Predictive adaptive cruise control method, device and equipment based on driving intention of preceding vehicle and storage medium

Abstract

The invention discloses a front vehicle driving intention-based predictive adaptive cruise control method, device and equipment and a storage medium, relates to the technical field of vehicle control, and discloses a front vehicle driving intention-based predictive adaptive cruise control method, which comprises the following steps of: predicting a front vehicle potential lane changing behavior according to front vehicle chassis information; obtaining a front vehicle driving intention prediction result; a vehicle control mode is determined according to the front vehicle relative distance and / or the front vehicle driving intention prediction result, and the vehicle control mode comprises a predictive cruise control mode and a vehicle following control mode; and completing predictive adaptive cruise control according to the vehicle control mode. According to the scheme, the vehicle change condition of the front lane can be fully considered, and the safe and economical vehicle speed is planned in advance.

Description

Technical Field

[0001] The present application relates to the technical field of vehicle control, and particularly to a predictive adaptive cruise control method, device, equipment and storage medium based on the driving intention of the vehicle ahead. Background Art

[0002] With the precipitation of technology and the rapid development of the economy, the logistics transportation market and infrastructure construction of heavy trucks have achieved all-round development. And heavy trucks that develop both fuel-saving and environmental protection effects are the mainstream trend of the current industry development. Predictive Adaptive Cruise Control (PACC) has gradually become a technology pursued by vehicle manufacturers due to its high advantages in fuel saving and driving safety, and will play a significant positive role in reducing the current energy consumption.

[0003] Existing solutions utilize cloud control platform technology to realize vehicle economic speed planning by using cloud resources through data intercommunication between the vehicle end and the cloud, and then input the planning information into the vehicle end. However, PACC systems based on cloud control platforms and intelligent networking technologies all assume that the vehicle ahead is always driving in the front lane. Under actual traffic conditions, the driving conditions of the vehicle may be affected by vehicles entering and exiting the front lane, resulting in the inability to balance the safety and economy of the vehicle. Therefore, how to consider the vehicle changes in the front lane and plan a safe and economic speed has become a problem to be solved.

[0004] The above content is only used to assist in understanding the technical solution of the present application, and does not represent an admission that the above content is prior art. Summary of the Invention

[0005] The main purpose of the present application is to provide a predictive adaptive cruise control method, device, equipment and storage medium based on the driving intention of the vehicle ahead, aiming to solve the technical problem of how to consider the vehicle changes in the front lane and plan a safe and economic speed.

[0006] To achieve the above purpose, the present application proposes a predictive adaptive cruise control method based on the driving intention of the vehicle ahead, and the method includes:

[0007] Predict the potential lane-changing behavior of the vehicle ahead according to the chassis information of the vehicle ahead to obtain a prediction result of the driving intention of the vehicle ahead;

[0008] Determine the vehicle control mode according to the relative distance of the vehicle ahead and / or the prediction result of the driving intention of the vehicle ahead, wherein the vehicle control mode includes a predictive cruise control mode and a following control mode;

[0009] Complete predictive adaptive cruise control according to the vehicle control mode.

[0010] In one embodiment, the step of completing anticipatory adaptive cruise control according to the vehicle control mode includes:

[0011] When the vehicle control mode is the vehicle following control mode, determining a planning time according to the vehicle speed information of the vehicle ahead;

[0012] Determining an expected safety distance according to a first preset safety distance, the relative speed of the vehicle ahead, and the planning time;

[0013] Completing anticipatory adaptive cruise control according to the expected safety distance.

[0014] In one embodiment, the step of determining a planning time according to the vehicle speed information of the vehicle ahead when the vehicle control mode is the vehicle following control mode includes:

[0015] When the vehicle control mode is the vehicle following control mode, calculating the lane change time of the vehicle ahead according to the lane dimension information and the vehicle speed information of the vehicle ahead;

[0016] Calculating the sensor sensing time according to the sensor sensing range information and the vehicle speed information of the vehicle ahead;

[0017] Calculating a planning time according to the lane change time of the vehicle ahead and the sensor sensing time.

[0018] In one embodiment, the step of completing anticipatory adaptive cruise control according to the expected safety distance includes:

[0019] Constructing a state quantity according to the actual safety distance, the relative speed of the vehicle ahead, and the acceleration of the host vehicle;

[0020] Calculating the state deviation of the state quantity based on the expected safety distance and the actual safety distance;

[0021] Constructing an error control function based on a control quantity and the state deviation, and solving to obtain a target control quantity based on the error control function;

[0022] Completing anticipatory adaptive cruise control based on the target control quantity.

[0023] In one embodiment, the step of completing anticipatory adaptive cruise control according to the vehicle control mode includes:

[0024] When the vehicle control mode is the anticipatory cruise control mode, constructing a target fuel consumption function according to the planned vehicle speed of the road;

[0025] Solving a target speed sequence based on the target fuel consumption function;

[0026] Calculating the engine torque based on the road gradient information and the target speed sequence;

[0027] Complete anticipatory adaptive cruise control based on the engine torque.

[0028] In one embodiment, the step of determining the vehicle control mode according to the relative distance to the vehicle ahead and / or the prediction result of the driving intention of the vehicle ahead includes:

[0029] When the relative distance to the vehicle ahead is greater than or equal to the second preset safety distance, determine the vehicle control mode as the anticipatory cruise control mode;

[0030] When the relative distance to the vehicle ahead is less than the second preset safety distance and the prediction result of the driving intention of the vehicle ahead is accelerating to change lanes, determine the vehicle control mode as the anticipatory cruise control mode;

[0031] When the relative distance to the vehicle ahead is less than the second preset safety distance and the prediction result of the driving intention of the vehicle ahead is decelerating to change lanes, determine the vehicle control mode as the following vehicle control mode.

[0032] In one embodiment, the step of predicting the potential lane change behavior of the vehicle ahead based on the chassis information of the vehicle ahead to obtain the prediction result of the driving intention of the vehicle ahead includes:

[0033] Perform temporal encoding on the chassis information of the vehicle ahead to obtain a temporal feature vector;

[0034] Input the temporal feature vector into a long short-term memory network to predict the lane change intention of the vehicle ahead and the intention of the vehicle ahead to change speed;

[0035] Determine the potential lane change behavior of the vehicle ahead according to the lane change intention of the vehicle ahead and the intention of the vehicle ahead to change speed to obtain the prediction result of the driving intention of the vehicle ahead.

