Vehicle speed planning method, device, storage medium and electronic equipment

Abstract

The present invention relates to a vehicle speed planning method, device, storage medium, and electronic device. The vehicle speed planning method, applied to the field of vehicle speed planning technology, includes obtaining multi-obstacle decision information, vehicle speed limit information, and a reference trajectory; constructing a variable optimization model based on the multi-obstacle decision information, vehicle speed limit information, and reference trajectory, wherein the variable optimization model includes a target variable and a constraint relationship for the target variable; solving the target variable in the variable optimization model and outputting a planned trajectory, wherein the travel path of the planned trajectory is consistent with the travel path of the reference trajectory; and obtaining a planned vehicle speed based on the planned trajectory so as to control vehicle travel based on the planned vehicle speed. In this way, the safety and rationality of vehicle speed planning are improved by considering and restricting multiple factors.

Description

Technical Field

[0001] The present invention relates to the field of autonomous driving technology, and in particular to a vehicle speed planning method, device, storage medium, and electronic device. Background Art

[0002] Vehicle speed planning is a key component of autonomous vehicle decision-making and control, and it's also a crucial aspect drivers must consider during daily driving. The rationality of vehicle speed planning directly impacts the safety and quality of driving. This is particularly important for autonomous driving, especially without human intervention. Summary of the Invention

[0003] In view of this, embodiments of the present invention hope to provide a vehicle driving speed planning method, device, autonomous driving vehicle, storage medium and electronic device.

[0004] The technical solution of the present invention is achieved as follows:

[0005] In a first aspect, the present invention provides a vehicle speed planning method.

[0006] A vehicle speed planning method provided by an embodiment of the present invention includes: obtaining multi-obstacle decision information, vehicle speed limit information, and a reference trajectory; constructing a variable optimization model based on the multi-obstacle decision information, the vehicle speed limit information, and the reference trajectory, wherein the variable optimization model includes a target variable and a constraint relationship for the target variable; solving the target variable for the variable optimization model and outputting a planned trajectory, wherein the driving path of the planned trajectory is consistent with the driving path of the reference trajectory; and obtaining a vehicle planned speed based on the planned trajectory, so as to control vehicle driving based on the vehicle planned speed.

[0007] In some embodiments, the constraint relationship includes a cost function and hard constraints; constructing a variable optimization model based on the multi-obstacle decision information, the vehicle speed limit information and the reference trajectory includes: determining the cost function and variable value range constraints for the target variable based on the multi-obstacle decision information, the vehicle speed limit information and the reference trajectory; obtaining the hard constraints based on the variable value range constraints; and obtaining the variable optimization model based on the target variable, the cost function and the hard constraints.

[0008] In some embodiments, the hard constraint is obtained based on the variable value range constraint, including: obtaining the hard constraint based on the variable value range constraint and the kinematic constraint, wherein the target variable includes a first-category target variable and a second-category target variable, the first-category target variable includes at least one of a displacement variable, a velocity variable, and an acceleration variable, and the second-category target variable includes at least one of a vehicle front safety distance relaxation variable, a vehicle rear safety distance relaxation variable, a speed limit relaxation variable, a comfortable deceleration relaxation variable, and a comfortable acceleration relaxation variable; wherein, for any one of the first-category target variable and the second-category target variable, the variable value range constraint includes a value range corresponding to at least one target variable; wherein, for any one of the second-category target variable, the variable value range constraint also includes an additional value range, wherein the additional value range is determined by the upper limit values ​​corresponding to the first-category target variable and the first-category target variable.

[0009] In some embodiments, based on the multi-obstacle decision information and the reference trajectory, determining a cost function for the target variable includes: determining at least one of a displacement domain cost function, a velocity domain cost function, and an acceleration domain cost function based on the multi-obstacle decision information and the reference trajectory; and obtaining a cost function for the target variable based on at least one of the displacement domain cost function, the velocity domain cost function, and the acceleration domain cost function.

[0010] In some embodiments, based on the multi-obstacle decision information and the reference trajectory, a displacement domain cost function is determined, including: based on the multi-obstacle decision information and the reference trajectory, determining at least one of the front obstacle following cost, the rear obstacle overtaking cost, the intrusion cost of the vehicle's front safety distance, and the intrusion cost of the vehicle's rear safety distance; based on at least one of the front obstacle following cost, the rear obstacle overtaking cost, the intrusion cost of the vehicle's front safety distance, and the intrusion cost of the vehicle's rear safety distance, determining the displacement domain cost function.

[0011] In some embodiments, the target variable includes a displacement variable and a speed variable; the front obstacle following cost and the rear obstacle overtaking cost are both determined based on a weight, a relative distance between the vehicle and the key obstacle, and an expected distance term between the vehicle and the key obstacle; the relative distance between the vehicle and the key obstacle is associated with the displacement variable, and the expected distance term between the vehicle and the key obstacle is associated with the speed variable, wherein the key obstacle is determined based on the relative distance between the obstacle and the vehicle or the expected distance term between the obstacle and the vehicle calculated based on the speed.

[0012] In some embodiments, the expected distance term between the vehicle and the key obstacle includes a steady-state distance term and a dynamic distance term, wherein: the steady-state distance term is associated with the speed variable, the time distance, and the fixed minimum following distance; the dynamic distance term is associated with the speed variable and the relative speed between the vehicle and the obstacle, wherein the dynamic distance term is associated with the timing of vehicle acceleration or deceleration.

[0013] In some embodiments, the weight corresponding to the cost of following the front obstacle is determined by at least one of the basic weight, the following distance discount weight, and the time domain discount weight, wherein the following distance discount weight is associated with the relative position and relative speed of the obstacle and the vehicle at the preview moment, and the time domain discount weight is associated with the corresponding time point when predicting the planned trajectory; the weight corresponding to the cost of overtaking the rear obstacle is determined by the weight corresponding to the cost of following the front obstacle, the set minimum following distance between the vehicle and the front vehicle, the expected following position of the front vehicle, and the expected following position of the rear vehicle.

[0014] In some embodiments, the target variable includes a vehicle front safety distance relaxation variable and a vehicle rear safety distance relaxation variable, wherein the intrusion cost of the vehicle front safety distance is associated with the vehicle front safety distance relaxation variable and the corresponding weight, and the intrusion cost of the vehicle rear safety distance is associated with the vehicle rear safety distance relaxation variable and the corresponding weight.

