A vehicle control method, apparatus, storage medium, and electronic device

Abstract

This invention provides a vehicle control method, device, storage medium, and electronic device. The method includes: constructing a multi-objective optimization model based on a game theory framework; inputting acquired vehicle state information, external environment information, and set model parameters into the multi-objective optimization model for data processing to generate updated model parameters; calculating the updated model parameters to generate a vehicle control strategy; and generating vehicle control commands based on the current vehicle state information and the vehicle control strategy, thereby controlling the vehicle according to the vehicle control commands. The technical solution provided by this invention achieves an effective trade-off between multiple objectives in the vehicle control system based on the multi-objective optimization model, improving the overall performance of the vehicle in actual driving, and achieving an optimal combination of energy, time, and cost while ensuring safety.

Description

Technical Field

[0001] This invention relates to the field of vehicle technology, and more particularly to a vehicle control method, device, storage medium, and electronic device. Background Technology

[0002] Current vehicle control systems primarily focus on improving the performance of a single objective, such as driving safety, time efficiency, or energy efficiency. However, failing to limit oneself to optimizing a single aspect can easily lead to conflicts between various performance optimization goals.

[0003] There is no unified framework in related technologies to simultaneously consider and resolve multiple potentially conflicting objectives. Existing vehicle control systems cannot adapt to constantly changing external environmental conditions and internal vehicle states, thus failing to achieve an optimal combination of energy, time, and cost while ensuring safety. Summary of the Invention

[0004] In view of this, embodiments of the present invention provide a vehicle control method, device, storage medium, and electronic device to achieve an effective trade-off between multiple objectives in the vehicle control system, improve the overall performance of the vehicle in actual driving, and achieve the optimal combination of energy, time, and cost while ensuring safety.

[0005] On one hand, embodiments of the present invention provide a vehicle control method, including:

[0006] A multi-objective optimization model is constructed based on the game theory framework. The multi-objective optimization model includes: a total objective function, a policy space, and a Nash equilibrium condition. The total objective function is used to represent multiple optimization objectives of the driving vehicle. The policy space is used to represent the set of actions of the vehicle. The Nash equilibrium condition is used to represent the vehicle control method that satisfies the total objective function, the policy space, and the Nash equilibrium.

[0007] The acquired vehicle status information, external environment information, and set model parameters are input into the multi-objective optimization model for data processing to generate updated model parameters.

[0008] The updated model parameters are used to calculate and generate a vehicle control strategy;

[0009] The vehicle control command is generated based on the current vehicle status information and the vehicle control strategy, and the vehicle is controlled according to the vehicle control command.

[0010] Optionally, the step of inputting the acquired vehicle state information, external environment information, and set model parameters into the multi-objective optimization model for data processing to generate updated model parameters includes:

[0011] The vehicle status information and the external environment information are preprocessed to generate first preprocessed data and second preprocessed data.

[0012] Updated model parameters are generated based on the first preprocessed data, the second preprocessed data, and the model parameters.

[0013] Optionally, generating updated model parameters based on the first preprocessed data, the second preprocessed data, and the model parameters includes:

[0014] The updated strategy space is generated by updating the strategy space based on the vehicle speed and vehicle acceleration in the first preprocessed data.

[0015] An environmental index is generated based on the second preprocessed data;

[0016] The adjusted revenue function is generated by adjusting the revenue function based on the environmental index.

[0017] The updated strategy space, the adjusted payoff function, and the model parameters are integrated into the multi-objective optimization model to generate updated model parameters.

[0018] Optionally, the step of calculating and generating a vehicle control strategy from the updated model parameters includes:

[0019] Based on the Nash equilibrium solution algorithm, the updated model parameters are calculated to generate a vehicle control strategy.

[0020] Optionally, the step of calculating and generating a vehicle control strategy based on the updated model parameters using the Nash equilibrium solution algorithm includes:

[0021] The updated model parameters are then input into the multi-objective optimization model;

[0022] Create the initial population;

[0023] The initial population is iterated using a genetic algorithm, and a vehicle control strategy is generated when the genetic algorithm converges.

[0024] Optionally, the step of iterating the initial population using a genetic algorithm, and generating a vehicle control strategy when the genetic algorithm converges, includes:

[0025] A new population is generated by iterating through the initial population using a genetic algorithm.

[0026] The fitness function is used to evaluate the benefit of each individual in the new population, and a benefit value is generated.

[0027] When the genetic algorithm converges, the strategy corresponding to the individual with the highest return value among multiple individuals is taken as the vehicle control strategy.

[0028] Optionally, the step of generating a vehicle control command based on the current vehicle status information and the vehicle control strategy, and then controlling the vehicle according to the vehicle control command, includes:

[0029] Based on the current vehicle status information and the vehicle control strategy, a vehicle control command is generated and sent to the accelerator pedal or electric motor so that the accelerator pedal or electric motor can control the vehicle according to the vehicle control command.