[0036] In addition, to achieve the above object, the present application also proposes an anticipatory adaptive cruise control device based on the driving intention of the vehicle ahead, and the anticipatory adaptive cruise control device based on the driving intention of the vehicle ahead includes:

[0037] An intention prediction module for predicting the potential lane change behavior of the vehicle ahead based on the chassis information of the vehicle ahead to obtain the prediction result of the driving intention of the vehicle ahead;

[0038] A mode switching module for determining the vehicle control mode according to the relative distance to the vehicle ahead and / or the prediction result of the driving intention of the vehicle ahead, wherein the vehicle control mode includes an anticipatory cruise control mode and a following vehicle control mode;

[0039] A vehicle control module for completing anticipatory adaptive cruise control according to the vehicle control mode.

[0040] In addition, to achieve the above object, the present application also provides a predictive adaptive cruise control device based on the driving intention of the vehicle ahead. The device includes: a memory, a processor, and a computer program stored on the memory and executable on the processor. The computer program is configured to implement the steps of the predictive adaptive cruise control method based on the driving intention of the vehicle ahead as described above.

[0041] In addition, to achieve the above object, the present application also provides a storage medium, which is a computer-readable storage medium. A computer program is stored on the storage medium. When the computer program is executed by a processor, it implements the steps of the predictive adaptive cruise control method based on the driving intention of the vehicle ahead as described above.

[0042] In addition, to achieve the above object, the present application also provides a computer program product. The computer program product includes a computer program. When the computer program is executed by a processor, it implements the steps of the predictive adaptive cruise control method based on the driving intention of the vehicle ahead as described above.

[0043] One or more technical solutions proposed by the present application have at least the following technical effects:

[0044] Predict the potential lane-changing behavior of the vehicle ahead based on the chassis information of the vehicle ahead to obtain the prediction result of the driving intention of the vehicle ahead; determine the vehicle control mode according to the relative distance of the vehicle ahead and / or the prediction result of the driving intention of the vehicle ahead, where the vehicle control mode includes a predictive cruise control mode and a following control mode; complete the predictive adaptive cruise control according to the vehicle control mode. By predicting the potential lane-changing behavior of the vehicle ahead based on the chassis information of the vehicle ahead, such as accelerating from the left lane into the own lane or decelerating from the own lane to the right lane, etc., to obtain the prediction result of the driving intention of the vehicle ahead, and determine the vehicle control mode as the predictive cruise control mode or the following control mode according to the prediction result of the driving intention of the vehicle ahead and / or the relative distance of the vehicle ahead. When the prediction result of the driving intention of the vehicle ahead and / or the relative distance of the vehicle ahead meet the conditions of the predictive cruise control, enter the predictive cruise control mode to plan the speed of the own vehicle, optimize the fuel consumption while ensuring safety; when the prediction result of the driving intention of the vehicle ahead and the relative distance of the vehicle ahead meet the conditions of the following control mode, enter the following control mode, adjust the own speed according to the safety distance requirement, and maintain a safe distance from the vehicle ahead to achieve stable following. The solution of the present application can fully consider the vehicle changes in the front lane and plan a safe and economical vehicle speed in advance. Description of the Drawings

[0045] The drawings here are incorporated into the specification and form a part of this specification, showing embodiments consistent with the present application, and are used together with the specification to explain the principles of the present application.

[0046] To more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, for those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0047] Figure 1 FIG. 4 is a schematic flowchart provided for the first embodiment of the anticipatory adaptive cruise control method based on the driving intention of the vehicle ahead in the present application;

[0048] Figure 2 FIG. 8 is a prediction flowchart of a long short-term memory network provided for the first embodiment of the anticipatory adaptive cruise control method based on the driving intention of the vehicle ahead in the present application;

[0049] Figure 3 FIG. 12 is a schematic diagram of the structure of a long short-term memory network unit provided for the first embodiment of the anticipatory adaptive cruise control method based on the driving intention of the vehicle ahead in the present application;

[0050] Figure 4 FIG. 16 is a schematic flowchart provided for the second embodiment of the anticipatory adaptive cruise control method based on the driving intention of the vehicle ahead in the present application;

[0051] Figure 5 FIG. 20 is a schematic diagram of the scenario where the vehicle ahead changes lanes provided for the second embodiment of the anticipatory adaptive cruise control method based on the driving intention of the vehicle ahead in the present application;

[0052] Figure 6 FIG. 24 is a brief schematic flowchart of the anticipatory adaptive cruise control method based on the driving intention of the vehicle ahead provided for the second embodiment of the present application;

[0053] Figure 7 FIG. 28 is a schematic diagram of the module structure of the anticipatory adaptive cruise control device based on the driving intention of the vehicle ahead according to the embodiment of the present application;

[0054] Figure 8 FIG. 32 is a schematic diagram of the device structure of the hardware operating environment involved in the anticipatory adaptive cruise control method based on the driving intention of the vehicle ahead in the embodiment of the present application.

[0055] The implementation, functional features and advantages of the present application will be further described with reference to the embodiments and the drawings. Detailed Embodiments

[0056] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application and are not used to limit the present application.

[0057] To better understand the technical solutions of the present application, the following will be described in detail in combination with the drawings in the specification and the specific embodiments.

[0058] The main solution of the embodiment of the present application is: a predictive adaptive cruise control method based on the driving intention of the vehicle ahead, including: predicting the potential lane-changing behavior of the vehicle ahead according to the chassis information of the vehicle ahead to obtain the prediction result of the driving intention of the vehicle ahead; determining the vehicle control mode according to the relative distance of the vehicle ahead and / or the prediction result of the driving intention of the vehicle ahead, wherein the vehicle control mode includes a predictive cruise control mode and a following control mode; and completing the predictive adaptive cruise control according to the vehicle control mode.

[0059] In this embodiment, for the convenience of description, the following will be described with the vehicle end as the execution subject.

[0060] Since the existing solution uses the cloud control platform technology to realize the vehicle economic speed planning by using the cloud resources through the data intercommunication between the vehicle end and the cloud, and then inputs the planning information into the vehicle end. However, the predictive adaptive cruise control (PACC) systems based on the cloud control platform and intelligent networking technology all assume that the vehicle ahead always drives in the front lane. Under actual traffic conditions, the driving condition of the vehicle may be affected by the vehicles driving in and out of the front lane, resulting in the inability to balance the safety and economy of the vehicle. Therefore, how to consider the vehicle changes in the front lane and plan a safe and economic vehicle speed has become a problem to be solved.