[0015] In some embodiments, determining a speed domain cost function based on the multi-obstacle decision information and the reference trajectory includes: determining at least one of an efficiency cost and a speed limit relaxation cost based on the multi-obstacle decision information and the reference trajectory; and determining a speed domain cost function based on at least one of the efficiency cost and the speed limit relaxation cost.

[0016] In some embodiments, the target variable includes a speed variable and a speed limit slack variable, wherein: the efficiency cost is determined by the weight corresponding to the efficiency term, the speed variable, and the target speed; the speed limit slack cost is determined by the weight corresponding to the speed limit term and the speed limit slack variable.

[0017] In some embodiments, based on the multi-obstacle decision information and the reference trajectory, an acceleration domain cost function is determined, including: based on the multi-obstacle decision information and the reference trajectory, determining at least one of the acceleration cost, the jerk cost, the comfort acceleration relaxation cost, and the comfort deceleration relaxation cost; based on at least one of the acceleration cost, the jerk cost, the comfort acceleration relaxation cost, and the comfort deceleration relaxation cost, determining the acceleration domain cost function.

[0018] In some embodiments, the target variable includes an acceleration variable, a comfort acceleration slack variable, and a comfort deceleration slack variable, wherein: the acceleration cost is determined by the acceleration variable and the corresponding weight; the jerk cost is determined by the jerk and the corresponding weight, wherein the jerk includes the rate of change of the acceleration variable; the comfort acceleration slack cost is determined by the comfort acceleration slack variable and the corresponding weight; and the comfort deceleration slack cost is determined by the comfort deceleration slack variable and the corresponding weight.

[0019] In some embodiments, solving the target variable of the variable optimization model and outputting the planning trajectory include: adjusting the weight according to preset rules with the purpose of optimizing the cost function and / or with the hard constraint condition as a hard constraint, and solving to obtain the value of the target variable, wherein the preset rule is associated with the vehicle driving scenario; based on the solved value of the target variable, obtaining the planning trajectory and outputting it.

[0020] In a second aspect, the present invention provides a vehicle driving speed planning device, comprising: an acquisition module for acquiring multi-obstacle decision information, vehicle speed limit information and a reference trajectory; a construction module for constructing a variable optimization model based on the multi-obstacle decision information, the vehicle speed limit information and the reference trajectory, wherein the variable optimization model includes a target variable and a constraint relationship for the target variable; an output module for solving the target variable of the variable optimization model and outputting a planned trajectory, wherein the driving path of the planned trajectory is consistent with the driving path of the reference trajectory; an acquisition module for obtaining a vehicle planned speed based on the planned trajectory, so as to control vehicle driving based on the vehicle planned speed.

[0021] In a third aspect, the present invention provides an autonomous driving vehicle, which is used to implement the vehicle driving speed planning method described in the first aspect above.

[0022] In a fourth aspect, the present invention provides a computer-readable storage medium on which a vehicle driving speed planning program is stored. When the vehicle driving speed planning program is executed by a processor, the vehicle driving speed planning method described in the first aspect is implemented.

[0023] In a fifth aspect, the present invention provides an electronic device comprising a memory, a processor, and a vehicle driving speed planning program stored in the memory and executable on the processor. When the processor executes the vehicle driving speed planning program, the vehicle driving speed planning method described in the first aspect is implemented.

[0024] According to an embodiment of the present invention, a vehicle speed planning method includes: obtaining multi-obstacle decision information, vehicle speed limit information, and a reference trajectory; constructing a variable optimization model based on the multi-obstacle decision information, vehicle speed limit information, and reference trajectory, wherein the variable optimization model includes a target variable and a constraint relationship for the target variable; solving the target variable for the variable optimization model and outputting a planned trajectory, wherein the driving path of the planned trajectory is consistent with the driving path of the reference trajectory; obtaining a vehicle planned speed based on the planned trajectory, so as to control vehicle driving based on the vehicle planned speed. In order to improve the rationality of vehicle speed planning, the present invention considers multiple factors during vehicle speed planning, including obtaining multi-obstacle decision information, vehicle speed limit information, and a reference trajectory; constructing a variable optimization model based on the multi-obstacle decision information, vehicle speed limit information, and reference trajectory; then solving the target variable for the variable optimization model and outputting a planned trajectory; and obtaining a vehicle planned speed based on the planned trajectory. In this way, by considering and restricting multiple factors, the safety and rationality of vehicle speed planning are improved.

[0025] Additional aspects and advantages of the present invention will be set forth in part in the description which follows and, in part, will be obvious from the description which follows, or may be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] Figure 1 is a flow chart of a vehicle speed planning method according to an exemplary embodiment;

[0027] Figure 2 is a schematic diagram showing vehicle speed planning according to an exemplary embodiment;

[0028] Figure 3 The figure is a schematic structural diagram of a vehicle speed planning device according to an exemplary embodiment. DETAILED DESCRIPTION

[0029] The following describes embodiments of the present invention in detail, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present invention, and are not to be construed as limiting the present invention.

[0030] Vehicle speed planning is a key component of autonomous vehicle decision-making and control, and it's also a crucial aspect drivers must consider during daily driving. The rationality of vehicle speed planning directly impacts the safety and quality of driving. This is particularly important for autonomous driving, especially without human intervention.

[0031] The vehicle autonomous driving of related technologies takes into account a small number of obstacles and fails to consider how to resolve conflicts between different decisions for multiple obstacles; it fails to consider the control of the following distance of obstacles in continuous space, and how to accurately control the acceleration and deceleration timing of the following target; it fails to express the uncertainty of obstacle perception and predicted trajectory, and either fully believes it or does not use it at all, and cannot quantitatively adjust the impact of uncertainty on the speed trajectory; it fails to express the delay in control and actual vehicle execution.

[0032] To address the above situation, the present invention provides a vehicle speed planning method that can, within a single framework, comprehensively consider longitudinal distance control to obstacles, driving efficiency, and acceleration / deceleration comfort, accurately controlling acceleration and deceleration timing; coordinating conflicts between different decisions regarding multiple obstacles in front and behind to ensure safety and comfort; and, during speed planning, quantitatively expressing the uncertainty of the predicted obstacle trajectory and influencing the vehicle's speed planning results based on this uncertainty; and, during speed planning, expressing the delays of downstream controls and actuators.