[0030] Optionally, the construction of the multi-objective optimization model based on the game theory framework includes:

[0031] Define objective functions, including a safety objective function, a time efficiency objective function, an energy consumption objective function, and a cost objective function;

[0032] The objective function is weighted to establish the overall objective function;

[0033] Construct the policy space, which includes the speed range of vehicle driving;

[0034] The Nash equilibrium is obtained by solving the Nash equilibrium condition based on the total objective function and the policy space.

[0035] The multi-objective optimization model is constructed based on the overall objective function, the policy space, and the Nash equilibrium condition.

[0036] On the other hand, embodiments of the present invention provide a vehicle control device, including:

[0037] A construction module is used to construct a multi-objective optimization model based on a game theory framework. The multi-objective optimization model includes: a total objective function, a policy space, and a Nash equilibrium condition. The total objective function is used to characterize multiple optimization objectives of the driving vehicle. The policy space is used to characterize the set of actions of the vehicle. The Nash equilibrium condition is used to characterize the vehicle control method that satisfies the total objective function, the policy space, and the Nash equilibrium.

[0038] The data processing module is used to input the acquired vehicle status information, external environment information, and set model parameters into the multi-objective optimization model for data processing, and generate updated model parameters.

[0039] The calculation module is used to calculate the updated model parameters to generate a vehicle control strategy;

[0040] The control module is used to generate vehicle control commands based on the current vehicle status information and the vehicle control strategy, so as to control the vehicle according to the vehicle control commands.

[0041] On the other hand, embodiments of the present invention provide a storage medium, including: the storage medium includes a stored program, wherein, when the program is executed, it controls the device where the storage medium is located to execute the above-described vehicle control method.

[0042] On the other hand, embodiments of the present invention provide an electronic device, including a memory and a processor. The memory is used to store information including program instructions, and the processor is used to control the execution of the program instructions. When the program instructions are loaded and executed by the processor, the steps of the above-described vehicle control method are implemented.

[0043] The technical solution of the vehicle control method provided in this invention involves constructing a multi-objective optimization model based on a game theory framework. Acquired vehicle state information, external environment information, and set model parameters are input into the multi-objective optimization model for data processing to generate updated model parameters. The updated model parameters are then used to calculate and generate a vehicle control strategy. Finally, vehicle control commands are generated based on the current vehicle state information and the vehicle control strategy, and the vehicle is controlled according to these commands. This technical solution, based on the multi-objective optimization model, enables the vehicle control system to effectively balance multiple objectives, improving the overall performance of the vehicle in actual driving and achieving an optimal combination of energy, time, and cost while ensuring safety. Attached Figure Description

[0044] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0045] Figure 1 A flowchart of a vehicle control method provided in an embodiment of the present invention;

[0046] Figure 2 A flowchart for generating updated model parameters is provided in one embodiment of the present invention;

[0047] Figure 3 A flowchart illustrating the generation of a vehicle control strategy is provided in one embodiment of the present invention;

[0048] Figure 4 This is a schematic diagram of the structure of a vehicle control device according to an embodiment of the present invention;

[0049] Figure 5 This is a schematic diagram of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0050] To better understand the technical solution of the present invention, the embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0051] It should be understood that the described embodiments are merely some, not all, of the embodiments of the present invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without inventive effort are within the scope of protection of the present invention.

[0052] The terminology used in the embodiments of this invention is for the purpose of describing particular embodiments only and is not intended to limit the invention. The singular forms “a,” “the,” and “the” as used in the embodiments of this invention and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise.

[0053] It should be understood that the term "and / or" used in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. Additionally, the character " / " in this article generally indicates that the preceding and following related objects have an "or" relationship.

[0054] With the increasing maturity of autonomous driving technology and in-vehicle information systems, the expectations for intelligent vehicles are no longer limited to the optimization of a single aspect, but rather to the pursuit of a comprehensive solution that can handle multiple objectives simultaneously and maintain the best balance between them.

[0055] However, vehicle control systems in related technologies have significant limitations when dealing with multiple conflicting objectives. For example, attempting to shorten travel time while simultaneously reducing energy consumption can be directly contradictory; increased speed might reduce travel time but increase energy consumption, while energy-saving modes might extend travel time. Furthermore, safety-oriented vehicle control strategies often sacrifice travel efficiency and maximizing energy utilization. Moreover, they tend to overlook personalized user needs, such as those of users who might be willing to sacrifice some travel time for higher energy efficiency or lower costs.

[0056] Furthermore, traditional vehicle control systems often struggle to respond quickly in complex traffic environments. They may fail to effectively handle variable factors such as emergencies and traffic congestion, resulting in an inability to achieve optimal control under various conditions. Similarly, in emergency avoidance situations, they may be unable to consider objectives other than safety, such as minimizing the impact of an accident on traffic efficiency.

[0057] The root cause of these problems lies in the lack of a unified framework in the relevant technologies to simultaneously consider and resolve multiple potentially conflicting objectives. Due to this lack of a framework, vehicle control systems in these technologies cannot adapt to constantly changing external environmental conditions and internal vehicle states, thus failing to achieve an optimal combination of energy, time, and cost while ensuring safety.

