Optimal lane change trajectory selection method, device, equipment and readable storage medium

Abstract

This application relates to an optimal lane-changing trajectory selection method, apparatus, device, and readable storage medium, relating to the field of decision-making and planning technology for autonomous commercial vehicles. The method includes acquiring multiple candidate trajectories, including the vehicle's current driving trajectory; calculating the risk cost of each candidate trajectory based on vehicle collision time parameters, vehicle interval time parameters, and equivalent energy velocity parameters; calculating the comfort cost of each candidate trajectory based on acceleration rate of change parameters; calculating the speed cost of each candidate trajectory based on speed parameters; calculating the dynamic cost of each candidate trajectory based on mass parameters, acceleration parameters, speed parameters, and gradient parameters; and selecting the candidate trajectory with the minimum total cost from the multiple candidate trajectories based on the risk cost, comfort cost, speed cost, and dynamic cost as the optimal lane-changing trajectory for the vehicle, effectively achieving the selection of the optimal lane-changing trajectory for commercial vehicles.

Description

Technical Field

[0001] This application relates to the field of decision-making and planning technology for autonomous commercial vehicles, and in particular to an optimal lane-changing trajectory selection method, device, equipment, and readable storage medium. Background Technology

[0002] Commercial vehicles refer to automobiles used for transporting people and goods, mainly divided into five categories: buses, trucks, semi-trailer tractors, incomplete bus vehicles, and incomplete truck vehicles. They play an important role in national economic development, urbanization, and foreign trade, and are currently in a crucial stage of transitioning from high-speed growth to high-quality development. However, compared to passenger cars, commercial vehicles experience greater load variations due to their cargo-carrying nature, leading to significant changes in the vehicle's inertial parameters and further affecting its dynamic response characteristics. Therefore, when commercial vehicles are heavily loaded, acceleration performance decreases, requiring drivers to consider the vehicle's power usage during lane changes and choose appropriate routes. Simultaneously, the increased vehicle weight reduces the driver's willingness to change lanes.

[0003] In related technologies, traditional lane-changing trajectory planning algorithms do not consider the impact of vehicle load changes on lane-changing trajectory selection. As a result, commercial vehicles may not select the optimal path during lane-changing, which can easily lead to undesirable vehicle performance degradation and may also increase unnecessary lane changes. Summary of the Invention

[0004] This application provides an optimal lane-changing trajectory selection method, apparatus, device, and readable storage medium to solve the problem that traditional lane-changing trajectory planning algorithms in related technologies cannot select the optimal lane-changing trajectory for commercial vehicles.

[0005] Firstly, an optimal lane-changing trajectory selection method is provided, including the following steps:

[0006] Obtain multiple candidate trajectories, including the current driving trajectory of this vehicle;

[0007] The risk cost of each candidate trajectory is calculated based on vehicle collision time parameters, vehicle interval time parameters, and equivalent energy velocity parameters.

[0008] The comfort cost of each candidate trajectory is calculated based on the acceleration rate of change parameter;

[0009] Calculate the velocity cost for each candidate trajectory based on velocity parameters;

[0010] The dynamic cost of each candidate trajectory is calculated based on mass parameters, acceleration parameters, velocity parameters, and slope parameters.

[0011] Based on risk cost, comfort cost, speed cost, and power cost, the candidate trajectory with the minimum total cost is selected from multiple candidate trajectories as the optimal lane-changing trajectory for this vehicle.

[0012] In some embodiments, calculating the dynamic cost of each candidate trajectory based on mass parameters, acceleration parameters, velocity parameters, and slope parameters includes:

[0013] The vehicle mass was calculated using the least squares method and vehicle dynamics equations.

[0014] Substituting the vehicle mass, longitudinal acceleration of the candidate trajectory, longitudinal velocity of the candidate trajectory, and slope of the ramp containing the candidate trajectory into the first calculation formula, the dynamic cost of each candidate trajectory is obtained. The first calculation formula is:

[0015]

[0016] In the formula, C m t represents the cost of dynamism. F This represents the time domain for candidate trajectory planning, where m represents the vehicle mass. Let g represent the longitudinal acceleration of the candidate trajectory, f represent the gravitational acceleration, f represent the rolling resistance coefficient, and A represent the frontal area of ​​the vehicle. α represents the longitudinal velocity of the candidate trajectory, and α represents the slope of the ramp where the candidate trajectory is located.

[0017] In some embodiments, calculating the risk cost of each candidate trajectory based on vehicle collision time parameters, vehicle interval time parameters, and equivalent energy velocity parameters includes:

[0018] The first collision probability is determined based on the collision time between the vehicle and the target vehicle and the mapping relationship between the collision time and the collision probability.

[0019] The second collision probability is determined based on the time interval between the vehicle and the target vehicle and the mapping relationship between the time interval and the collision probability.

[0020] The equivalent energy velocity is calculated based on the mass of this vehicle, the speed of this vehicle before the collision, the mass of the target vehicle, and the speed of the target vehicle before the collision.

[0021] The risk cost of each candidate trajectory is calculated based on the first collision probability, the second collision probability, and the equivalent energy velocity.