[0061] The present application provides a solution. By predicting the potential lane-changing behavior of the vehicle ahead according to the chassis information of the vehicle ahead, such as accelerating from the left lane into the own lane or decelerating from the own lane to the right lane, etc., to obtain the prediction result of the driving intention of the vehicle ahead, and determining the vehicle control mode as the predictive cruise control mode or the following control mode according to the prediction result of the driving intention of the vehicle ahead and / or the relative distance of the vehicle ahead. When the prediction result of the driving intention of the vehicle ahead and / or the relative distance of the vehicle ahead meet the conditions of the predictive cruise control, enter the predictive cruise control mode to plan the vehicle speed of the own vehicle, optimize the fuel consumption while ensuring safety; when the prediction result of the driving intention of the vehicle ahead and the relative distance of the vehicle ahead meet the conditions of the following control mode, enter the following control mode, adjust the own speed according to the safety distance requirement, and keep a safe distance from the vehicle ahead to achieve stable following. The solution of the present application can fully consider the vehicle changes in the front lane and plan a safe and economic vehicle speed in advance.

[0062] It should be noted that the execution subject of this embodiment can be a computing service device with data processing, network communication, and program running functions, such as a tablet computer, a personal computer, a mobile phone, etc., or an electronic device, a vehicle end, etc. that can implement the above functions. Hereinafter, the vehicle end will be taken as an example to describe this embodiment and the following embodiments.

[0063] Based on this, the embodiments of the present application provide a predictive adaptive cruise control method based on the driving intention of the vehicle ahead. Refer to Figure 1 , Figure 1 which is a schematic flowchart of the first embodiment of the predictive adaptive cruise control method based on the driving intention of the vehicle ahead in the present application.

[0064] In this embodiment, the predictive adaptive cruise control method based on the driving intention of the vehicle ahead includes steps S10 to S30:

[0065] Step S10, predicting the potential lane-changing behavior of the vehicle ahead according to the chassis information of the vehicle ahead to obtain the prediction result of the driving intention of the vehicle ahead;

[0066] It should be noted that predictive adaptive cruise control (PACC) is an automotive driving assistance technology. Based on traditional adaptive cruise control (ACC), it can combine road information, traffic conditions, and vehicle status, and optimize the vehicle speed and following strategy through prediction algorithms. However, existing PACC systems based on cloud control platforms and intelligent networking technologies all assume that the vehicle ahead always drives in the front lane, without considering the lateral movement of the vehicle ahead, and cannot respond in time to the working conditions where the vehicle ahead suddenly enters or exits the front lane.

[0067] It should be understood that different sensors (such as millimeter-wave radar, lidar, etc.) can be used in the environment perception layer to detect the surrounding environment and identify whether there are other vehicles in front of the host vehicle. When it is detected that there are other vehicles in front of the host vehicle, relevant information of the vehicle ahead can be captured in real time. For example, through vehicle networking technology, the chassis information of the vehicle ahead can be obtained, including vehicle speed, acceleration, brake pedal position, throttle pedal position, throttle pedal speed, steering wheel angle, and steering wheel angular velocity, etc., to obtain the chassis information of the vehicle ahead. The chassis information of the vehicle ahead reflects the driving state and driving intention of the vehicle ahead, and can provide a data basis for predicting the potential lane-changing behavior of the vehicle ahead. For example, if it is detected according to the chassis information of the vehicle ahead that the steering wheel angle of the vehicle ahead gradually turns to the left and there is no vehicle or the vehicle distance is appropriate in the left lane, it may be predicted that the vehicle ahead has a left lane-changing intention.

[0068] It should be noted that the leading vehicle can be the vehicle in front in the same lane as the host vehicle (i.e., the host vehicle's lane), or the vehicle in front in an adjacent lane (left lane or right lane) of the host vehicle. By inputting the chassis information of the leading vehicle into a pre-trained time series network model, the potential lane-changing behavior of the leading vehicle can be predicted to obtain the prediction result of the driving intention of the leading vehicle. Specifically, the potential lane-changing behavior of the leading vehicle includes accelerating from the left lane into the host vehicle's lane, accelerating from the right lane into the host vehicle's lane, accelerating out of the host vehicle's lane into the left lane, accelerating out of the host vehicle's lane into the right lane, decelerating from the left lane into the host vehicle's lane, decelerating from the right lane into the host vehicle's lane, decelerating out of the host vehicle's lane into the left lane, and decelerating out of the host vehicle's lane into the right lane.

[0069] In addition, it should be noted that if it is detected according to the chassis information of the leading vehicle that the leading vehicle has no intention of changing lanes, the prediction result of the driving intention of the leading vehicle will not be output, but the detection and update of the chassis information of the leading vehicle will continue.

[0070] In a feasible implementation manner, step S10 may include steps S11 to S13:

[0071] Step S11, performing time series encoding on the chassis information of the leading vehicle to obtain a time series feature vector;

[0072] It should be understood that the chassis information of the leading vehicle has the characteristic of continuous dynamic change in time. By performing time series encoding on the chassis information of the leading vehicle collected in real time, it can be converted into a time series feature vector that can reflect its time series change law.

[0073] It should be noted that during the process of time series encoding, preliminary preprocessing will be performed on the collected chassis information of the leading vehicle, including removing noise points and filling in missing values, to ensure the accuracy and integrity of the data. For example, the sliding average method is used to remove noise points, and the linear interpolation method is used to fill in missing values to obtain a continuous and relatively accurate chassis information sequence of the leading vehicle. The preprocessed chassis information sequence of the leading vehicle is divided into several time series windows, each time series window contains a fixed number of time steps (such as 10 time steps, corresponding to a 1-second time window), and the data within each time series window is used as an independent sample for subsequent feature extraction and encoding.