[0058] To address the technical problems in related technologies, this invention provides a vehicle control method that dynamically balances and weighs multiple objectives, including safety, efficiency, cost, and user preferences, using advanced mathematical tools and algorithms. This vehicle control method adapts to various road and traffic conditions, adjusting vehicle behavior in real time to meet diverse driving needs while improving overall driving efficiency and safety.

[0059] Figure 1 A flowchart of a vehicle control method provided in an embodiment of the present invention is shown below. Figure 1 As shown, the method includes:

[0060] Step 102: The electronic device constructs a multi-objective optimization model based on the game theory framework.

[0061] In this embodiment of the invention, the electronic device can be a vehicle control system.

[0062] In this embodiment of the invention, the electronic device can construct a game theory framework and build a multi-objective optimization model based on that framework. The electronic device can also obtain a multi-objective optimization model from a computer device. The computer device can construct a game theory framework and build a multi-objective optimization model based on that framework.

[0063] In this embodiment of the invention, the multi-objective optimization model includes: a total objective function, a policy space, and a Nash equilibrium condition. The total objective function is used to characterize multiple optimization objectives of the driving vehicle, the policy space is used to characterize the set of actions of the vehicle, and the Nash equilibrium condition is used to characterize the vehicle control method that satisfies the total objective function, the policy space, and the Nash equilibrium.

[0064] Specifically, constructing a game theory framework can include:

[0065] Define the participants: Identify the participants in a game, i.e., the decision-making entities in this game. In a vehicle control system, the system itself can be considered as a participant, and other external factors (such as other vehicles, traffic signals) can be assumed to be other participants.

[0066] Define the policy space: Define the set of all possible policies that each participant can adopt. For a vehicle control system, policies can be behaviors such as speed selection, path planning, acceleration, or deceleration.

[0067] Define a payoff function: assign a payoff value to each strategy combination, which reflects how well the strategy combination achieves the objective optimization.

[0068] Introducing the concept of Nash equilibrium: Define an equilibrium state in which no participant can gain a higher payoff by unilaterally changing their strategy.

[0069] Specifically, constructing a multi-objective optimization model based on a game theory framework can include:

[0070] 1. Define the objective function: Based on different objectives (safety, time, energy consumption, cost, etc.), establish corresponding objective functions for the system. For example, objective functions may include safety objective functions, time efficiency objective functions, energy consumption objective functions, and cost objective functions.

[0071] The safety objective function can be: f1(s) = -ks·cr(s), where s represents the system state, cr(s) is a safety-related risk assessment index, ks is a weighting coefficient, and f1(s) is the safety objective function.

[0072] The objective function for time efficiency can be: f2(t) = -kt·t, where t represents the travel time, kt is the time efficiency weighting coefficient, and f2(t) is the objective function for time efficiency.

[0073] The energy consumption objective function can be: f3(e) = ke·e, where e represents energy consumption, ke is the energy consumption weighting coefficient, and f3(e) is the energy consumption objective function.

[0074] The cost objective function can be: f4(c) = -kc·c, where c represents the driving cost, kc is the cost weighting coefficient, and f4(c) is the cost objective function.

[0075] 2. Establish the overall objective function: Specifically, the objective functions are weighted to establish the overall objective function. Combining the objective functions, some may maximize the objective, while others may minimize it. Since they may conflict, weighting is necessary to express the relative importance of the different objectives. An example of an overall objective function is shown below:

[0076] F(x)=w1·f1(s)+w2·f2(t)+w3·f3(e)+w4·f4(c)

[0077] Where x represents the strategy vector, w1, w2, w3, w4 are the weights associated with security, time efficiency, energy consumption, and cost, respectively, f1(s) is the security objective function, f2(t) is the time efficiency objective function, f3(e) is the energy consumption objective function, and f4(c) is the cost objective function.

[0078] 3. Constructing the policy space: The policy space reflects the set of all possible actions a vehicle can take. For example, if speed *v* is considered as a control variable, the policy space includes the speed range the vehicle can drive, i.e., all allowed speed values. Assuming the vehicle's speed range is between *vmin* and *vmax*, the policy space is represented as {v | *vmin* ≤ *v* ≤ *vmax*}.

[0079] 4. Solving for Nash Equilibrium: Specifically, solve for the Nash equilibrium based on the overall objective function and the policy space to obtain the Nash equilibrium conditions. Use an appropriate algorithm to find the set of policies x* that satisfy the Nash equilibrium, in which no single decision entity can gain more benefit by changing its policy.

[0080] Nash equilibrium condition: For all participants i,

[0081]

[0082] Among them, U i S is the payoff function of participant i. i Let x be the strategy space of participant i. -i This represents the strategies of the participants other than i.

[0083] 5. Construct a multi-objective optimization model based on the overall objective function, policy space, and Nash equilibrium conditions.

[0084] Through the above steps, we will construct a complete multi-objective optimization model and be able to solve for the optimal vehicle control method based on Nash equilibrium, thereby achieving an effective balance among multiple objectives.

[0085] Step 104: The electronic device inputs the acquired vehicle status information, external environment information, and set model parameters into the multi-objective optimization model for data processing, and generates updated model parameters.