[0022] In some embodiments, the calculation of the equivalent energy velocity based on the vehicle's mass, its pre-collision velocity, the target vehicle's mass, and the target vehicle's pre-collision velocity includes:

[0023] Substituting the mass of the vehicle, its pre-collision speed, the mass of the target vehicle, and its pre-collision speed into the second calculation formula, we obtain the equivalent energy velocity. The second calculation formula is as follows:

[0024]

[0025] In the formula, EES represents the equivalent energy velocity, M represents the vehicle's mass, V represents the vehicle's velocity before the collision, and M s V represents the target vehicle mass. s This indicates the speed of the target vehicle before the collision.

[0026] In some embodiments, the calculation of the risk cost for each candidate trajectory based on the first collision probability, the second collision probability, and the equivalent energy velocity includes:

[0027] The cost of the first collision is calculated based on the first collision probability and the equivalent energy velocity.

[0028] The cost of the second collision is calculated based on the second collision probability and the equivalent energy velocity.

[0029] The risk cost of each candidate trajectory is calculated based on the first collision cost and the second collision cost.

[0030] In some embodiments, calculating the comfort cost of each candidate trajectory based on the acceleration change rate parameter includes:

[0031] Substituting the longitudinal acceleration rate of change and the lateral acceleration rate of change of the candidate trajectories into the third calculation formula, the comfort cost of each candidate trajectory is obtained. The third calculation formula is as follows:

[0032]

[0033] In the formula, C c Indicating the cost of comfort, This represents the rate of change of longitudinal acceleration of the candidate trajectory. t represents the rate of change of lateral acceleration of the candidate trajectory. F W represents the time domain for candidate trajectory planning. d This represents the horizontal weighting coefficient.

[0034] In some embodiments, calculating the velocity cost for each candidate trajectory based on velocity parameters includes:

[0035] Substituting the velocity, desired velocity, and preset maximum speed limit of the candidate trajectory into the fourth calculation formula, we obtain the velocity cost for each candidate trajectory. The fourth calculation formula is as follows:

[0036] C V =|V Tra -min(V E Vmax )|

[0037] In the formula, C V V represents the speed cost. Tra V represents the velocity of the candidate trajectory. E V represents the desired speed. max This indicates the maximum speed limit.

[0038] Secondly, an optimal lane-changing trajectory selection device is provided, comprising:

[0039] The acquisition unit is used to acquire multiple candidate trajectories, including the current driving trajectory of the vehicle.

[0040] The calculation unit is used to calculate the risk cost of each candidate trajectory based on vehicle collision time parameters, vehicle interval time parameters, and equivalent energy velocity parameters; calculate the comfort cost of each candidate trajectory based on acceleration change rate parameters; calculate the velocity cost of each candidate trajectory based on velocity parameters; and calculate the dynamic cost of each candidate trajectory based on mass parameters, acceleration parameters, velocity parameters, and slope parameters.

[0041] The filtering unit is used to select the candidate trajectory with the minimum total cost from multiple candidate trajectories based on risk cost, comfort cost, speed cost, and power cost as the optimal lane-changing trajectory for this vehicle.

[0042] Thirdly, an optimal lane change trajectory screening device is provided, comprising: a memory and a processor, wherein the memory stores at least one instruction, and the at least one instruction is loaded and executed by the processor to implement the aforementioned optimal lane change trajectory screening method.

[0043] Fourthly, a computer-readable storage medium is provided, the computer storage medium storing a computer program that, when executed by a processor, implements the aforementioned optimal lane-changing trajectory selection method.

[0044] This application provides a method, apparatus, device, and readable storage medium for selecting the optimal lane-changing trajectory. The method includes acquiring multiple candidate trajectories, including the current driving trajectory of the vehicle; calculating the risk cost of each candidate trajectory based on vehicle collision time parameters, vehicle interval time parameters, and equivalent energy velocity parameters; calculating the comfort cost of each candidate trajectory based on acceleration rate of change parameters; calculating the speed cost of each candidate trajectory based on speed parameters; calculating the dynamic cost of each candidate trajectory based on mass parameters, acceleration parameters, speed parameters, and gradient parameters; and selecting the candidate trajectory with the minimum total cost from the multiple candidate trajectories based on the risk cost, comfort cost, speed cost, and dynamic cost as the optimal lane-changing trajectory for the vehicle. This application assesses the risk of a series of candidate trajectories considering the significant load variations of commercial vehicles. It not only calculates the risk cost, comfort cost, and speed cost of each trajectory but also calculates the dynamic cost based on vehicle mass, ultimately selecting the trajectory with the minimum cost as the optimal trajectory for the vehicle. The increase in the dynamic cost index can improve vehicle performance during lane-changing and avoid unnecessary lane changes, effectively achieving the selection of the optimal lane-changing trajectory for commercial vehicles. Attached Figure Description

[0045] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0046] Figure 1 A flowchart illustrating an optimal lane-changing trajectory selection method provided in an embodiment of this application;

[0047] Figure 2 A schematic diagram illustrating the overall framework of the optimal lane-changing trajectory selection method provided in the embodiments of this application;

[0048] Figure 3 TTC and P provided for embodiments of this application TTC A diagram illustrating the mapping relationship between them;

[0049] Figure 4 TIV and P provided for embodiments of this application TIV A diagram illustrating the mapping relationship between them;

[0050] Figure 5 A schematic diagram of the vehicle quality estimator architecture provided in an embodiment of this application;

[0051] Figure 6 This is one of the simulation results of the planned trajectory provided in the embodiments of this application;

[0052] Figure 7 Another simulation result of the planned trajectory provided in this application embodiment;

[0053] Figure 8 This is a schematic diagram of the structure of an optimal lane change trajectory screening device provided in an embodiment of this application. Detailed Implementation

[0054] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0055] This application provides an optimal lane-changing trajectory selection method, apparatus, device, and readable storage medium, which can solve the problem that traditional lane-changing trajectory planning algorithms in related technologies cannot select the optimal lane-changing trajectory for commercial vehicles.

