Method and device for determining vehicle speed curve, equipment, medium and product

Abstract

The invention provides a method, a device, equipment, a medium and a product for determining a vehicle speed curve, and relates to the technical field of vehicle speed control and path optimizing.The method comprises the steps that on the basis of a preset distance step length, a to-be-driven path of a vehicle is divided, N position points are obtained, and N is an integer larger than or equal to 2; determining a candidate speed sequence corresponding to each position point; determining a target speed from the candidate speed sequence corresponding to each next position point based on the fuel consumption target function and the independent fuel consumption value from each position point to the corresponding next position point; the fuel consumption objective function is used for representing an accumulated fuel consumption value before the position point; and based on each target speed, determining a target speed curve corresponding to the to-be-driven path. According to the invention, the precision and efficiency of the optimization result of the vehicle speed curve are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of vehicle speed control and path optimization, and particularly to a method, device, equipment, medium and product for determining a vehicle speed curve. Background Art

[0002] Currently, vehicle speed planning and fuel economy optimization are key links in autonomous driving and intelligent driving assistance systems. The core goal is to plan a vehicle speed curve with the lowest fuel consumption according to a complex road environment (such as slope changes and multi-curved road sections).

[0003] However, due to the limitations of existing technologies in optimizing the vehicle speed curve, such as real-time performance, local optimal solutions, slopes, etc., the accuracy and efficiency of the optimization results of the vehicle speed curve are reduced. Summary of the Invention

[0004] The present invention provides a method, device, equipment, medium and product for determining a vehicle speed curve, aiming to solve the defect in the prior art that the accuracy and efficiency of the optimization results of the vehicle speed curve are reduced, and to achieve the improvement of the accuracy and efficiency of the optimization results of the vehicle speed curve.

[0005] The present invention provides a method for determining a vehicle speed curve, including: Dividing the to-be-traveled path of the vehicle based on a preset distance step size to obtain N position points, where N is an integer greater than or equal to 2; Determining a candidate speed sequence corresponding to each of the position points; Based on a fuel consumption objective function and an independent fuel consumption value from each of the position points to the corresponding next position point, determining a target speed from the candidate speed sequences corresponding to each of the next position points; the fuel consumption objective function is used to represent the cumulative fuel consumption value before the position point; Based on each of the target speeds, determining a target speed curve corresponding to the to-be-traveled path.

[0006] A method for determining a vehicle speed curve according to the present invention, which determines a target speed from the candidate speed sequences corresponding to each of the next position points based on the fuel consumption objective function and the independent fuel consumption values from each of the position points to the corresponding next position point, includes: determining the cumulative fuel consumption value corresponding to each first candidate speed in the candidate speed sequence corresponding to the position point based on the fuel consumption objective function; determining the first candidate speed corresponding to the minimum cumulative fuel consumption value as the first speed; determining the independent fuel consumption value corresponding to each second candidate speed in the candidate speed sequence corresponding to the next position point based on the first speed and the candidate speed sequence corresponding to the next position point; and determining the target speed from the candidate speed sequences corresponding to each of the next position points based on the cumulative fuel consumption value and the independent fuel consumption value.

[0007] A method for determining a vehicle speed curve according to the present invention, which determines the target speed from the candidate speed sequences corresponding to each of the next position points based on the cumulative fuel consumption value and the independent fuel consumption value, includes: determining the total fuel consumption cost value corresponding to each second candidate speed in the candidate speed sequence corresponding to the next position point based on the cumulative fuel consumption value and the independent fuel consumption value; and determining the second candidate speed corresponding to the minimum total fuel consumption cost value as the target speed.

[0008] A method for determining a vehicle speed curve according to the present invention, which determines the independent fuel consumption value corresponding to each second candidate speed in the candidate speed sequence corresponding to the next position point based on the first speed and the candidate speed sequence corresponding to the next position point, includes: determining the distance between the position point and the next position point; determining the speed difference between the first speed and each of the second candidate speeds; and determining the independent fuel consumption value corresponding to each of the second candidate speeds based on the distance, the speed difference, and the slope angle corresponding to the position point.

[0009] A method for determining a vehicle speed curve according to the present invention, which determines the fuel consumption objective function, includes: determining a first expression of the fuel consumption corresponding to the air resistance where the vehicle is located; determining a second expression of the fuel consumption corresponding to the acceleration of the vehicle; determining a third expression of the fuel consumption corresponding to the gravitational resistance of the slope angle at the position point where the vehicle is located; determining a fourth expression of the fuel consumption corresponding to the road friction resistance at the position point where the vehicle is located; and determining the fuel consumption objective function based on the first expression, the second expression, the third expression, and the fourth expression.