[0074] Further, for the data within each time series window, feature engineering can be performed on the leading vehicle's chassis information to extract preliminary features. Specifically, calculate the mean, variance, maximum value, minimum value of each parameter of the leading vehicle's chassis information within each time step, as well as the change rate of each parameter between adjacent time steps, to obtain preliminary features. Arrange the preliminary feature vectors within each time series window in the order of time steps to form a two-dimensional matrix, where the rows represent time steps and the columns represent different feature dimensions. According to the requirements of the pre-trained time series network model, necessary dimension adjustments are made to the matrix, such as adding a batch dimension, etc., to obtain the time series feature vector.

[0075] Step S12, input the time series feature vector into a long short-term memory network to predict the leading vehicle's lane change intention and the leading vehicle's speed change intention;

[0076] It should be noted that in this solution, a pre-trained long short-term memory network (LSTM) can be selected as the target time series network model to predict the leading vehicle's potential lane change behavior based on the leading vehicle's chassis information. LSTM is a special type of recurrent neural network (RNN) used to solve the problems of gradient disappearance and gradient explosion encountered by traditional RNNs when dealing with long time series. LSTM controls the flow of information by introducing a gating mechanism, enabling the network to better remember long-term dependency information. Specifically, input the time series feature vector obtained after processing the leading vehicle's chassis information into the pre-trained LSTM, and the leading vehicle's lane change intention (including entering the host vehicle's lane from the left lane, entering the host vehicle's lane from the right lane, exiting the host vehicle's lane to the left lane, and exiting the host vehicle's lane to the right lane) and the leading vehicle's speed change intention (accelerating or decelerating) can be obtained.

[0077] Exemplarily, referring to Figure 2 , Figure 2 is the long short-term memory network prediction flowchart provided for the first embodiment of the anticipatory adaptive cruise control method based on the leading vehicle's driving intention in this application. As Figure 2 shown, for the input leading vehicle's chassis information, the vehicle speed, acceleration, brake pedal position, throttle pedal position, throttle pedal speed, steering wheel angular velocity, and brake acceleration are respectively marked as the first feature the second feature the third feature the fourth feature the fifth feature the sixth feature and the seventh feature Perform time series encoding on the first feature, the second feature, the third feature, the fourth feature, the fifth feature, the sixth feature, and the seventh feature to obtain the time series feature vector X t, the sequential feature vector X t is used as the input vector. After being processed by the target time series network model LSTM, it passes through the output gate o t to obtain the prediction result including the intention of the leading vehicle to change lanes and the intention of the leading vehicle to change speed.

[0078] Exemplarily, referring to Figure 3 , Figure 3 is the schematic structural diagram of the long short-term memory network unit provided in the first embodiment of the predictive adaptive cruise control method based on the driving intention of the leading vehicle in this application. As Figure 3 shown, LSTM is composed of a threshold and a memory cell. C t represents the information of the storage unit at time t, and C t-1 represents the information of the storage unit at time t - 1. is the candidate memory cell information, representing the new memory information at the current moment. h t represents the output information of the hidden layer at time t, and h t-1 represents the output information of the hidden layer at time t - 1. f t represents the forget gate, which is used to determine how much information in C t-1 is forgotten. i t represents the input gate, which is used to obtain the importance of the input information at time t. O t represents the output gate, which is used to obtain the importance of the output information at time t. σ and tanh are activation functions, which are used to introduce non-linear characteristics. Among them, σ is the sigmoid function, which can map the input to between 0 and 1, and tanh is the hyperbolic tangent function, which can map the input to between -1 and 1. x t is the input vector at time t, representing the sequential feature vector obtained by performing sequential encoding on the chassis information of the leading vehicle. y t is the output vector at time t, representing the predicted probability distribution of the intention of the leading vehicle to change lanes and the intention of the leading vehicle to change speed. The output expression of the memory cell of the LSTM unit is as follows:

[0079] i t =σ i (X t W ix +O t-1 W io +b i )

[0080] o t =σ o (X t W ox +O t-1 W oo +b o )

[0081] f t =σf (X t W fx +O t-1 W fo +b f )

[0082]

[0083] In the formula, X t represents the input vector at time t, and this input vector is a time-series feature vector containing the information of the chassis of the vehicle in front. W ix is the input weight matrix corresponding to the input gate, indicating the influence of the current input X t on the input gate i t ; W ox is the input weight matrix corresponding to the output gate, indicating the influence of the current input X t on the output gate O t ; W fx is the input weight matrix corresponding to the forget gate, indicating the influence of the current input X t on the forget gate f t ; W cx is the input weight matrix of the candidate memory cell, indicating the influence of the current input X t on the candidate memory content (candidate C t ). W io is the hidden state weight matrix corresponding to the input gate, indicating the influence of the output O t-1 at the previous moment on the input gate i t ; W oo is the hidden state weight matrix corresponding to the output gate, indicating the influence of the output O t-1 at the previous moment on the output gate O t ; W fo is the input weight matrix corresponding to the forget gate, indicating the influence of the output O t-1 at the previous moment on the forget gate f t ; W co is the hidden state weight matrix of the candidate memory cell, indicating the influence of the output O t-1 at the previous moment on the candidate memory content. b i , b o , b f , b c respectively represent the bias vectors of the input gate, output gate, forget gate, and candidate memory cell. σ i , σ o , σ f respectively represent the activation functions of the input gate, output gate, and forget gate, which are sigmoid functions, and σ(x) is the expression of the sigmoid function. tanh represents the activation function of the candidate memory cell, which is the hyperbolic tangent function.

[0084] Step S13: Determine the potential lane-changing behavior of the leading vehicle based on the leading vehicle's lane-changing intention and speed change intention, and obtain the prediction result of the leading vehicle's driving intention.

