A vehicle deceleration control method, device, equipment and storage medium

Abstract

This application provides a vehicle deceleration control method, device, equipment, and storage medium. The method acquires the vehicle's current driving information and driving environment information to predict expected road traffic behavior within a preset time period. If the prediction indicates that deceleration is required, a target driving information to be achieved within the preset time period is determined based on the current driving information and driving environment information, including a target driving speed. A corresponding vehicle deceleration control command is generated based on the determined target driving information, and the intensity of the vehicle's kinetic energy recovery system and / or the force of the mechanical brakes are controlled according to the command to ensure that the vehicle can smoothly decelerate to the target speed at a predetermined time point. This effectively improves driving safety and comfort and optimizes energy efficiency.

Description

Technical Field

[0001] This application relates to the field of intelligent driving technology, specifically to a vehicle deceleration control method, device, equipment, and storage medium. Background Technology

[0002] With the continuous advancement of automotive technology, particularly in the fields of intelligent driving and vehicle automation, the demand for improved driving safety and comfort is growing. Traditional driving methods rely on the driver's immediate reaction to traffic conditions to operate the braking system. This can lead to a series of problems in complex and ever-changing road environments, such as driver fatigue, accelerated brake system wear, and potential safety risks. In modern traffic environments, especially in congested urban areas, frequent starts and stops not only increase the driver's workload but also cause rapid wear on the braking system and increase the risk of traffic accidents. Furthermore, the kinetic energy generated during traditional braking is usually dissipated as heat, which is not ideal in terms of energy efficiency.

[0003] In recent years, with the increasing popularity of electric vehicles (EVs) and hybrid electric vehicles (HEVs), kinetic energy recovery mechanisms or regenerative braking systems have become important means of optimizing energy use. These systems can convert some of the kinetic energy into electrical energy and store it in the battery during vehicle deceleration, thereby reducing energy waste and extending the vehicle's driving range. However, how to efficiently integrate kinetic energy recovery with mechanical braking to achieve smooth and efficient deceleration control remains a challenge. Summary of the Invention

[0004] In view of the shortcomings of the prior art described above, this application provides a vehicle deceleration control method, device, equipment and storage medium to solve the above technical problems.

[0005] This application provides a vehicle deceleration control method, the method comprising: acquiring current driving information and driving environment information of the vehicle, wherein the current driving information is parameter information describing the current motion state of the vehicle, and the driving environment information is information about the driving scenario in which the vehicle is located; predicting the expected road traffic behavior of the vehicle within a preset future time period based on the current driving information and the driving environment information; if the expected road traffic behavior includes vehicle deceleration, determining target driving information of the vehicle within the preset future time period based on the current driving information and the driving environment information, wherein the target driving information is parameter information describing the future motion state of the vehicle; generating a vehicle deceleration control command based on the target driving information, and controlling the intensity of the vehicle's kinetic energy recovery system and / or the force of the mechanical braking according to the vehicle deceleration control command, so that the vehicle decelerates to the target driving speed in the target driving information after a preset time period.

[0006] In one embodiment of this application, determining the target driving information of a vehicle within a future preset time period based on the current driving information and the driving environment information includes: using the current driving information and the driving environment information as input information; inputting the input information into a trained vehicle driving information determination model to obtain the output result of the vehicle driving information determination model, and determining the output result as the target driving information; the vehicle driving information determination model includes: a driving state prediction sub-model, used to predict the expected road traffic behavior of the vehicle within a future preset time period based on the current driving information and the driving environment information; and a driving information generation sub-model, used to determine the target driving information of the vehicle within a future preset time period based on the current driving information, the driving environment information, and the output of the driving state prediction sub-model.

[0007] In one embodiment of this application, predicting a vehicle's road traffic behavior within a preset time period based on the current driving information and the driving environment information includes: predicting the vehicle's target position after the preset time period based on the current driving speed and the vehicle's current position, wherein the current position is obtained based on the current driving information; identifying the road traffic status of the interval road segment between the current position and the target position, wherein the road traffic status includes at least a free-flowing state and a blocked state; if the road traffic status is free-flowing, the vehicle's driving behavior through the interval road segment does not include deceleration; if the road traffic status is blocked, the vehicle's driving behavior through the interval road segment includes deceleration.

[0008] In one embodiment of this application, the target driving information includes a target speed and a target deceleration. Determining the target driving information of the vehicle within a preset future time period includes: identifying obstacles between the current position and the target position based on the environmental information, and recording the position and speed of each obstacle; wherein the obstacles include dynamic obstacles and stationary obstacles; calculating the interval distance between the vehicle and each obstacle based on the current position of the vehicle and the positions of each obstacle, and calculating the estimated collision time between the vehicle and each obstacle based on the interval distance, the speed of the obstacle, and the current driving speed; if the estimated collision time is less than a preset safe time threshold, calculating the target speed based on the current speed and the interval distance to ensure that the vehicle stops before reaching the obstacle; and calculating the target deceleration to reduce the vehicle to the target speed based on the current speed and the target speed.

[0009] In one embodiment of this application, generating a vehicle deceleration control command based on the target driving information includes: obtaining a deceleration threshold of the vehicle's kinetic energy recovery system; if the target deceleration is less than or equal to the deceleration threshold of the kinetic energy recovery system, calculating the kinetic energy recovery intensity based on the target deceleration; if the target deceleration is greater than the deceleration threshold of the kinetic energy recovery system, calculating the deceleration difference between the deceleration threshold of the kinetic energy recovery system and the target deceleration, and determining the mechanical braking force based on the deceleration difference; converting the calculated mechanical braking force and kinetic energy recovery intensity into control commands, and performing deceleration control on the vehicle based on the control commands to avoid collisions between the vehicle and obstacles.

[0010] In one embodiment of this application, the vehicle deceleration control method further includes: constructing an initial neural network model, the initial neural network model being implemented based on a preset machine learning algorithm; training the initial neural network model based on historical driving information and corresponding driving environment information to generate a vehicle driving information determination model; inputting the current driving information into the vehicle driving information determination model to predict the road conditions of the vehicle in a future preset time period; generating corresponding target driving information based on the predicted road conditions, the target driving information including at least a target speed and a target deceleration; and gradually adjusting the force of the mechanical brakes and the intensity of the kinetic energy recovery system to enable the vehicle to smoothly transition from the current driving state to the driving state indicated by the target driving information.

[0011] In one embodiment of this application, after controlling the intensity of the vehicle's kinetic energy recovery system and / or the force of the mechanical brake according to the vehicle deceleration control command, the method further includes at least one of the following: real-time monitoring of the vehicle's actual deceleration, including at least changes in vehicle speed, acceleration, and the response of the braking system; dynamically adjusting the braking force and / or kinetic energy recovery intensity based on the difference between the monitored actual deceleration and the expected deceleration target to ensure that the actual deceleration process conforms to the expected deceleration curve; continuously evaluating changes in driving environment information during deceleration, such as changes in the position of obstacles ahead or sudden changes in road conditions, and dynamically adjusting the deceleration strategy according to the changes to ensure driving safety; and recording data throughout the deceleration process, including the issued deceleration control command, the actual deceleration effect, and any adjustment measures, to optimize the vehicle driving information determination model after the vehicle reaches the preset target speed or comes to a complete stop.