[0010] A method for determining a vehicle speed curve provided by the present invention, wherein determining the candidate speed sequences corresponding to the respective position points includes: determining the maximum speed corresponding to each position point and the minimum speed corresponding to the position point based on the road curvature corresponding to each position point and the maximum centrifugal force corresponding to each position point; discretizing the speed of each position point based on the maximum speed and the minimum speed to obtain each candidate speed sequence.

[0011] The present invention also provides a device for determining a vehicle speed curve, including the following modules: A division module, configured to divide the to-be-traveled path of the vehicle based on a preset distance step size to obtain N position points, where N is an integer greater than or equal to 2; A speed sequence determination module, configured to determine the candidate speed sequences corresponding to the respective position points; A target speed determination module, configured to determine a target speed from the candidate speed sequences corresponding to the respective next position points based on a fuel consumption objective function and the independent fuel consumption values from each position point to the corresponding next position point; the fuel consumption objective function is used to represent the cumulative fuel consumption value before the position point; A target speed curve determination module, configured to determine the target speed curve corresponding to the to-be-traveled path based on the respective target speeds.

[0012] The present invention also provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein when the processor executes the computer program, the method for determining a vehicle speed curve as described in any one of the above is implemented.

[0013] The present invention also provides a non-transitory computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the method for determining a vehicle speed curve as described in any one of the above is implemented.

[0014] The present invention also provides a computer program product, including a computer program, and when the computer program is executed by a processor, the method for determining a vehicle speed curve as described in any one of the above is implemented.

[0015] The method, device, equipment, medium and product for determining a vehicle speed curve provided by the present invention divide the to-be-traveled path of the vehicle based on a preset distance step length to obtain a plurality of position points, and determine candidate speed sequences corresponding to each position point; determine a target speed from the candidate speed sequences corresponding to each next position point based on a fuel consumption objective function and the independent fuel consumption value from each position point to the corresponding next position point; the fuel consumption objective function is used to represent the cumulative fuel consumption value before the position point; determine the target speed curve corresponding to the to-be-traveled path based on each target speed. In this way, the target speed of the next position point is comprehensively determined through the fuel consumption objective function and the fuel consumption from the position point to the next position point, reducing the state expansion amount of the fuel consumption objective function, reducing the computational complexity, improving the real-time performance. At the same time, the fuel consumption objective function avoids the problem of being easily trapped in local optima, improving the accuracy and efficiency of the optimization result of the vehicle speed curve. Moreover, using fixed-distance division instead of traditional time-step division ensures the spatial uniformity of the optimization result and improves the smoothness of the speed curve and the actual driving stability. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0017] Figure 1 FIG. is one of the flow diagrams of the method for determining a vehicle speed curve provided by the present invention.

[0018] Figure 2 FIG. is another flow diagram of the method for determining a vehicle speed curve provided by the present invention.

[0019] Figure 3 FIG. is a structural diagram of the device for determining a vehicle speed curve provided by the present invention.

[0020] Figure 4 FIG. is a structural diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0021] To make the objectives, technical solutions, and advantages of the present invention clearer, the following will clearly and completely describe the technical solutions in the present invention with reference to the accompanying drawings in the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art without creative efforts based on the embodiments in the present invention belong to the scope of protection of the present invention.

[0022] First, the existing technical solutions for vehicle speed planning and fuel economy optimization are described as follows: The first one is the dynamic programming method. Dynamic programming is a classic path optimization method that can find the optimal solution through global search, ensuring the global optimal solution. It is particularly suitable for scenarios with a small state space and relatively simple road conditions. However, when encountering the exponential growth of the state space, there will be a problem that the calculation time is difficult to meet the requirements of real-time applications.

[0023] The second method is the heuristic algorithm. The heuristic algorithm quickly finds an approximate solution by designing a heuristic estimation function to improve the calculation efficiency, and can give an optimization result in a short time, which is suitable for scenarios with high real-time requirements. However, the heuristic method cannot guarantee the global optimal solution and is prone to falling into a local optimum in a complex environment, resulting in poor fuel economy. In addition, a simple estimation function is usually adopted in the heuristic method, ignoring the complex relationship between fuel consumption and factors such as slope and dynamics, and the optimization accuracy is insufficient.

[0024] Regarding the research on the fuel consumption model, in traditional methods, the calculation model of fuel consumption is usually based on the simple functional relationship between acceleration and speed. The model is simple and the calculation is fast. However, the traditional model fails to incorporate slope information into the optimization process and cannot accurately reflect the impact of complex terrain conditions on fuel economy. It cannot accurately describe the complex relationship between fuel consumption and vehicle dynamics, resulting in a large deviation between the optimization result and the actual situation. In terms of the planning step size, traditional speed planning methods often divide the path based on a fixed time step size. The method design is simple and easy to implement. However, the time step size division method cannot guarantee the spatial uniformity of the speed planning result in complex road conditions (such as areas with drastic slope changes), resulting in poor vehicle driving smoothness. In the case of long distances or variable terrains, it is difficult for the time-step-based planning method to capture road characteristics, and the optimization effect is limited.

