Transient energy-saving control method, device, equipment and storage medium for autonomous driving vehicle

Abstract

The present application discloses a method, device, equipment and storage medium for transient energy-saving control of an autonomous driving vehicle, the method comprising: constructing a transient energy consumption model through historical driving data and historical energy consumption data of the autonomous driving vehicle; taking driving distance and driving time as boundary conditions, and taking the minimum total instantaneous energy consumption value in a future preset time period as the objective function, calculating the optimal energy consumption value for a future preset time period based on the transient energy consumption model; calculating the energy consumption values ​​corresponding to all possible driving plans in the future preset time period through the transient energy consumption model, and calculating the energy consumption penalty factor corresponding to each driving plan based on the deviation between each energy consumption value in the future preset time period and the optimal energy consumption value; deciding the speed distribution and acceleration distribution in the future preset time period based on the energy consumption penalty factors corresponding to all possible driving plans, thereby improving the technical problem that the existing autonomous driving system fails to fully consider the energy consumption problem, affecting the energy efficiency and endurance of the autonomous driving vehicle.

Description

Technical Field

[0001] The present application relates to the field of autonomous driving technology, and in particular to a method, device, equipment and storage medium for transient energy-saving control of an autonomous driving vehicle. Background Art

[0002] With the global environmental protection requirements for energy-saving and consumption-reduction measures in recent years and the increasingly apparent energy consumption problem leading to insufficient vehicle range, it is very important to reduce the energy consumption caused by the autonomous driving system. For high-level autonomous driving vehicles that use new energy vehicles as carriers, improving vehicle energy efficiency and vehicle range are of great significance to increasing the operational efficiency of autonomous driving vehicles.

[0003] Currently, autonomous driving planning and decision-making have not fully considered the impact of energy consumption. Summary of the invention

[0004] The present application provides a method, device, equipment and storage medium for transient energy-saving control of an autonomous driving vehicle, which are used to improve the technical problem that existing autonomous driving systems fail to fully consider energy consumption issues, affecting the energy efficiency and endurance of autonomous driving vehicles.

[0005] In view of this, the first aspect of the present application provides a method for transient energy-saving control of an autonomous driving vehicle, comprising:

[0006] Construct a transient energy consumption model of the autonomous driving vehicle based on the historical driving data and historical energy consumption data of the autonomous driving vehicle;

[0007] Taking the driving distance and driving time as boundary conditions and minimizing the total instantaneous energy consumption in the future preset time period as the objective function, the optimal energy consumption value in the future preset time period is calculated based on the transient energy consumption model;

[0008] The energy consumption values ​​corresponding to all possible driving plans within the future preset time period are calculated by the transient energy consumption model, and the energy consumption penalty factors corresponding to all possible driving plans within the future preset time period are calculated according to the deviations between the energy consumption values ​​within the future preset time period and the optimal energy consumption value, wherein all possible driving plans within the future preset time period include the speed distribution and the acceleration distribution within the future preset time period;

[0009] The speed distribution and acceleration distribution within the future preset time period are determined based on the energy consumption penalty factors corresponding to all possible driving plans within the future preset time period.

[0010] Optionally, the step of constructing a transient energy consumption model of the autonomous driving vehicle using historical driving data and historical energy consumption data of the autonomous driving vehicle includes:

[0011] The speed, acceleration and instantaneous energy consumption value of the autonomous driving vehicle at each historical moment are obtained through the historical driving data and historical energy consumption data of the autonomous driving vehicle;

[0012] The convolutional neural network is trained with the speed and acceleration at each historical moment as input data and the instantaneous energy consumption value at each historical moment as the training target to obtain the transient energy consumption model of the autonomous driving vehicle.

[0013] Optionally, the process of obtaining the instantaneous energy consumption value is:

[0014] Acquire historical energy consumption data of the autonomous driving vehicle through sensors of the autonomous driving vehicle, wherein the historical energy consumption data includes power consumption, power output, heat dissipation loss, and low-voltage system consumption at each historical moment;

[0015] The total output energy of the autonomous driving vehicle at each historical moment is calculated according to the power consumption, power output, heat dissipation loss and low-voltage system consumption of the autonomous driving vehicle at each historical moment, and the instantaneous energy consumption value of the autonomous driving vehicle at each historical moment is obtained.

[0016] Optionally, the method of taking the driving distance and driving time as boundary conditions, taking the minimum total instantaneous energy consumption value in the future preset time period as the objective function, and calculating the optimal energy consumption value in the future preset time period based on the transient energy consumption model includes:

[0017] Taking the driving distance and driving time as boundary conditions and minimizing the total instantaneous energy consumption in the future preset time period as the objective function, the optimal speed distribution and the optimal acceleration distribution in the future preset time period are calculated based on the transient energy consumption model;

[0018] The optimal energy consumption value of the future preset time period is calculated through the optimal speed distribution and the optimal acceleration distribution in the future preset time period.

