A speed planning method and device for intelligent driving

Abstract

The application provides a speed planning method and device for intelligent driving, wherein the method comprises the following steps: obtaining an energy-saving driving speed planning corresponding to a kinematic vehicle prediction model and an energy-saving driving speed planning corresponding to a dynamic vehicle prediction model; adjusting the weights of the energy-saving driving speed planning corresponding to the kinematic vehicle prediction model and the energy-saving driving speed planning corresponding to the dynamic vehicle prediction model according to the confidence of the energy-saving driving speed planning corresponding to the kinematic vehicle prediction model and the confidence of the dynamic vehicle prediction model; and weighting and fusing the energy-saving driving speed planning corresponding to the kinematic vehicle prediction model and the energy-saving driving speed planning corresponding to the dynamic vehicle prediction model to determine a final energy-saving driving speed planning. The optimality and robustness of the vehicle fuel-saving speed planning are improved.

Description

Technical Field

[0001] This invention relates to the field of energy-saving autonomous driving, and in particular to a speed planning method and apparatus for intelligent driving. Background Technology

[0002] Current methods for planning fuel-saving (energy-efficient) vehicle speeds typically rely on vehicle dynamics models (or dynamic vehicle prediction models) and road and traffic information for prediction and planning. However, the dynamics models used have numerous parameters, some of which are dynamically changing and cannot be directly measured. This limits the applicability of the dynamics models, resulting in weak robustness of the related fuel-saving speed planning algorithms and a limited coverage of energy-efficient driving scenarios. Summary of the Invention

[0003] This invention provides a speed planning method and apparatus for intelligent driving.

[0004] In a first aspect, the present invention provides a speed planning method for intelligent driving, comprising: obtaining an energy-saving driving speed plan corresponding to a kinematic vehicle prediction model and an energy-saving driving speed plan corresponding to a dynamic vehicle prediction model, wherein the energy-saving driving speed plan represents continuous vehicle speed change values ​​within a preset range for the purpose of energy saving; determining the confidence level of the energy-saving driving speed plan corresponding to the kinematic vehicle prediction model and the confidence level of the dynamic vehicle prediction model; adjusting the weights of the energy-saving driving speed plan corresponding to the kinematic vehicle prediction model and the energy-saving driving speed plan corresponding to the dynamic vehicle prediction model based on the confidence levels of the kinematic vehicle prediction model and the dynamic vehicle prediction model; and weightedly fusing the energy-saving driving speed plan corresponding to the kinematic vehicle prediction model and the energy-saving driving speed plan corresponding to the dynamic vehicle prediction model according to the weights to determine the final energy-saving driving speed plan.

[0005] Furthermore, the acquisition of energy-saving driving speed planning corresponding to the kinematic vehicle prediction model and the dynamic vehicle prediction model includes: determining the range of the target road and the dynamic parameters of the vehicle and surrounding vehicles within a preset time period based on the acquired data from the vehicle's onboard sensors and traffic road information within a preset range using the kinematic vehicle prediction model / dynamic vehicle prediction model; and determining the energy-saving driving speed planning corresponding to the kinematic vehicle prediction model / dynamic vehicle prediction model based on preset constraints of target vehicle speed, energy-saving requirements, and safe distance, according to the range of the target road and the dynamic parameters of the vehicle and surrounding vehicles within the preset time period.

[0006] Furthermore, determining the confidence level of the energy-saving driving speed plan corresponding to the kinematic vehicle prediction model includes: determining the confidence level of the energy-saving driving speed plan corresponding to the kinematic vehicle prediction model based on the negative correlation between the vehicle's speed and the road gradient.

[0007] Furthermore, the confidence level of the dynamic vehicle prediction model is determined based on the mean square error between the model-predicted values ​​of the vehicle's speed or acceleration and the values ​​of the vehicle's speed or acceleration measured by the vehicle's sensors.

[0008] Further, adjusting the weights of the energy-saving driving speed planning corresponding to the kinematic vehicle prediction model and the energy-saving driving speed planning corresponding to the dynamic vehicle prediction model based on the confidence levels of the kinematic vehicle prediction model and the dynamic vehicle prediction model includes: normalizing the confidence levels of the kinematic vehicle prediction model and the dynamic vehicle prediction model to obtain the weights of the energy-saving driving speed planning corresponding to the kinematic vehicle prediction model and the energy-saving driving speed planning corresponding to the dynamic vehicle prediction model.