[0025] Based on the above problems, the present invention proposes a method for determining a vehicle speed curve. By the fuel consumption objective function and the fuel consumption from the current position point to the next position point, the target speed of the next position point is comprehensively determined, reducing the state expansion amount of the fuel consumption objective function, lowering the calculation complexity, and improving the real-time performance. At the same time, the fuel consumption objective function avoids the problem of being prone to falling into a local optimum, improving the accuracy and efficiency of the optimization result of the vehicle speed curve. Moreover, a fixed distance division (such as every 10 meters as a unit) is adopted instead of the traditional time step size division to ensure the spatial uniformity of the optimization result, improving the smoothness of the speed curve and the actual driving stability.

[0026] The following is combined with Figure 1 - Figure 2A method for determining a vehicle speed curve according to the present invention is applicable to speed optimization for any vehicle model on any road. The execution entity of this method can be an electronic device or a method for determining a vehicle speed curve set in the electronic device. The device for determining the vehicle speed curve can be implemented by software, hardware, or a combination of both.

[0027] Figure 1 It is one of the flow schematic diagrams of the method for determining a vehicle speed curve provided by the present invention. As Figure 1 shown, the method includes the following: Step 101: Divide the to-be-driven path of the vehicle based on a preset distance step size to obtain N position points.

[0028] Wherein, N is an integer greater than or equal to 2.

[0029] Here, the to-be-driven path can be of any suitable length and gradient, generally 200 meters; the preset step size can be any suitable value, generally 10 meters. For example, divide the future 200-meter to-be-driven path into 20 segments, each with a length of 10 meters, to obtain the position point set { x 1, x 2,..., x 20}.

[0030] Step 102: Determine the candidate speed sequences corresponding to each of the position points.

[0031] Here, any suitable method can be used to determine the candidate speed sequence. For example, use a speed calculation formula to calculate the candidate speed, or use a neural network model to output the candidate speed sequence based on position point information (such as gradient, road friction coefficient, etc.).

[0032] Exemplarily, determining the candidate speed sequences corresponding to each of the position points includes: determining the maximum speed corresponding to each of the position points and the minimum speed corresponding to the position point based on the road curvature corresponding to each of the position points and the maximum centrifugal force corresponding to each of the position points; performing discretization processing on the speeds of each of the position points based on the maximum speed and the minimum speed to obtain each of the candidate speed sequences.

[0033] Here, the minimum speed can be a preset suitable value, and the maximum speed can be determined according to the lateral curvature and centrifugal force corresponding to the position point.

[0034] Exemplarily, the calculation of the maximum speed can be as follows in formula (1): (1) Wherein, Represents the maximum centrifugal force that can be borne when the vehicle turns, usually expressed as a multiple of the gravitational acceleration g. The value of R depends on various factors such as the vehicle design and road friction coefficient; Represents the lateral curvature at the position point, Represents the Position point.

[0035] In the embodiment of the present invention, the speed discretization process refers to dividing the range between the maximum speed and the minimum speed. For example, after determining the maximum speed and the minimum speed, a preset step size is set, and the range between the minimum speed and the maximum speed is divided according to the preset step size.

[0036] Exemplarily, the speed range is 10~30 km / h (kilometer per hour), the discrete step size is 2 km / h, and the obtained first speed sequence is 10 km / h, 12 km / h, ……, 28 km / h, 30 km / h.

[0037] Here, each speed in the candidate speed sequence refers to the candidate speed corresponding to the position point.

[0038] It should be noted that in order to ensure the accuracy of the speed at each position point, multiple speeds need to be set for each position point, and the most suitable speed for the position point is determined through the fuel consumption value corresponding to each speed.

[0039] Here, the method for determining the candidate speed sequence can be any suitable method. For example, different speeds are randomly set for the position points; or, the first speed sequence is determined according to a preset rule.

[0040] In the embodiment of the present invention, by performing speed discretization on each position point, each position point obtains multiple candidate speeds, and the optimal speed of each position point is determined from the multiple candidate speeds according to the total fuel consumption cost value, so as to obtain the target speed curve and improve the accuracy and precision of the target speed curve.

[0041] Step 103: Based on the fuel consumption objective function and the independent fuel consumption values from each of the position points to the corresponding next position point, determine the target speed from the candidate speed sequences corresponding to each of the next position points.

[0042] Among them, the fuel consumption objective function is used to represent the cumulative fuel consumption value before the position point.