[0019] Optionally, the method further includes:

[0020] Calculate the safety penalty factor, traffic efficiency penalty factor and comfort penalty factor corresponding to all possible driving plans within the future preset time period;

[0021] The method of determining the speed distribution and acceleration distribution within a future preset time period based on the energy consumption penalty factors corresponding to all possible driving plans within the future preset time period includes:

[0022] The speed distribution and acceleration distribution within the future preset time period are determined according to the energy consumption penalty factor, safety penalty factor, traffic efficiency penalty factor and comfort penalty factor corresponding to all possible driving plans within the future preset time period.

[0023] Optionally, calculate the safety penalty factors corresponding to all possible driving plans within a preset time period in the future, including:

[0024] The safety penalty factors corresponding to all possible driving plans in the future preset time period are calculated according to the intersection degree of the expected driving trajectories corresponding to all possible driving plans in the future preset time period and the obstacle prediction trajectories in the future preset time period.

[0025] Optionally, calculate the comfort penalty factors corresponding to all possible driving plans within a preset time period in the future, including:

[0026] The comfort penalty factors corresponding to all possible driving plans within the future preset time period are calculated according to the acceleration distribution corresponding to all possible driving plans within the future preset time period.

[0027] Optionally, calculate the traffic efficiency penalty factors corresponding to all possible driving plans in the future preset time period, including:

[0028] The traffic efficiency penalty factors corresponding to all possible driving plans within the future preset time period are calculated according to the estimated driving distances corresponding to all possible driving plans within the future preset time period.

[0029] Optionally, the determining of the speed distribution and acceleration distribution within the future preset time period according to the energy consumption penalty factor, safety penalty factor, traffic efficiency penalty factor and comfort penalty factor corresponding to all possible driving plans within the future preset time period includes:

[0030] Calculate the sum of energy consumption penalty factors, safety penalty factors, traffic efficiency penalty factors, and comfort penalty factors corresponding to all possible driving plans in the future preset time period, and obtain the total amount of penalty factors corresponding to all possible driving plans in the future preset time period;

[0031] The speed distribution and acceleration distribution in the driving plan corresponding to the minimum value of the total amount of penalty factors within a preset time period in the future are selected as the final speed distribution and acceleration distribution.

[0032] A second aspect of the present application provides a transient energy-saving control device for an autonomous driving vehicle, comprising:

[0033] A construction unit, used to construct a transient energy consumption model of the autonomous driving vehicle through historical driving data and historical energy consumption data of the autonomous driving vehicle;

[0034] A first calculation unit is used to calculate the optimal energy consumption value of the future preset time period based on the transient energy consumption model, taking the driving distance and driving time as boundary conditions and the minimum total instantaneous energy consumption value of the future preset time period as the objective function;

[0035] A second calculation unit is used to calculate the energy consumption values ​​corresponding to all possible driving plans within the future preset time period through the transient energy consumption model, and calculate the energy consumption penalty factors corresponding to all possible driving plans within the future preset time period according to the deviations between each energy consumption value within the future preset time period and the optimal energy consumption value, wherein all possible driving plans within the future preset time period include speed distribution and acceleration distribution within the future preset time period;

[0036] The decision unit is used to decide the speed distribution and acceleration distribution within a future preset time period based on the energy consumption penalty factors corresponding to all possible driving plans within the future preset time period.

[0037] A third aspect of the present application provides a transient energy-saving control device for an autonomous driving vehicle, the device comprising a processor and a memory;

[0038] The memory is used to store program code and transmit the program code to the processor;

[0039] The processor is used to execute the transient energy-saving control method for an autonomous driving vehicle as described in any one of the first aspects according to the instructions in the program code.

[0040] In a fourth aspect, the present application provides a computer-readable storage medium, which is used to store program code. When the program code is executed by a processor, it implements the transient energy-saving control method for an autonomous driving vehicle described in any one of the first aspects.

[0041] It can be seen from the above technical solutions that this application has the following advantages:

[0042] The present application provides a method for transient energy-saving control of an autonomous driving vehicle, including: constructing a transient energy consumption model of the autonomous driving vehicle through historical driving data and historical energy consumption data of the autonomous driving vehicle; taking driving distance and driving time as boundary conditions, and taking the minimum total instantaneous energy consumption value of a future preset time period as the objective function, calculating the optimal energy consumption value of the future preset time period based on the transient energy consumption model; calculating the energy consumption values ​​corresponding to all possible driving plans within the future preset time period through the transient energy consumption model, and calculating the energy consumption penalty factors corresponding to all possible driving plans within the future preset time period according to the deviations between each energy consumption value within the future preset time period and the optimal energy consumption value, wherein all possible driving plans within the future preset time period include the speed distribution and acceleration distribution within the future preset time period; and deciding the speed distribution and acceleration distribution within the future preset time period based on the energy consumption penalty factors corresponding to all possible driving plans within the future preset time period.