[0012] This application provides a vehicle deceleration control device, comprising: an information acquisition module for acquiring current driving information and driving environment information of the vehicle, wherein the current driving information is parameter information describing the current motion state of the vehicle, and the driving environment information is information about the driving scenario in which the vehicle is located; a target driving information generation module for predicting the expected road traffic behavior of the vehicle within a preset future time period based on the current driving information and the driving environment information; if the expected road traffic behavior includes vehicle deceleration, determining the target driving information of the vehicle within the preset future time period based on the current driving information and the driving environment information, wherein the target driving information is parameter information describing the future motion state of the vehicle; and a deceleration control module for generating a vehicle deceleration control command based on the target driving information, and controlling the intensity of the vehicle's kinetic energy recovery system and / or the force of the mechanical brakes according to the vehicle deceleration control command, so that the vehicle decelerates to the target driving speed in the target driving information after a preset time.

[0013] This application provides an electronic device, including a processor, a memory, and a communication bus; the communication bus is used to connect the processor and the memory; the processor is used to execute a computer program stored in the memory to implement the vehicle deceleration control method described above.

[0014] This application provides a computer-readable storage medium having a computer program stored thereon, the computer program being used to cause a computer to execute the vehicle deceleration control method described above.

[0015] The beneficial effects of this application are as follows: The vehicle deceleration control method in this application, by acquiring and analyzing the vehicle's current driving information and driving environment information in real time, can accurately predict road traffic behavior within a preset time period. When the prediction result indicates that deceleration is required, based on the current driving information and environmental information, it intelligently determines a target driving information to be achieved within the preset time period, especially the target driving speed, thereby generating corresponding vehicle deceleration control commands. Based on these commands, it precisely adjusts the intensity of the kinetic energy recovery system and / or the force of the mechanical brakes to ensure that the vehicle can smoothly and efficiently decelerate to the target speed at the predetermined time point. This method not only reduces the driver's operational burden and alleviates fatigue caused by frequent braking, but also effectively slows down the wear of the braking system and extends its service life. More importantly, by rationally utilizing the kinetic energy recovery mechanism, it significantly improves energy utilization efficiency, providing electric vehicles and hybrid vehicles with a longer driving range.

[0016] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and do not limit this application. Attached Figure Description

[0017] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application. It is obvious that the drawings described below are merely some embodiments of this application, and those skilled in the art can obtain other drawings based on these drawings without any inventive effort. In the drawings:

[0018] Figure 1 This is a schematic diagram illustrating the implementation environment of a vehicle deceleration control method according to an exemplary embodiment of this application;

[0019] Figure 2 This is a flowchart illustrating a vehicle deceleration control method in an exemplary embodiment of this application;

[0020] Figure 3 This is a schematic diagram illustrating the training process of a vehicle driving information determination model, as shown in an exemplary embodiment of this application.

[0021] Figure 4 This is a schematic diagram of the overall scheme of a vehicle deceleration control method shown in an exemplary embodiment of this application;

[0022] Figure 5 This is a block diagram illustrating a vehicle deceleration control device in an exemplary embodiment of this application;

[0023] Figure 6 A schematic diagram of the structure of a computer system suitable for implementing the electronic device of the present application is shown. Detailed Implementation

[0024] The embodiments of this application will be described below with reference to the accompanying drawings and preferred embodiments. Those skilled in the art can easily understand other advantages and effects of this application from the content disclosed in this specification. This application can also be implemented or applied through other different specific embodiments, and various details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of this application. It should be understood that the preferred embodiments are only for illustrating this application and are not intended to limit the scope of protection of this application.

[0025] It should be noted that the illustrations provided in the following embodiments are only schematic representations of the basic concept of this application. Therefore, the drawings only show the components related to this application and are not drawn according to the actual number, shape and size of the components in the actual implementation. In the actual implementation, the form, quantity and proportion of each component can be arbitrarily changed, and the layout of the components may also be more complex.

[0026] In the following description, numerous details are explored to provide a more thorough explanation of embodiments of the present application. However, it will be apparent to those skilled in the art that embodiments of the present application may be practiced without these specific details. In other embodiments, well-known structures and devices are shown in block diagram form rather than in detail to avoid obscuring embodiments of the present application.

[0027] First, it's important to note that kinetic energy recovery mechanisms are widely used as an innovative energy management technology. Also known as regenerative braking systems, this mechanism converts kinetic energy that would otherwise be lost as heat into electrical energy during vehicle deceleration or braking, storing it in the battery for later use. Specifically, when the driver presses the brake pedal or releases the accelerator pedal, the electric motor's operating mode switches from driving mode to power generation mode. At this time, the electric motor acts as a generator, converting rotational kinetic energy into electrical energy and feeding it back into the battery pack. This not only reduces energy waste but also extends the vehicle's driving range.

[0028] This application focuses on discussing how, in autonomous driving scenarios, target deceleration speed and target acceleration are obtained based on predictions of future road conditions. The intensity of the vehicle's kinetic energy recovery system and the force of mechanical braking are then comprehensively adjusted based on these target speeds and accelerations. This allows for greater kinetic energy recovery to achieve vehicle deceleration and recover more mechanical kinetic energy, thus improving energy utilization efficiency. Furthermore, energy recovery based on predicted road information gives the vehicle more reaction time, and adjusting the energy recovery intensity according to the target deceleration makes the energy recovery process more accurate, efficient, and smooth. Therefore, it not only improves energy utilization efficiency but also enhances user comfort and experience.

[0029] DDPG (Deep Deterministic Policy Gradient) is a reinforcement learning algorithm particularly suitable for solving problems in continuous action spaces. It combines deep learning with traditional deterministic policy gradient methods.

[0030] ADAS (Advanced Driver Assistance Systems) is a collective term for a series of technologies and systems designed to improve vehicle safety and enhance the driving experience.

[0031] V2X (Vehicle to Everything) communication technology is a technology that enables vehicles to communicate with various entities in their surrounding environment, including other vehicles (V2V), infrastructure (V2I), pedestrians (V2P), and networks (V2N). The goal of V2X is to improve road safety, traffic efficiency, and the driving experience through real-time information exchange.

[0032] Figure 1 This is a schematic diagram illustrating the implementation environment of a vehicle deceleration control method according to an exemplary embodiment of this application.

[0033] like Figure 1 As shown, the implementation environment of the vehicle deceleration control method includes a data acquisition device 101 and a computer device 102. The data acquisition device 101 is responsible for collecting current driving data and driving environment data during vehicle operation. This data includes, but is not limited to, current location, current driving speed, navigation information, road conditions ahead, and distance to the vehicle in front. The current location can be determined by obtaining the vehicle's real-time geographical location through GPS or other positioning systems; the current driving speed is obtained from real-time vehicle speed information provided by vehicle speed sensors or onboard systems; navigation information is generated from route planning and road type information obtained from onboard navigation systems or external navigation services; road conditions ahead are acquired through perception technologies such as onboard cameras, radar, or lidar, which can identify obstacles, traffic light status, road conditions, etc.; the distance to the vehicle in front is measured by radar or ultrasonic sensors. Therefore, the data acquisition device can be various sensors installed on the vehicle (such as GPS modules, vehicle speed sensors, cameras, radar, or ultrasonic sensors), or it can be an external device connected to the vehicle wirelessly or via wired means. This application does not impose any restrictions on the specific implementation form of the data acquisition device.