[0033] Figure 1 FIG. 1 is a flow chart of a vehicle speed planning method according to an exemplary embodiment. Figure 1 As shown, the vehicle speed planning method includes:

[0034] Step 10: Obtain multi-obstacle decision information, vehicle speed limit information, and reference trajectory;

[0035] Step 11: construct a variable optimization model based on the multi-obstacle decision information, the vehicle speed limit information, and the reference trajectory, wherein the variable optimization model includes a target variable and a constraint relationship for the target variable;

[0036] Step 12: solving the target variable of the variable optimization model and outputting a planned trajectory, wherein the driving path of the planned trajectory is consistent with the driving path of the reference trajectory;

[0037] Step 13: Based on the planned trajectory, obtain the planned vehicle speed so as to control the vehicle driving based on the planned vehicle speed.

[0038] In this exemplary embodiment, multi-obstacle decision information includes options such as following (including other similar meanings such as yielding, stopping, and following), overtaking (including other similar meanings such as overtaking and overtaking), and speed limit (the upper speed limit that the vehicle must meet at different times or locations in the future). Multi-obstacle decision information includes yielding under a first condition, stopping under a second condition, and following under a third condition. The first condition may be a vehicle yielding condition specified in road traffic, such as turning right to turning left or turning to going straight. The second condition may include vehicle stopping conditions specified in road traffic, such as stopping at a red light, a traffic accident ahead, or requiring a vehicle to stop in an emergency. The third condition may include vehicle following conditions specified in road traffic and information on the following distance required for the vehicle to follow, such as vehicles traveling on a one-way street.

[0039] In this exemplary embodiment, the vehicle speed limit information includes the road speed limit, for example, a lane's current speed limit of 60 km / h. The reference trajectory can be the vehicle's route from its origin to its destination. This route can be determined as needed, for example, including the shortest route, the shortest travel time, or the route with the fewest traffic lights.

[0040] In this exemplary embodiment, solving for the target variable in the variable optimization model and outputting a planned trajectory may include solving for the target variable based on the target variable and constraints on the target variable, and outputting the planned trajectory. The planned trajectory may include various parameter data, such as at least a planned vehicle speed. After obtaining the planned trajectory, the planned vehicle speed may be extracted from the planned trajectory to control vehicle travel based on the planned vehicle speed.

[0041] In order to improve the rationality of vehicle speed planning, the present invention considers multiple factors during vehicle speed planning, including obtaining multi-obstacle decision information, vehicle speed limit information and reference trajectory; constructing a variable optimization model based on the multi-obstacle decision information, vehicle speed limit information and reference trajectory; then solving the target variable of the variable optimization model and outputting the planned trajectory; and obtaining the vehicle planned speed based on the planned trajectory. In this way, by considering and restricting multiple factors, the safety and rationality of vehicle speed planning are improved.

[0042] (1) Overall modeling

[0043] The present invention proposes a speed planner based on optimal numerical optimization, which models speed planning as a nonlinear optimization problem. It takes multi-obstacle decision-making, speed limit and reference trajectory as input, considers multiple soft and hard constraints, and outputs a trajectory that comprehensively considers obstacle distance control, efficiency, safety and comfort. It can coordinate the decision results of multiple obstacles, while considering the uncertainty and delay of upstream and downstream information, and has good adaptability and adjustability.

[0044] Figure 2 It is a schematic diagram showing vehicle travel speed planning according to an exemplary embodiment.

[0045] like Figure 2 As shown, the variable optimization model can be a nonlinear optimization model, which includes constraints and target variables to be optimized. The input data of the nonlinear optimization model includes multi-obstacle decision information, vehicle speed limit information, and a reference trajectory. The output data of the nonlinear optimization model includes a comfortable and safe vehicle (ego vehicle) planned trajectory.

[0046] Constraints include cost functions and hard constraints. The cost function in the present invention can be understood as a form of soft constraint expression. Hard constraints can include variable value range constraints and kinematic constraints.

[0047] In this exemplary embodiment, the target variables may include displacement variables, speed variables, acceleration variables, vehicle front safety distance relaxation variables, vehicle rear safety distance relaxation variables, speed limit relaxation variables, comfortable deceleration relaxation variables, and comfortable acceleration relaxation variables, etc.

[0048] For example, the target variable includes the displacement variable , speed variables , acceleration variable , vehicle front safety distance relaxation variable , vehicle rear safety distance relaxation variable , speed limit slack variable , Comfort deceleration relaxation variable and the comfort acceleration relaxation variable At least one of .

[0049] For example, the target variable to be optimized is modeled as a sequence of discrete time points, that is:

[0050]

[0051] The target variable at each time point is:

[0052]

[0053] In some embodiments, a variable optimization model is constructed based on multi-obstacle decision information, vehicle speed limit information, and a reference trajectory, including: determining a cost function and variable value range constraints for a target variable based on the multi-obstacle decision information, vehicle speed limit information, and the reference trajectory; deriving hard constraints based on the variable value range constraints; and obtaining a variable optimization model based on the target variable, the cost function, and the hard constraints. The reference trajectory serves as a reference or trajectory constraint throughout the modeling and speed planning process, ensuring that the resulting planned trajectory's driving path is consistent with the reference trajectory's driving path.

[0054] The hard constraint conditions are obtained based on the variable value range constraint conditions, including: obtaining the hard constraint conditions based on the variable value range constraint conditions and the kinematic constraint conditions.

[0055] Exemplarily, based on multi-obstacle decision information and a reference trajectory, determining a cost function for a target variable includes: determining at least one of a displacement domain cost function, a velocity domain cost function, and an acceleration domain cost function based on the multi-obstacle decision information and the reference trajectory; and obtaining a cost function for the target variable based on at least one of the displacement domain cost function, the velocity domain cost function, and the acceleration domain cost function.

[0056] For example, the cost function of the target variable This can include:

[0057]

[0058] in, is the cost function of the displacement domain; is the cost function in the velocity domain; is the cost function in the acceleration domain.