[0085] It should be understood that based on the prediction results of the combination (including driving into the host vehicle's lane from the left lane, driving into the host vehicle's lane from the right lane, driving out of the host vehicle's lane to the left lane, and driving out of the host vehicle's lane to the right lane) and the leading vehicle's speed change intention (accelerating or decelerating), the potential lane-changing behavior of the leading vehicle can be determined in one step to obtain the prediction result of the leading vehicle's driving intention. Specifically, different potential lane-changing behaviors of the leading vehicle can be marked with corresponding prediction results of the leading vehicle's driving intention to obtain the marking information of eight potential lane-changing behaviors, namely, accelerating into the host vehicle's lane from the left lane (LIU), accelerating into the host vehicle's lane from the right lane (RIU), accelerating out of the host vehicle's lane to the left lane (LLU), accelerating out of the host vehicle's lane to the right lane (RLU), decelerating into the host vehicle's lane from the left lane (LID), decelerating into the host vehicle's lane from the right lane (RID), decelerating out of the host vehicle's lane to the left lane (LLD), and decelerating out of the host vehicle's lane to the right lane (RLD). The expression of the set I of the prediction results of the leading vehicle's driving intention is as follows:

[0086] I = [LIU, RIU, LLU, RLU, LID, RID, LLD, RLD]

[0087] Step S20: Determine the vehicle control mode based on the relative distance of the leading vehicle and / or the prediction result of the leading vehicle's driving intention, where the vehicle control mode includes a predictive cruise control mode and a following control mode;

[0088] It should be understood that the relative distance of the leading vehicle is the real-time distance between the host vehicle and the leading vehicle, which can be measured by on-vehicle sensors (such as millimeter-wave radar, lidar, etc.). When the relative distance of the leading vehicle is large (such as greater than the preset safety distance), the immediate impact of the leading vehicle on the driving safety of the host vehicle is small. When the relative distance of the leading vehicle is small (such as less than the preset safety distance), sudden operations of the leading vehicle such as sudden braking and sudden lane-changing will immediately pose a direct safety threat to the host vehicle.

[0089] In addition, it should be understood that in the predictive cruise control mode, the speed, engine torque, and acceleration of the host vehicle will be reasonably planned and controlled according to the road information to achieve the purpose of energy conservation. In the following control mode, the speed, engine torque, and acceleration of the host vehicle will be reasonably planned and controlled according to the driving state of the leading vehicle and the safety distance requirement to ensure maintaining a safe distance from the leading vehicle and improve driving safety.

[0090] It should be noted that the objective function of the lower-layer control algorithm in the traditional PACC system is often determined by the relative distance to the leading vehicle. If the relative distance to the leading vehicle is small, the vehicle control mode of the host vehicle is the following control mode. When the leading vehicle suddenly enters or exits the lane, the relative distance to the leading vehicle does not change significantly at this time, and the lower-layer control algorithm fails to adjust the vehicle's behavior in time. The host vehicle will continue to maintain a non-optimal driving state in the following control mode, reducing the energy efficiency. This solution determines the vehicle control mode by combining the relative distance to the leading vehicle and / or the driving intention of the leading vehicle, and can detect the sudden entry or exit behavior (accelerating lane change or decelerating lane change) of the leading vehicle in time. When the leading vehicle suddenly changes lanes, the speed, engine torque, and acceleration of the host vehicle can be planned in advance to maintain the economy of speed planning as much as possible while ensuring the driving safety of the host vehicle.

[0091] In a feasible implementation manner, step S20 may include: when the relative distance to the leading vehicle is greater than or equal to the second preset safety distance, determining that the vehicle control mode is the predictive cruise control mode; when the relative distance to the leading vehicle is less than the second preset safety distance and the predicted result of the driving intention of the leading vehicle is accelerating lane change, determining that the vehicle control mode is the predictive cruise control mode; when the relative distance to the leading vehicle is less than the second preset safety distance and the predicted result of the driving intention of the leading vehicle is decelerating lane change, determining that the vehicle control mode is the following control mode.

[0092] It should be noted that the second preset safety distance is the maximum safety distance, which can be set according to the road traffic conditions and is used to define the switching condition between the following control mode and the predictive cruise mode. When the relative distance to the leading vehicle is greater than or equal to the maximum safety distance, it indicates that the collision risk with the leading vehicle is low, and the host vehicle has sufficient time to respond to the sudden situation of the leading vehicle, and can switch to the predictive cruise mode that pays more attention to energy conservation to reduce unnecessary acceleration and deceleration, thereby reducing fuel consumption. When the relative distance to the leading vehicle is less than the maximum safety distance, it indicates that the collision risk with the leading vehicle is high. At this time, it is necessary to combine the predicted result of the driving intention of the leading vehicle to judge whether to switch to the following control mode to avoid affecting the driving efficiency and economy of the host vehicle due to frequent switching of the vehicle control mode.

[0093] It should be understood that accelerating lane change includes four situations: accelerating from the left lane into the host vehicle lane (LIU), accelerating from the right lane into the host vehicle lane (RIU), accelerating out of the host vehicle lane to the left lane (LLU), and accelerating out of the host vehicle lane to the right lane (RLU). Decelerating lane change includes four situations: decelerating from the left lane into the host vehicle lane (LID), decelerating from the right lane into the host vehicle lane (RID), decelerating out of the host vehicle lane to the left lane (LLD), and decelerating out of the host vehicle lane to the right lane (RLD).

[0094] In addition, it should be understood that if the relative distance of the vehicle ahead is less than the maximum safe distance and the predicted result of the driving intention of the vehicle ahead is to accelerate and change lanes, it indicates that the distance between the host vehicle and the vehicle ahead will increase in the short term in the future. At this time, the host vehicle does not need to switch to the following control mode to improve driving efficiency and economy on the premise of ensuring safety. If the relative distance of the vehicle ahead is less than the maximum safe distance and the predicted result of the driving intention of the vehicle ahead is to decelerate and change lanes, it indicates that the distance between the host vehicle and the vehicle ahead will decrease in the short term in the future. At this time, the host vehicle needs to switch to the following control mode to timely adjust the speed of the host vehicle according to the deceleration situation and lane-changing dynamics of the vehicle ahead, ensure a safe distance from the vehicle ahead, avoid collision accidents and ensure the smoothness of the driving process.

[0095] Step S30, perform anticipatory adaptive cruise control according to the vehicle control mode.

[0096] It should be understood that after determining the vehicle control mode, the corresponding cruise control strategy will be executed according to different modes. In the anticipatory cruise control mode, the speed, engine torque, etc. of the vehicle will be reasonably planned and controlled based on the road gradient information to achieve the purpose of energy conservation. For example, when going uphill, the vehicle speed is appropriately reduced to reduce the engine load, and when going downhill, the gravitational potential energy is converted into kinetic energy, thereby reducing the fuel consumption during the driving of the host vehicle. In the following control mode, according to the driving state of the vehicle ahead and the safety distance requirement, the speed and acceleration of the host vehicle are adjusted to ensure a safe distance from the vehicle ahead and improve driving safety at the same time. For example, when the vehicle ahead decelerates and changes lanes, the braking force to be applied will be calculated according to the relative speed of the vehicle ahead and the relative distance of the vehicle ahead to decelerate the host vehicle and maintain a safe distance from the vehicle ahead.