[0009] Furthermore, the traffic and road information includes traffic information and / or road information, whereby the traffic information includes the position and speed information of surrounding vehicles within a preset range, and the road information includes road gradient information.

[0010] Secondly, the present invention also provides a speed planning device for intelligent driving, comprising: a first processing module, configured to acquire an energy-saving driving speed plan corresponding to a kinematic vehicle prediction model and an energy-saving driving speed plan corresponding to a dynamic vehicle prediction model, wherein the energy-saving driving speed plan represents continuous vehicle speed change values ​​within a preset range for the purpose of energy saving; a second processing module, configured to determine the confidence level of the energy-saving driving speed plan corresponding to the kinematic vehicle prediction model and the confidence level of the dynamic vehicle prediction model, and adjust the weights of the energy-saving driving speed plan corresponding to the kinematic vehicle prediction model and the energy-saving driving speed plan corresponding to the dynamic vehicle prediction model based on the confidence levels of the kinematic vehicle prediction model and the dynamic vehicle prediction model; and a third processing module, configured to weightedly fuse the energy-saving driving speed plan corresponding to the kinematic vehicle prediction model and the energy-saving driving speed plan corresponding to the dynamic vehicle prediction model according to the weights, and determine the final energy-saving driving speed plan.

[0011] Thirdly, the present invention also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the steps of the speed planning method for intelligent driving as described above.

[0012] Fourthly, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the speed planning method for intelligent driving as described above.

[0013] Fifthly, the present invention also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of any of the above-described speed planning methods for intelligent driving.

[0014] This invention provides a speed planning method and apparatus for intelligent driving. It involves acquiring energy-saving driving speed plans corresponding to a kinematic vehicle prediction model and a dynamic vehicle prediction model, where the energy-saving speed plan represents continuous vehicle speed changes within a preset range for energy conservation. The method then determines the confidence levels of the energy-saving speed plans corresponding to the kinematic and dynamic vehicle prediction models, adjusts their weights based on these confidence levels, and finally weights and fuses them to determine the final energy-saving driving speed plan. It can be seen that because the kinematic vehicle prediction model does not depend on dynamic parameters, it has a wider range of applications, stronger resistance to environmental interference, and better stability. The dynamic vehicle prediction model has high prediction accuracy. By combining the prediction results of the two models in a weighted fusion manner, the advantages of both models can be combined. This not only solves the problem of limited coverage of energy-saving driving scenarios, but also effectively improves the optimality and robustness of vehicle fuel-saving speed planning. Attached Figure Description

[0015] To more clearly illustrate the technical solutions in this invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0016] Figure 1 This is a flowchart illustrating some embodiments of the speed planning method for intelligent driving provided by the present invention;

[0017] Figure 2 This is a schematic diagram of some embodiments of the speed planning device for intelligent driving provided by the present invention;

[0018] Figure 3This is a schematic diagram of the structure of an electronic device provided according to the present invention. Detailed Implementation

[0019] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without creative effort are within the scope of protection of this invention.

[0020] It should also be noted that, for ease of description, only the parts relevant to the invention are shown in the accompanying drawings. Unless otherwise specified, the embodiments and features described herein can be combined with each other.

[0021] It should be noted that the concepts of "first" and "second" mentioned in this invention are only used to distinguish different devices, modules or units, and are not used to limit the order of functions performed by these devices, modules or units or their interdependencies.

[0022] It should be noted that the terms "a" and "a plurality of" used in this invention are illustrative rather than restrictive. Those skilled in the art should understand that, unless otherwise expressly indicated in the context, they should be understood as "one or more".

[0023] The names of the messages or information exchanged between the multiple devices in the embodiments of the present invention are for illustrative purposes only and are not intended to limit the scope of these messages or information.

[0024] The present invention will now be described in detail with reference to the accompanying drawings and embodiments.