[0059] (2) Cost function:

[0060] (2.1) Cost function in displacement domain

[0061] Exemplarily, based on multi-obstacle decision information and a reference trajectory, a displacement domain cost function is determined, including: based on multi-obstacle decision information (such as vehicle following, vehicle overtaking, etc.) and a reference trajectory, determining at least one of the following cost of a front obstacle, the overtaking cost of a rear obstacle, the intrusion cost of a safe distance in front of the vehicle, and the intrusion cost of a safe distance behind the vehicle; and determining a displacement domain cost function based on at least one of the following cost of a front obstacle, the overtaking cost of a rear obstacle, the intrusion cost of a safe distance in front of the vehicle, and the intrusion cost of a safe distance behind the vehicle.

[0062] For example, the cost function in the displacement domain is It can be expressed as:

[0063]

[0064] in, The cost of following the obstacle ahead; Rear obstacle overtaking cost; The cost of intrusion into the safe distance in front of the vehicle; The cost of intrusion into the safety distance behind the vehicle.

[0065] is the relaxation variable of the safety distance in front of the vehicle; is the weight corresponding to the relaxation variable of the safety distance in front of the vehicle; is the vehicle rear safety distance relaxation variable; is the weight corresponding to the relaxation variable of the rear safety distance of the vehicle.

[0066] The following cost for the front obstacle and the overtaking cost for the rear obstacle have similar forms. Both the following cost for the front obstacle and the overtaking cost for the rear obstacle are determined based on the weight, the relative distance between the vehicle and the key obstacle, and the expected distance term between the vehicle and the key obstacle calculated based on the speed. The relative distance between the vehicle and the key obstacle is associated with the displacement variable, and the expected distance term between the vehicle and the key obstacle is associated with the speed variable. Taking the following cost for the front obstacle as an example, the following cost for the front obstacle is the quadratic cost of the distance the ego vehicle position exceeds the expected following position:

[0067]

[0068] in, is the displacement variable in the target variable; Refers to the key following obstacle at that moment Position; ( ) is the relative distance between the vehicle and the key obstacle, and is related to the vehicle displacement variable associated; Refers to the expected distance term between the vehicle and the key obstacle, where ; is the weight, according to the specified time The vehicle state and obstacle state settings, namely ; is the speed of the key following obstacle at that moment; is the speed of the vehicle at preview time j; is the basic weight; is the following distance discount weight; among them, the following distance discount weight It is determined by the relative position and relative speed of the obstacle and the vehicle at the preview time j.

[0069] The expected distance term between the vehicle (ego vehicle) and the key obstacle Including steady-state following distance and the dynamic following distance term related to relative speed (The following examples provide an implementation method), that is, By adjusting the dynamic following distance item, the desired following distance can be controlled according to the relative speed, which plays a role in controlling the deceleration timing.

[0070] Among them, the weight corresponding to the following cost of the front obstacle is composed of the basic weight , Following distance discount weight , time domain discount weight For example, the weight is further expressed as:

[0071]

[0072] in, is the speed of the key following obstacle at that moment; For the vehicle at the preview moment speed; is the displacement variable of the vehicle at preview time j; is the position of the key following obstacle at preview time j.

[0073] Among them, the following distance discount weight With obstacles and vehicles at the preview moment The relative position and relative velocity are related, that is, Time domain discount weight Associated with the time point corresponding to the predicted planned trajectory, e.g., temporal discount The uncertainty of the predicted trajectory is taken into account. For example, the uncertainty of the prediction in the distant time domain is usually large, so the discount value at the distant time can be set to be smaller; is the position of the vehicle at preview time j, is the speed of the vehicle at preview time j; is the position of the key following obstacle at preview time j; is the velocity of the key following obstacle at that moment.

[0074] As mentioned above, the cost function in the displacement domain includes the following cost of the front obstacle, the overtaking cost of the rear obstacle, the intrusion cost of the front safety gap, and the intrusion cost of the rear safety gap. Among them, the intrusion cost of the front safety gap and the intrusion cost of the rear safety gap represent the safety of the key obstacles in front and behind. The following cost of the front obstacle and the overtaking cost of the rear obstacle are respectively composed of several parts:

[0075] a. Key obstacle screening. For example, key obstacles are selected based on the relative distance between the obstacle and the vehicle or the distance between the obstacle and the vehicle. The key obstacles that have the greatest impact on the vehicle at each moment can be determined by different strategies, such as directly determining them based on the relative distance between the obstacle and the vehicle at the current moment, or calculating the expected distance between the obstacle and the vehicle based on the predicted trajectory of the obstacle. (i.e. expected following / overtaking distance ) Then decide on the key obstacles.

[0076] b. Expected distance between the obstacle and the vehicle (i.e. expected following / overtaking distance ) calculation. The expected distance term between the vehicle and the key obstacle Including steady-state distance term and dynamic distance terms The steady-state distance term and the vehicle speed variable , time interval, fixed minimum following distance; the dynamic distance term is associated with the vehicle speed variable , the relative speed between the vehicle and the obstacle ( ), where the dynamic distance term is associated with the timing of vehicle acceleration or deceleration. In order to facilitate the control of the timing of deceleration / acceleration of the ego vehicle, it is necessary not only to consider the stable following distance of the obstacle but also to obtain the expected distance based on the current relative speed of the ego vehicle and the obstacle, that is, .in, Can be implemented as , that is, the vehicle speed and time interval The product of the fixed minimum following distance , Can be implemented as , where the parameter It can be set according to the actual scenario and needs, for example, it can be set to 0.25 or other values. , you can control the timing of deceleration to follow obstacles.

[0077] c. Weight setting in obstacle following cost. When setting the cost of following the obstacle ahead, the weight setting determines the priority of this cost relative to efficiency, safety and comfort, and affects the deceleration in response to the obstacle ahead. The weight is determined by the basic weight , Following distance discount and time domain discounts Joint decision, i.e. Among them, the following distance discount The obstacles and the vehicle at the preview moment The relative position and relative speed of , so that the delay of downstream actuators can be taken into account and timely acceleration and deceleration can be performed in advance. The uncertainty of the predicted trajectory is taken into account. For example, the prediction uncertainty in the distant time domain is usually large, so the discount value at the distant time can be set to be smaller.