[0086] In this embodiment of the invention, vehicle status information may include vehicle speed, vehicle acceleration, etc. External environment information may include traffic conditions, weather conditions, etc.

[0087] For example, the model parameters can include a safety weight of 0.4, a time efficiency weight of 0.3, an energy consumption weight of 0.2, and a cost weight of 0.1. Vehicle status information includes the current vehicle speed of 50 km / h and the current vehicle acceleration of 0 m / s². 2 External environmental information includes traffic conditions and weather conditions. The traffic conditions are slightly congested, which can be quantified as a traffic condition index of 0.6. The weather conditions are sunny and have no impact, which can be quantified as a weather index of 0.1.

[0088] In this embodiment of the invention, appropriate sensors, such as speed sensors, acceleration sensors, cameras, Global Positioning System (GPS), and weather sensors, can be selected based on the vehicle status information and external environmental information that need to be monitored. These sensors need to be installed in appropriate locations on the vehicle. For example, speed and acceleration sensors are connected to the wheels and engine, cameras are installed at the front and rear of the vehicle to monitor surrounding traffic conditions, and GPS is used to track the vehicle's position. The outputs of all sensors are integrated into the central processing unit of the vehicle control system via an in-vehicle network to ensure that data can be collected and processed synchronously.

[0089] Figure 2 A flowchart for generating updated model parameters is provided in one embodiment of the present invention, such as... Figure 2 As shown, step 104 includes:

[0090] Step 1042: The electronic device performs data preprocessing on the vehicle status information and external environment information to generate first preprocessed data and second preprocessed data.

[0091] Specifically, the electronic device performs data preprocessing on vehicle status information to generate first preprocessed data, and performs data preprocessing on external environment information to generate second preprocessed data. Data preprocessing involves converting the data collected by sensors into a format suitable for multi-objective optimization models, or normalizing or quantifying external environment information (traffic conditions, weather conditions, etc.).

[0092] Step 1044: The electronic device updates the strategy space based on the vehicle speed and vehicle acceleration in the first preprocessed data, and generates the updated strategy space.

[0093] In this embodiment of the invention, the selectable speed range can be adjusted based on vehicle speed and vehicle acceleration. For example, if congestion is detected, the maximum speed limit can be reduced.

[0094] Step 1046: The electronic device generates an environmental index based on the second preprocessed data.

[0095] In this embodiment of the invention, environmental factors such as traffic conditions and weather conditions can be converted into influencing parameters, such as env_effect = traffic_index * w t +weather_index*w e Where traffic_index is the traffic condition index, w t For time efficiency weighting, weather_index is the weather condition index, w e Energy consumption is the weight, and env_effect is the environmental index.

[0096] Step 1048: The electronic device adjusts the revenue function according to the environmental index to generate the adjusted revenue function.

[0097] In this embodiment of the invention, the benefit function can be adjusted according to the environmental index, and different weights can be adjusted to increase the weights that are sensitive to the current environmental response.

[0098] Step 1050: The electronic device integrates the updated policy space, the adjusted payoff function, and the model parameters into the multi-objective optimization model to generate updated model parameters.

[0099] In this embodiment of the invention, the model parameters updated in real time can be provided to the next game solution process.

[0100] The updated model parameters are calculated using a specific example below.

[0101] Assuming congestion reduces our maximum speed by 20%, the new speed range is: New maximum speed = v currentmax (1-traffic_index*0.2), where v currentmax Let `traffic_index` be the original maximum speed and `traffic_index` be the traffic condition index. For example, if the original maximum speed was 120 km / h, then: New maximum speed = 120 km / h * (1 - 0.6 * 0.2) = 120 km / h * 0.88 = 105.6 km / h. The updated benefit function might increase the weight of time efficiency because congestion increases the cost of travel time. New time efficiency weight = w t +traffic_index(1-w t For example, if the original time efficiency weight is 0.3, then: the new time efficiency weight = 0.3 + 0.6(1-0.3) = 0.3 + 0.42 = 0.72, so the new time efficiency weight in the real-time updated model parameters is 0.72.

[0102] In this embodiment of the invention, the safety weight can remain unchanged, representing a fixed user preference. The time efficiency weight can be adjusted based on real-time traffic conditions. The energy consumption weight may be affected by other external factors and change, but it remains unchanged in this embodiment. The cost weight can also remain unchanged. Since traffic conditions have been taken into account, the maximum value of the selectable speed range is reduced to 105.6 km / h. The traffic condition index ranges from 0 to 1, with higher numbers indicating more congested traffic. The weather condition index also ranges from 0 to 1, with higher numbers indicating a greater impact of weather on driving conditions.

[0103] Step 106: The electronic device calculates the updated model parameters to generate a vehicle control strategy.

[0104] Specifically, the electronic device uses the Nash equilibrium solution algorithm to calculate and generate a vehicle control strategy based on the updated model parameters.

[0105] Figure 3 A flowchart for generating a vehicle control strategy is provided in one embodiment of the present invention, such as... Figure 3 As shown, step 106 includes:

[0106] Step 1062: The electronic device inputs the updated model parameters into the multi-objective optimization model.