[0056] See Figure 1 and Figure 2 As shown in the figure, this application provides an optimal lane-changing trajectory selection method, including the following steps:

[0057] Step S10: Obtain multiple candidate trajectories, including the current driving trajectory of the vehicle;

[0058] As an example, in this embodiment, trajectory planning for autonomous driving generally includes two steps: candidate trajectory generation and optimal trajectory selection. The specific process of candidate trajectory generation is as follows: First, determine the predicted trajectory of the target vehicle located in front of the current vehicle and the target lane where the current vehicle may change lanes. Then, perform polynomial trajectory planning based on the predicted trajectory and the target lane. For example, a fifth-order polynomial can be used to generate candidate trajectories, and the candidate trajectory cluster can be represented as:

[0059]

[0060] In the formula, s and d are the longitudinal and lateral coordinates of the trajectory in the Frenet coordinate system (i.e., the lane coordinate system), respectively; a and b represent the polynomial coefficients; and t is the time parameter. Solving this polynomial, based on the initial state conditions of the vehicle and the final state conditions determined by the lane-changing intention, yields the candidate trajectories and their corresponding parameters: longitudinal displacement, longitudinal velocity, and longitudinal acceleration of the candidate trajectory in the Frenet coordinate system; lateral displacement, lateral velocity, and lateral acceleration of the candidate trajectory in the Frenet coordinate system; and the sum of the squares of the longitudinal and lateral jerk (i.e., acceleration) of the candidate trajectory.

[0061] It should be understood that the target vehicle can be a passenger car or a commercial vehicle, depending on the actual situation, and is not limited here; it should be understood that the target lane includes the lane in which the vehicle is located, and therefore the generated candidate trajectory includes the trajectory in which the vehicle is currently traveling.

[0062] After generating the candidate trajectories, multiple candidate trajectories and their corresponding longitudinal displacement, longitudinal velocity, longitudinal acceleration, lateral displacement, lateral velocity, lateral acceleration, and the sum of squares of the longitudinal and lateral jerk values ​​in the Frenet coordinate system can be obtained.

[0063] Step S20: Calculate the risk cost of each candidate trajectory based on vehicle collision time parameters, vehicle interval time parameters, and equivalent energy velocity parameters;

[0064] Furthermore, the calculation of the risk cost for each candidate trajectory based on vehicle collision time parameters, vehicle interval time parameters, and equivalent energy velocity parameters includes:

[0065] The first collision probability is determined based on the collision time between the vehicle and the target vehicle and the mapping relationship between the collision time and the collision probability.

[0066] The second collision probability is determined based on the time interval between the vehicle and the target vehicle and the mapping relationship between the time interval and the collision probability.

[0067] The equivalent energy velocity is calculated based on the mass of this vehicle, the speed of this vehicle before the collision, the mass of the target vehicle, and the speed of the target vehicle before the collision.

[0068] Specifically, the equivalent energy velocity calculated based on the vehicle's mass, its pre-collision speed, the target vehicle's mass, and its pre-collision speed includes:

[0069] Substituting the mass of the vehicle, its pre-collision speed, the mass of the target vehicle, and its pre-collision speed into the second calculation formula, we obtain the equivalent energy velocity. The second calculation formula is as follows:

[0070]

[0071] In the formula, EES represents the equivalent energy velocity, M represents the vehicle's mass, V represents the vehicle's velocity before the collision, and M s V represents the target vehicle mass. s This indicates the speed of the target vehicle before the collision.

[0072] The risk cost of each candidate trajectory is calculated based on the first collision probability, the second collision probability, and the equivalent energy velocity.

[0073] Specifically, the risk cost calculated for each candidate trajectory based on the first collision probability, the second collision probability, and the equivalent energy velocity includes:

[0074] The cost of the first collision is calculated based on the first collision probability and the equivalent energy velocity.

[0075] The cost of the second collision is calculated based on the second collision probability and the equivalent energy velocity.

[0076] The risk cost of each candidate trajectory is calculated based on the first collision cost and the second collision cost.

[0077] As an example, after generating candidate trajectories, the generated candidate trajectories will be evaluated and screened. It should be understood that since the evaluation methods and principles for all candidate trajectories are the same, for the sake of simplicity, the following embodiments will only illustrate the evaluation process of one candidate trajectory.

[0078] In this embodiment, the risk cost of each candidate trajectory will be evaluated. Specifically, the risk cost is calculated from two parts: the vehicle collision time (TTC) and the vehicle interval time (TIV). TTC is the relative distance ΔD between the two vehicles. s Divide by relative velocity, i.e.

[0079]

[0080] In the formula, TTC represents the collision time between the vehicle and the target vehicle, and ΔD s V represents the relative distance between the vehicle and the target vehicle, and V represents the speed of the vehicle. s This indicates the speed of the target vehicle.

[0081] TIV represents the relative distance ΔD between the two vehicles. s Divide the speed of the following vehicle (i.e., this vehicle) by V, that is

[0082]

[0083] In the formula, TIV represents the time interval between the current vehicle and the target vehicle.