[0034] Furthermore, the computer device 102 is used to process the data collected by the data acquisition device 101, specifically including: by acquiring and analyzing the vehicle's current driving information and driving environment information in real time, it can accurately predict road traffic behavior within a preset time period in the future; when the prediction result indicates that deceleration is required, based on the current driving information and environmental information, it intelligently determines a target driving information to be reached within a preset time period in the future, especially the target driving speed, thereby generating corresponding vehicle deceleration control commands, and precisely adjusting the intensity of the kinetic energy recovery system and / or the force of the mechanical brakes according to these commands, ensuring that the vehicle can smoothly and efficiently decelerate to the target speed at the predetermined time node. Therefore, the computer device 102 can be a high-performance processor, a dedicated in-vehicle computing platform, or an embedded system integrated into the vehicle, etc. This application also does not impose any restrictions on the specific type of computer device.

[0035] It should be noted that through this implementation environment configuration, the vehicle deceleration control system can effectively utilize real-time collected data to make intelligent decisions, thereby improving driving safety and providing the driver with a more comfortable driving experience.

[0036] Figure 2 This is a flowchart illustrating a vehicle deceleration control method in an exemplary embodiment of this application.

[0037] like Figure 2 As shown, in an exemplary embodiment, the vehicle deceleration control method includes at least steps S210 to S230, which are described in detail below:

[0038] Step S210: Obtain the vehicle's current driving information and driving environment information, wherein the current driving information is parameter information used to describe the vehicle's motion state, and the driving environment information is information about the driving scenario in which the vehicle is located.

[0039] In one embodiment of this application, current driving information is obtained, which describes the vehicle's motion state. This current driving information generally characterizes driving-related information on the vehicle side, including but not limited to vehicle speed data, acceleration data, steering angle, accelerator pedal position, and brake pedal position. The data collection methods are as follows:

[0040] Vehicle speed data: Vehicle speed is monitored in real time using wheel speed sensors mounted on the vehicle's wheel hubs. For example, suppose the current vehicle speed is 60 km / h.

[0041] Acceleration data: The vehicle's longitudinal acceleration is measured using a built-in triaxial accelerometer. For example, the current acceleration is 0.5 m / s². 2 .

[0042] Steering angle: The steering input is obtained from the steering wheel angle sensor. For example, the current steering angle is +10 degrees (turning right).

[0043] Accelerator pedal position: The accelerator pedal position is monitored by a accelerator pedal position sensor to understand the driver's acceleration needs. For example, the current accelerator pedal position is 30%.

[0044] Brake pedal position: The brake pedal position is monitored by a brake position sensor to determine the degree of braking. For example, the current brake pedal position is 0% (no brake applied).

[0045] In addition, driving environment information used to describe the driving scenario in which the vehicle is located generally refers to environmental information in the natural world and environmental information related to human activities, including but not limited to road conditions ahead, weather conditions, traffic flow, road conditions, and road surface type. The methods for collecting each type of information are as follows:

[0046] Road conditions ahead: Front camera: Captures images of the road ahead using a front camera and identifies lane lines, traffic signs, and other obstacles using image processing algorithms. For example, it detects a stop line 50 meters ahead. Radar / LiDAR: Detects the distance and relative speed of obstacles ahead using radar or lidar. For example, it detects a stationary vehicle 100 meters ahead.

[0047] Weather conditions: Current weather conditions are obtained through onboard weather sensors or weather forecast data received from external service providers. For example, the current weather is sunny with a temperature of 25°C.

[0048] Traffic flow: Real-time traffic flow information is obtained by receiving data from other vehicles and infrastructure in the surrounding area through V2X (Vehicle to Everything) communication technology. For example, the traffic flow on the current road segment is moderate.

[0049] Get the latest traffic updates through the built-in navigation system; for example, the navigation system shows that there is slight congestion 2 kilometers ahead.

[0050] Road surface type: By analyzing the images captured by the front-facing camera using image processing technology, the type of road surface being driven on is determined. For example, the current road surface is a dry asphalt road surface.

[0051] It should be noted that after collecting the above data, further data preprocessing and data fusion are required. The processed data will then be used for road condition prediction and target driving information determination. Similar to current driving information, target driving information refers to parameter information describing the vehicle's motion state, and its data category is the same as the aforementioned current driving information. Data preprocessing includes preprocessing the collected data, such as filtering and denoising, and unit conversion, to ensure data quality. Data fusion involves using multi-sensor data fusion algorithms, such as Kalman filters or other fusion algorithms, to combine information from different sources to form comprehensive driving and environmental information.

[0052] Step S220: Based on the current driving information and driving environment information, predict the vehicle's expected road traffic behavior within a preset time period in the future; if the expected road traffic behavior includes vehicle deceleration, determine the vehicle's target driving information within the preset time period in the future based on the current driving information and driving environment information.

[0053] In one embodiment of this application, the vehicle deceleration control method includes: constructing an initial neural network model, the initial neural network model being implemented based on a preset machine learning algorithm; training the initial neural network model based on historical driving information and corresponding driving environment information to generate a vehicle driving information determination model; inputting current driving information into the vehicle driving information determination model to predict the road conditions of the vehicle in a future preset time period; generating corresponding target driving information based on the predicted road conditions, the target driving information including at least a target speed and a target deceleration; and gradually adjusting the force of the mechanical brakes and the intensity of the kinetic energy recovery system to enable the vehicle to smoothly transition from the current driving state to the driving state indicated by the target driving information.

[0054] Before building a neural network model, it is necessary to initialize the relevant systems of the vehicle and obtain relevant parameters, as well as perform environmental perception and data fusion.

[0055] This involves initializing the vehicle's relevant systems and obtaining related parameters, as detailed below:

[0056] Once the vehicle starts, the intelligent braking system first performs self-initialization, checking and ensuring all sensors and actuators are functioning properly. Next, the system communicates with the vehicle's CAN bus to acquire key driving parameters in real time. These parameters include, but are not limited to, current speed, acceleration, deceleration, steering wheel angle, gear information, and various vehicle status indicators. Furthermore, the system obtains real-time location information via the vehicle's navigation system. This information includes not only the vehicle's precise current location but also important data such as route planning, road type, and traffic signs. Using this data, the system can determine whether the vehicle is about to enter an area requiring special attention, such as schools, pedestrian crossings, sharp turns, or construction zones.

[0057] The environmental perception and data fusion are detailed below:

[0058] While the vehicle is in motion, the intelligent braking system continuously uses various sensors to perceive its environment. Driving cameras capture visual information ahead, identifying road signs, pedestrians, and other obstacles. Millimeter-wave radar, ultrasonic radar, and lidar provide precise data on the distance, speed, and direction of objects ahead.

[0059] Different data fusion strategies will produce different results. This article mainly introduces the fusion strategy based on complementary features. Because different sensors can capture the unrelated size features of the same target, this provides better recognition capabilities for target identification and detection. The features extracted in the ADAS system include target parameters and feature data extraction.