[0078] d. Coordination of multi-obstacle decision conflicts. Weight corresponding to the cost of following the obstacle ahead Similarly, the weight corresponding to the cost of overtaking the rear obstacle The weight corresponding to the cost of following the obstacle in front , Set the minimum following distance between the vehicle and the vehicle in front 、The expected following position of the vehicle ahead 、The following vehicle's expected following position Sure.

[0079] Specifically, when considering the decision-making information of obstacles in front and behind, it is necessary to ensure the safety of following the vehicle in front while overtaking the rear obstacle, and avoid panic caused by excessive approaching the vehicle in front. Therefore, a minimum following distance is set for the vehicle in front. , the weight of the rear obstacle overtaking cost is discounted according to the positional relationship between the leading vehicle's expected following position and the rear vehicle's expected following position relative to the minimum following distance, that is, the weight corresponding to the rear obstacle overtaking cost It can be expressed as:

[0080]

[0081] In another example, the target variable includes a vehicle front safety distance slack variable , the intrusion cost of the safety distance in front of the vehicle and the relaxation variable of the safety distance in front of the vehicle and the corresponding weights As shown above, the intrusion cost of the safety distance in front of the front vehicle can be expressed as .

[0082] In another example, the target variable includes a vehicle rear safety distance slack variable , the intrusion cost of the vehicle rear safety distance and the relaxation variable of the vehicle rear safety distance and the corresponding weights As shown above, the intrusion cost of the safety distance behind the front vehicle can be expressed as .

[0083] (2.2) Cost function in velocity domain

[0084] Specifically, based on the multi-obstacle decision information and the reference trajectory, a speed domain cost function is determined, including: based on the multi-obstacle decision information and the reference trajectory, determining at least one of an efficiency cost and a speed limit relaxation cost; based on at least one of the efficiency cost and the speed limit relaxation cost, determining the speed domain cost function.

[0085] Among them, the target variables include vehicle speed variables and rate limit slack variables The efficiency cost is determined by the weight corresponding to the efficiency term , vehicle speed variable Target speed Determine; the cost of the speed limit relaxation is determined by the weight corresponding to the speed limit item , speed limit slack variable Sure.

[0086] Specifically, the cost function in the speed domain is the quadratic cost of efficiency cost and speed limit relaxation, that is:

[0087]

[0088] in, represents the target speed at each moment, represents the weight of the efficiency term, Indicates the weight of the speed limit item.

[0089] (2.3) Cost function in the acceleration domain

[0090] Specifically, the acceleration domain cost function is determined based on the multi-obstacle decision information and the reference trajectory, including: determining at least one of the acceleration cost, the jerk cost, the comfortable acceleration relaxation cost, and the comfortable deceleration relaxation cost based on the multi-obstacle decision information and the reference trajectory; and determining the acceleration domain cost function based on at least one of the acceleration cost, the jerk cost, the comfortable acceleration relaxation cost, and the comfortable deceleration relaxation cost.

[0091] Among them, the target variables include acceleration variables , Comfort acceleration relaxation variable and the comfortable deceleration relaxation variable .in:

[0092] The acceleration cost is determined by the acceleration variable and the corresponding weights Sure;

[0093] The jerk cost is determined by the jerk and the corresponding weights Determine, where the jerk Including acceleration variables rate of change;

[0094] Comfort acceleration relaxation cost is determined by comfort acceleration relaxation variable and the corresponding weights Sure;

[0095] Comfort deceleration relaxation cost is determined by the comfort deceleration relaxation variable and the corresponding weights Sure.

[0096] Specifically, the cost function of the acceleration domain includes the acceleration quadratic cost, the jerk cost, and the acceleration cost. The quadratic cost of , the quadratic cost of comfortable acceleration relaxation, and the quadratic cost of comfortable deceleration relaxation, namely:

[0097]

[0098] Since the cost of acceleration and jerk is taken into account here, a more comfortable acceleration and deceleration sensation can be obtained.

[0099] (3) Constraints (hard constraints)

[0100] The constraint relationship includes a cost function and hard constraints, and the cost function is as described above.

[0101] The target variables include first-class target variables and second-class target variables. The first-class target variables include at least one of displacement variables, velocity variables, and acceleration variables. The second-class target variables include at least one of vehicle front safety distance relaxation variables, vehicle rear safety distance relaxation variables, speed limit relaxation variables, comfortable deceleration relaxation variables, and comfortable acceleration relaxation variables.

[0102] Hard constraints include the range of solution variables and kinematic constraints, i.e., kinematic constraints. Second-order continuous kinematic constraints are considered, including kinematic continuity constraints in the displacement domain and velocity domain at each moment, i.e.:

[0103] ;

[0104] ;

[0105] in, is the time difference between adjacent moments, Indicates a smaller value.

[0106] For any target variable in the first category and the second category, the variable value range constraint includes the value range corresponding to the target variable. For example, for the variable value range constraint, the solution variable has a certain value range, that is, , , , , the slack variables are all greater than 0, that is, ; For vehicles at time The lower limit of acceleration, For vehicles at time The upper limit of acceleration when is the lower limit of the vehicle's displacement at preview time i, is the upper limit of the vehicle's displacement at preview time i; is the lower speed limit of the vehicle at preview time i, is the upper limit of the vehicle's speed at the preview time i; the second type of target variable includes the vehicle's front safety distance relaxation variable , vehicle rear safety distance relaxation variable , speed limit slack variable , Comfort deceleration relaxation variable and the comfort acceleration relaxation variable At least one.

[0107] For any target variable in the second category, the variable value range constraint also includes an additional value range, which is determined by the first category target variable (such as ) and the upper limit value corresponding to the first type of target variable (such as ) is determined. For example, there are constraints on the slack variables and the corresponding variables in their respective domains, which means that the cost item corresponding to the slack variable will be triggered only when the corresponding variable in the domain exceeds the specified value, including , , , , .by For example, for ease of understanding, convert to , that is, the relaxation amount should be greater than or equal to the part of the displacement that exceeds the safety upper limit, and the constraints of the remaining relaxation amounts can be obtained in the same way; among them, is the first type of target variable The corresponding lower limit value; For vehicles at time Speed ​​limit at 10:00 am; is the relaxation variable of the safety distance in front of the vehicle; is the first type of target variable The corresponding upper limit value;

[0108] is the first type of target variable The corresponding lower limit value; is the vehicle rear safety distance relaxation variable;

[0109] is the speed limit slack variable; is the speed limit of the vehicle at preview time i;

[0110] is the comfort acceleration relaxation variable; For comfortable acceleration;

[0111] Deceleration for comfort; is the comfortable deceleration relaxation variable.