[0107] For example, updated model parameters may include a safety weight of 0.4, a time efficiency weight of 0.72, an energy consumption weight of 0.2, and a cost weight of 0.1. Electronic devices can input these updated model parameters into a multi-objective optimization model to load the model parameters.

[0108] Step 1064: Electronic devices create the initial population.

[0109] In this embodiment of the invention, each individual in the initial population represents a possible speed strategy. For example, the initial population may include the first individual at 25 km / h, the second at 45 km / h, the third at 65 km / h, the fourth at 85 km / h, and the fifth at 100 km / h.

[0110] Step 1066: The electronic device iterates through the initial population using a genetic algorithm to generate a new population.

[0111] In this embodiment of the invention, the core of the genetic algorithm is to iteratively evolve the population through selection, crossover, and mutation operations.

[0112] Step 1068: The electronic device evaluates the benefit of each individual in the new population using a fitness function and generates a benefit value.

[0113] For example, in the first generation iteration: the reward of each velocity strategy depends on the weights and the current environmental conditions. Assume this is achieved through the function f(v) = w s *safety_score+w t The *time_efficiency_score… is used to calculate the revenue value, where w s For safety weights, safety_score is the safety score, w t The time efficiency weight is used, and the time_efficiency_score is the time efficiency score.

[0114] The safety score depends on the relationship between speed and accident rate. Generally, the higher the speed, the higher the probability of an accident, but within certain ranges, increasing speed may not significantly increase the probability of an accident. The following data and formula can be used for calculation: When the vehicle speed is below 20 km / h, the accident probability remains relatively stable at a very low level, assumed to be 0.2%. When the vehicle speed is between 20-80 km / h, the accident probability increases linearly with speed, from 0.2% to 1%. When the vehicle speed is above 80 km / h, the accident probability rises sharply to over 2%.

[0115] Based on the above data, we can assume the probability of an accident (P) accident The relationship between () and vehicle speed (v) is as follows:

[0116]

[0117] To convert the accident probability into a safety score, the reciprocal of the accident probability can be used, scaled appropriately for easier calculation: safety_score = (1 / P) accident ) / 1000, where safety_score is the safety score, P accident This represents the probability of an accident.

[0118] The time efficiency score depends on the relationship between vehicle speed and travel time. Generally speaking, the faster the vehicle speed, the shorter the travel time required to complete the journey. However, above a certain speed, the additional time savings will decrease due to road restrictions and traffic regulations.

[0119] Assuming no other traffic congestion, the ideal travel time (T) ideal The actual travel time (T) is inversely proportional to the vehicle speed, while the actual travel time (T) is... actual We also need to consider factors such as traffic signals. We can assume a simple model: the travel distance is fixed at 10km. Ideally, the travel time is determined solely by speed: T ideal =Distance / v, where T ideal The ideal travel time is defined by Distance, where Distance is the distance traveled and v is the vehicle speed. However, in reality, there is a fixed delay time, let's say 3 minutes, representing the waiting time at traffic lights.

[0120] The expression for actual travel time can be: T actual =T ideal +T delay , among which, T ideal For the ideal travel time, T actual T represents the actual travel time. delay For the delay time, for example, T delayIt is 3 minutes (which can represent the waiting time at a traffic light).

[0121] The time efficiency score can be expressed as the ratio of the ideal travel time to the actual travel time; that is, the higher the vehicle speed, the higher the time efficiency score: time_efficiency_score = (T ideal / T actual )*100, where time_efficiency_score is the time efficiency score, T ideal For the ideal travel time, T actual This refers to the actual travel time.

[0122] In this embodiment of the invention, individuals to be crossbred can be selected based on fitness (gain value). Assume that 65 km / h and 85 km / h have the highest gain. The speed values ​​of the selected individuals are combined to generate new offspring. For example, an average value can be taken: (65+85) / 2 = 75 km / h. Small random variations are introduced into the new offspring. For example, 75 km / h might become 78 km / h.

[0123] A new population is formed, which may include some existing individuals and newly generated offspring. For example: the first individual travels at 45 km / h (retained), the second at 65 km / h (retained), the third at 85 km / h (retained), the fourth at 75 km / h (new offspring), and the fifth at 78 km / h (mutated offspring). The benefits of each individual in the new population are then evaluated.

[0124] Second-generation iteration: Repeat the process of selection, crossover, mutation, and payoff evaluation until a convergent solution is found.

[0125] Step 1070: When the genetic algorithm converges, the electronic device uses the strategy corresponding to the individual with the highest reward value among the multiple individuals as the vehicle control strategy.

[0126] In this embodiment of the invention, it is checked whether the strategy with the highest return remains unchanged across several iterations. If the change is small or nonexistent, the genetic algorithm is considered to have converged.

[0127] For example, the strategy corresponding to the individual with the highest profit value among multiple individuals, i.e., the vehicle control strategy, is a vehicle speed of 78 km / h.

[0128] Step 108: The electronic device generates a vehicle control command based on the current vehicle status information and vehicle control strategy, and performs vehicle control according to the vehicle control command.