[0025] Please see Figure 1 , Figure 1 These are schematic flowcharts illustrating some embodiments of the speed planning method for intelligent driving provided by the present invention. Figure 1 As shown, the method includes the following steps:

[0026] Step 101: Obtain the energy-saving driving speed plan corresponding to the kinematic vehicle prediction model and the energy-saving driving speed plan corresponding to the dynamic vehicle prediction model. The energy-saving driving speed plan represents the continuous vehicle speed change value within a preset range for the purpose of energy saving.

[0027] When planning energy-efficient driving speeds, you can consider only the surrounding vehicles in the road traffic environment, only the road gradient, or both for comprehensive planning.

[0028] As an example, the preset range can be a certain time range or a certain distance range, which can be set according to specific needs.

[0029] Energy-saving driving speed planning indicates the predicted speed changes over a period of time or distance. It can be an array, such as [3km / h, 4km / h, 5km / h, 5km / h], where one speed value represents the speed within one minute. This array represents the speed changes over four consecutive minutes.

[0030] Step 102: Determine the confidence level of the energy-saving driving speed planning corresponding to the kinematic vehicle prediction model and the confidence level of the dynamic vehicle prediction model. Based on the confidence levels of the kinematic vehicle prediction model and the dynamic vehicle prediction model, adjust the weights of the energy-saving driving speed planning corresponding to the kinematic vehicle prediction model and the energy-saving driving speed planning corresponding to the dynamic vehicle prediction model.

[0031] In one embodiment, a reference table of confidence levels and weights can be preset. Based on the confidence levels of the energy-saving driving speed planning corresponding to the kinematic vehicle prediction model and the dynamic vehicle prediction model, the reference table is queried to adjust the weights of the energy-saving driving speed planning corresponding to the kinematic vehicle prediction model and the energy-saving driving speed planning corresponding to the dynamic vehicle prediction model.

[0032] As an example, the weights of the energy-saving driving speed planning corresponding to the kinematic vehicle prediction model are determined by querying the confidence reference table; the weights of the energy-saving driving speed planning corresponding to the dynamic vehicle prediction model are determined by querying the confidence reference table.

[0033] Step 103: Based on the weights, the energy-saving driving speed plans corresponding to the kinematic vehicle prediction model and the energy-saving driving speed plans corresponding to the dynamic vehicle prediction model are weighted and fused to determine the final energy-saving driving speed plan.

[0034] The speed planning method for intelligent driving disclosed in some embodiments of this invention obtains energy-saving driving speed plans corresponding to a kinematic vehicle prediction model and a dynamic vehicle prediction model. The energy-saving driving speed plan represents continuous vehicle speed changes within a preset range for energy conservation. The method determines the confidence levels of the energy-saving driving speed plans corresponding to the kinematic vehicle prediction model and the dynamic vehicle prediction model. Based on these confidence levels, the weights of the energy-saving driving speed plans corresponding to the kinematic vehicle prediction model and the dynamic vehicle prediction model are adjusted. Finally, the energy-saving driving speed plans corresponding to the kinematic vehicle prediction model and the dynamic vehicle prediction model are weighted and fused to determine the final energy-saving driving speed plan. It can be seen that because the kinematic vehicle prediction model does not depend on dynamic parameters, it has a wider range of applications, stronger resistance to environmental interference, and better stability. The dynamic vehicle prediction model has high prediction accuracy. By combining the prediction results of the two models in a weighted fusion manner, the advantages of both models can be combined. This not only solves the problem of limited coverage of energy-saving driving scenarios, but also effectively improves the optimality and robustness of vehicle fuel-saving speed planning.

[0035] In some optional implementations, obtaining the energy-saving driving speed plan corresponding to the kinematic vehicle prediction model and the energy-saving driving speed plan corresponding to the dynamic vehicle prediction model includes: determining the range of the target road and the dynamic parameters of the vehicle and surrounding vehicles within a preset time period based on the acquired data from the vehicle's onboard sensors and traffic road information within a preset range using the kinematic vehicle prediction model / dynamic vehicle prediction model; and determining the energy-saving driving speed plan corresponding to the kinematic vehicle prediction model / energy-saving driving speed plan corresponding to the dynamic vehicle prediction model based on preset constraints of vehicle driving target speed, energy-saving requirements, and safety distance, according to the range of the target road and the dynamic parameters of the vehicle and surrounding vehicles within a preset time period.