[0043] In the present application, a transient energy consumption model of an autonomous driving vehicle is constructed through the historical driving data and historical energy consumption data of the autonomous driving vehicle, with driving distance and driving time as boundary conditions and the minimum total instantaneous energy consumption in a future preset time period as the objective function. The optimal energy consumption value for the future preset time period is calculated based on the transient energy consumption model, and the energy consumption penalty factor corresponding to each driving plan is obtained by calculating the deviation between the energy consumption values ​​corresponding to all possible driving plans in the future preset time period planned by the autonomous driving system at the current moment and the optimal energy consumption value. The energy consumption penalty factor participates in the final decision of the autonomous driving system, thereby taking energy consumption into consideration to improve the energy efficiency and endurance of the autonomous driving vehicle, thereby improving the technical problem that the existing autonomous driving system fails to fully consider the energy consumption problem and affects the energy efficiency and endurance of the autonomous driving vehicle. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0045] Figure 1 A schematic flow chart of a method for transient energy saving control of an autonomous driving vehicle provided in an embodiment of the present application;

[0046] Figure 2 Another schematic diagram of a flow chart of a transient energy-saving control method for an autonomous driving vehicle provided in an embodiment of the present application;

[0047] Figure 3 A structural schematic diagram of a transient energy-saving control device for an autonomous driving vehicle provided in an embodiment of the present application. DETAILED DESCRIPTION

[0048] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0049] For easier understanding, see Figure 1 , the embodiment of the present application provides a transient energy-saving control method for an autonomous driving vehicle, comprising:

[0050] Step 101: construct a transient energy consumption model of the autonomous driving vehicle based on the historical driving data and historical energy consumption data of the autonomous driving vehicle.

[0051] In order to incorporate the impact of energy consumption into the final decision of the autonomous driving system, the embodiment of the present application needs to obtain the optimal energy consumption planning and decision based on the transient energy consumption model of the autonomous driving vehicle. The transient energy consumption model of the autonomous driving vehicle can be obtained by combining the hardware characteristics and operating condition characteristics of the autonomous driving vehicle and taking the autonomous driving vehicle operation big data as a benchmark. Specifically, the speed, acceleration and instantaneous energy consumption value of the autonomous driving vehicle at each historical moment can be obtained through the historical driving data and historical energy consumption data of the autonomous driving vehicle; the convolutional neural network is trained with the speed and acceleration at each historical moment as input data and the instantaneous energy consumption value at each historical moment as the training target to obtain the transient energy consumption model of the autonomous driving vehicle. By fitting the historical driving data and historical energy consumption data of the autonomous driving vehicle through the convolutional neural network, a transient energy consumption model based on time series can be obtained, and the corresponding instantaneous energy consumption value can be obtained by inputting the speed and acceleration into the transient energy consumption model.

[0052] High-level autonomous vehicles are equipped with many sensors that traditional vehicles do not have (such as radars, temperature sensors, etc.). They can collect the power consumption (air conditioning, headlights, cooling fans, etc.), power output (wheel-end output power), heat dissipation loss (host, motor heat dissipation) and low-voltage system consumption (vehicle standby, cloud control system, etc.) of the autonomous driving vehicle at each historical moment through various sensors of the motor, brake, and steering modules, thermal management sensors of the autonomous driving system, and various sensors of the power-consuming accessory controller, so as to obtain the historical energy consumption data of the autonomous driving vehicle; the total output energy of the autonomous driving vehicle at each historical moment is calculated based on the power consumption, power output, heat dissipation loss and low-voltage system consumption of the autonomous driving vehicle at each historical moment, so as to obtain the instantaneous energy consumption value of the autonomous driving vehicle at each historical moment.

[0053] It should be noted that historical driving data and historical energy consumption data of the same type of autonomous driving vehicles under different operating conditions can be obtained to construct transient energy consumption models of the same type of autonomous driving vehicles under different operating conditions; historical driving data and historical energy consumption data of different types of autonomous driving vehicles under different operating conditions can also be obtained to construct transient energy consumption models of various types of autonomous driving vehicles under various operating conditions.

[0054] Step 102: Taking the driving distance and driving time as boundary conditions and minimizing the total instantaneous energy consumption in the future preset time period as the objective function, the optimal energy consumption value in the future preset time period is calculated based on the transient energy consumption model.