[0043] Here, the fuel consumption objective function can be understood as dynamic programming.

[0044] Here, the optimization objective of the fuel consumption objective function is to minimize the cumulative fuel consumption value of the vehicle from the starting point to the end point during the process.

[0045] Here, the position point can be understood as the current position point, and the next position point is the next position point of the current position point. Among them, each position point can be used as the current position point and the next position point at different times. The optimal speed of the next position point is based on the optimal speed of the current position point and the independent fuel consumption value from the current position point to the corresponding next position point.

[0046] Here, the target speed refers to the optimal speed of each position point, that is, the speed with the minimum fuel consumption value.

[0047] Furthermore, determining the fuel consumption objective function includes: determining a first expression for the fuel consumption corresponding to the air resistance where the vehicle is located; determining a second expression for the fuel consumption corresponding to the acceleration of the vehicle; determining a third expression for the fuel consumption corresponding to the gravitational resistance of the slope angle at the position point where the vehicle is located; determining a fourth expression for the fuel consumption corresponding to the road friction resistance at the position point where the vehicle is located; and determining the fuel consumption objective function based on the first expression, the second expression, the third expression, and the fourth expression.

[0048] Here, the air resistance is related to the air density, the frontal area of the vehicle, and the air resistance coefficient. The gravitational resistance of the slope angle is related to the slope angle, the mass, and the gravitational acceleration. The road friction resistance is related to the rolling resistance coefficient, the mass, the gravitational acceleration, and the vehicle speed.

[0049] Here, the method for determining the fuel consumption objective function can be any suitable method. For example, the fuel consumption objective function is formed by weighted addition of the four expressions; or for another example, the fuel consumption objective function is formed by directly adding the four expressions.

[0050] Exemplarily, the fuel consumption objective function is as follows in formula (2): (2) where represents the cumulative fuel consumption before the current position point, represents the current position point, represents the speed at the current position point, represents the acceleration, the slope at the current position point, represents the rolling resistance coefficient, represents the fuel consumption function at the current position.

[0051] Furthermore, the expression of the fuel consumption function f(v,a,g,μ) is as follows in formula (3): (3) where represents the speed, represents the acceleration, represents the vehicle mass, represents the gravitational acceleration, represents the slope angle, represents the rolling resistance coefficient, and α represents the proportionality coefficient in the first expression, represents the proportionality coefficient in the second expression, represents the proportionality coefficient in the third expression, represents the proportionality coefficient in the fourth expression.

[0052] Constraints are set for the speed and acceleration with respect to the fuel consumption objective function. Among them, the speed constraint is as shown in the following formula (4): (4) Among them, represents the minimum speed, represents the maximum speed.

[0053] The speed constraint is as shown in the following formula (5): (5) Among them, represents the minimum acceleration, represents the maximum acceleration.

[0054] The update of the speed state needs to satisfy the dynamic equation, as shown in the following formula (6): (6) Among them, represents the th speed, represents the distance between two adjacent position points, represents the component of the gravitational acceleration caused by the slope.

[0055] In the implementation of the present invention, a fuel consumption model incorporating slope information is introduced, integrating road terrain (such as slope, etc.) into the planning process, improving the accuracy of fuel economy optimization, and making the optimization result more in line with the actual road conditions.

[0056] Exemplarily, determining a target speed from the candidate speed sequences corresponding to each of the next position points based on the fuel consumption objective function and the independent fuel consumption values of each of the position points to the corresponding next position point includes: determining the cumulative fuel consumption value corresponding to each first candidate speed in the candidate speed sequence corresponding to the position point based on the fuel consumption objective function; determining the first candidate speed corresponding to the minimum cumulative fuel consumption value as the first speed; determining the independent fuel consumption value corresponding to each second candidate speed in the candidate speed sequence corresponding to the next position point based on the first speed and the candidate speed sequence corresponding to the next position point; and determining the target speed from the candidate speed sequences corresponding to each of the next position points based on the cumulative fuel consumption value and the independent fuel consumption value.

[0057] Here, the fuel consumption from a position point to the next position point can be understood as introducing a heuristic function based on the fuel consumption objective function.

[0058] It should be noted that each position point corresponds to multiple second candidate speeds, and when traveling at different second candidate speeds, the fuel consumption from the position point to the next position point is different.

[0059] Here, the target speed is the optimal speed of the next position point, and the total fuel consumption cost value corresponding to this target speed can be the minimum.

[0060] Exemplarily, determining the target speed from the candidate speed sequences corresponding to each of the next position points based on the cumulative fuel consumption value and the independent fuel consumption value includes: determining the total fuel consumption cost value corresponding to each second candidate speed in the candidate speed sequence corresponding to the next position point based on the cumulative fuel consumption value and the independent fuel consumption value; and determining the second candidate speed corresponding to the minimum total fuel consumption cost value as the target speed.