[0097] In a feasible implementation manner, step S30 may include steps A11 to A14:

[0098] Step A11, when the vehicle control mode is the anticipatory cruise control mode, construct a target fuel consumption function according to the road planned speed.

[0099] It should be noted that the road planned speed is the expected speed of the host vehicle during driving within a preset driving cycle (such as one kilometer). The target fuel consumption function is an index for measuring the total fuel consumption of the vehicle within a preset driving cycle, which is used to optimize the fuel consumption performance of the host vehicle within a preset driving cycle and obtain the corresponding optimal speed sequence. The preset driving cycle is divided into multiple road segments, and the target fuel consumption function can be obtained by substituting the road planned speeds of multiple road segments into the segmented fuel consumption function and summing them. The segmented fuel consumption function is used to describe the fuel consumption situation of the host vehicle at a specific road planned speed.

[0100] It should be understood that when constructing the target fuel consumption function, engine torque limits, speed limits, and acceleration limits are set. Among them, the engine torque limit is used to constrain the power output of the vehicle during driving to avoid engine overload and unnecessary fuel waste; the speed limit is used to ensure that the vehicle travels within the range permitted by safety and regulations; the acceleration limit is used to constrain the rate of change of the vehicle speed to ensure driving smoothness and comfort.

[0101] Exemplarily, the expression formula of the target fuel consumption function J is as follows:

[0102]

[0103] In the formula, v(k+i) represents the planned road speed of the (k+i)-th road segment, a(k+i) represents the acceleration of the (k+i)-th road segment, f represents the sectional fuel consumption function of the (k+i)-th road segment, N represents the total time step, which defines the distance range of the preset driving cycle. For example, when N = 1, it means the distance range of the preset driving cycle is one kilometer.

[0104] Exemplarily, the expression formulas of the engine torque limit, speed limit, and acceleration limit are as follows:

[0105]

[0106] In the formula, T min represents the minimum allowable value of the engine torque, T max represents the maximum allowable value of the engine torque, and T(k+i) represents the engine torque of the (k+i)-th road segment. v min represents the minimum allowable value of the planned road speed, v max represents the maximum allowable value of the planned road speed, and v(k+i) represents the planned road speed of the (k+i)-th road segment. a min represents the minimum allowable value of the acceleration, a max represents the maximum allowable value of the acceleration, and a(k+i) represents the acceleration of the (k+i)-th road segment.

[0107] Step A12, solve the target speed sequence based on the target fuel consumption function;

[0108] It should be understood that by using optimization algorithms such as dynamic programming and genetic algorithms to solve the target fuel consumption function, the optimal road planned speed sequence that minimizes fuel consumption within the preset driving cycle can be obtained, and the target speed sequence is obtained. The target speed sequence is used to guide the host vehicle to drive in the most energy-efficient manner in the predictive cruise control mode. For example, when N = 1, the target speed sequence includes v(k) and v(k+1).

[0109] Step A13, calculate the engine torque based on the road slope information and the target speed sequence;

[0110] It should be understood that the road gradient information includes gradient information and gradient length information. According to the road gradient information and the target speed sequence, the engine output torque for driving the vehicle to travel or maintaining the vehicle to travel stably at the planned road speed in the target speed sequence can be calculated to obtain the engine torque. Specifically, when the vehicle is traveling on an uphill section, the engine torque is calculated according to parameters such as the gradient and the vehicle mass to overcome the ramp resistance and maintain the planned road speed. When traveling on a flat road, the engine torque is calculated according to the planned road speed and the rolling resistance of the vehicle, etc., to ensure that the vehicle can travel stably at the planned road speed and achieve energy-saving control at the same time.

[0111] Step A14, complete the anticipatory adaptive cruise control based on the engine torque.

[0112] It should be understood that according to the calculated engine torque, by adjusting control parameters such as the throttle opening and fuel injection volume of the engine, the engine can output the corresponding torque, so as to drive the host vehicle to travel according to the target speed sequence. During the whole driving process, information such as the actual speed and road gradient of the vehicle will be monitored in real time, and the target speed sequence and engine torque will be calculated in real time to dynamically adjust the driving state of the host vehicle, ensuring that the host vehicle can achieve energy-saving, stable and comfortable driving in the anticipatory cruise control mode.

[0113] In this embodiment, the potential lane-changing behavior of the leading vehicle is predicted based on the leading vehicle chassis information to obtain the prediction result of the leading vehicle driving intention; the vehicle control mode is determined according to the relative distance of the leading vehicle and / or the prediction result of the leading vehicle driving intention, wherein the vehicle control mode includes an anticipatory cruise control mode and a following control mode; the anticipatory adaptive cruise control is completed according to the vehicle control mode. By predicting the potential lane-changing behavior of the leading vehicle based on the leading vehicle chassis information, such as accelerating from the left lane into the host vehicle lane or decelerating from the host vehicle lane to the right lane, etc., the prediction result of the leading vehicle driving intention is obtained, and the vehicle control mode is determined as the anticipatory cruise control mode or the following control mode according to the prediction result of the leading vehicle driving intention and / or the relative distance of the leading vehicle. When the prediction result of the leading vehicle driving intention and / or the relative distance of the leading vehicle meet the conditions of the anticipatory cruise control, enter the anticipatory cruise control mode to plan the vehicle speed of the host vehicle, optimizing fuel consumption while ensuring safety; when the prediction result of the leading vehicle driving intention and the relative distance of the leading vehicle meet the conditions of the following control mode, enter the following control mode, adjust the own speed according to the safety distance requirement, and maintain a safe distance from the leading vehicle to achieve stable following. The solution of the present application can fully consider the vehicle changes in the front lane and plan a safe and economical vehicle speed in advance.