[0055] Taking the driving distance and driving time as boundary conditions, taking the minimum total instantaneous energy consumption in the future preset time period as the objective function, the optimal speed distribution and the optimal acceleration distribution in the future preset time period are calculated based on the transient energy consumption model; the optimal energy consumption value of the future preset time period is calculated by the optimal speed distribution and the optimal acceleration distribution in the future preset time period. The automatic driving system in the embodiment of the present application will plan the driving path of the future preset time period at each moment, such as planning the driving path for the next 8 seconds. At this time, the driving time can be set to 8 seconds, and the driving distance can be determined according to the maximum speed limit, minimum speed limit and driving time of the current road, thereby determining the boundary conditions. Taking the minimum total instantaneous energy consumption in the future preset time period as the objective function, the optimal speed distribution and the optimal acceleration distribution in the future preset time period can be solved through the transient energy consumption model. The optimal speed and the optimal acceleration at each moment in the future preset time period are input into the transient energy consumption model to obtain the optimal instantaneous energy consumption value at each moment in the future preset time period. Then, the optimal instantaneous energy consumption value at each moment in the future preset time period is summed up to obtain the optimal energy consumption value of the future preset time period.

[0056] In the embodiment of the present application, the autonomous driving system discretizes the driving path into multiple path points and performs driving planning and control between the path points, takes the driving distance and driving time as boundary conditions, takes the optimal energy consumption driving planning as the objective function, and solves the optimal speed and acceleration between the path points based on the transient energy consumption model, and then calculates the optimal energy consumption value. It is understandable that the corresponding transient energy consumption model can be selected according to the vehicle type and current working conditions of the autonomous driving vehicle.

[0057] Step 103, calculate the energy consumption values ​​corresponding to all possible driving plans within the future preset time period through the transient energy consumption model, and calculate the energy consumption penalty factors corresponding to all possible driving plans within the future preset time period according to the deviations between the energy consumption values ​​within the future preset time period and the optimal energy consumption value. All possible driving plans within the future preset time period include the speed distribution and acceleration distribution within the future preset time period.

[0058] When planning, the automatic driving system will calculate all possible driving plans within the future preset time period based on the current traffic environment, map information, etc., and will calculate the distance that each driving plan should travel (i.e., the expected driving distance), the speed distribution and acceleration distribution to be adopted, and input the speed and acceleration of each driving plan at each moment in the future preset time period into the transient energy consumption model, so as to obtain the instantaneous energy consumption value of each driving plan at each moment in the future preset time period. By summing the instantaneous energy consumption values ​​of each driving plan at each moment in the future preset time period, the energy consumption value of each driving plan in the future preset time period can be obtained.

[0059] The energy consumption penalty factors corresponding to all possible driving plans in the future preset time period are calculated according to the deviations between the energy consumption values ​​in the future preset time period and the optimal energy consumption value. The greater the deviation between the energy consumption values ​​of each driving plan in the future preset time period and the optimal energy consumption value, the greater the energy consumption penalty factors corresponding to each driving plan.

[0060] Step 104: Determine the speed distribution and acceleration distribution within the future preset time period based on the energy consumption penalty factors corresponding to all possible driving plans within the future preset time period.

[0061] After calculating the energy consumption penalty factors corresponding to all possible driving plans within a preset time period in the future, the energy consumption penalty factors are introduced when making the final decision. Based on the energy consumption penalty factors, the final driving plan is selected from all possible driving plans within the preset time period in the future, and the autonomous driving vehicle is controlled to drive according to the driving plan selected by the final decision, so that the impact of energy consumption is considered in the final decision.

[0062] In an embodiment of the present application, a transient energy consumption model of the autonomous driving vehicle is constructed using the historical driving data and historical energy consumption data of the autonomous driving vehicle, with driving distance and driving time as boundary conditions and minimizing the total instantaneous energy consumption in a future preset time period as the objective function. The optimal energy consumption value for the future preset time period is calculated based on the transient energy consumption model, and the energy consumption penalty factor corresponding to each driving plan is obtained by calculating the deviation between the energy consumption values ​​corresponding to all possible driving plans in the future preset time period planned by the autonomous driving system at the current moment and the optimal energy consumption value. The energy consumption penalty factor participates in the final decision of the autonomous driving system, thereby taking energy consumption into consideration to improve the energy efficiency and endurance of the autonomous driving vehicle, thereby improving the technical problem that the existing autonomous driving system fails to fully consider energy consumption issues and affects the energy efficiency and endurance of the autonomous driving vehicle.

[0063] The above is an embodiment of a transient energy-saving control method for an autonomous driving vehicle provided by the present application. The following is another embodiment of a transient energy-saving control method for an autonomous driving vehicle provided by the present application.

[0064] Please refer to Figure 2 , an embodiment of the present application provides a transient energy-saving control method for an autonomous driving vehicle, comprising:

[0065] Step 201: construct a transient energy consumption model of the autonomous driving vehicle using the historical driving data and historical energy consumption data of the autonomous driving vehicle.