[0060] Target parameter extraction: This includes extracting target information such as size, distance, orientation, velocity, and acceleration from preprocessed data. Many studies extract the positional features of radar or lidar targets and assist image recognition by generating regions of interest (ROIs). The ROI directly converts the location of the radar-detected target into an image to form a region.

[0061] Data Feature Extraction: Data features are features extracted from images or other processed data, such as target contours, textures, temporal and frequency features, and color distributions, for classification and recognition. In computer vision, a large number of Regions of Interest (ROIs) that may contain targets are typically generated in an image. These ROIs are then classified using pre-trained classification models. Furthermore, the ROI with the highest confidence is the location of the target. Determining the target's location in this way requires significant computation. Due to the advantages of LiDAR and millimeter-wave radar in detecting target locations, the computational cost is relatively low. Therefore, many studies first use radar and LiDAR to extract the target's distance and orientation information, then map the location information onto the image data to generate fewer ROIs. Finally, a pre-trained model is used to further identify these ROIs and accurately classify the target category. After ROI extraction, many studies apply machine learning methods to further perceptual tasks. Traditional machine learning methods typically require extracting standard features, such as the Haar operator, HOG operator, and gray-level co-occurrence matrix, to extract features from the image, and then applying SVM, Adaboost, and other methods to classify these features.

[0062] Then, based on all the data obtained above, an initial neural network model is constructed, and a vehicle driving information determination model is trained. This embodiment takes the deep deterministic policy gradient algorithm as an example, and its specific steps are as follows:

[0063] Based on the fused perception data, the intelligent braking system uses predictive algorithms to make short-term predictions about the road conditions ahead. These predictions include, but are not limited to, changes in the speed of vehicles ahead, the movement trajectories of pedestrians, and the development trends of potential risks.

[0064] To achieve a better kinetic energy recovery strategy, reinforcement learning algorithms can be considered. Because driving in the real world is a continuous action, traditional reinforcement learning, while achieving steady improvement and even surpassing human performance in many games, has proven effective.

[0065] However, these achievements are difficult to replicate in the field of autonomous driving because the spatial conditions of the real world are more complex, the action space is continuous, and precise control is required. Autonomous vehicles should also prioritize functional safety in complex environments. Therefore, a deep deterministic policy gradient algorithm can be considered, which uses deterministic rather than stochastic action functions. In particular, DDPG combines the advantages of deterministic policy gradient algorithms, actor-critic networks, and deep Q-networks.

[0066] The DDPG network structure consists of four networks: the current Actor network, the target Actor network, the current Q-network, and the target Q-network. The current Actor and target Actor networks take states as input and actions as outputs. For example... Figure 3 As shown, the current Actor network takes the current state S as input and outputs the action 'a' under the current state S. The target Actor network takes the next state S' as input and outputs the action 'a' under the next state S'. The Critic network takes both state and action as input and outputs the Q-value of taking this action under this state. Specifically, the current Critic network takes the current state S and current action 'a' as input and outputs the Q-value of taking the next action 'a' under the current state S. The target Critic network takes the next state S' and next action 'a' as input and outputs the Q-value of taking the next action 'a' under the next state S'.

[0067] Therefore, the specific process for building a DDPG network is as follows:

[0068] Step 1: Data Acquisition. Given the need for a large amount of real-world data to train our algorithm model, we will primarily use the HighD and Ngsim datasets. Both are open-source datasets based on real-world road conditions (highways, expressways, urban roads, etc.) and employ advanced cameras and other sensors to acquire various dynamic parameters of moving vehicles, allowing researchers to more quickly build and use algorithm models. We will randomly select 5000 complete dataset entries and divide them into training, validation, and test sets in a 7:2:1 ratio. Next, we will process the raw data, handling missing and outlier data (random forest completion, deletion, etc.). Then, we will extract useful features, such as the target object's position parameters, vehicle speed, vehicle acceleration, number of data frames, and total number of data frames, as input states for the DDPG model. Then, we define the state and action parameters. We can set the state vector as the current vehicle's speed, position, and distance to the vehicle in front. The action vector includes the vehicle's acceleration and the intensity of kinetic energy recovery. Finally, the previous data is normalized to obtain the processed data, which will be in the range of [0, 1] or [-1, 1]. It should be noted that the processed data can accelerate convergence, avoid numerical instability, and improve the performance of the model.

[0069] Step two: Set up the environment. Use OpenAi Gym to build a simulation environment model and construct the Actor network, Critic network, experience replay pool, and target network. Details are as follows:

[0070] Step a: In the Actor network, the input layer is state S, and the two hidden layers are connected to the output layer action a using two ReLU functions and the last Tanh activation function.

[0071] Step b: Set the input layer of the Critic network to state S and the action a just obtained, and the output to the target value Q.

[0072] Step c, define the experience replay pool. The experience replay pool stores the agent's historical experiences interacting with the environment. Its main purpose is to break down correlations between data by randomly sampling from the stored experience, thereby improving the stability and efficiency of training. The experience replay pool typically contains the following information: current state S, action a, reward r, next state S′, and whether it is the final state "done" (a boolean value indicating whether the endpoint has been reached). Furthermore, the storage capacity N and the mini-batch size can also be defined.

[0073] Step d: Define the DDPG agent. The DDPG agent is the main body used for training and execution in reinforcement learning. It includes Actor and Critic networks, as well as experience replay pools and target networks. The DDPG workflow includes: obtaining the current state from the environment; selecting actions using the Actor network and a noise generator; executing actions and observing new states and rewards; storing experiences (state, action, reward, next state, completion flag) in the experience replay pool; randomly sampling batches of samples from the experience replay pool and calculating the target Q-value using the Critic network; updating the Critic network by training it to minimize the mean squared error of the Q-value; updating the Actor network using the gradients of the Critic network to optimize the policy; and softly updating the weights of the target network (i.e., gradually transferring the weights of the main network to the target network).

[0074] Let the target value Q′ be the result we want. According to the Bellman equation, we can obtain:

[0075] Q′=r+γ.Q(s′,a′) Formula (1)

[0076] Where r is the current reward, γ is the discount factor (usually in the range [0,1]), and Q′(s′,a′) is the Q-value prediction of the target Critic network for the next state s′ and the next action a′.

[0077] Subsequently, all parameters θ are updated using gradient descent to update the critic network, as follows:

[0078]

[0079] Where N is the batch size, (si,ai,ri,si′,di) is the i-th sample drawn from the experience replay pool, and yi is the corresponding target Q value.

[0080] Finally, the loss function is minimized using the optimization function (Adam), and the parameters of the critic network are updated. The model is now complete.

[0081] Step 3, Model Training. Import data from the pre-built environment model to begin training the model. Through continuous optimization and parameter tuning, the desired model is obtained. After training, the model can be fed into the trained DDPG model using data obtained from fusion sensing and location information from GPS to determine whether the intelligent braking system needs to be activated and the intensity of kinetic energy recovery.

[0082] In another embodiment of this application, determining the target driving information of a vehicle within a preset future time period based on current driving information and driving environment information includes: using the current driving information and driving environment information as input information; inputting the input information into a trained vehicle driving information determination model to obtain the output result of the vehicle driving information determination model, and determining the output result as the target driving information; the vehicle driving information determination model includes: a driving state prediction sub-model, used to predict the expected road traffic behavior of the vehicle within a preset future time period based on the current driving information and driving environment information; and a driving information generation sub-model, used to determine the target driving information of the vehicle within a preset future time period based on the current driving information, driving environment information, and the output of the driving state prediction sub-model.