[0114] Based on the first embodiment of the present application, in the second embodiment of the present application, the same or similar content as the above-mentioned embodiment one can be referred to the above introduction and will not be repeated hereinafter. On this basis, please refer toFigure 4 , step S30 may include steps B11 to B13:

[0115] Step B11, when the vehicle control mode is the following vehicle control mode, determine the planning time according to the preceding vehicle speed information;

[0116] It should be noted that when the relative distance of the preceding vehicle is less than the maximum safety distance and the prediction result of the driving intention of the preceding vehicle is to decelerate and change lanes, the vehicle control mode of the host vehicle will be determined as the following vehicle control mode at this time. When it is recognized that the preceding vehicle has the intention of decelerating and changing lanes, a desired safety distance from the preceding vehicle will be planned in advance for a certain period of time to improve the safety of the following vehicle control mode. Refer to Figure 5 , Figure 5 This is a schematic diagram of the preceding vehicle lane change scenario provided for the second embodiment of the predictive adaptive cruise control method based on the driving intention of the preceding vehicle in this application. When there are vehicles entering and exiting the front lane, the PACC system can plan the future engine torque and gear in advance according to the planning time.

[0117] It should be noted that the preceding vehicle speed information is the lateral component speed of the preceding vehicle speed. The lateral speed information of the preceding vehicle can be received from the preceding vehicle through vehicle networking technology to obtain the preceding vehicle speed information. The planning time is the time to plan the host vehicle speed in advance. The time required for the preceding vehicle to complete a lane change can be calculated based on the lateral component speed of the preceding vehicle speed, and the planning time can be obtained by combining the calculated sensor sensing time.

[0118] In a feasible implementation manner, step B11 may include steps B111 to B113:

[0119] Step B111, when the vehicle control mode is the following vehicle control mode, calculate the preceding vehicle lane change time according to the lane size information and the preceding vehicle speed information;

[0120] It should be noted that the lane size information includes the lane widths of the host vehicle's lane and the adjacent lanes. The preceding vehicle lane change time is the time required for the preceding vehicle to complete a lane change, that is, the time required for the preceding vehicle to start changing lanes to completely enter the target lane.

[0121] In addition, it should be noted that when the deceleration lane change intention of the preceding vehicle is to decelerate and drive out of the host vehicle's lane to the left lane (LLD) or decelerate and drive out of the host vehicle's lane to the right lane (RLD), the preceding vehicle size information, that is, the body width of the preceding vehicle, will also be obtained, and the preceding vehicle lane change time will be calculated according to the lane size information, the preceding vehicle size information, and the preceding vehicle speed information. When the deceleration lane change intention of the preceding vehicle is to decelerate and drive into the host vehicle's lane from the left lane (LID) and decelerate and drive into the host vehicle's lane from the right lane (RID), the preceding vehicle lane change time will be calculated according to the lane size information and the preceding vehicle speed information.

[0122] Exemplarily, the preceding vehicle lane change time tc The calculation formula is as follows:

[0123]

[0124] In the formula, d road represents d veh , d veh represents the body width of the vehicle ahead, and v 0fx represents the lateral component velocity of the speed of the vehicle ahead.

[0125] Step B112: Calculate the sensor sensing time according to the sensor sensing range information and the vehicle speed information of the vehicle ahead;

[0126] It should be noted that the sensor sensing range information includes the effective detection range information of sensors such as millimeter-wave radars and lidar. Through the sensor sensing range information, the maximum distance at which the sensor can sense the lane change of the vehicle ahead, that is, the sensor sensing distance, can be determined, and then the sensor sensing time can be calculated. The sensor sensing time represents the length of time during which the sensor can continuously track the vehicle ahead from the moment it senses the intention of the vehicle ahead to change lanes until the vehicle ahead completely changes lanes to the target lane.

[0127] Exemplarily, the calculation formula for the sensor sensing time t t is as follows:

[0128]

[0129] In the formula, d t represents the sensor sensing distance, and v 0fx represents the lateral component velocity of the speed of the vehicle ahead.

[0130] Step B113: Calculate the planning time according to the lane change time of the vehicle ahead and the sensor sensing time.

[0131] It should be understood that by combining the lane change time of the vehicle ahead and the sensor sensing time, the time for the host vehicle to react in advance can be calculated to obtain the planning time.

[0132] Exemplarily, the calculation formula for the planning time t a is as follows:

[0133] t a = |t c - t t |

[0134] In the formula, t c represents the lane change time of the vehicle ahead, and t t represents the sensor sensing time.

[0135] Step B12: Determine the desired safety distance according to the first preset safety distance, the relative speed of the vehicle ahead, and the planning time;

[0136] It should be understood that the first preset safety distance is the minimum safety distance, which can be calculated based on the braking performance (such as the maximum deceleration) and the current speed of the host vehicle, representing the shortest distance that should be maintained between the host vehicle and the preceding vehicle to ensure that the host vehicle can brake safely in an emergency. The relative speed of the preceding vehicle is the difference between the speed of the preceding vehicle and the speed of the host vehicle, and is used to calculate the distance that the vehicle needs to maintain to avoid collision. The speed of the preceding vehicle can be obtained according to the chassis information of the preceding vehicle, and the relative speed between the preceding vehicle and the host vehicle is calculated to obtain the relative speed of the preceding vehicle. The second preset safety distance is the minimum safety distance, and the relative speed between the preceding vehicle and the host vehicle can be obtained according to the chassis information of the preceding vehicle.

[0137] It should be noted that the desired safety distance is updated in real time during the process of the host vehicle's planning. The compensation safety distance for the minimum safety distance can be calculated based on the planning time and the relative speed of the preceding vehicle, and the desired safety distance is obtained based on the compensation safety distance and the minimum safety distance, so as to avoid the distance between the host vehicle and the preceding vehicle being less than the minimum safety distance due to the deceleration of the preceding vehicle when following the preceding vehicle within the planning time.

[0138] Exemplarily, the calculation formula for the desired safety distance is as follows:

[0139] d s = t a v rel + d0

[0140] In the formula, t a represents the planning time, v rel represents the relative speed between the preceding vehicle and the host vehicle, and d0 represents the minimum safety distance.

[0141] Step B13, perform anticipatory adaptive cruise control according to the desired safety distance.

[0142] It should be understood that after obtaining the desired safety distance, the speed and acceleration of the host vehicle will be adjusted in real time according to the deviation between the actual safety distance between the host vehicle and the preceding vehicle and the desired safety distance to maintain the desired safety distance from the preceding vehicle. At the same time, considering factors such as driving comfort and energy consumption, the change in acceleration will be smoothed, and the control strategy will be dynamically adjusted according to the deviation between the actual safety distance and the desired safety distance to achieve safe, comfortable and energy-saving following cruise control.