[0066] Step 202: Taking the driving distance and driving time as boundary conditions and minimizing the total instantaneous energy consumption in the future preset time period as the objective function, the optimal energy consumption value in the future preset time period is calculated based on the transient energy consumption model.

[0067] Step 203, calculate the energy consumption values ​​corresponding to all possible driving plans within the future preset time period through the transient energy consumption model, and calculate the energy consumption penalty factors corresponding to all possible driving plans within the future preset time period according to the deviations between each energy consumption value within the future preset time period and the optimal energy consumption value. All possible driving plans within the future preset time period include the speed distribution and acceleration distribution within the future preset time period.

[0068] The specific contents of steps 201 to 203 in the embodiment of the present application are consistent with the specific contents of steps 101 to 103 in the aforementioned embodiment, and will not be repeated here.

[0069] Step 204: Calculate the safety penalty factor, traffic efficiency penalty factor, and comfort penalty factor corresponding to all possible driving plans within a preset time period in the future.

[0070] In the embodiment of the present application, in order to take into account safety, traffic efficiency and comfort while considering energy consumption, the safety penalty factor, traffic efficiency penalty factor and comfort penalty factor corresponding to all possible driving plans in the future preset time period are further calculated.

[0071] In an embodiment of the present application, the safety penalty factor corresponding to all possible driving plans in the future preset time period can be calculated based on the degree of intersection between the expected driving trajectory corresponding to all possible driving plans in the future preset time period and the obstacle prediction trajectory in the future preset time period. When calculating each possible driving plan, the automatic driving system will also predict the trajectory of the obstacles around the automatic driving vehicle in the future preset time period, and obtain the obstacle prediction trajectory in the future preset time period. The degree of intersection between the expected driving trajectory and the obstacle prediction trajectory corresponding to each driving plan in the future preset time period can be calculated to obtain the safety penalty factor corresponding to each frame of the driving plan in the future preset time period. Specifically, the degree of intersection can be obtained by calculating the ratio of the overlapping length of the two trajectories to the length of the expected driving trajectory. Of course, other calculation methods can also be used, which are not specifically limited here. The greater the degree of intersection, the greater the corresponding safety penalty factor. By selecting a driving plan with a small safety penalty factor, collisions with obstacles can be avoided.

[0072] The traffic efficiency penalty factors corresponding to all possible driving plans in the future preset time period are calculated based on the estimated driving distances corresponding to all possible driving plans in the future preset time period. The estimated driving distance of each driving plan in the future preset time period can be calculated based on all possible driving plans in the future preset time period. The longer the estimated driving distance, the higher the traffic efficiency. For example, plan a follows the slow-moving vehicle in front, and the travel distance is small in the same time, while plan b bypasses and overtakes, and the travel distance is long in the same time, that is, the traffic efficiency of plan b is higher than that of plan a. The inverse of the estimated driving distance of each driving plan in the future preset time period can be calculated as the traffic efficiency penalty factor corresponding to each driving plan.

[0073] The comfort penalty factors corresponding to all possible driving plans in the future preset time period can be calculated according to the acceleration distribution corresponding to all possible driving plans in the future preset time period. The comfort penalty factor corresponding to each driving plan can be calculated according to the acceleration corresponding to each driving plan or the inverse of the acceleration. The greater the acceleration, the greater the corresponding comfort penalty factor.

[0074] Step 205: Determine the speed distribution and acceleration distribution within the future preset time period according to the energy consumption penalty factor, safety penalty factor, traffic efficiency penalty factor and comfort penalty factor corresponding to all possible driving plans within the future preset time period.

[0075] The sum of the energy consumption penalty factor, safety penalty factor, traffic efficiency penalty factor and comfort penalty factor corresponding to all possible driving plans in the future preset time period is calculated to obtain the total amount of penalty factors corresponding to all possible driving plans in the future preset time period; the speed distribution and acceleration distribution in the driving plan corresponding to the minimum total amount of penalty factors in the future preset time period are selected as the final speed distribution and acceleration distribution. Different weights can also be set for the energy consumption penalty factor, safety penalty factor, traffic efficiency penalty factor and comfort penalty factor, and the total amount of penalty factors can be obtained by weighted summing the energy consumption penalty factor, safety penalty factor, traffic efficiency penalty factor and comfort penalty factor.

[0076] In an embodiment of the present application, the speed distribution and acceleration distribution within a future preset time period are determined based on the energy consumption penalty factor, safety penalty factor, traffic efficiency penalty factor and comfort penalty factor corresponding to all possible driving plans within the future preset time period, so that the automatic driving system decides the optimal energy consumption plan under the premise of satisfying comfort, safety and communication efficiency.