[0083] In one embodiment of this application, predicting a vehicle's road traffic behavior within a preset time period based on current driving information and driving environment information includes: predicting the vehicle's target position after the preset time period based on the current driving speed and the vehicle's current position, wherein the current position is obtained based on the current driving information; identifying the road traffic status of the interval road segment between the current position and the target position, wherein the road traffic status includes at least a free-flowing state and a blocked state; if the road traffic status is free-flowing, the vehicle's driving behavior through the interval road segment does not include deceleration; if the road traffic status is blocked, the vehicle's driving behavior through the interval road segment includes deceleration.

[0084] In one specific embodiment of this application, the current vehicle speed is acquired in real time using a vehicle speed sensor, for example, the current vehicle speed is 60 km / h, and the current location of the vehicle is determined using a GPS module or an in-vehicle navigation system, for example, the vehicle is currently located at point A on a main road in a city. Taking a preset time of 30 seconds as an example, the specific execution is as follows:

[0085] First, based on the current driving speed (60 km / h) and the preset time period (30 seconds), calculate the vehicle's expected position after 30 seconds. Assuming no deceleration or other disturbances, the vehicle will travel approximately 500 meters. Therefore, target location B is approximately 500 meters ahead of point A.

[0086] Then, based on the images of the road ahead captured by the front-facing camera, lane lines, traffic signs and other obstacles are identified; the distance and relative speed of obstacles ahead are detected by radar / LiDAR; genjuV2X communication receives data from other vehicles or infrastructure to understand the traffic conditions ahead; and, based on the navigation system, real-time traffic updates are provided, including congestion information, construction areas, etc.

[0087] Next, the road traffic conditions are further categorized. Specifically, if there are no obstacles or traffic jams between point A and point B, and the road conditions ahead are good, the road segment is considered to be in a free-flowing state. If any of the following situations exist between point A and point B, the road segment is considered to be in a blocked state: there are stationary or slowly moving vehicles ahead, the area is in a traffic accident or construction zone, the traffic light is red or about to turn red, the road surface is slippery, or other adverse weather conditions require slowing down.

[0088] Next, the system predicts driving behavior based on road conditions. If the road between points A and B is clear, the system predicts that the vehicle will not need to decelerate in the next 30 seconds and will continue to travel at its current speed (60 km / h) until it reaches point B. If the road between points A and B is blocked, the system predicts that the vehicle will need to decelerate in the next 30 seconds. For example, if there is a red light 500 meters ahead, the system predicts that the vehicle will need to decelerate and stop safely before the red light.

[0089] Finally, if the system predicts that deceleration is necessary, it will generate deceleration control commands based on current driving information and driving environment information. These commands may include adjusting the intensity of the regenerative braking system and / or the force of the mechanical brakes to ensure the vehicle smoothly decelerates to a safe speed and comes to a complete stop if necessary. Furthermore, the system continuously monitors the vehicle's actual deceleration and dynamically adjusts the deceleration strategy accordingly to ensure the vehicle smoothly decelerates to the target speed at predetermined time points.

[0090] It should be noted that, based on the method proposed in the above embodiments, the vehicle system can accurately predict the vehicle's road traffic behavior within a preset time period based on current driving information and driving environment information, and take corresponding deceleration control measures according to the prediction results, thereby improving driving safety and comfort.

[0091] In one embodiment of this application, the target driving information includes a target speed and a target deceleration. Determining the target driving information of the vehicle within a preset time period in the future includes: identifying obstacles between the current position and the target position based on environmental information, and recording the position and speed of each obstacle; wherein, the obstacles include dynamic obstacles and stationary obstacles; calculating the interval distance between the vehicle and each obstacle based on the current position of the vehicle and the positions of each obstacle, and calculating the estimated collision time between the vehicle and each obstacle based on the interval distance, the speed of the obstacle, and the current driving speed; if the estimated collision time is less than a preset safe time threshold, calculating the target speed based on the current speed and the interval distance to ensure that the vehicle stops before reaching the obstacle; and calculating the target deceleration to reduce the vehicle to the target speed based on the current speed and the target speed.

[0092] In one specific embodiment of this application, sensors such as a front-facing camera, radar, and LiDAR are used to detect and identify obstacles between the current location and the target location. Image processing and object recognition algorithms are used to distinguish between dynamic obstacles (such as other vehicles, pedestrians, etc.) and stationary obstacles (such as parked vehicles, roadblocks, etc.). The position coordinates and speed of each obstacle are recorded. For example, a vehicle traveling at 30 km / h is detected 200 meters ahead, and a stationary roadblock is detected 150 meters ahead. Then, based on the vehicle's current position and the position coordinates of each obstacle, the distance between the vehicle and each obstacle is calculated. Taking the vehicle currently at point A, the distance between the vehicle at point B 200 meters ahead is 200 meters; the distance between the roadblock at point C 150 meters ahead is 150 meters, the current vehicle speed is 60 km / h, and the preset safe time threshold is 3 seconds as an example, the specific steps are as follows:

[0093] First, based on the distance between the obstacles, their speeds, and the current driving speed, the estimated collision time with each obstacle is calculated. For example, if the vehicle 200 meters ahead is traveling at 30 km / h, the relative speed between the current vehicle and the vehicle in front is calculated to be 8.34 m / s, resulting in an estimated collision time of 24 seconds. Furthermore, for a stationary obstacle 150 meters ahead, the estimated collision time is approximately 9 seconds.

[0094] Then, if the estimated collision time is less than a preset safe time threshold, a target speed is calculated based on the current speed and the distance between obstacles to ensure the vehicle stops before reaching the obstacle. In this embodiment, for a stationary obstacle 150 meters ahead, the estimated collision time is 9 seconds, which is greater than the 3-second safe time threshold, so immediate stopping is not required. However, for a vehicle 200 meters ahead, the estimated collision time is 24 seconds, which is greater than the 3-second safe time threshold, but if the vehicle continues to travel at its current speed, it may need to decelerate in advance to maintain a safe distance. Assuming that it needs to decelerate to a safe speed within 10 seconds, then the target speed = (distance between obstacles - safe distance) / 10 seconds. Assuming the safe distance is 50 meters, then the target speed = (200m - 50m) / 10s = 15m / s (approximately 54km / h).

[0095] Next, based on the current speed and the target speed, calculate the target deceleration to reduce the vehicle to the target speed. The current speed is 16.67 m / s, the target speed is 15 m / s, and the deceleration needs to be completed within 10 seconds. Therefore, the target deceleration is 0.167 m / s. 2 .

[0096] Finally, based on the calculated target deceleration, corresponding deceleration control commands are generated. These commands include adjusting the intensity of the kinetic energy recovery system and / or the force of the mechanical brakes to ensure the vehicle smoothly decelerates to the target speed and comes to a complete stop if necessary. Furthermore, the system continuously monitors the vehicle's actual deceleration and dynamically adjusts the deceleration strategy accordingly to ensure the vehicle smoothly decelerates to the target speed at predetermined time points.