[0084] See Figure 3 and Figure 4 As shown, TTC and TIV are mapped to collision probabilities P respectively. TTC and P TIV (Right now Figure 3 and Figure 4 The ordinate (Possibility) in the equation represents the collision probability. A smaller TTC and TIV values ​​indicate a higher probability of collision. Therefore, the first collision probability P is determined based on the collision time TTC between the vehicle and the target vehicle and the mapping relationship between collision time and collision probability. TTCThe second collision probability P is determined based on the time interval (TIV) between the vehicle and the target vehicle and the mapping relationship between the time interval and the collision probability. TIV .

[0085] Then, the equivalent energy velocity (EES) is calculated, which represents the severity of the collision. Considering that this vehicle is a commercial vehicle, and the target vehicle is generally a passenger car, EES can be expressed as the change in the target vehicle's velocity after the collision: Assuming the collision between our vehicle and the target vehicle is elastic, then according to the conservation laws, we can obtain:

[0086]

[0087] In the formula, M and M s These are the masses of the vehicle itself and the target vehicle, V and V, respectively. s These are the speeds of the vehicle and the target vehicle before the collision. and These are the speeds of the vehicle and the target vehicle after the collision.

[0088] From equation (4), we can obtain:

[0089]

[0090] Finally, the total collision cost (i.e., risk cost) of the candidate trajectories is calculated, and we get:

[0091] R = R TTC +R TIV (6)

[0092] In the formula, R represents the risk cost, R TTC R represents the cost of the first collision. TIV This represents the cost of the second collision. Where:

[0093]

[0094] In the formula, a min This represents the maximum deceleration of the vehicle, which is a negative value.

[0095] It should be noted that the risk cost calculation is the sum of the risks throughout the entire process, that is, in the candidate trajectory planning time domain t. F Within, every sampling time T s Calculate the risk cost once, and the average of the calculated risk costs is the final risk cost of the candidate trajectory.

[0096] Step S30: Calculate the comfort cost of each candidate trajectory based on the acceleration change rate parameter;

[0097] Furthermore, the calculation of the comfort cost for each candidate trajectory based on the acceleration change rate parameter includes:

[0098] Substituting the longitudinal acceleration rate of change and the lateral acceleration rate of change of the candidate trajectories into the third calculation formula, the comfort cost of each candidate trajectory is obtained. The third calculation formula is as follows:

[0099]

[0100] In the formula, C c Indicating the cost of comfort, This represents the rate of change of longitudinal acceleration of the candidate trajectory. t represents the rate of change of lateral acceleration of the candidate trajectory. F W represents the time domain for candidate trajectory planning. d This represents the horizontal weighting coefficient.

[0101] As an example, in this embodiment, the comfort cost is expressed as the integral of the square of the rate of change of acceleration of the candidate trajectory within the planning time domain. That is, by substituting the rate of change of longitudinal acceleration and the rate of change of lateral acceleration of the candidate trajectory into the following calculation formula, the comfort cost of the candidate trajectory can be obtained:

[0102]

[0103] In the formula, C c Indicating the cost of comfort, This represents the rate of change of longitudinal acceleration of the candidate trajectory. t represents the rate of change of lateral acceleration of the candidate trajectory. F W represents the time domain for candidate trajectory planning. d This represents the horizontal weighting coefficient. It should be noted that W... d The specific value can be determined based on actual needs and is not limited here. It should be understood that the calculation of the comfort cost is also the average cost of the entire process.

[0104] Step S40: Calculate the velocity cost for each candidate trajectory based on the velocity parameters;

[0105] Furthermore, the calculation of the velocity cost for each candidate trajectory based on the velocity parameters includes:

[0106] Substituting the velocity, desired velocity, and preset maximum speed limit of the candidate trajectory into the fourth calculation formula, we obtain the velocity cost for each candidate trajectory. The fourth calculation formula is as follows:

[0107] C V =|V Tra -min(V E V max )|

[0108] In the formula, C V V represents the speed cost.Tra V represents the velocity of the candidate trajectory. E V represents the desired speed. max This indicates the maximum speed limit.

[0109] As an example, in this embodiment, the speed cost is represented as the difference between the planned trajectory speed and the desired speed or the maximum speed limit. That is, by substituting the candidate trajectory speed, the desired speed, and the preset maximum speed limit into the following calculation formula, the speed cost of each candidate trajectory can be obtained:

[0110] C V =|V Tra -min(V E V max (9)

[0111] In the formula, C V V represents the speed cost. Tra V represents the velocity of the candidate trajectory. E V represents the desired speed. max This represents the maximum speed limit. It should be understood that the speed cost is also the average cost of the entire process.

[0112] Step S50: Calculate the dynamic cost of each candidate trajectory based on mass parameters, acceleration parameters, velocity parameters, and slope parameters;

[0113] Furthermore, the calculation of the dynamic cost of each candidate trajectory based on mass parameters, acceleration parameters, velocity parameters, and slope parameters includes:

[0114] The vehicle mass was calculated using the least squares method and vehicle dynamics equations.

[0115] Substituting the vehicle mass, longitudinal acceleration of the candidate trajectory, longitudinal velocity of the candidate trajectory, and slope of the ramp containing the candidate trajectory into the first calculation formula, the dynamic cost of each candidate trajectory is obtained. The first calculation formula is:

[0116]

[0117] In the formula, C m t represents the cost of dynamism. F This represents the time domain for candidate trajectory planning, where m represents the vehicle mass. Let g represent the longitudinal acceleration of the candidate trajectory, f represent the gravitational acceleration, f represent the rolling resistance coefficient, and A represent the frontal area of ​​the vehicle. α represents the longitudinal velocity of the candidate trajectory, and α represents the slope of the ramp where the candidate trajectory is located.