[0077] The above is another embodiment of a transient energy-saving control method for an autonomous driving vehicle provided in an embodiment of the present application. The following is an embodiment of a transient energy-saving control device for an autonomous driving vehicle provided in the present application.

[0078] Please refer to Figure 3 , an embodiment of the present application provides a transient energy-saving control device for an autonomous driving vehicle, comprising:

[0079] A construction unit, used to construct a transient energy consumption model of the autonomous driving vehicle through historical driving data and historical energy consumption data of the autonomous driving vehicle;

[0080] The first calculation unit is used to calculate the optimal energy consumption value of the future preset time period based on the transient energy consumption model, taking the driving distance and driving time as boundary conditions and the minimum total instantaneous energy consumption value of the future preset time period as the objective function;

[0081] A second calculation unit is used to calculate the energy consumption values ​​corresponding to all possible driving plans within the future preset time period through a transient energy consumption model, and calculate the energy consumption penalty factors corresponding to all possible driving plans within the future preset time period according to the deviations between each energy consumption value within the future preset time period and the optimal energy consumption value, wherein all possible driving plans within the future preset time period include speed distribution and acceleration distribution within the future preset time period;

[0082] The decision unit is used to decide the speed distribution and acceleration distribution within a future preset time period based on the energy consumption penalty factors corresponding to all possible driving plans within the future preset time period.

[0083] As a further improvement, the building block is specifically used for:

[0084] The speed, acceleration and instantaneous energy consumption value of the autonomous driving vehicle at each historical moment are obtained through the historical driving data and historical energy consumption data of the autonomous driving vehicle;

[0085] The convolutional neural network is trained with the speed and acceleration at each historical moment as input data and the instantaneous energy consumption value at each historical moment as the training target to obtain the transient energy consumption model of the autonomous driving vehicle.

[0086] The process of obtaining the instantaneous energy consumption value is as follows:

[0087] The historical energy consumption data of the autonomous driving vehicle is obtained through the sensors of the autonomous driving vehicle, and the historical energy consumption data includes the power consumption, power output, heat dissipation loss and low-voltage system consumption at each historical moment;

[0088] The total output energy of the autonomous driving vehicle at each historical moment is calculated according to the power consumption, power output, heat dissipation loss and low-voltage system consumption of the autonomous driving vehicle at each historical moment, and the instantaneous energy consumption value of the autonomous driving vehicle at each historical moment is obtained.

[0089] As a further improvement, the first computing unit is specifically used for:

[0090] Taking the driving distance and driving time as boundary conditions and the minimum total instantaneous energy consumption in the future preset time period as the objective function, the optimal speed distribution and the optimal acceleration distribution in the future preset time period are calculated based on the transient energy consumption model;

[0091] The optimal energy consumption value of the future preset time period is calculated through the optimal speed distribution and the optimal acceleration distribution in the future preset time period.

[0092] In an embodiment of the present application, a transient energy consumption model of the autonomous driving vehicle is constructed using the historical driving data and historical energy consumption data of the autonomous driving vehicle, with driving distance and driving time as boundary conditions and minimizing the total instantaneous energy consumption in a future preset time period as the objective function. The optimal energy consumption value for the future preset time period is calculated based on the transient energy consumption model, and the energy consumption penalty factor corresponding to each driving plan is obtained by calculating the deviation between the energy consumption values ​​corresponding to all possible driving plans in the future preset time period planned by the autonomous driving system at the current moment and the optimal energy consumption value. The energy consumption penalty factor participates in the final decision of the autonomous driving system, thereby taking energy consumption into consideration to improve the energy efficiency and endurance of the autonomous driving vehicle, thereby improving the technical problem that the existing autonomous driving system fails to fully consider energy consumption issues and affects the energy efficiency and endurance of the autonomous driving vehicle.

[0093] In one embodiment, the apparatus further comprises:

[0094] The third calculation unit is used to calculate the safety penalty factor, traffic efficiency penalty factor and comfort penalty factor corresponding to all possible driving plans in a future preset time period;

[0095] The decision-making unit is specifically used to decide the speed distribution and acceleration distribution within a future preset time period according to the energy consumption penalty factor, safety penalty factor, traffic efficiency penalty factor and comfort penalty factor corresponding to all possible driving plans within the future preset time period.

