( , )、( , )、( , ), the real-time coordinate positions of the four vertices are obtained according to the Ackerman steering model; when the bus enters the station, the outer edge of the vehicle has a safe distance from the road and the platform boundary, and the obstacle avoidance constraint is expressed as: (1) Control safety, the vehicle travels within a controllable range; straight-line uniform speed driving distance constraint , straight line deceleration driving distance constraint ; (3) The rear of the vehicle has not entered the harbor, and the front of the vehicle has not entered the harbor. When, meet , , , ; (4) The rear of the vehicle has not entered the harbor, and the front of the vehicle is in the deceleration zone. , When, meet , , , , ; in, is the steering angle of the bus, which is expressed as follows: （37）； in, is the relationship between the longitudinal running trajectory of the bus and time, is the relationship between the lateral running trajectory of the bus and time; (5) The rear of the vehicle has not entered the harbor, and the front of the vehicle is in the parking area. , When, meet , , , , ; (6) The rear of the vehicle is in the deceleration zone, and the front of the vehicle is in the deceleration zone. , When, meet , , , ; (7) The rear of the vehicle is in the deceleration zone and the front of the vehicle is in the parking zone. , When, meet , , , ; (8) The rear of the vehicle is in the parking area, and the front of the vehicle is in the parking area. , When, meet , , , ; In addition, the state constraints at the bus origin and destination are expressed as: (1) The initial state of the bus is ; (2) The bus terminal status is .

Images