[0112] As mentioned above, hard constraints are divided into kinematic constraints and optimization variable range constraints. Kinematic constraints take into account second-order continuity, that is, the acceleration must change continuously to ensure physical comfort.

[0113] In the variable range constraint, it is noted that the adjacent acceleration changes are taken into account ( ), that is, the range of jerk values, thereby avoiding drastic changes in acceleration and ensuring the comfort of body sensation. For each relaxation amount, it has a positive value and is related to the direct amount. Since the nonlinear optimization objective function of the planner is to minimize the cost function, the relaxation amount should be greater than the degree to which the corresponding direct amount intrudes into the set boundary. Taking the constraint relationship between the comfortable deceleration relaxation amount and the direct acceleration amount as an example, , for ease of understanding, it is transformed into ,in is the set comfortable deceleration. If the direct quantity to be solved is is less than the comfortable deceleration, in the process of minimizing the cost function, the relaxation amount will approach ; If the direct quantity to be solved is If the deceleration is greater than the comfortable deceleration, the relaxation amount will tend to 0 in the process of minimizing the cost function, that is, there is no corresponding cost, thus playing the role of relaxation amount.

[0114] (4) Solving the target variable

[0115] Exemplarily, the target variable of the variable optimization model is solved and the planning trajectory is output, including: with the purpose of cost function optimization and / or with hard constraints as hard constraints, adjusting the weights according to preset rules, and solving for the value of the target variable, wherein the preset rules are associated with the vehicle driving scenario; based on the solved value of the target variable, the planning trajectory is obtained and output.

[0116] As mentioned above, the solution variable is a sequence of discrete time points, that is: , the optimization variable at each time point is , respectively represent the displacement, velocity, acceleration, front safety gap relaxation, rear safety gap relaxation, speed limit relaxation variable, comfortable deceleration relaxation, and comfortable acceleration relaxation at a specified time point on a given path.

[0117] The slack of the front safety gap and the slack of the back safety gap The speed limit slack variable is related to the amount of intrusion of the displacement into the safety distance of the key obstacle in front and the key obstacle behind at each moment. The more the intrusion, the greater the cost. It is related to the degree to which the speed exceeds the speed limit at each moment. The more it exceeds, the greater the penalty. By adjusting its weight, the effect of allowing or not allowing the speed limit to be exceeded in some cases can be achieved. Comfort deceleration and comfort acceleration relaxation They are respectively related to the acceleration exceeding the set comfortable deceleration and acceleration degree at each moment, making it easy to control the results of the planned acceleration in different scenarios.

[0118] The planner outputs a trajectory that follows the same path as the input reference trajectory. The direct quantities are displacement, velocity, and acceleration at different time points along this path. To calculate these direct quantities, safety and comfort must be considered. Therefore, soft constraints are added, modeled as cost functions, and these constraints are applied to the direct quantities. By balancing the weights of the different costs, an optimal trajectory is obtained. Expressing the soft constraints as slack quantities facilitates expressing the cost function as a quadratic term and the constraints as a linear term, improving solution efficiency. Furthermore, by adjusting the weights of the cost function corresponding to the slack quantities, the optimization results for the corresponding direct quantities can be tailored to different scenarios, increasing adaptability and adjustability. For example, setting a comfort acceleration slack quantity can address the requirement that, under normal circumstances, different speeds correspond to different comfort accelerations, meaning that the given comfort acceleration should not be exceeded during acceleration, but that the comfort acceleration can be exceeded in overtaking scenarios.

[0119] In summary, the technical solution of the present invention achieves control over the distance to obstacles ahead and the timing of acceleration and deceleration, a coordinated mechanism for front and rear obstacle decision-making, ensuring safety and comfort, and accounting for the uncertainty of upstream perception and prediction information, as well as the latency of downstream actuators. By utilizing numerical optimization methods, precise obstacle distance control can be achieved while balancing safety, comfort, and efficiency. Simultaneous consideration of the decision-making results for multiple obstacles allows for coordination of different decision-making outcomes, resulting in strong comprehensiveness. The impact of prediction information on planning results is also considered, allowing for adjustment of corresponding parameters based on prediction quality, resulting in strong adaptability. The latency of downstream actuators can also be accounted for, resulting in good adjustability.

[0120] The invention provides a vehicle speed planning device.

[0121] Figure 3 The figure is a schematic structural diagram of a vehicle speed planning device according to an exemplary embodiment.

[0122] like Figure 3 As shown, the vehicle speed planning device includes:

[0123] An acquisition module 20 is used to obtain multi-obstacle decision information, vehicle speed limit information and reference trajectory;

[0124] A construction module 21 is used to construct a variable optimization model based on the multi-obstacle decision information, the vehicle speed limit information and the reference trajectory, wherein the variable optimization model includes a target variable and a constraint relationship for the target variable;

[0125] an output module 22 for solving the target variable of the variable optimization model and outputting a planned trajectory, wherein the driving path of the planned trajectory is consistent with the driving path of the reference trajectory;

[0126] The obtaining module 23 is used to obtain the planned vehicle speed based on the planned trajectory, so as to control the vehicle driving based on the planned vehicle speed.

[0127] It can be understood that the vehicle speed planning device of the present invention can refer to the vehicle speed planning method above.

[0128] The present invention provides an autonomous driving vehicle, which is used to implement the vehicle speed planning methods of the above-mentioned embodiments.

[0129] The present invention provides a computer-readable storage medium on which a vehicle driving speed planning program is stored. When the vehicle driving speed planning program is executed by a processor, the vehicle driving speed planning method of the above-mentioned embodiments is implemented.

[0130] The present invention provides an electronic device, comprising a memory, a processor, and a vehicle driving speed planning program stored in the memory and executable on the processor. When the processor executes the vehicle driving speed planning program, the vehicle driving speed planning method described in the above embodiments is implemented.