[0096] As a further improvement, the third computing unit is specifically used for:

[0097] Calculate the safety penalty factors corresponding to all possible driving plans in the future preset time period according to the intersection degree of the predicted driving trajectories corresponding to all possible driving plans in the future preset time period and the obstacle prediction trajectories in the future preset time period;

[0098] Calculate the comfort penalty factors corresponding to all possible driving plans within the future preset time period according to the acceleration distribution corresponding to all possible driving plans within the future preset time period;

[0099] Calculate the traffic efficiency penalty factors corresponding to all possible driving plans within the future preset time period according to the estimated driving distances corresponding to all possible driving plans within the future preset time period;

[0100] The decision-making unit is specifically used to calculate the sum of energy consumption penalty factors, safety penalty factors, traffic efficiency penalty factors and comfort penalty factors corresponding to all possible driving plans in a future preset time period, and obtain the total amount of penalty factors corresponding to all possible driving plans in the future preset time period; select the speed distribution and acceleration distribution in the driving plan corresponding to the minimum value of the total amount of penalty factors in the future preset time period as the final speed distribution and acceleration distribution.

[0101] In an embodiment of the present application, the speed distribution and acceleration distribution within a future preset time period are determined based on the energy consumption penalty factor, safety penalty factor, traffic efficiency penalty factor and comfort penalty factor corresponding to all possible driving plans within the future preset time period, so that the automatic driving system decides the optimal energy consumption plan under the premise of satisfying comfort, safety and communication efficiency.

[0102] The embodiment of the present application also provides a transient energy-saving control device for an autonomous driving vehicle, the device comprising a processor and a memory;

[0103] The memory is used to store the program code and transmit the program code to the processor;

[0104] The processor is used to execute the transient energy-saving control method for the autonomous driving vehicle in the aforementioned method embodiment according to the instructions in the program code.

[0105] An embodiment of the present application also provides a computer-readable storage medium, which is used to store program code. When the program code is executed by a processor, the transient energy-saving control method for the autonomous driving vehicle in the aforementioned method embodiment is implemented.

[0106] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described devices and units can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0107] The terms "first", "second", "third", "fourth", etc. (if any) in the specification of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein, for example. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0108] It should be understood that in the present application, "at least one (item)" means one or more, and "plurality" means two or more. "And / or" is used to describe the association relationship of associated objects, indicating that three relationships may exist. For example, "A and / or B" can mean: only A exists, only B exists, and A and B exist at the same time, where A and B can be singular or plural. The character " / " generally indicates that the objects associated before and after are in an "or" relationship. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b or c can mean: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, c can be single or multiple.

[0109] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0110] 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 on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0111] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0112] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for executing all or part of the steps of the method described in each embodiment of the present application through a computer device (which can be a personal computer, a server, or a network device, etc.). The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (full name in English: Read-Only Memory, English abbreviation: ROM), random access memory (full name in English: Random Access Memory, English abbreviation: RAM), disk or optical disk and other media that can store program codes.

[0113] As described above, the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A transient energy-saving control method for an autonomous driving vehicle, characterized in that: include: Construct a transient energy consumption model of the autonomous driving vehicle based on the historical driving data and historical energy consumption data of the autonomous driving vehicle; Taking the driving distance and driving time as boundary conditions and minimizing the total instantaneous energy consumption in the future preset time period as the objective function, the optimal energy consumption value in the future preset time period is calculated based on the transient energy consumption model; The energy consumption values ​​corresponding to all possible driving plans within the future preset time period are calculated by the transient energy consumption model, and the energy consumption penalty factors corresponding to all possible driving plans within the future preset time period are calculated according to the deviations between the energy consumption values ​​within the future preset time period and the optimal energy consumption value, wherein all possible driving plans within the future preset time period include the speed distribution and the acceleration distribution within the future preset time period; The speed distribution and acceleration distribution within the future preset time period are determined based on the energy consumption penalty factors corresponding to all possible driving plans within the future preset time period.

2. The method for transient energy saving control of an automatic driving vehicle according to claim 1, characterized in that: The method of constructing a transient energy consumption model of the autonomous driving vehicle using historical driving data and historical energy consumption data of the autonomous driving vehicle includes: The speed, acceleration and instantaneous energy consumption value of the autonomous driving vehicle at each historical moment are obtained through the historical driving data and historical energy consumption data of the autonomous driving vehicle; The convolutional neural network is trained with the speed and acceleration at each historical moment as input data and the instantaneous energy consumption value at each historical moment as the training target to obtain the transient energy consumption model of the autonomous driving vehicle.

3. The method for controlling transient energy saving of an automatic driving vehicle according to claim 2, characterized in that: The process of obtaining the instantaneous energy consumption value is as follows: Acquire historical energy consumption data of the autonomous driving vehicle through sensors of the autonomous driving vehicle, wherein the historical energy consumption data includes power consumption, power output, heat dissipation loss, and low-voltage system consumption at each historical moment; The total output energy of the autonomous driving vehicle at each historical moment is calculated according to the power consumption, power output, heat dissipation loss and low-voltage system consumption of the autonomous driving vehicle at each historical moment, and the instantaneous energy consumption value of the autonomous driving vehicle at each historical moment is obtained.