[0036] Predictive models, whether kinematic or dynamic, are essentially optimization control algorithms. They predict the vehicle's motion state, optimize the objective, solve an open-loop optimization problem within a finite time period, and apply the first part of the predicted time period's control input to the controlled object. One optional implementation provided by this invention is to establish optimization control using data from the vehicle's onboard sensors and traffic information within a preset range, solving for the target road range and the dynamic parameters of the vehicle and surrounding vehicles within a preset time period. Then, based on the obtained target road range, the dynamic parameters of the vehicle and surrounding vehicles within the preset time period, and constraints, the corresponding energy-saving driving speed plan is determined. As an example, linear recursion can be used, such as the speed at the next moment = the speed at the previous moment + the acceleration at the previous moment * the time interval, to determine the dynamic speed parameters of the vehicle and surrounding vehicles.

[0037] As an example, the data acquired from the vehicle's onboard sensors includes the vehicle's speed, acceleration, etc.

[0038] As an example, the preset range can be a range set as needed; the traffic information within the preset range includes the speed and acceleration of surrounding vehicles.

[0039] As an example, the range of the target road represents the length of the road that the vehicle will travel.

[0040] As an example, the scope of the target road and the dynamic parameters of the vehicle and surrounding vehicles within a preset time period can be input into the optimizer. The optimizer's constraints are set as preset target vehicle speed, energy-saving requirements, and safe distance. The optimization result is then obtained, i.e., the energy-saving driving speed plan corresponding to the kinematic vehicle prediction model / the energy-saving driving speed plan corresponding to the dynamic vehicle prediction model. The optimizer can be OSQP (Operator Splitting Quadratic Program) or IPOPT. OSQP is an OSQP solver based on ADMM. IPOPT is a toolset for solving nonlinear programming optimization problems.

[0041] In some optional implementations, the confidence level of the energy-saving driving speed planning corresponding to the kinematic vehicle prediction model is determined, including: determining the confidence level of the energy-saving driving speed planning corresponding to the kinematic vehicle prediction model based on the negative correlation between the vehicle's speed and the road gradient.

[0042] Vehicle speed and road gradient are negatively correlated; that is, the steeper the road gradient, the slower the vehicle speed. As an example, data on vehicle speed and road gradient over a period of time can be obtained, and the degree of negative correlation can be calculated. A higher negative correlation indicates a higher confidence level.

[0043] As an example, the confidence level of the energy-saving driving speed plan corresponding to the kinematic vehicle prediction model can also be determined by calculating the correlation between the position of the surrounding vehicles and the speed of the vehicle itself. The confidence level can be represented by the normalized similarity, which is the correlation coefficient between two dynamic variables (i.e., the position of the surrounding vehicles and the speed of the vehicle itself).

[0044] In some alternative implementations, the confidence level of the dynamic vehicle prediction model is determined based on the mean square error between the model-predicted values ​​of the vehicle's speed or acceleration and the values ​​of the vehicle's speed or acceleration measured by its sensors.

[0045] In some embodiments, the vehicle itself may have a built-in model for predicting speed or acceleration. This model predicts the speed or acceleration at the next moment (i.e., the current moment) by receiving speed or acceleration measurements from the vehicle's sensors at the previous moment. Simultaneously, the vehicle's own sensors can also measure the vehicle's current speed or acceleration. Then, a mean squared error is calculated based on the model's predicted speed or acceleration and the speed or acceleration values ​​measured by the vehicle's sensors. The mean squared error value corresponds to a preset confidence level to determine the confidence level of the dynamic vehicle prediction model.

[0046] As an example, the suitability of a dynamic vehicle prediction model and its energy-saving driving speed planning can be calculated based on error evaluation indicators and / or correlation evaluation indicators.

[0047] In some embodiments, the confidence level of the dynamic vehicle prediction model can also be determined by the method of online model validation absolute value error.