[0129] In this embodiment of the invention, vehicle control commands may include acceleration, deceleration, steering, etc.

[0130] As an alternative, the electronic device can generate vehicle control commands based on the current vehicle status information and vehicle control strategy, and send the vehicle control commands to the accelerator pedal or electric motor so that the accelerator pedal or electric motor can control the vehicle according to the vehicle control commands.

[0131] For example, if the vehicle control strategy is for a speed of 78 km / h, and the current vehicle status information shows a speed of 50 km / h, with a turning requirement of going straight, then converting the speeds to SI units (m / s): 50 km / h ≈ 13.89 m / s, 78 km / h ≈ 21.67 m / s. If the goal is to increase the speed from 50 km / h to 78 km / h within 10 seconds, then a = (21.67 m / s - 13.89 m / s) / 10 s, which simplifies to a ≈ 0.778 m / s. 2 This means the vehicle needs to travel at approximately 0.778 m / s 2 The vehicle accelerates from 50 km / h to 78 km / h. The vehicle control system generates vehicle control commands based on the calculated acceleration, adjusting the accelerator pedal position or electric motor power output, ensuring a smooth, gentle acceleration to 78 km / h. Since the steering requirement is straight-line driving, the vehicle control system does not need to adjust the steering wheel angle unless the vehicle deviates from the preset path or requires minor adjustments.

[0132] The technical solution provided in this invention involves constructing a multi-objective optimization model based on a game theory framework. Acquired vehicle state information, external environment information, and set model parameters are input into the multi-objective optimization model for data processing to generate updated model parameters. The updated model parameters are then used to calculate and generate a vehicle control strategy. Based on the current vehicle state information and the vehicle control strategy, vehicle control commands are generated to control the vehicle. This technical solution, based on the multi-objective optimization model, enables the vehicle control system to effectively balance multiple objectives, improving the overall performance of the vehicle in actual driving and achieving an optimal combination of energy, time, and cost while ensuring safety.

[0133] In the technical solution provided by the embodiments of the present invention, by designing a multi-objective optimization model, various driving parameters such as speed, acceleration, and path selection can be considered simultaneously, and these parameters can be optimized to achieve the best combination of time, cost and energy efficiency.

[0134] In the technical solution provided by this invention, vehicles must make rapid adjustments to maintain an optimized state in a constantly changing traffic environment. The employed onboard sensors and environmental perception technology enable the vehicle to collect external information (such as road conditions, traffic flow, and weather conditions) and internal state data (such as fuel or electricity consumption and vehicle performance indicators) in real time, and dynamically adjust its driving strategy based on this information. This enhances the adaptability and flexibility of the vehicle control system, allowing the vehicle to better cope with uncertainties such as traffic conditions and weather changes, ensuring long-term driving efficiency and passenger safety and comfort.

[0135] In the technical solution provided by the embodiments of the present invention, when encountering an emergency, such as needing to avoid obstacles or perform emergency braking, the system uses an efficient calculation model to quickly reassess the situation and minimizes the impact on other objectives (such as time and cost) while ensuring safety.

[0136] The technical solution provided by the embodiments of the present invention can plan the trip based on the current energy market price, the distribution of charging stations and the expected energy demand, aiming to reduce the overall operating cost.

[0137] In the technical solution provided by the embodiments of the present invention, by integrating advanced machine learning algorithms, it is possible to learn from historical data and optimize its decision-making model, thereby making more accurate decision support in future driving.

[0138] The technical solution provided in this invention integrates multi-objective optimization theory into vehicle driving control, solving a series of challenges faced by autonomous vehicles in complex and ever-changing modern traffic environments. This not only enhances the vehicle's intelligence level and provides a safer, more efficient, and economical driving mode, but also offers users an unprecedented personalized driving experience.

[0139] One embodiment of the present invention provides a vehicle control device. Figure 4 This is a schematic diagram of the structure of a vehicle control device according to an embodiment of the present invention, as shown below. Figure 4 As shown, the device includes: a construction module 11, a data processing module 12, a computing module 13, and a control module 14.

[0140] Module 11 is used to construct a multi-objective optimization model based on the game theory framework. The multi-objective optimization model includes: a total objective function, a policy space, and a Nash equilibrium condition. The total objective function is used to represent multiple optimization objectives of the driving vehicle, the policy space is used to represent the set of actions of the vehicle, and the Nash equilibrium condition is used to represent the vehicle control method that satisfies the total objective function, the policy space, and the Nash equilibrium.

[0141] The data processing module 12 is used to input the acquired vehicle status information, external environment information and set model parameters into the multi-objective optimization model for data processing and to generate updated model parameters.

[0142] The calculation module 13 is used to calculate the updated model parameters to generate a vehicle control strategy.

[0143] The control module 14 is used to generate vehicle control commands based on the current vehicle status information and vehicle control strategy, so as to control the vehicle according to the vehicle control commands.

[0144] In this embodiment of the invention, the data processing module 12 is specifically used to preprocess vehicle status information and external environment information to generate first preprocessed data and second preprocessed data; and to generate updated model parameters based on the first preprocessed data, the second preprocessed data and model parameters.