[0118] As an example, in this embodiment, the varying cargo loads on commercial vehicles cause significant changes in vehicle inertia, affecting acceleration performance. Therefore, the power cost should be considered when changing lanes; that is, when a vehicle is heavily loaded, acceleration performance decreases, and the use of vehicle power during lane changes needs to be taken into account to select a suitable vehicle route.

[0119] See Figure 5 As shown, this embodiment will use the recursive least squares (RLS) method to estimate the total vehicle mass; where T t Indicates engine torque, u r α represents wind speed, α represents road gradient, and T represents wind speed. t u r And α is used as the correction factor for the estimator, and k represents the time count. This indicates the estimated vehicle weight.

[0120] It is understandable that the main force acting on a vehicle during operation is the driving force F. t Rolling resistance F from the ground f Air resistance F from the air w and the slope resistance F when driving on a slope i Therefore, according to Newton's second law, a simplified equation for vehicle dynamics can be obtained:

[0121]

[0122] In the formula, m represents the mass of the car. It represents acceleration.

[0123] Among them, the driving force F of the car t for:

[0124]

[0125] In the formula, T t Let i0 represent the engine torque, i0 represent the transmission ratio, η represent the mechanical efficiency of the transmission coefficient, and r represent the transmission torque. w This indicates the rolling radius of the wheel / tire.

[0126] Rolling resistance F from the ground during vehicle movement f for:

[0127] F f =mgfcosα (12)

[0128] In the formula, g represents the acceleration due to gravity, f represents the rolling resistance coefficient, and α represents the road slope.

[0129] Air resistance F during car driving w for:

[0130]

[0131] In the formula, C D The value represents the air drag coefficient, A represents the frontal area of ​​the car, ρ represents the air density, and u = u r +V represents the relative speed between the car and the wind, u r V represents wind speed, and V represents vehicle speed.

[0132] The car's gradient resistance F when driving on a slope i for:

[0133] F i =mgsinα (14)

[0134] In summary, equation (10) can be transformed into:

[0135]

[0136] Since the road gradient is relatively small, we can assume that cosα = 1 and sinα = i; when estimating the vehicle mass, we assume that the road gradient is a known quantity, so equation (15) can be transformed into

[0137]

[0138] In this embodiment, recursive least squares is used for vehicle mass estimation, and a forgetting factor is introduced. Therefore, by transforming equation (16) into the least squares format, we can obtain:

[0139]

[0140] In the formula, y represents the system output, E represents the system observation matrix, m represents the system parameters to be identified, and e represents the system's white noise. To improve the real-time performance of quality estimation and prevent "data saturation," a suitable forgetting factor needs to be selected. The empirical formula for selecting the forgetting factor is typically as follows:

[0141] λ(t) = 1 - 0.05·0.98 t (18)

[0142] In this embodiment, the forgetting factor can preferably be selected within the range of [0.95, 1].

[0143] Define the recognition quality at time k-1 and time k as follows: and Then the output and observation matrix at time k are y(k) and E(k), respectively. Therefore, the mass least squares recursive formula can be obtained as follows:

[0144]

[0145] In the formula, K(k) represents the gain matrix, P(k) represents the covariance matrix, and I represents the identity matrix.

[0146] In summary, the cost of dynamic performance C m It can be expressed by the following formula:

[0147]

[0148] In equation (20), m is the vehicle mass estimated using the least squares method. This represents the longitudinal acceleration of the candidate trajectory. The longitudinal velocity of the candidate trajectory is represented by α, and the gradient of the road on which the candidate trajectory is located is represented by α, which can be obtained from a high-precision map.

[0149] Step S60: Select the candidate trajectory with the smallest total cost from multiple candidate trajectories based on risk cost, comfort cost, speed cost, and power cost as the optimal lane-changing trajectory for this vehicle.

[0150] As an example, in this embodiment, the risk cost R and comfort cost C calculated according to the foregoing steps are... c Speed ​​Cost C V and the cost of dynamics C m The total cost of each candidate trajectory can be evaluated. This total cost is expressed as a weighted sum of the costs mentioned above. The weights are used to scale each cost to the same order of magnitude. The formula for calculating the total cost is:

[0151] C = W R R+W V C V +W C C C +W m C m (twenty one)

[0152] In the formula, C represents the total cost, and W... R W is the risk cost weighting factor. V W is the speed cost weighting factor. C W is the weighting factor for the cost of comfort. m The weighting coefficient for dynamic costs should be noted that W R W V W C and W mThe specific value can be determined according to actual needs and is not limited here; then, the candidate trajectory with the minimum total cost is selected from a series of generated candidate trajectories as the final optimal lane-changing trajectory for this vehicle; then, based on the Frenet coordinate information, the trajectory coordinates (x, y), velocity v, acceleration a, and heading angle in the Cartesian coordinate system are solved using the s, d, and first and second derivatives of the optimal lane-changing trajectory. And curvature k; finally, the vehicle is controlled based on the various parameters in the Cartesian coordinate system calculated above.