[0131] It should be noted that the logic and / or steps represented in the flowcharts or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing the logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (e.g., a computer-based system, a system including a processor, or other system that can fetch and execute instructions from an instruction execution system, apparatus, or device). For purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport a program for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (non-exhaustive list) of computer-readable media include the following: an electrical connection with one or more wires (electronic device), a portable computer disk cartridge (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and programmable read-only memory (EPROM or flash memory), fiber optic devices, and a portable compact disc read-only memory (CDROM). Furthermore, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium and then editing, interpreting or otherwise processing it in a suitable manner if necessary, and then storing it in a computer memory.

[0132] It should be understood that various components of the present invention may be implemented using hardware, software, firmware, or a combination thereof. In the above-described embodiments, multiple steps or methods may be implemented using software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented using hardware, as in another embodiment, any one of the following technologies known in the art or a combination thereof may be used: a discrete logic circuit having logic gate circuits for implementing logic functions on data signals, an application-specific integrated circuit having suitable combinational logic gate circuits, a programmable gate array (PGA), a field-programmable gate array (FPGA), etc.

[0133] Throughout this specification, reference to terms such as "one embodiment," "some embodiments," "examples," "specific examples," or "some examples" means that a specific feature, structure, material, or characteristic described in conjunction with that embodiment or example is included in at least one embodiment or example of the present invention. In this specification, schematic representations of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.

[0134] In the description of the present invention, it should be understood that the terms "center", "longitudinal", "lateral", "length", "width", "thickness", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", "clockwise", "counterclockwise", "axial", "radial", "circumferential" and the like to indicate orientations or positional relationships based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as limiting the present invention.

[0135] In addition, the terms "first" and "second" used in the embodiments of the present invention are only used for descriptive purposes and should not be understood as indicating or implying relative importance, or implicitly indicating the number of technical features indicated in this embodiment. Therefore, the features defined by the terms "first" and "second" in the embodiments of the present invention can explicitly or implicitly indicate that the embodiment includes at least one of such features. In the description of the present invention, the word "plurality" means at least two or two or more, such as two, three, four, etc., unless otherwise clearly and specifically defined in the embodiments.

[0136] In the present invention, unless otherwise clearly specified or limited in the embodiments, the terms "installed," "connected," "connect," and "fixed" appearing in the embodiments should be understood in a broad sense. For example, the connection may be a fixed connection, a detachable connection, or an integral connection. It can also be a mechanical connection, an electrical connection, etc.; of course, it can also be a direct connection, or an indirect connection through an intermediate medium, or it can be internal communication between two elements, or an interaction between two elements. For those skilled in the art, the specific meanings of the above terms in the present invention can be understood based on the specific implementation.

[0137] In the present invention, unless otherwise expressly specified or limited, when a first feature is "above" or "below" a second feature, it may mean that the first and second features are in direct contact, or that the first and second features are in indirect contact through an intermediary. Furthermore, when a first feature is "above," "above," or "above" a second feature, it may mean that the first feature is directly above or diagonally above the second feature, or simply means that the first feature is at a higher level than the second feature. When a first feature is "below," "below," or "below" a second feature, it may mean that the first feature is directly below or diagonally below the second feature, or simply means that the first feature is at a lower level than the second feature.

[0138] Although the embodiments of the present invention have been shown and described above, it will be understood that the above embodiments are illustrative and are not to be construed as limitations on the present invention. A person skilled in the art may change, modify, replace and modify the above embodiments within the scope of the present invention.

Claims

1. A vehicle speed planning method, characterized in that: include: Obtain multi-obstacle decision information, vehicle speed limit information and reference trajectory; Based on the multi-obstacle decision information, the vehicle speed limit information, and the reference trajectory, a variable optimization model is constructed, wherein the variable optimization model includes a target variable and a constraint relationship for the target variable; wherein the constraint relationship includes a cost function and a hard constraint condition; the constructing of the variable optimization model based on the multi-obstacle decision information, the vehicle speed limit information, and the reference trajectory includes: determining a cost function and a variable value range constraint condition for the target variable based on the multi-obstacle decision information, the vehicle speed limit information, and the reference trajectory; obtaining the hard constraint condition based on the variable value range constraint condition; and obtaining the variable optimization model based on the target variable, the cost function, and the hard constraint condition. Solving the variable optimization model for target variables and outputting a planned trajectory, wherein the driving path of the planned trajectory is consistent with the driving path of the reference trajectory; Based on the planned trajectory, a planned vehicle speed is obtained, so as to control the vehicle driving based on the planned vehicle speed.

2. The vehicle speed planning method according to claim 1, characterized in that: The obtaining of the hard constraint condition based on the variable value range constraint condition includes: Based on the variable value range constraint and the kinematic constraint, the hard constraint is obtained. The target variables include first-category target variables and second-category target variables, the first-category target variables include at least one of displacement variables, velocity variables, and acceleration variables, and the second-category target variables include at least one of vehicle front safety distance relaxation variables, vehicle rear safety distance relaxation variables, speed limit relaxation variables, comfortable deceleration relaxation variables, and comfortable acceleration relaxation variables; Wherein, for any one of the first type of target variables and the second type of target variables, the variable value range constraint condition includes a value range corresponding to at least one target variable; Among them, for any target variable in the second category of target variables, the variable value range constraint condition also includes an additional value range, wherein the additional value range is determined by the first category of target variables and the upper limit value corresponding to the first category of target variables.

3. The vehicle speed planning method according to claim 1 or 2, characterized in that: Determining a cost function for a target variable based on the multi-obstacle decision information and the reference trajectory includes: Determining at least one of a displacement domain cost function, a velocity domain cost function, and an acceleration domain cost function based on the multi-obstacle decision information and the reference trajectory; A cost function for a target variable is obtained based on at least one of the displacement domain cost function, the velocity domain cost function, and the acceleration domain cost function.

4. The vehicle speed planning method according to claim 3, characterized in that: Determining a displacement domain cost function based on the multi-obstacle decision information and the reference trajectory includes: Determining at least one of a front obstacle following cost, a rear obstacle overtaking cost, an intrusion cost of a front safety distance of the vehicle, and an intrusion cost of a rear safety distance of the vehicle based on the multi-obstacle decision information and the reference trajectory; A displacement domain cost function is determined based on at least one of the front obstacle following cost, the rear obstacle overtaking cost, the intrusion cost of the vehicle front safety distance, and the intrusion cost of the vehicle rear safety distance.