[0048] In some optional implementations, the weights of the energy-saving driving speed planning corresponding to the kinematic vehicle prediction model and the energy-saving driving speed planning corresponding to the dynamic vehicle prediction model are adjusted based on the confidence levels of the kinematic vehicle prediction model and the dynamic vehicle prediction model. This includes: normalizing the confidence levels of the kinematic vehicle prediction model and the dynamic vehicle prediction model to obtain the weights of the energy-saving driving speed planning corresponding to the kinematic vehicle prediction model and the energy-saving driving speed planning corresponding to the dynamic vehicle prediction model.

[0049] Since the confidence scores of the kinematic vehicle prediction model and the dynamic vehicle prediction model are not calculated under the same conditions, they need to be normalized. The sum of their normalized confidence scores is 1, as the normalized confidence scores represent the corresponding weights. Alternatively, a pre-defined table of confidence scores and weights can be used to adjust the weights based on the normalized confidence scores—increasing the weights for higher confidence scores and decreasing them for lower confidence scores. This achieves the fusion of the two methods.

[0050] In some optional implementations, traffic and road information includes traffic information and / or road information. Traffic information includes the position and speed information of surrounding vehicles within a preset range, and road information includes road gradient information.

[0051] This invention integrates energy-saving speed planning based on vehicle kinematics and dynamics characteristics, which not only ensures the accuracy and optimality of energy-saving driving speed planning, but also improves the applicability of the algorithm, enhances the robustness of the energy-saving driving algorithm, and enables coverage of more energy-saving driving scenarios.

[0052] Please see Figure 2 , Figure 2 These are schematic diagrams illustrating the structure of some embodiments of a speed planning device for intelligent driving provided by the present invention. As an implementation of the methods shown in the above figures, the present invention also provides some embodiments of a speed planning device for intelligent driving, which are similar to... Figure 1 The embodiments of some of the methods shown correspond to this, and the device can be applied to a variety of electronic devices.

[0053] like Figure 2 As shown, some embodiments of a speed planning device for intelligent driving include a first processing module 201, a second processing module 202, and a third processing module 203: The first processing module 201 is used to obtain energy-saving driving speed plans corresponding to a kinematic vehicle prediction model and energy-saving driving speed plans corresponding to a dynamic vehicle prediction model, wherein the energy-saving driving speed plan represents continuous vehicle speed change values ​​within a preset range for the purpose of energy saving; the second processing module 202 is used to determine the confidence level of the energy-saving driving speed plan corresponding to the kinematic vehicle prediction model and the confidence level of the dynamic vehicle prediction model, and adjust the weights of the energy-saving driving speed plans corresponding to the kinematic vehicle prediction model and the dynamic vehicle prediction model according to the confidence levels of the kinematic vehicle prediction model and the dynamic vehicle prediction model; the third processing module 203 is used to weightedly fuse the energy-saving driving speed plans corresponding to the kinematic vehicle prediction model and the dynamic vehicle prediction model according to the weights to determine the final energy-saving driving speed plan.

[0054] In some optional implementations of the embodiments, the first processing module 201 is further configured to: determine the range of the target road and the dynamic parameters of the vehicle and surrounding vehicles within a preset time period based on the data from the vehicle's onboard sensors and traffic road information within a preset range, using a kinematic vehicle prediction model / dynamic vehicle prediction model; and determine the energy-saving driving speed plan corresponding to the kinematic vehicle prediction model / energy-saving driving speed plan corresponding to the dynamic vehicle prediction model based on preset constraints of vehicle driving target speed, energy-saving requirements, and safety distance, according to the range of the target road and the dynamic parameters of the vehicle and surrounding vehicles within a preset time period.

[0055] In some optional implementations of the embodiments, the second processing module 202 is further configured to: determine the confidence level of the energy-saving driving speed planning corresponding to the kinematic vehicle prediction model based on the negative correlation between the vehicle's speed and the road gradient.

[0056] In some optional implementations of embodiments, the second processing module 202 is further configured to: determine the confidence level of the dynamic vehicle prediction model based on the mean square error between the model prediction value of the vehicle's speed or acceleration and the value of the speed or acceleration measured by the vehicle's sensors.

[0057] In some optional implementations of the embodiments, the second processing module 202 is further configured to: normalize the confidence of the energy-saving driving speed planning corresponding to the kinematic vehicle prediction model and the confidence of the dynamic vehicle prediction model to obtain the weights of the energy-saving driving speed planning corresponding to the kinematic vehicle prediction model and the energy-saving driving speed planning corresponding to the dynamic vehicle prediction model.