[0153] Therefore, this embodiment proposes an optimal lane-changing trajectory selection method suitable for commercial vehicles. Its goal is to obtain the optimal lane-changing trajectory when considering significant load variations in commercial vehicles. Specifically, it includes: assessing the risk of a series of candidate trajectories based on the target vehicle trajectory prediction results; calculating the risk cost, comfort cost, and expected speed cost of each candidate trajectory; and adding a dynamic cost index by estimating vehicle mass to simulate the driver's selection of lane-changing trajectories under different vehicle loads, thereby further improving vehicle performance during lane-changing. Then, based on risk assessment, comfort assessment, expected speed assessment, and dynamic cost assessment, the total lane-changing cost is calculated, and the candidate trajectory with the lowest cost is selected as the optimal lane-changing trajectory for the vehicle. Finally, the selected optimal lane-changing trajectory is transformed into the vehicle coordinate system, and the expected future coordinates, planned longitudinal speed, trajectory heading angle, curvature, and polynomial coefficients are output for vehicle control.

[0154] This embodiment will simulate two different gross vehicle weights, 10 tons and 49 tons, based on the characteristics of commercial vehicles: taking intelligent driving of commercial vehicles as an example, see... Figure 6 As shown, the horizontal axis represents the planned vertical distance, and the vertical axis represents the planned horizontal distance; where the risk cost weight W... R The default value is 0.1, and the speed cost weight W is... V The default value is 5, with a comfort cost weight of W. C The default value is 0.03, and the dynamic cost weight W is... m The default value is 1e. -4 Simulation results show that when the vehicle weight is large, the trajectory of lane changing is relatively smooth, and the lateral movement is small for the same longitudinal distance.

[0155] For manually driven commercial vehicles, if a power cost weighting factor is added, while the risk cost weighting W... R Speed ​​cost weight W V and comfort cost weight W C All remain unchanged, that is, W R W is 0.1 V It is 5, W C It is 0.03, while W m For 3e-4 See also Figure 7 As shown in the simulation results, increasing the inertia weight (i.e., W) indicates that... m After that, when fully loaded, the vehicle chooses not to change lanes, but continues to drive in the same lane, which is closer to the real human driving style and effectively avoids unnecessary lane changes.

[0156] This application embodiment also provides an optimal lane-changing trajectory screening device, including:

[0157] The acquisition unit is used to acquire multiple candidate trajectories, including the current driving trajectory of the vehicle.

[0158] The calculation unit is used to calculate the risk cost of each candidate trajectory based on vehicle collision time parameters, vehicle interval time parameters, and equivalent energy velocity parameters; calculate the comfort cost of each candidate trajectory based on acceleration change rate parameters; calculate the velocity cost of each candidate trajectory based on velocity parameters; and calculate the dynamic cost of each candidate trajectory based on mass parameters, acceleration parameters, velocity parameters, and slope parameters.

[0159] The filtering unit is used to select the candidate trajectory with the minimum total cost from multiple candidate trajectories based on risk cost, comfort cost, speed cost, and power cost as the optimal lane-changing trajectory for this vehicle.

[0160] Furthermore, the computing unit is specifically used for:

[0161] The vehicle mass was calculated using the least squares method and vehicle dynamics equations.

[0162] Substituting the vehicle mass, longitudinal acceleration of the candidate trajectory, longitudinal velocity of the candidate trajectory, and slope of the ramp containing the candidate trajectory into the first calculation formula, the dynamic cost of each candidate trajectory is obtained. The first calculation formula is:

[0163]

[0164] In the formula, C m t represents the cost of dynamism. F This represents the time domain for candidate trajectory planning, where m represents the vehicle mass. Let g represent the longitudinal acceleration of the candidate trajectory, f represent the gravitational acceleration, f represent the rolling resistance coefficient, and A represent the frontal area of ​​the vehicle. α represents the longitudinal velocity of the candidate trajectory, and α represents the slope of the ramp where the candidate trajectory is located.

[0165] Furthermore, the computing unit is specifically used for:

[0166] The first collision probability is determined based on the collision time between the vehicle and the target vehicle and the mapping relationship between the collision time and the collision probability.

[0167] The second collision probability is determined based on the time interval between the vehicle and the target vehicle and the mapping relationship between the time interval and the collision probability.

[0168] The equivalent energy velocity is calculated based on the mass of this vehicle, the speed of this vehicle before the collision, the mass of the target vehicle, and the speed of the target vehicle before the collision.

[0169] The risk cost of each candidate trajectory is calculated based on the first collision probability, the second collision probability, and the equivalent energy velocity.

[0170] Furthermore, the computing unit is specifically used for:

[0171] Substituting the mass of the vehicle, its pre-collision speed, the mass of the target vehicle, and its pre-collision speed into the second calculation formula, we obtain the equivalent energy velocity. The second calculation formula is as follows:

[0172]

[0173] In the formula, EES represents the equivalent energy velocity, M represents the vehicle's mass, V represents the vehicle's velocity before the collision, and M s V represents the target vehicle mass. s This indicates the speed of the target vehicle before the collision.

[0174] Furthermore, the computing unit is specifically used for:

[0175] The cost of the first collision is calculated based on the first collision probability and the equivalent energy velocity.

[0176] The cost of the second collision is calculated based on the second collision probability and the equivalent energy velocity.

[0177] The risk cost of each candidate trajectory is calculated based on the first collision cost and the second collision cost.