4. The method for controlling transient energy saving of an automatic driving vehicle according to claim 1, characterized in that: The method of taking the driving distance and driving time as boundary conditions, taking the minimum total instantaneous energy consumption value in the future preset time period as the objective function, and calculating the optimal energy consumption value in the future preset time period based on the transient energy consumption model includes: Taking the driving distance and driving time as boundary conditions and minimizing the total instantaneous energy consumption in the future preset time period as the objective function, the optimal speed distribution and the optimal acceleration distribution in the future preset time period are calculated based on the transient energy consumption model; The optimal energy consumption value of the future preset time period is calculated through the optimal speed distribution and the optimal acceleration distribution in the future preset time period.

5. The method for controlling transient energy saving of an automatic driving vehicle according to claim 1, characterized in that: The method further comprises: Calculate the safety penalty factor, traffic efficiency penalty factor and comfort penalty factor corresponding to all possible driving plans within the future preset time period; The method of determining the speed distribution and acceleration distribution within a future preset time period based on the energy consumption penalty factors corresponding to all possible driving plans within the future preset time period includes: The speed distribution and acceleration distribution within the future preset time period are determined according to the energy consumption penalty factor, safety penalty factor, traffic efficiency penalty factor and comfort penalty factor corresponding to all possible driving plans within the future preset time period.

6. The method for controlling transient energy saving of an automatic driving vehicle according to claim 5, characterized in that: Calculate the safety penalty factors corresponding to all possible driving plans within the preset time period in the future, including: The safety penalty factors corresponding to all possible driving plans in the future preset time period are calculated according to the intersection degree of the expected driving trajectories corresponding to all possible driving plans in the future preset time period and the obstacle prediction trajectories in the future preset time period.

7. The method for controlling transient energy saving of an automatic driving vehicle according to claim 5, characterized in that: Calculate the comfort penalty factors corresponding to all possible driving plans within the preset time period in the future, including: The comfort penalty factors corresponding to all possible driving plans within the future preset time period are calculated according to the acceleration distribution corresponding to all possible driving plans within the future preset time period.

8. The method for controlling transient energy saving of an automatic driving vehicle according to claim 5, characterized in that: Calculate the traffic efficiency penalty factors corresponding to all possible driving plans in the future preset time period, including: The traffic efficiency penalty factors corresponding to all possible driving plans within the future preset time period are calculated according to the estimated driving distances corresponding to all possible driving plans within the future preset time period.

9. The method for controlling transient energy saving of an automatic driving vehicle according to claim 5, characterized in that: The method of determining the speed distribution and acceleration distribution in the future preset time period according to the energy consumption penalty factor, safety penalty factor, traffic efficiency penalty factor and comfort penalty factor corresponding to all possible driving plans in the future preset time period includes: Calculate the sum of energy consumption penalty factors, safety penalty factors, traffic efficiency penalty factors, and comfort penalty factors corresponding to all possible driving plans in the future preset time period, and obtain the total amount of penalty factors corresponding to all possible driving plans in the future preset time period; The speed distribution and acceleration distribution in the driving plan corresponding to the minimum value of the total amount of penalty factors within a preset time period in the future are selected as the final speed distribution and acceleration distribution.

10. A transient energy-saving control device for an automatic driving vehicle, characterized in that: include: A construction unit, used to construct a transient energy consumption model of the autonomous driving vehicle through historical driving data and historical energy consumption data of the autonomous driving vehicle; A first calculation unit is used to calculate the optimal energy consumption value of the future preset time period based on the transient energy consumption model, taking the driving distance and driving time as boundary conditions and the minimum total instantaneous energy consumption value of the future preset time period as the objective function; A second calculation unit is used to calculate the energy consumption values ​​corresponding to all possible driving plans within the future preset time period through the transient energy consumption model, and calculate the energy consumption penalty factors corresponding to all possible driving plans within the future preset time period according to the deviations between each energy consumption value within the future preset time period and the optimal energy consumption value, wherein all possible driving plans within the future preset time period include speed distribution and acceleration distribution within the future preset time period; The decision unit is used to decide the speed distribution and acceleration distribution within a future preset time period based on the energy consumption penalty factors corresponding to all possible driving plans within the future preset time period.

11. A transient energy-saving control device for an autonomous driving vehicle, characterized in that: The device comprises a processor and a memory; The memory is used to store program code and transmit the program code to the processor; The processor is used to execute the transient energy-saving control method for an autonomous driving vehicle according to any one of claims 1-9 according to the instructions in the program code.

12. A computer-readable storage medium, characterized in that: The computer-readable storage medium is used to store program code, and when the program code is executed by a processor, it implements the transient energy-saving control method for an autonomous driving vehicle as described in any one of claims 1-9.

Images