[0097] It should be noted that, based on the method proposed in this embodiment, the vehicle system can accurately predict the target driving information of the vehicle within a preset time period in the future based on the current driving information and driving environment information, and take corresponding deceleration control measures, thereby improving driving safety and comfort.

[0098] Step S230: Generate a vehicle deceleration control command based on the target driving information, and control the intensity of the vehicle's kinetic energy recovery system and / or the force of the mechanical brake according to the vehicle deceleration control command, so that the vehicle decelerates to the target driving speed in the target driving information after a preset time.

[0099] In one embodiment of this application, generating a vehicle deceleration control command based on target driving information includes: obtaining a deceleration threshold of the vehicle's kinetic energy recovery system; if the target deceleration is less than or equal to the deceleration threshold of the kinetic energy recovery system, calculating the kinetic energy recovery intensity based on the target deceleration; if the target deceleration is greater than the deceleration threshold of the kinetic energy recovery system, calculating the deceleration difference between the deceleration threshold of the kinetic energy recovery system and the target deceleration, and determining the mechanical braking force based on the deceleration difference; converting the calculated mechanical braking force and kinetic energy recovery intensity into control commands, and performing deceleration control on the vehicle based on the control commands to avoid collisions between the vehicle and obstacles.

[0100] In one embodiment of this application, the deceleration threshold of the kinetic energy recovery system is read from the vehicle's electronic control unit (ECU) or related sensors. Taking a deceleration threshold of 0.3g for the kinetic energy recovery system as an example, the kinetic energy recovery intensity and mechanical braking force are calculated based on the target deceleration as follows:

[0101] When the target deceleration is less than or equal to the deceleration threshold of the kinetic energy recovery system. Assume the target deceleration (e.g., 0.25g, approximately 2.45m / s²). 2 If the deceleration rate is less than or equal to the deceleration threshold of the kinetic energy recovery system (0.3g), then only the kinetic energy recovery system will be used for deceleration. Kinetic energy recovery intensity = target deceleration / deceleration threshold of the kinetic energy recovery system * 100%. For example, kinetic energy recovery intensity = 0.25g / 0.3g * 100% ≈ 83.33%.

[0102] When the target deceleration exceeds the deceleration threshold of the kinetic energy recovery system. Assume the target deceleration (e.g., 0.4g, approximately 3.92 m / s²). 2 If the deceleration exceeds the deceleration threshold of the kinetic energy recovery system (0.3g), then a combination of the kinetic energy recovery system and mechanical braking is needed to achieve the target deceleration. Therefore, the calculated deceleration difference is: Deceleration Difference = Target Deceleration - Deceleration Threshold of the Kinetic Energy Recovery System (0.1g). Thus, the mechanical braking force = Deceleration Difference / Deceleration Threshold of the Mechanical Brake * 100%. Assuming the deceleration threshold of the mechanical brake is 0.5g (approximately 4.9m / s²),... 2 If the mechanical braking force is 0.1g / 0.5g * 100% = 20%.

[0103] Finally, the calculated mechanical braking force and kinetic energy recovery intensity are converted into specific control commands. For example, if the kinetic energy recovery intensity is 83.33%, a corresponding kinetic energy recovery system control command is generated; if the mechanical braking force is 20%, a corresponding mechanical braking control command is generated. The ECU then sends the generated control commands to the kinetic energy recovery system and the mechanical braking system. The kinetic energy recovery system adjusts its intensity according to the control commands to achieve the required deceleration, while the mechanical braking system adjusts its braking force to supplement the target deceleration that the kinetic energy recovery system cannot achieve. Furthermore, the system continuously monitors the actual deceleration effect and dynamically adjusts the control commands based on the actual situation to ensure the vehicle smoothly decelerates to the target speed, avoiding collisions with obstacles.

[0104] It should be noted that through the above steps, the vehicle system can generate precise vehicle deceleration control commands based on the target driving information, and by making reasonable use of the kinetic energy recovery system and the mechanical braking system, ensure that the vehicle decelerates smoothly within a safe time, thereby improving driving safety and comfort.

[0105] In one embodiment of this application, after controlling the intensity of the vehicle's kinetic energy recovery system and / or the force of the mechanical brake according to the vehicle deceleration control command, the method further includes at least one of the following: real-time monitoring of the actual deceleration of the vehicle, including at least changes in vehicle speed, acceleration, and the response of the braking system; dynamically adjusting the braking force and / or kinetic energy recovery intensity based on the difference between the monitored actual deceleration and the expected deceleration target to ensure that the actual deceleration process conforms to the expected deceleration curve; continuously evaluating changes in driving environment information during deceleration, such as changes in the position of obstacles ahead or sudden changes in road conditions, and dynamically adjusting the deceleration strategy according to the changes to ensure driving safety; and recording data throughout the deceleration process, including the issued deceleration control command, the actual deceleration effect, and any adjustment measures, to optimize the vehicle driving information determination model after the vehicle reaches the preset target speed or comes to a complete stop.

[0106] In one embodiment of this application, when the decision algorithm determines that action is required, the intelligent braking system precisely adjusts the operating state of the kinetic energy recovery system through the execution unit. This may include increasing or decreasing the intensity of kinetic energy recovery to achieve fine control of vehicle speed. When necessary, the system may also trigger mechanical braking to ensure driving safety. To enhance the driver's perception of the system status, the intelligent braking system provides real-time feedback through the user interface. This includes information such as the current intensity of kinetic energy recovery, braking status, predicted driving conditions, and potential risks. Through this feedback, the driver can more intuitively understand the system's operating status and intervene manually when necessary. Furthermore, when the vehicle stops and the ignition switch is turned off, the intelligent braking system automatically executes a shutdown procedure. During this process, the system saves its current state and data for quick restoration upon the next startup. Subsequently, the system enters a dormant state to reduce energy consumption and extend the equipment's lifespan.

[0107] Figure 4 This is a schematic diagram of the overall scheme of a vehicle deceleration control method shown in an exemplary embodiment of this application.

[0108] like Figure 4 As shown, in the overall process of the vehicle deceleration control method, the current driving information and driving environment information of the vehicle are first acquired. Based on the current driving information and driving environment information, the road traffic status for a certain future stage is predicted, and the prediction result is either a smooth state or a blocked state. If the traffic status of the road ahead is blocked, the deceleration is further calculated to obtain the corresponding target deceleration. If the target deceleration is greater than the deceleration threshold of the vehicle's kinetic energy recovery system, the intensity of the kinetic energy recovery system and the force of the mechanical brakes are controlled to achieve vehicle deceleration. If the target deceleration is not greater than the deceleration threshold of the vehicle's kinetic energy recovery system, the intensity of the kinetic energy recovery system is directly controlled to achieve vehicle deceleration. The deceleration threshold of the kinetic energy recovery system is a preset value, and its value varies depending on the kinetic energy recovery system and the vehicle's driving mode. Therefore, this application does not impose any limitations on the method or specific value of the deceleration threshold of the recovery system.