[0145] In this embodiment of the invention, the data processing module 12 is specifically used to update the strategy space based on the vehicle speed and vehicle acceleration in the first preprocessed data to generate an updated strategy space; generate an environment index based on the second preprocessed data; adjust the reward function based on the environment index to generate an adjusted reward function; and integrate the updated strategy space, the adjusted reward function, and the model parameters into a multi-objective optimization model to generate updated model parameters.

[0146] In this embodiment of the invention, the calculation module 13 is specifically used to calculate and generate a vehicle control strategy based on the updated model parameters using the Nash equilibrium solution algorithm.

[0147] In this embodiment of the invention, the calculation module 13 is specifically used to input the updated model parameters into the multi-objective optimization model; create an initial population; iterate the initial population through a genetic algorithm, and generate a vehicle control strategy when the genetic algorithm converges.

[0148] In this embodiment of the invention, the calculation module 13 is specifically used to iterate the initial population through a genetic algorithm to generate a new population; to evaluate the benefit of each individual in the new population through a fitness function to generate a benefit value; and when the genetic algorithm converges, to use the strategy corresponding to the individual with the highest benefit value among the multiple individuals as the vehicle control strategy.

[0149] In this embodiment of the invention, the control module 14 is specifically used to generate vehicle control commands based on the current vehicle status information and vehicle control strategy, and send the vehicle control commands to the accelerator pedal or the electric motor so that the accelerator pedal or the electric motor can control the vehicle according to the vehicle control commands.

[0150] In this embodiment of the invention, the construction module 11 is specifically used to define objective functions, including safety objective functions, time efficiency objective functions, energy consumption objective functions, and cost objective functions; to perform weighted processing on the objective functions to establish a total objective function; to construct a policy space, which includes the speed range of vehicle driving; to solve for Nash equilibrium based on the total objective function and the policy space to obtain Nash equilibrium conditions; and to construct a multi-objective optimization model based on the total objective function, the policy space, and the Nash equilibrium conditions.

[0151] The technical solution provided in this invention involves constructing a multi-objective optimization model based on a game theory framework. Acquired vehicle state information, external environment information, and set model parameters are input into the multi-objective optimization model for data processing to generate updated model parameters. The updated model parameters are then used to calculate and generate a vehicle control strategy. Based on the current vehicle state information and the vehicle control strategy, vehicle control commands are generated to control the vehicle. This technical solution, based on the multi-objective optimization model, enables the vehicle control system to effectively balance multiple objectives, improving the overall performance of the vehicle in actual driving and achieving an optimal combination of energy, time, and cost while ensuring safety.

[0152] The vehicle control device provided in this embodiment can be used to achieve the above. Figure 1 For a detailed description of the vehicle control method described above, please refer to the embodiments of the vehicle control method, which will not be repeated here.

[0153] This invention provides a storage medium that includes a stored program. When the program runs, it controls the device where the storage medium is located to execute the steps of the above-described vehicle control method. For a detailed description, please refer to the embodiments of the above-described vehicle control method.

[0154] This invention provides an electronic device, including a memory and a processor. The memory stores information including program instructions, and the processor controls the execution of the program instructions. When the program instructions are loaded and executed by the processor, they implement the steps of the above-described vehicle control method. For a detailed description, please refer to the above-described vehicle control method embodiments.

[0155] Figure 5 This is a schematic diagram of an electronic device provided in an embodiment of the present invention. (See diagram below.) Figure 5As shown, the electronic device 20 of this embodiment includes: a processor 21, a memory 22, and a computer program 23 stored in the memory 22 and executable on the processor 21. When the computer program 23 is executed by the processor 21, it implements the vehicle control method described in the embodiment. To avoid repetition, it will not be described in detail here. Alternatively, when the computer program is executed by the processor 21, it implements the functions of each model / unit in the vehicle control device described in the embodiment. To avoid repetition, it will not be described in detail here.

[0156] Electronic device 20 includes, but is not limited to, a processor 21 and a memory 22. Those skilled in the art will understand that... Figure 5 This is merely an example of electronic device 20 and does not constitute a limitation on electronic device 20. It may include more or fewer components than shown, or combine certain components, or different components. For example, electronic device may also include input / output devices, network access devices, buses, etc.

[0157] The processor 21 may be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor.

[0158] The memory 22 can be an internal storage unit of the electronic device 20, such as a hard disk or RAM of the electronic device 20. The memory 22 can also be an external storage device of the electronic device 20, such as a plug-in hard disk, Smart Media Card (SMC), Secure Digital (SD) card, or Flash Card equipped on the electronic device 20. Furthermore, the memory 22 can include both internal and external storage units of the electronic device 20. The memory 22 is used to store computer programs and other programs and data required by the electronic device. The memory 22 can also be used to temporarily store data that has been output or will be output.

[0159] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0160] In the embodiments provided by this invention, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection between devices or units through some interfaces, and may be electrical, mechanical, or other forms.

[0161] 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 units can be selected to achieve the purpose of this embodiment according to actual needs.