5. The vehicle speed planning method according to claim 4, characterized in that: The target variables include displacement variables and speed variables; The front obstacle following cost and the rear obstacle overtaking cost are both determined based on a weight, a relative distance between the vehicle and the key obstacle, and an expected distance term between the vehicle and the key obstacle, wherein the relative distance between the vehicle and the key obstacle is associated with the displacement variable, and the expected distance term between the vehicle and the key obstacle is associated with the speed variable. The key obstacle is determined based on the relative distance between the obstacle and the vehicle or the expected distance between the obstacle and the vehicle calculated according to the speed.

6. The vehicle speed planning method according to claim 5, characterized in that: The expected distance term between the vehicle and the key obstacle includes a steady-state distance term and a dynamic distance term, where: The steady-state distance term is associated with the speed variable, the time headway, and the fixed minimum following distance; The dynamic distance term is associated with the speed variable and the relative speed of the vehicle and the obstacle, wherein the dynamic distance term is associated with a timing of acceleration or deceleration of the vehicle.

7. The vehicle speed planning method according to claim 5, characterized in that: The weight corresponding to the following cost of the front obstacle is determined by at least one of a base weight, a following distance discount weight, and a time domain discount weight, wherein the following distance discount weight is associated with the relative position and relative speed of the obstacle and the vehicle at the preview moment, and the time domain discount weight is associated with the time point corresponding to the prediction of the planned trajectory; The weight corresponding to the rear obstacle overtaking cost is determined by the weight corresponding to the front obstacle following cost, the set minimum following distance between the vehicle and the preceding vehicle, the preceding vehicle's expected following position, and the following vehicle's expected following position.

8. The vehicle speed planning method according to claim 4, characterized in that: The target variables include the vehicle front safety distance relaxation variable and the vehicle rear safety distance relaxation variable, The intrusion cost of the vehicle front safety distance is associated with the vehicle front safety distance relaxation variable and the corresponding weight, and the intrusion cost of the vehicle rear safety distance is associated with the vehicle rear safety distance relaxation variable and the corresponding weight.

9. The vehicle speed planning method according to claim 3, characterized in that: Determining a speed domain cost function based on the multi-obstacle decision information and the reference trajectory includes: determining at least one of an efficiency cost and a speed limit relaxation cost based on the multi-obstacle decision information and the reference trajectory; A speed domain cost function is determined based on at least one of the efficiency cost and the speed limit relaxation cost.

10. The vehicle speed planning method according to claim 9, characterized in that: The target variables include speed variables and speed limit slack variables, where: The efficiency cost is determined by the weight corresponding to the efficiency term, the speed variable, and the target speed; The speed limit relaxation cost is determined by the weight corresponding to the speed limit item and the speed limit relaxation variable.

11. The vehicle speed planning method according to claim 3, characterized in that: Determining an acceleration domain cost function based on the multi-obstacle decision information and the reference trajectory includes: Determining at least one of an acceleration cost, a jerk cost, a comfortable acceleration relaxation cost, and a comfortable deceleration relaxation cost based on the multi-obstacle decision information and the reference trajectory; An acceleration domain cost function is determined based on at least one of the acceleration cost, the jerk cost, the comfort acceleration relaxation cost, and the comfort deceleration relaxation cost.

12. The vehicle speed planning method according to claim 11, characterized in that: The target variables include acceleration variables, comfortable acceleration relaxation variables, and comfortable deceleration relaxation variables, wherein: The acceleration cost is determined by the acceleration variable and the corresponding weight; The jerk cost is determined by the jerk and the corresponding weight, wherein the jerk includes the rate of change of the acceleration variable; The comfort acceleration relaxation cost is determined by the comfort acceleration relaxation variable and the corresponding weight; The comfort deceleration relaxation amount cost is determined by a comfort deceleration relaxation variable and a corresponding weight.

13. The vehicle speed planning method according to any one of claims 5-7, 10, and 12, characterized in that: Solving the target variable of the variable optimization model and outputting the planning trajectory includes: With the cost function optimization as the purpose and / or the hard constraint condition as the hard constraint, the weight is adjusted according to a preset rule to obtain the value of the target variable, wherein the preset rule is associated with the vehicle driving scenario; Based on the value of the target variable obtained by solving, the planned trajectory is obtained and output.

14. A vehicle speed planning device, characterized in that: include: Acquisition module, used to obtain multi-obstacle decision information, vehicle speed limit information and reference trajectory; a construction module for constructing a variable optimization model based on the multi-obstacle decision information, the vehicle speed limit information, and the reference trajectory, wherein the variable optimization model includes a target variable and a constraint relationship for the target variable; wherein the constraint relationship includes a cost function and a hard constraint condition; constructing the variable optimization model based on the multi-obstacle decision information, the vehicle speed limit information, and the reference trajectory, comprising: determining a cost function and a variable value range constraint condition for the target variable based on the multi-obstacle decision information, the vehicle speed limit information, and the reference trajectory; obtaining the hard constraint condition based on the variable value range constraint condition; and obtaining the variable optimization model based on the target variable, the cost function, and the hard constraint condition; an output module, configured to solve the target variable of the variable optimization model and output a planned trajectory, wherein the driving path of the planned trajectory is consistent with the driving path of the reference trajectory; The acquisition module is used to obtain the vehicle planned speed based on the planned trajectory, so as to control the vehicle driving based on the vehicle planned speed.

15. An autonomous driving vehicle, characterized in that: The autonomous driving vehicle is used to implement the vehicle driving speed planning method described in any one of claims 1-13.

16. A computer-readable storage medium, characterized in that A vehicle driving speed planning program is stored thereon, and when the vehicle driving speed planning program is executed by a processor, the vehicle driving speed planning method according to any one of claims 1 to 13 is implemented.

17. An electronic device, characterized in that: The method comprises a memory, a processor and a vehicle driving speed planning program stored in the memory and executable on the processor. When the processor executes the vehicle driving speed planning program, the vehicle driving speed planning method according to any one of claims 1 to 13 is implemented.

Images