[0061] Here, the method for determining the target speed corresponding to the next position point can be any suitable method. For example, taking the weighted average of all total fuel consumption cost values and determining the target speed according to the average value; or, determining one or more target total fuel consumption cost values from the total fuel consumption cost values and determining the target speed according to the target total fuel consumption cost values.

[0062] In the example of the present invention, by designing a heuristic estimation function to guide the dynamic programming search direction, the search volume of the state space is effectively reduced. Compared with the traditional pure dynamic programming method, this method significantly reduces the computational complexity, improves the real-time performance, and can meet the millisecond-level optimization requirements in autonomous driving and complex road environments. At the same time, with the guarantee of the global search ability, the problem that a simple heuristic algorithm is prone to falling into local optimality is avoided.

[0063] Exemplarily, determine the minimum total fuel consumption proxy value from each total fuel consumption proxy value; determine the second candidate speed corresponding to the minimum total fuel consumption proxy value as the target speed.

[0064] It should be noted that during vehicle driving, the lower the total fuel consumption proxy value, the better the corresponding second candidate speed.

[0065] In the embodiment of the present invention, determining the second candidate speed corresponding to the lowest total fuel consumption proxy value as the optimal speed improves the accuracy of the optimal speed at each position point, and further improves the accuracy of the target speed curve.

[0066] Further, determining the independent fuel consumption value corresponding to each second candidate speed in the candidate speed sequence corresponding to the next position point based on the first speed and the candidate speed sequence corresponding to the next position point includes: determining the distance between the position point and the next position point; determining the speed difference between the first speed and each of the second candidate speeds; and determining the independent fuel consumption value corresponding to each of the second candidate speeds based on the distance, the speed difference, and the slope angle corresponding to the current position point.

[0067] Here, the method for determining the fuel consumption from the current position point to the next position point can be any suitable method. For example, it can be determined through the mapping relationship among the distance, the speed difference, and the slope angle corresponding to the current position point and the fuel consumption from the current position value to the next position point; or it can be determined according to the fuel consumption calculation formula from the current position value to the next position point.

[0068] Exemplarily, the fuel consumption from the current position to the next position point is as follows in formula (7): 2 (7) Wherein, represents the end position point (i.e., the next position point), represents the current position point, represents the speed of the end position point (i.e., the next position point), represents the speed of the current position point, represents the slope angle of the current position point, represents the sum of the slope angles from the current position point to the end position point, represents the distance proportionality coefficient, represents the speed proportionality coefficient, represents the slope angle proportionality coefficient.

[0069] In the embodiments of the present invention, road slope information is incorporated into the fuel consumption model, and the comprehensive influence of slope on dynamics and fuel economy is introduced into the state transition rule. Through the combination of dynamic programming recursion and slope perception model, the optimization algorithm can more accurately calculate fuel consumption in complex terrains (such as mountainous areas or downhill sections with drastic slope changes), significantly improving fuel economy in the optimization results and reducing ineffective energy consumption.

[0070] Step 104: Based on each of the target speeds, determine the target speed curve corresponding to the to-be-traveled path.

[0071] Here, the target speed curve is obtained by connecting the target speeds corresponding to each position point.

[0072] Here, according to the fuel consumption objective function, determine the cumulative fuel consumption value corresponding to the last position point corresponding to the target speed, then determine the fuel consumption from the next position point to the last position point, determine the total fuel consumption cost value based on the cumulative fuel consumption value and the independent fuel consumption value from the next position point to the last position point, determine the target speed of the last position point according to the total fuel consumption cost value, and finally output the target speeds of each position point to obtain the target speed curve.

[0073] In the embodiments of the present invention, by dividing the to-be-traveled path of the vehicle, at least three position points are obtained; based on the first speed sequence corresponding to the current position point among the at least three position points and the fuel consumption objective function, determine the second speed of the next position point corresponding to each first speed in the first speed sequence; based on each second speed, the fuel consumption objective function, and the fuel consumption from the current position point corresponding to each second speed to the next position point, determine the target speed corresponding to the next position point; based on the fuel consumption objective function, the target speed, and the fuel consumption from the next position point to the last position point, determine the target speed curve corresponding to the to-be-traveled path. In this way, by comprehensively considering the fuel consumption objective function and the fuel consumption from the current position point to the next position point, the target speed of the next position point is determined, reducing the state expansion amount of the fuel consumption objective function, lowering the computational complexity, improving the real-time performance. At the same time, the fuel consumption objective function avoids the problem of being easily trapped in local optima, improving the accuracy and efficiency of the optimization result of the vehicle speed curve. Moreover, using fixed-distance division instead of traditional time-step division ensures the spatial uniformity of the optimization result, enhancing the smoothness of the speed curve and the actual driving stability.