[0178] Furthermore, the computing unit is specifically used for:

[0179] Substituting the longitudinal acceleration rate of change and the lateral acceleration rate of change of the candidate trajectories into the third calculation formula, the comfort cost of each candidate trajectory is obtained. The third calculation formula is as follows:

[0180]

[0181] In the formula, C c Indicating the cost of comfort, This represents the rate of change of longitudinal acceleration of the candidate trajectory. t represents the rate of change of lateral acceleration of the candidate trajectory. F W represents the time domain for candidate trajectory planning. d This represents the horizontal weighting coefficient.

[0182] Furthermore, the computing unit is specifically used for:

[0183] Substituting the velocity, desired velocity, and preset maximum speed limit of the candidate trajectory into the fourth calculation formula, we obtain the velocity cost for each candidate trajectory. The fourth calculation formula is as follows:

[0184] C V =|V Tra -min(V E V max )|

[0185] In the formula, C V V represents the speed cost. Tra V represents the velocity of the candidate trajectory. E V represents the desired speed. max This indicates the maximum speed limit.

[0186] It should be noted that those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the device and each unit described above can be referred to the corresponding processes in the aforementioned embodiment of the optimal lane change trajectory screening method, and will not be repeated here.

[0187] The optimal lane-changing trajectory filtering device provided in the above embodiments can be implemented as a computer program, which can, for example, Figure 8 The optimal lane change trajectory screening device shown is running.

[0188] This application embodiment also provides an optimal lane change trajectory screening device, including: a memory, a processor, and a network interface connected via a system bus, wherein the memory stores at least one instruction, and the at least one instruction is loaded and executed by the processor to implement all or part of the steps of the aforementioned optimal lane change trajectory screening method.

[0189] The network interface is used for network communication, such as sending assigned tasks. Those skilled in the art will understand that... Figure 8 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0190] A processor can be a CPU, or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. A general-purpose processor can be a microprocessor, or any conventional processor. The processor is the control center of a computer device, connecting all parts of the computer device through various interfaces and lines.

[0191] Memory can be used to store computer programs and / or modules. The processor performs various functions of the computer device by running or executing the computer programs and / or modules stored in the memory, and by accessing data stored in the memory. Memory can primarily include a program storage area and a data storage area. The program storage area can store the operating system, application programs required for at least one function (such as video playback, image playback, etc.), etc.; the data storage area can store data created based on the use of the mobile phone (such as video data, image data, etc.). Furthermore, memory can include high-speed random access memory (RAM), and can also include non-volatile memory, such as hard disks, RAM, plug-in hard disks, SmartMedia Cards (SMC), Secure Digital Cards (SD cards), Flash Cards, at least one disk storage device, flash memory devices, or other volatile solid-state storage devices.

[0192] This application also provides a computer-readable storage medium storing a computer program thereon. When the computer program is executed by a processor, it implements all or part of the steps of the aforementioned optimal lane change trajectory selection method.

[0193] The embodiments of this application can implement all or part of the aforementioned processes, or they can be accomplished by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various methods described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include: any entity or device capable of carrying computer program code, recording media, USB flash drives, portable hard drives, magnetic disks, optical disks, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media, etc. It should be noted that the content included in the computer-readable medium can be appropriately added to or subtracted according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electrical carrier signals and telecommunication signals.

[0194] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, servers, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product implemented on one or more computer-usable storage media (including, but not limited to, disk storage and optical storage) containing computer-usable program code.

[0195] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or system. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or system that includes that element.

[0196] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create a machine for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0197] The above description is merely a specific embodiment of this application, enabling those skilled in the art to understand or implement this application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this application. Therefore, this application is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features claimed herein.

Claims

1. An optimal lane-changing trajectory selection method, characterized in that, Includes the following steps: Obtain multiple candidate trajectories, including the current driving trajectory of this vehicle; The risk cost of each candidate trajectory is calculated based on vehicle collision time parameters, vehicle interval time parameters, and equivalent energy velocity parameters. The calculation of the risk cost for each candidate trajectory based on vehicle collision time parameters, vehicle interval time parameters, and equivalent energy velocity parameters includes: The first collision probability is determined based on the collision time between the vehicle and the target vehicle and the mapping relationship between the collision time and the collision probability. The second collision probability is determined based on the time interval between the vehicle and the target vehicle and the mapping relationship between the time interval and the collision probability. The equivalent energy velocity is calculated based on the mass of this vehicle, the speed of this vehicle before the collision, the mass of the target vehicle, and the speed of the target vehicle before the collision. The risk cost of each candidate trajectory is calculated based on the first collision probability, the second collision probability, and the equivalent energy velocity. The comfort cost of each candidate trajectory is calculated based on the acceleration rate of change parameter; Calculate the velocity cost for each candidate trajectory based on velocity parameters; The dynamic cost of each candidate trajectory is calculated based on mass parameters, acceleration parameters, velocity parameters, and slope parameters. The calculation of the dynamic cost of each candidate trajectory based on mass parameters, acceleration parameters, velocity parameters, and slope parameters includes: The vehicle mass was calculated using the least squares method and vehicle dynamics equations. Substituting the vehicle mass, longitudinal acceleration of the candidate trajectory, longitudinal velocity of the candidate trajectory, and slope of the ramp containing the candidate trajectory into the first calculation formula, the dynamic cost of each candidate trajectory is obtained. The first calculation formula is: In the formula, Indicates the cost of driving force. Represents the time domain for candidate trajectory planning. Indicates vehicle mass. This represents the longitudinal acceleration of the candidate trajectory. g Represents gravitational acceleration. Indicates the rolling resistance coefficient. This indicates the frontal area of ​​the vehicle. Represents the longitudinal velocity of the candidate trajectory. Indicates the slope of the ramp where the candidate trajectory is located; Based on risk cost, comfort cost, speed cost, and power cost, the candidate trajectory with the minimum total cost is selected from multiple candidate trajectories as the optimal lane-changing trajectory for this vehicle.