[0109] In one embodiment of this application, a machine learning model (such as the Deep Deterministic Policy Gradient (DDPG) algorithm) is used to predict the road traffic status at a certain future stage (e.g., 30 seconds later) based on current driving information and driving environment information. The prediction result can be either a smooth traffic flow or an obstructed traffic flow. For example, if the prediction shows a stationary vehicle 100 meters ahead, resulting in an obstructed traffic flow, the distance between the vehicle and the obstacle is calculated based on the current position and the obstacle's position. The estimated collision time is then calculated based on the distance, the obstacle's speed, and the current driving speed, thus obtaining the corresponding deceleration requirement and the target deceleration. If the target deceleration is greater than the maximum deceleration of the kinetic energy recovery system, the kinetic energy recovery system and mechanical braking are combined to achieve the target deceleration. This involves calculating the maximum deceleration that the kinetic energy recovery system can provide, and then calculating the force of the mechanical braking based on the difference in deceleration.

[0110] It should be noted that the vehicle deceleration control method proposed in this application provides an advanced method that significantly improves energy efficiency by dynamically adjusting the regenerative braking intensity and the use of mechanical brakes. In different driving scenarios, the system can maximize energy recovery, especially during downhill driving and sharp turns, converting more kinetic energy into electrical energy for storage, thereby extending the battery's driving range. Furthermore, in safe, straight, and obstacle-free conditions, the system can adjust the regenerative braking intensity to a low level, providing a driving experience close to that of a traditional gasoline vehicle, increasing driving comfort. This method also significantly enhances driving safety. In congested traffic or while waiting at traffic lights, the system can dynamically adjust the resistance of the brake and accelerator pedals based on the distance to the vehicle in front and the waiting position, avoiding the risk of collisions caused by the rapid acceleration of the electric vehicle. Simultaneously, by intelligently adjusting regenerative braking, reliance on the traditional braking system is reduced, thereby reducing brake system wear, extending its service life, and consequently reducing long-term maintenance and replacement costs. This not only saves economic costs but also further improves energy efficiency and reduces energy consumption. In addition, the intelligent system possesses high real-time performance and responsiveness, capable of quickly identifying driving situations and reacting accordingly, ensuring driving safety. The automatic braking and acceleration system reduces the driver's workload in complex driving environments, lowers driving stress, and makes driving easier and safer. In summary, the method of this application not only improves energy efficiency and driving experience but also enhances driving safety and system durability, demonstrating significant comprehensive benefits.

[0111] Figure 5 This is a block diagram illustrating a vehicle deceleration control device according to an exemplary embodiment of this application. The device can be applied to… Figure 1The implementation environment shown is illustrated. This device can also be applied to other exemplary implementation environments and specifically configured in other devices. This embodiment does not limit the implementation environment to which the device is applicable.

[0112] like Figure 5 As shown, the exemplary vehicle deceleration control device includes: an information acquisition module 510, a target driving information generation module 520, and a deceleration control module 530.

[0113] The information acquisition module 510 is used to acquire the vehicle's current driving information and driving environment information. The current driving information is parameter information describing the vehicle's motion state, and the driving environment information is information about the driving scenario in which the vehicle is located. The target driving information generation module 520 is used to predict the vehicle's expected road traffic behavior within a preset time period based on the current driving information and driving environment information. If the expected road traffic behavior includes vehicle deceleration, the target driving information for the vehicle within the preset time period is determined based on the current driving information and driving environment information. The target driving information is parameter information describing the vehicle's future motion state. The deceleration control module 530 is used to generate a vehicle deceleration control command based on the target driving information, and control the intensity of the vehicle's kinetic energy recovery system and / or the force of the mechanical brakes according to the vehicle deceleration control command, so that the vehicle decelerates to the target driving speed in the target driving information after a preset time.

[0114] It should be noted that the vehicle deceleration control device and the vehicle deceleration control method provided in the above embodiments belong to the same concept. The specific operation methods of each module and unit have been described in detail in the method embodiments and will not be repeated here. In practical applications, the vehicle deceleration control device provided in the above embodiments can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. This is not a limitation here.

[0115] Embodiments of this application also provide an electronic device, including: one or more processors; and a storage device for storing one or more programs, which, when executed by the one or more processors, cause the electronic device to implement the vehicle deceleration control method provided in the above embodiments.

[0116] Figure 6 A schematic diagram of a computer system suitable for implementing the embodiments of this application is shown. It should be noted that... Figure 6 The computer system 600 of the electronic device shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments of this application.

[0117] like Figure 6 As shown, the computer system 600 includes a Central Processing Unit (CPU) 601, which can perform various appropriate actions and processes based on programs stored in Read-Only Memory (ROM) 602 or programs loaded from Storage Unit 608 into Random Access Memory (RAM) 603, such as performing the methods described in the above embodiments. The RAM 603 also stores various programs and data required for system operation. The CPU 601, ROM 602, and RAM 603 are interconnected via a bus 604. An Input / Output (I / O) interface 605 is also connected to the bus 604.

[0118] The following components are connected to I / O interface 605: an input section 606 including a keyboard, mouse, etc.; an output section 607 including a cathode ray tube (CRT), liquid crystal display (LCD), etc., and speakers, etc.; a storage section 608 including a hard disk, etc.; and a communication section 609 including a network interface card such as a LAN (Local Area Network) card, modem, etc. The communication section 609 performs communication processing via a network such as the Internet. A drive 610 is also connected to I / O interface 605 as needed. A removable medium 611, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., is installed on drive 610 as needed so that computer programs read from it can be installed into storage section 608 as needed.

[0119] Specifically, according to embodiments of this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program including a computer program for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication section 609, and / or installed from removable medium 611. When the computer program is executed by central processing unit (CPU) 601, it performs various functions defined in the system of this application.

[0120] It should be noted that the computer-readable medium shown in the embodiments of this application can be a computer-readable signal medium or a computer-readable storage medium, or any combination of the two. A computer-readable storage medium can be, for example, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), flash memory, optical fiber, portable compact disc read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this application, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, carrying a computer-readable computer program. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media can also be any computer-readable medium other than computer-readable storage media, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The computer program contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to wireless, wired, etc., or any suitable combination thereof.

[0121] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. Each block in a flowchart or block diagram may represent a module, segment, or portion of code, which contains one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram or flowchart, and combinations of blocks in a block diagram or flowchart, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0122] The units described in the embodiments of this application can be implemented in software or hardware, and the described units can also be located in a processor. The names of these units do not necessarily limit the specific unit itself.

[0123] Another aspect of this application provides a computer-readable storage medium storing a computer program thereon, which, when executed by a computer's processor, causes the computer to perform the vehicle deceleration control method as described above. This computer-readable storage medium may be included in the electronic device described in the above embodiments, or it may exist independently and not incorporated into the electronic device.

[0124] Another aspect of this application provides a computer program product or computer program including computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform the vehicle deceleration control method provided in the various embodiments described above.

[0125] The above embodiments are merely illustrative of the principles and effects of this application and are not intended to limit this application. Any person skilled in the art can modify or alter the above embodiments without departing from the spirit and scope of this application. Therefore, all equivalent modifications or alterations made by those skilled in the art without departing from the spirit and technical concept disclosed in this application should still be covered by the claims of this application.