[0058] In some optional implementations of the embodiments, traffic road information includes traffic information and / or road information, where traffic information includes the position and speed information of surrounding vehicles within a preset range, and road information includes road slope information.

[0059] It is understandable that the modules described in this device are consistent with the reference. Figure 1 The steps in the described method correspond to each other. Therefore, the operations, features, and beneficial effects described above for the method also apply to the device and the modules and units contained therein, and will not be repeated here.

[0060] Figure 3 An example is a schematic diagram of the physical structure of an electronic device, such as... Figure 3As shown, the electronic device may include: a processor 310, a communication interface 320, a memory 330, and a communication bus 340, wherein the processor 310, the communication interface 320, and the memory 330 communicate with each other through the communication bus 340. The processor 310 can call logic instructions in the memory 330 to execute a speed planning method for intelligent driving. This method includes: acquiring energy-saving driving speed plans corresponding to a kinematic vehicle prediction model and a dynamic vehicle prediction model, where the energy-saving driving speed plan represents continuous vehicle speed changes within a preset range for energy saving; determining the confidence levels of the energy-saving driving speed plans corresponding to the kinematic vehicle prediction model and the dynamic vehicle prediction model; adjusting the weights of the energy-saving driving speed plans corresponding to the kinematic vehicle prediction model and the dynamic vehicle prediction model based on their respective confidence levels; and weightedly fusing the energy-saving driving speed plans corresponding to the kinematic vehicle prediction model and the dynamic vehicle prediction model according to their weights to determine the final energy-saving driving speed plan.

[0061] Furthermore, the logical instructions in the aforementioned memory 330 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0062] On the other hand, the present invention also provides a computer program product, which includes a computer program stored on a non-transitory computer-readable storage medium. The computer program includes program instructions, and when the program instructions are executed by a computer, the computer is able to execute the speed planning method for intelligent driving provided by the above methods. The method includes: obtaining an energy-saving driving speed plan corresponding to a kinematic vehicle prediction model and an energy-saving driving speed plan corresponding to a dynamic vehicle prediction model, wherein the energy-saving driving speed plan represents a continuous vehicle speed change value within a preset range for the purpose of energy saving; determining the confidence level of the energy-saving driving speed plan corresponding to the kinematic vehicle prediction model and the confidence level of the dynamic vehicle prediction model; adjusting the weights of the energy-saving driving speed plan corresponding to the kinematic vehicle prediction model and the energy-saving driving speed plan corresponding to the dynamic vehicle prediction model based on the confidence levels of the kinematic vehicle prediction model and the dynamic vehicle prediction model; and weightedly fusing the energy-saving driving speed plan corresponding to the kinematic vehicle prediction model and the energy-saving driving speed plan corresponding to the dynamic vehicle prediction model according to the weights to determine the final energy-saving driving speed plan.

[0063] In another aspect, the present invention also provides a non-transitory computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the speed planning methods for intelligent driving provided above. The method includes: obtaining an energy-saving driving speed plan corresponding to a kinematic vehicle prediction model and an energy-saving driving speed plan corresponding to a dynamic vehicle prediction model, wherein the energy-saving driving speed plan represents continuous vehicle speed changes within a preset range for energy saving; determining the confidence level of the energy-saving driving speed plan corresponding to the kinematic vehicle prediction model and the confidence level of the dynamic vehicle prediction model; adjusting the weights of the energy-saving driving speed plan corresponding to the kinematic vehicle prediction model and the energy-saving driving speed plan corresponding to the dynamic vehicle prediction model based on the confidence levels of the kinematic vehicle prediction model and the dynamic vehicle prediction model; and weightedly fusing the energy-saving driving speed plan corresponding to the kinematic vehicle prediction model and the energy-saving driving speed plan corresponding to the dynamic vehicle prediction model according to the weights to determine the final energy-saving driving speed plan.