[0074] The following is an application scenario of a method for determining a vehicle speed curve provided by an embodiment of the present invention.

[0075] It should be noted that before implementing the method for determining the vehicle speed curve, it is also necessary to input data and system parameters. The data includes high-precision map data, and the high-precision map data includes road slope { and road curvature Here, it can be the road slope and road curvature within a range of 200 meters in the future. The vehicle parameters include: vehicle mass m, air density ρ, the frontal area A of the vehicle, vehicle speed v , air resistance coefficient ; rolling resistance coefficient μ. In the initial state, the values of these parameters are respectively 0, initial speed. In the target state, the values of these parameters are respectively x_end = 200 meters. In addition, it is also necessary to construct a fuel consumption function, i.e., the above formula (3), and a fuel consumption target function, i.e., the above formula (2).

[0076] Figure 2 is the second flow schematic diagram of the method for determining the vehicle speed curve provided by the present invention. As Figure 2 shown, the method includes: Step 201, preset a distance step size, divide the path to be traveled by the vehicle, and obtain N position points.

[0077] Step 202, discretize the speed for each position point to obtain a candidate speed sequence corresponding to each position point.

[0078] Step 203, define the state for the candidate speed of each position point.

[0079] Here, the state can be represented by , indicating that the vehicle speed at position is .

[0080] Step 204, perform speed path search using the fuel consumption function and the heuristic estimation function.

[0081] Here, the heuristic estimation function can be the fuel consumption from the current position point to the end position point.

[0082] The specific implementation process of Step 204 can refer to the above Steps 102 - 104, and will not be elaborated here.

[0083] Step 205, output the target speed curve and the cumulative fuel consumption value.

[0084] Here, the finally output cumulative fuel consumption value can be used for comparison with other algorithms.

[0085] In practical application scenarios, the method for determining the vehicle speed curve reduces the expansion amount of the dynamic programming states, the calculation time is reduced by about 50%, meeting the millisecond-level response requirements. The optimized fuel consumption is reduced by about 3% compared with the traditional method. The fixed-distance division improves the smoothness of the speed curve and reduces the acceleration and braking frequencies. In scenarios with drastic slope changes or curves, the optimization results are closer to the actual requirements, and the driving is safer and more efficient.

[0086] In the embodiments of the present invention, the method for determining the vehicle speed curve has the following effects: By designing a heuristic estimation function to guide the dynamic programming search direction, the search amount of the state space is effectively reduced. Compared with the traditional pure dynamic programming method, the computational complexity is reduced, the real-time performance is improved, and the millisecond-level optimization requirements in autonomous driving and complex road environments can be met. At the same time, with the guarantee of the global search ability, the problem that a simple heuristic algorithm is prone to fall into local optimality is avoided; The road slope information is incorporated into the fuel consumption model, and the comprehensive influence of the slope on dynamics and fuel economy is introduced into the state transition rule. Through the combination of dynamic programming recursion and the slope perception model, the optimization algorithm can more accurately calculate the fuel consumption in complex terrains (such as mountainous areas or downhill sections with drastic slope changes), making the optimization results significantly improve the fuel economy and reduce the ineffective energy consumption; The speed optimization method using fixed-distance division has a more uniform distribution in space for the optimization results compared with the traditional time-step-based planning method. This division method adapts to complex terrain environments (such as continuous slope changes and curves), generates a more smooth speed curve, and avoids frequent acceleration and braking behaviors caused by non-uniform space, improving the driving stability and comfort of the vehicle.

[0087] The device for determining the vehicle speed curve provided by the present invention will be described below. The device for determining the vehicle speed curve described below can be correspondingly referred to the method for determining the vehicle speed curve described above.

[0088] Figure 3 is a schematic structural diagram of the device for determining the vehicle speed curve provided by the present invention. As Figure 3 shown, the device 300 for determining the vehicle speed curve includes: A division module 301, configured to divide the to-be-driven path of the vehicle based on a preset distance step size to obtain N position points, where N is an integer greater than or equal to 2; A speed sequence determination module 302, configured to determine a candidate speed sequence corresponding to each of the position points; A target speed determination module 303, configured to determine a target speed from the candidate speed sequences corresponding to the next position points based on a fuel consumption objective function and the independent fuel consumption values from each of the position points to the corresponding next position point; the fuel consumption objective function is used to represent the cumulative fuel consumption value before the position point; A target speed curve determination module 304, configured to determine a target speed curve corresponding to the to-be-traveled path based on each of the target speeds.