[0162] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or in the form of hardware plus software functional units.

[0163] The integrated units implemented as software functional units described above can be stored in a computer-readable storage medium. These software functional units, stored in a storage medium, include several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) or processor to execute some 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.

[0164] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A vehicle control method, characterized in that, include: A multi-objective optimization model is constructed based on the game theory framework. The multi-objective optimization model includes: a total objective function, a policy space, and a Nash equilibrium condition. The total objective function is used to represent multiple optimization objectives of the driving vehicle. The policy space is used to represent the set of actions of the vehicle. The Nash equilibrium condition is used to represent the vehicle control method that satisfies the total objective function, the policy space, and the Nash equilibrium. The acquired vehicle status information, external environment information, and set model parameters are input into the multi-objective optimization model for data processing to generate updated model parameters. The updated model parameters are used to calculate and generate a vehicle control strategy; The vehicle control command is generated based on the current vehicle status information and the vehicle control strategy, and the vehicle is controlled according to the vehicle control command.

2. The method according to claim 1, characterized in that, The process of inputting the acquired vehicle status information, external environment information, and set model parameters into the multi-objective optimization model for data processing to generate updated model parameters includes: The vehicle status information and the external environment information are preprocessed to generate first preprocessed data and second preprocessed data. Updated model parameters are generated based on the first preprocessed data, the second preprocessed data, and the model parameters.

3. The method according to claim 2, characterized in that, The step of generating updated model parameters based on the first preprocessed data, the second preprocessed data, and the model parameters includes: The updated strategy space is generated by updating the strategy space based on the vehicle speed and vehicle acceleration in the first preprocessed data. An environmental index is generated based on the second preprocessed data; The adjusted revenue function is generated by adjusting the revenue function based on the environmental index. The updated strategy space, the adjusted payoff function, and the model parameters are integrated into the multi-objective optimization model to generate updated model parameters.

4. The method according to claim 1, characterized in that, The step of calculating and generating a vehicle control strategy from the updated model parameters includes: Based on the Nash equilibrium solution algorithm, the updated model parameters are calculated to generate a vehicle control strategy.

5. The method according to claim 4, characterized in that, The method based on the Nash equilibrium solution algorithm calculates the updated model parameters to generate a vehicle control strategy, including: The updated model parameters are then input into the multi-objective optimization model; Create the initial population; The initial population is iterated using a genetic algorithm, and a vehicle control strategy is generated when the genetic algorithm converges.

6. The method according to claim 5, characterized in that, The process of iterating through the initial population using a genetic algorithm, and generating a vehicle control strategy when the genetic algorithm converges, includes: A new population is generated by iterating through the initial population using a genetic algorithm. The fitness function is used to evaluate the benefit of each individual in the new population, and a benefit value is generated. When the genetic algorithm converges, the strategy corresponding to the individual with the highest return value among multiple individuals is taken as the vehicle control strategy.

7. The method according to claim 1, characterized in that, The step of generating vehicle control commands based on the current vehicle status information and the vehicle control strategy, and then controlling the vehicle according to the vehicle control commands, includes: Based on the current vehicle status information and the vehicle control strategy, a vehicle control command is generated and sent to the accelerator pedal or electric motor so that the accelerator pedal or electric motor can control the vehicle according to the vehicle control command.

8. The method according to claim 1, characterized in that, The multi-objective optimization model constructed based on the game theory framework includes: Define objective functions, including a safety objective function, a time efficiency objective function, an energy consumption objective function, and a cost objective function; The objective function is weighted to establish the overall objective function; Construct the policy space, which includes the speed range of vehicle driving; The Nash equilibrium is obtained by solving the Nash equilibrium condition based on the total objective function and the policy space. The multi-objective optimization model is constructed based on the overall objective function, the policy space, and the Nash equilibrium condition.

9. A vehicle control device, characterized in that, include: A construction module is used to construct a multi-objective optimization model based on a game theory framework. The multi-objective optimization model includes: a total objective function, a policy space, and a Nash equilibrium condition. The total objective function is used to characterize multiple optimization objectives of the driving vehicle. The policy space is used to characterize the set of actions of the vehicle. The Nash equilibrium condition is used to characterize the vehicle control method that satisfies the total objective function, the policy space, and the Nash equilibrium. The data processing module is used to input the acquired vehicle status information, external environment information, and set model parameters into the multi-objective optimization model for data processing, and generate updated model parameters. The calculation module is used to calculate the updated model parameters to generate a vehicle control strategy; The control module is used to generate vehicle control commands based on the current vehicle status information and the vehicle control strategy, so as to control the vehicle according to the vehicle control commands.

10. A storage medium, characterized in that, include: The storage medium includes a stored program, wherein, when the program is executed, it controls the device containing the storage medium to perform the vehicle control method according to any one of claims 1 to 8.

11. An electronic device comprising a memory and a processor, the memory for storing information including program instructions, and the processor for controlling the execution of the program instructions, characterized in that, When the program instructions are loaded and executed by the processor, they implement the steps of the vehicle control method according to any one of claims 1 to 8.

Images