Claims

1. A vehicle deceleration control method, characterized in that, The method includes: The vehicle's current driving information and driving environment information are obtained. The current driving information is parameter information used to describe the vehicle's current motion state, and the driving environment information is information about the driving scenario in which the vehicle is located. Based on the current driving information and the driving environment information, the expected road traffic behavior of the vehicle within a preset future time period is predicted. If the expected road traffic behavior includes vehicle deceleration, then the target driving information of the vehicle within the preset future time period is determined based on the current driving information and the driving environment information. The target driving information is parameter information used to describe the future motion state of the vehicle. Determining the target driving information of the vehicle within the preset future time period based on the current driving information and the driving environment information includes: using the current driving information and the driving environment information as input information; inputting the input information into a trained vehicle driving information determination model to obtain the output result of the vehicle driving information determination model, and determining the output result as the target driving information. The vehicle driving information determination model includes: a driving state prediction sub-model, used to predict the expected road traffic behavior of the vehicle within a preset future time period based on the current driving information and the driving environment information; and a driving information generation sub-model, used to determine the target driving information of the vehicle within the preset future time period based on the current driving information, the driving environment information, and the output of the driving state prediction sub-model. Based on the target driving information, a vehicle deceleration control command is generated, and the intensity of the vehicle's kinetic energy recovery system and / or the force of the mechanical brakes are controlled according to the vehicle deceleration control command. The actual deceleration of the vehicle and changes in the driving environment information are monitored in real time, and the deceleration control command is dynamically adjusted so that the vehicle decelerates to the target driving speed in the target driving information after a preset time.

2. The vehicle deceleration control method according to claim 1, characterized in that, Predicting vehicle road traffic behavior within a preset time period based on the current driving information and the driving environment information includes: Based on the current driving speed and the current position of the vehicle, predict the target position of the vehicle after a preset time, wherein the current position is obtained based on the current driving information; Identify the road traffic status of the interval road segment between the current location and the target location, wherein the road traffic status includes at least a smooth state and a blocked state; If the road traffic condition is unobstructed, the driving behavior of a vehicle passing through the interval section does not include deceleration; if the road traffic condition is obstructed, the driving behavior of a vehicle passing through the interval section includes deceleration.

3. The vehicle deceleration control method according to claim 1, characterized in that, The target driving information includes the target speed and the target deceleration. Determine the target driving information for the vehicle within a preset future time period, including: Based on the environmental information, obstacles between the current location and the target location are identified, and the position and velocity of each obstacle are recorded; wherein, the obstacles include dynamic obstacles and stationary obstacles; The distance between the vehicle and each obstacle is calculated based on the vehicle's current position and the positions of each obstacle. Based on the distance between the vehicle and each obstacle, the speed of the obstacle, and the current driving speed, the estimated collision time between the vehicle and each obstacle is calculated. If the estimated collision time is less than a preset safe time threshold, the target speed is calculated based on the current speed and the interval distance to ensure that the vehicle stops before reaching the obstacle; Based on the current speed and the target speed, calculate the target deceleration that will reduce the vehicle to the target speed.

4. The vehicle deceleration control method according to claim 3, characterized in that, Based on the target driving information, a vehicle deceleration control command is generated, including: Obtain the deceleration threshold of the vehicle's kinetic energy recovery system; If the target deceleration is less than or equal to the deceleration threshold of the kinetic energy recovery system, then the kinetic energy recovery intensity is calculated based on the target deceleration; If the target deceleration is greater than the deceleration threshold of the kinetic energy recovery system, then the deceleration difference between the deceleration threshold of the kinetic energy recovery system and the target deceleration is calculated, and the mechanical braking force is determined based on the deceleration difference. The calculated mechanical braking force and kinetic energy recovery intensity are converted into control commands, and the vehicle is decelerated based on the control commands to avoid collisions with obstacles.

5. The vehicle deceleration control method according to claim 1, characterized in that, The method further includes: An initial neural network model is constructed, which is based on a preset machine learning algorithm; The initial neural network model is trained based on historical driving information and corresponding driving environment information to generate a vehicle driving information determination model. The current driving information is input into the vehicle driving information determination model to predict the road conditions of the vehicle in the future within a preset time period; Based on the predicted road conditions, corresponding target driving information is generated, which includes at least target speed and target deceleration. Gradually adjust the force of the mechanical brakes and the intensity of the kinetic energy recovery system to smoothly transition the vehicle from the current driving state to the driving state indicated by the target driving information.

6. The vehicle deceleration control method according to any one of claims 1-5, characterized in that, After controlling the intensity of the vehicle's kinetic energy recovery system and / or the force of the mechanical braking according to the vehicle deceleration control command, it also includes at least one of the following: The system monitors the actual deceleration of the vehicle in real time, including changes in vehicle speed, acceleration, and braking system response. Based on the difference between the monitored actual deceleration and the expected deceleration target, the system dynamically adjusts the braking force and / or energy recovery intensity to ensure that the actual deceleration process conforms to the expected deceleration curve. During deceleration, continuously assess changes in driving environment information, including at least changes in the position of obstacles ahead and sudden changes in road conditions, and dynamically adjust the deceleration strategy based on these changes to ensure driving safety. Once the vehicle reaches the preset target speed or comes to a complete stop, the data from the entire deceleration process is recorded, including the deceleration control commands issued, the actual deceleration effect, and any adjustment measures, in order to optimize the vehicle driving information determination model.

7. A vehicle deceleration control device, characterized in that, The device includes: The information acquisition module is used to acquire the vehicle's current driving information and driving environment information. The current driving information is parameter information used to describe the vehicle's motion state, and the driving environment information is information about the driving scenario in which the vehicle is located. A target driving information generation module is used to predict the expected road traffic behavior of a vehicle within a preset future time period based on the current driving information and the driving environment information. If the expected road traffic behavior includes vehicle deceleration, then the target driving information of the vehicle within the preset future time period is determined based on the current driving information and the driving environment information. The target driving information is parameter information used to describe the future motion state of the vehicle. Determining the target driving information of the vehicle within the preset future time period based on the current driving information and the driving environment information includes: using the current driving information and the driving environment information as input information; inputting the input information into a trained vehicle driving information determination model to obtain the output result of the vehicle driving information determination model, and determining the output result as the target driving information. The vehicle driving information determination model includes: a driving state prediction sub-model, used to predict the expected road traffic behavior of the vehicle within a preset future time period based on the current driving information and the driving environment information; and a driving information generation sub-model, used to determine the target driving information of the vehicle within the preset future time period based on the current driving information, the driving environment information, and the output of the driving state prediction sub-model. The deceleration control module is used to generate vehicle deceleration control commands based on the target driving information, and control the intensity of the vehicle's kinetic energy recovery system and / or the force of the mechanical brakes according to the vehicle deceleration control commands. It monitors the actual deceleration of the vehicle and changes in driving environment information in real time, and dynamically adjusts the deceleration control commands so that the vehicle decelerates to the target driving speed in the target driving information after a preset time.

8. An electronic device, characterized in that, It includes a processor, a memory, and a communication bus; the communication bus is used to connect the processor and the memory; the processor is used to execute a computer program stored in the memory to implement the vehicle deceleration control method as described in any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, It stores a computer program that enables the computer to execute the vehicle deceleration control method as described in any one of claims 1-6.

Images