[0089] In some embodiments, the target speed determination module 303 is specifically configured to: determine the cumulative fuel consumption value corresponding to each first candidate speed in the candidate speed sequence corresponding to the position point based on the fuel consumption objective function; determine the first speed as the first candidate speed corresponding to the minimum cumulative fuel consumption value; determine the independent fuel consumption value corresponding to each second candidate speed in the candidate speed sequence corresponding to the next position point based on the first speed and the candidate speed sequence corresponding to the next position point; and determine the target speed from the candidate speed sequences corresponding to each of the next position points based on the cumulative fuel consumption value and the independent fuel consumption value.

[0090] In some embodiments, the target speed determination module 303 is further specifically configured to: determine the total fuel consumption cost value corresponding to each second candidate speed in the candidate speed sequence corresponding to the next position point based on the cumulative fuel consumption value and the independent fuel consumption value; and determine the second candidate speed corresponding to the minimum total fuel consumption cost value as the target speed.

[0091] In some embodiments, the target speed determination module 303 is further specifically configured to determine a fuel consumption model, specifically: determine the distance between the position point and the next position point; determine the speed difference between the first speed and each of the second candidate speeds; and determine the independent fuel consumption value corresponding to each of the second candidate speeds based on the distance, the speed difference, and the slope angle corresponding to the position point.

[0092] In some embodiments, the device 300 for determining the vehicle speed curve further includes: a fuel consumption objective function determination module, specifically configured to: determine a first expression of the fuel consumption corresponding to the air resistance where the vehicle is located; determine a second expression of the fuel consumption corresponding to the acceleration of the vehicle; determine a third expression of the fuel consumption corresponding to the gravitational resistance of the slope angle at the position point where the vehicle is located; determine a fourth expression of the fuel consumption corresponding to the road friction resistance at the position point where the vehicle is located; and determine the fuel consumption objective function based on the first expression, the second expression, the third expression, and the fourth expression.

[0093] In some embodiments, the speed sequence determination module 302 is specifically configured to: determine the maximum speed corresponding to each position point and the minimum speed corresponding to the position point based on the road curvature corresponding to each position point and the maximum centrifugal force corresponding to each position point; and perform discretization processing on the speed of each position point based on the maximum speed and the minimum speed to obtain each candidate speed sequence.

[0094] Figure 4 is a schematic structural diagram of the electronic device provided by the present invention. As Figure 4 shown, the electronic device may include: a processor 410, a communications interface 420, a memory 430, and a communication bus 440. Among them, the processor 410, the communications interface 420, and the memory 430 complete mutual communication through the communication bus 440. The processor 410 may call logic instructions in the memory 430 to execute a method for determining a vehicle speed curve. The method includes: dividing a to-be-traveled path of the vehicle based on a preset distance step size to obtain N position points, where N is an integer greater than or equal to 2; determining a candidate speed sequence corresponding to each of the position points; determining a target speed from the candidate speed sequences corresponding to each of the next position points based on a fuel consumption objective function and an independent fuel consumption value from each of the position points to the corresponding next position point; the fuel consumption objective function is used to represent an accumulated fuel consumption value before the position point; and determining a target speed curve corresponding to the to-be-traveled path based on each of the target speeds.

[0095] In addition, when the logic instructions in the foregoing memory 430 are implemented in the form of software function units and sold or used as an independent product, they may be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or a part of this technical solution, may be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present invention. The foregoing storage medium includes: various media such as a USB flash drive, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a magnetic disk, or an optical disc that can store program codes.

[0096] On the other hand, the present invention also provides a computer program product, which includes a computer program that can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the method for determining the vehicle speed curve provided by each of the above methods. The method includes: dividing the to-be-traveled path of the vehicle based on a preset distance step size to obtain N position points, where N is an integer greater than or equal to 2; determining a candidate speed sequence corresponding to each of the position points; determining a target speed from the candidate speed sequences corresponding to each of the next position points based on a fuel consumption objective function and the independent fuel consumption values from each of the position points to the corresponding next position point; the fuel consumption objective function is used to represent the cumulative fuel consumption value before the position point; and determining a target speed curve corresponding to the to-be-traveled path based on each of the target speeds.

[0097] On another aspect, the present invention also provides a non-transitory computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, it realizes the method for determining the vehicle speed curve provided by each of the above methods. The method includes: dividing the to-be-traveled path of the vehicle based on a preset distance step size to obtain N position points, where N is an integer greater than or equal to 2; determining a candidate speed sequence corresponding to each of the position points; determining a target speed from the candidate speed sequences corresponding to each of the next position points based on a fuel consumption objective function and the independent fuel consumption values from each of the position points to the corresponding next position point; the fuel consumption objective function is used to represent the cumulative fuel consumption value before the position point; and determining a target speed curve corresponding to the to-be-traveled path based on each of the target speeds.