[0064] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0065] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This 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 cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0066] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A speed planning method for intelligent driving, characterized in that, include: Obtain the energy-saving driving speed plan corresponding to the kinematic vehicle prediction model and the energy-saving driving speed plan corresponding to the dynamic vehicle prediction model. The energy-saving driving speed plan represents the continuous vehicle speed change value within a preset range for the purpose of energy saving. The confidence level of the energy-saving driving speed planning corresponding to the kinematic vehicle prediction model is determined based on the negative correlation between the vehicle's speed and the road slope; the higher the negative correlation between the vehicle's speed and the road slope, the higher the confidence level. The confidence level of the dynamic vehicle prediction model is determined based on the mean square error between the model's predicted speed or acceleration value and the speed or acceleration value measured by the vehicle's sensors. The weights of the energy-saving driving speed planning corresponding to the kinematic vehicle prediction model and the dynamic vehicle prediction model are adjusted based on their respective confidence levels. Based on the weights, the energy-saving driving speed plans corresponding to the kinematic vehicle prediction model and the energy-saving driving speed plans corresponding to the dynamic vehicle prediction model are weighted and fused to determine the final energy-saving driving speed plan.

2. The speed planning method for intelligent driving according to claim 1, characterized in that, The process of obtaining the energy-saving driving speed plan corresponding to the kinematic vehicle prediction model and the energy-saving driving speed plan corresponding to the dynamic vehicle prediction model includes: Based on the data from the vehicle's onboard sensors and traffic information within a preset range, the range of the target road and the dynamic parameters of the vehicle and surrounding vehicles within a preset time period are determined using a kinematic vehicle prediction model / dynamic vehicle prediction model. Based on the preset constraints of target vehicle speed, energy-saving requirements, and safe distance, the energy-saving driving speed planning corresponding to the kinematic vehicle prediction model and the energy-saving driving speed planning corresponding to the dynamic vehicle prediction model are determined according to the range of the target road and the dynamic parameters of the vehicle and surrounding vehicles within a preset time period.

3. The speed planning method for intelligent driving according to any one of claims 1-2, characterized in that, The step of adjusting the weights of the energy-saving driving speed plans corresponding to the kinematic vehicle prediction model and the dynamic vehicle prediction model based on the confidence levels of the kinematic vehicle prediction model and the dynamic vehicle prediction model includes: The confidence scores of the energy-saving driving speed planning corresponding to the kinematic vehicle prediction model and the dynamic vehicle prediction model are normalized to obtain the weights of the energy-saving driving speed planning corresponding to the kinematic vehicle prediction model and the energy-saving driving speed planning corresponding to the dynamic vehicle prediction model.

4. The speed planning method for intelligent driving according to claim 2, characterized in that, The traffic and road information includes traffic information and / or road information. The traffic information includes the position and speed information of surrounding vehicles within a preset range, and the road information includes road gradient information.

5. A speed planning device for intelligent driving, characterized in that, include: The first processing module is used to obtain the energy-saving driving speed plan corresponding to the kinematic vehicle prediction model and the energy-saving driving speed plan corresponding to the dynamic vehicle prediction model. The energy-saving driving speed plan represents the continuous vehicle speed change value within a preset range for the purpose of energy saving. The second processing module is used to determine the confidence level of the energy-saving driving speed planning corresponding to the kinematic vehicle prediction model based on the negative correlation between the vehicle's speed and the road slope; wherein, the higher the negative correlation between the vehicle's speed and the road slope, the higher the confidence level; the module determines the confidence level of the dynamic vehicle prediction model based on the mean square error between the model predicted value of the vehicle's speed or acceleration and the value of the vehicle's speed or acceleration measured by the vehicle's sensors; and adjusts the weights of the energy-saving driving speed planning corresponding to the kinematic vehicle prediction model and the energy-saving driving speed planning corresponding to the dynamic vehicle prediction model based on the confidence levels of the kinematic vehicle prediction model and the dynamic vehicle prediction model. The third processing module is used to weightedly fuse the energy-saving driving speed plan corresponding to the kinematic vehicle prediction model and the energy-saving driving speed plan corresponding to the dynamic vehicle prediction model according to the weights, and determine the final energy-saving driving speed plan.

6. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the steps of the speed planning method for intelligent driving as described in any one of claims 1 to 4.

7. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the speed planning method for intelligent driving as described in any one of claims 1 to 4.

Images