2. The optimal lane-changing trajectory selection method as described in claim 1, characterized in that, The equivalent energy velocity calculated based on the vehicle's mass, its pre-collision speed, the target vehicle's mass, and its pre-collision speed includes: Substituting the mass of the vehicle, its pre-collision speed, the mass of the target vehicle, and its pre-collision speed into the second calculation formula, we obtain the equivalent energy velocity. The second calculation formula is as follows: In the formula, Represents the equivalent energy velocity. This indicates the weight of the vehicle. Indicates the vehicle's speed before the collision. Indicates the mass of the target vehicle. This indicates the speed of the target vehicle before the collision.

3. The optimal lane-changing trajectory selection method as described in claim 1, characterized in that, The risk cost for each candidate trajectory, calculated based on the first collision probability, the second collision probability, and the equivalent energy velocity, includes: The cost of the first collision is calculated based on the first collision probability and the equivalent energy velocity. The cost of the second collision is calculated based on the second collision probability and the equivalent energy velocity. The risk cost of each candidate trajectory is calculated based on the first collision cost and the second collision cost.

4. The optimal lane-changing trajectory selection method as described in claim 1, characterized in that, The comfort cost of calculating each candidate trajectory based on the acceleration rate of change parameter includes: Substituting the longitudinal acceleration rate of change and the lateral acceleration rate of change of the candidate trajectories into the third calculation formula, the comfort cost of each candidate trajectory is obtained. The third calculation formula is as follows: In the formula, Indicating the cost of comfort, This represents the rate of change of longitudinal acceleration of the candidate trajectory. This represents the rate of change of lateral acceleration of the candidate trajectory. Represents the time domain for candidate trajectory planning. This represents the horizontal weighting coefficient.

5. The optimal lane-changing trajectory selection method as described in claim 1, characterized in that, The calculation of the velocity cost for each candidate trajectory based on velocity parameters includes: Substituting the velocity of the candidate trajectory, the desired velocity, or the preset maximum speed limit into the fourth calculation formula yields the velocity cost for each candidate trajectory. The fourth calculation formula is as follows: In the formula, Indicates the cost of speed. Indicates the velocity of the candidate trajectory. Indicates the desired speed. This indicates the maximum speed limit.

6. An optimal lane-changing trajectory selection device, characterized in that, include: The acquisition unit is used to acquire multiple candidate trajectories, including the current driving trajectory of the vehicle. The computing unit is used to calculate the risk cost of each candidate trajectory based on vehicle collision time parameters, vehicle interval time parameters, and equivalent energy velocity parameters. The comfort cost of each candidate trajectory is calculated based on the acceleration rate of change parameter; Calculate the velocity cost for each candidate trajectory based on velocity parameters; The dynamic cost of each candidate trajectory is calculated based on mass parameters, acceleration parameters, velocity parameters, and slope parameters. The calculation of the risk cost for each candidate trajectory based on vehicle collision time parameters, vehicle interval time parameters, and equivalent energy velocity parameters includes: The first collision probability is determined based on the collision time between the vehicle and the target vehicle and the mapping relationship between the collision time and the collision probability. The second collision probability is determined based on the time interval between the vehicle and the target vehicle and the mapping relationship between the time interval and the collision probability. The equivalent energy velocity is calculated based on the mass of this vehicle, the speed of this vehicle before the collision, the mass of the target vehicle, and the speed of the target vehicle before the collision. The risk cost of each candidate trajectory is calculated based on the first collision probability, the second collision probability, and the equivalent energy velocity. The dynamic cost of each candidate trajectory is calculated based on mass parameters, acceleration parameters, velocity parameters, and slope parameters, including: The vehicle mass was calculated using the least squares method and vehicle dynamics equations. Substituting the vehicle mass, longitudinal acceleration of the candidate trajectory, longitudinal velocity of the candidate trajectory, and slope of the ramp containing the candidate trajectory into the first calculation formula, the dynamic cost of each candidate trajectory is obtained. The first calculation formula is: In the formula, Indicates the cost of driving force. Represents the time domain for candidate trajectory planning. Indicates vehicle mass. This represents the longitudinal acceleration of the candidate trajectory. g Represents gravitational acceleration. Indicates the rolling resistance coefficient. This indicates the frontal area of ​​the vehicle. Represents the longitudinal velocity of the candidate trajectory. Indicates the slope of the ramp where the candidate trajectory is located; The filtering unit is used to select the candidate trajectory with the minimum total cost from multiple candidate trajectories based on risk cost, comfort cost, speed cost, and power cost as the optimal lane-changing trajectory for this vehicle.

7. An optimal lane-changing trajectory screening device, characterized in that, include: A memory and a processor, wherein the memory stores at least one instruction, which is loaded and executed by the processor to implement the optimal lane change trajectory screening method according to any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that: The computer storage medium stores a computer program, which, when executed by a processor, implements the optimal lane change trajectory screening method according to any one of claims 1 to 5.

Images