[0098] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art can understand and implement it without creative efforts.

[0099] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on such an understanding, the essence of the above technical solution, or the part that contributes to the prior art, can be embodied in the form of a software product. The computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0100] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit them. Although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements for some of the technical features. And these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for determining a vehicle speed profile, characterized in that: include: Based on the preset distance step, the vehicle's to-be-traveled path is divided into N position points, where N is an integer greater than or equal to 2; Determine a candidate speed sequence corresponding to each of the position points; Determining a target speed from a candidate speed sequence corresponding to each of the next position points based on a fuel consumption objective function and an independent fuel consumption value from each of the position points to a corresponding next position point; the fuel consumption objective function is used to characterize the cumulative fuel consumption value before the position point; Based on each of the target speeds, a target speed curve corresponding to the path to be traveled is determined.

2. The method for determining a vehicle speed profile according to claim 1, characterized in that: The step of determining the target speed from the candidate speed sequence corresponding to each of the next position points based on the fuel consumption objective function and the independent fuel consumption value from each of the position points to the corresponding next position point comprises: Based on the fuel consumption objective function, determining a cumulative fuel consumption value corresponding to each first candidate speed in the candidate speed sequence corresponding to the position point; Determine a first candidate speed corresponding to the minimum accumulated fuel consumption value as the first speed; Determine, based on the first speed and the candidate speed sequence corresponding to the next position point, an independent fuel consumption value corresponding to each second candidate speed in the candidate speed sequence corresponding to the next position point; Based on the accumulated fuel consumption value and the independent fuel consumption value, a target speed is determined from a candidate speed sequence corresponding to each of the next position points.

3. The method for determining a vehicle speed profile according to claim 2, characterized in that: The determining the target speed from the candidate speed sequences corresponding to each of the next position points based on the accumulated fuel consumption value and the independent fuel consumption value comprises: Determine, based on the accumulated fuel consumption value and the independent fuel consumption value, a total fuel consumption cost corresponding to each second candidate speed in the candidate speed sequence corresponding to the next position point; The second candidate speed corresponding to the minimum total cost of fuel consumption is determined as the target speed.

4. The method for determining a vehicle speed profile according to claim 2 or 3, characterized in that: The determining, based on the first speed and the candidate speed sequence corresponding to the next position point, an independent fuel consumption value corresponding to each second candidate speed in the candidate speed sequence corresponding to the next position point comprises: Determine the distance between the position point and the next position point; determining a speed difference between the first speed and each of the second candidate speeds; Based on the distance, the speed difference and the slope angle corresponding to the position point, an independent fuel consumption value corresponding to each of the second candidate speeds is determined.

5. The method for determining a vehicle speed profile according to any one of claims 1 to 3, characterized in that: Determining the fuel consumption objective function includes: Determine a first expression for fuel consumption corresponding to the air resistance of the vehicle; Determining a second expression for fuel consumption corresponding to the acceleration of the vehicle; Determine a third expression for the fuel consumption corresponding to the gravity resistance of the slope angle at the position point where the vehicle is located; Determine a fourth expression for the fuel consumption corresponding to the road friction resistance at the position point where the vehicle is located; The fuel consumption objective function is determined based on the first expression, the second expression, the third expression, and the fourth expression.

6. The method for determining a vehicle speed profile according to any one of claims 1 to 3, characterized in that: The determining of the candidate speed sequence corresponding to each of the position points comprises: Determining a maximum speed corresponding to each of the position points and a minimum speed corresponding to the position points based on a road curvature corresponding to each of the position points and a maximum centrifugal force corresponding to each of the position points; Based on the maximum speed and the minimum speed, the speed of each of the position points is discretized to obtain each of the candidate speed sequences.

7. A device for determining a vehicle speed profile, characterized in that: The device comprises: A division module, used for dividing the vehicle's to-be-traveled path based on a preset distance step length to obtain N position points, where N is an integer greater than or equal to 2; A speed sequence determination module, used to determine a candidate speed sequence corresponding to each of the position points; a target speed determination module, configured to determine a target speed from a candidate speed sequence corresponding to each of the next position points based on a fuel consumption objective function and an independent fuel consumption value from each of the position points to the corresponding next position point; the fuel consumption objective function is used to characterize the accumulated fuel consumption value before the position point; The target speed curve determination module is used to determine the target speed curve corresponding to the to-be-traveled path based on each of the target speeds.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When the processor executes the computer program, the method for determining a vehicle speed profile according to any one of claims 1 to 6 is implemented.

9. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for determining a vehicle speed profile according to any one of claims 1 to 6 is implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the method for determining a vehicle speed profile according to any one of claims 1 to 6 is implemented.

Images