[0143] In a feasible implementation manner, step B13 may include steps B131 to B134:

[0144] Step B131, construct a state quantity according to the actual safety distance, the relative speed of the preceding vehicle, and the acceleration of the host vehicle;

[0145] It should be noted that the actual safety distance is the distance actually maintained between the host vehicle and the leading vehicle in the following - vehicle control mode, which can be obtained by real - time measurement with sensors. The acceleration of the host vehicle is the rate of change of the speed of the host vehicle, which can be obtained through the feedback of the power system and braking system of the host vehicle. According to the actual safety distance, the relative speed of the leading vehicle, and the acceleration of the host vehicle, a state variable describing the following - vehicle state of the host vehicle can be constructed, and the state variable can be represented as a three - dimensional vector.

[0146] Exemplarily, the state variable X T has the following expression:

[0147] X T =[d r v rel a e

[0148] In the formula, d r represents the actual safety distance, v rel represents the relative speed of the leading vehicle, and a e represents the acceleration of the host vehicle.

[0149] It should be noted that when constructing the state variable, a state equation and an output equation will also be defined. Among them, the state equation is used to describe the variation law of the state variable with time in the following - vehicle control mode, and the output equation is used to convert the state vector into an output quantity to obtain the actual safety distance, which is convenient for monitoring and feedback control.

[0150] Exemplarily, the expressions of the state equation and the output equation are as follows:

[0151]

[0152] In the formula, X represents the state variable, A represents the state matrix, B represents the input matrix, C represents the output matrix, and Γ represents the external disturbance matrix. u represents the control input, which is the control input for adjusting the acceleration of the host vehicle. a f represents the external disturbance. represents the derivative of the state variable X with respect to time, that is, the rate of change of the state variable with time. Y represents the output vector, which is used to output the actual safety distance. Among them, represents the state equation, and Y = CX represents the output equation.

[0153] Exemplarily, the expressions of the state matrix A, the input matrix B, the output matrix C, and the external disturbance matrix Γ are as follows:

[0154] C = [1 0 0],

[0155] Step B132, calculate the state deviation of the state variable based on the desired safety distance and the actual safety distance; ​

[0156] It should be understood that by calculating the difference between the actual safety distance and the desired safety distance, the state deviation can be obtained. The state deviation is used to describe whether the actual safety distance between the host vehicle and the preceding vehicle deviates from the desired safety distance, providing a basis for subsequent control adjustments. Specifically, if the actual safety distance is less than the desired safety distance, the state deviation is negative, indicating that the host vehicle needs to decelerate to increase the actual safety distance; if the actual safety distance is greater than the desired safety distance, the state deviation is positive, indicating that the host vehicle needs to accelerate to reduce the actual safety distance.

[0157] Exemplarily, the expression of the state deviation e(t) is as follows:

[0158] e(t) = d s -d r

[0159] In the formula, d s represents the desired safety distance, and d r represents the actual safety distance.

[0160] Step B133: Construct an error control function based on the control quantity and the state deviation, and solve for the target control quantity based on the error control function;

[0161] It should be noted that the control quantity is used to represent the magnitude of the control input and can be the acceleration change. Based on the state deviation and the control quantity, an optimization objective function that can comprehensively consider the control error and the control quantity can be constructed to obtain the error control function. The error control function includes the state deviation and the control quantity. By minimizing the error control function through an optimization algorithm, the target control quantity that minimizes the system control error and makes the control quantity stable (such as the acceleration of the host vehicle) can be solved, which is used to adjust the driving state of the vehicle, achieving precise control of the actual safety distance while maintaining the stable driving of the vehicle.

[0162] Exemplarily, the expression of the error control function J is as follows:

[0163]

[0164] In the formula, e(t) represents the state deviation, u(t) represents the control quantity, q e represents the weighting value of the system control error, and r u represents the weighting value of the control quantity.

[0165] Step B134: Complete the anticipatory adaptive cruise control based on the target control quantity.

[0166] It should be understood that the target engine torque and gear can be solved according to the target control quantity, and the actuator operation command is sent according to the solved target engine torque and gear to change the acceleration of the host vehicle, so that the host vehicle follows the vehicle in accordance with the desired safety distance and driving state. At the same time, the actual safety distance and the state information of the vehicle ahead (the vehicle speed information of the vehicle ahead and the relative speed of the vehicle ahead) are monitored in real time, and the control decision is updated in real time to ensure the stability and safety of the following control, so as to complete the anticipatory adaptive cruise control.

[0167] In this embodiment, the planning time is determined by obtaining the vehicle speed information of the vehicle ahead in real time, and the desired safety distance is calculated based on the first preset safety distance, the relative speed of the vehicle ahead, and the planning time, so as to achieve precise distance control. At the same time, anticipatory adaptive cruise control is carried out in combination with the relative speed of the vehicle ahead and the desired safety distance to ensure driving safety and optimize fuel economy, effectively improving the driving comfort and the intelligent control level of the vehicle.

[0168] Exemplarily, in order to help understand the implementation process of the anticipatory adaptive cruise control method based on the driving intention of the vehicle ahead obtained by combining the above embodiment 1, please refer to Figure 6 , Figure 6 A brief flow schematic diagram of an anticipatory adaptive cruise control method based on the driving intention of the vehicle ahead is provided. Specifically:

[0169] The anticipatory adaptive cruise system in the solution of this application includes a vehicle-ahead perception layer, an upper-layer controller, and a lower-layer controller. Among them, the environment perception layer is used to convert the vehicle-ahead data collected by millimeter-wave radar, lidar, and vehicle networking into signals and input them into the upper-layer controller. The upper-layer controller is used to convert the input signals into control signals and output them to the lower-layer controller. The lower-layer controller is used to convert the control signals output by the upper-layer controller into action instructions and send them to the actuator, and the actuator runs according to the execution instructions. By inputting the driving information of surrounding vehicles (i.e., the chassis information of the vehicle ahead) into the pre-trained LSTM model, the driving intention of the vehicle ahead can be obtained, and the prediction result of the driving intention of the vehicle ahead can be obtained. According to the prediction result of the driving intention of the vehicle ahead, it can be judged whether the vehicle ahead enters the lane: if the lane is not changed, continue to monitor; if the lane is entered, calculate the safety distance; if the lane is exited, enter the optimal control stage. According to the safety distance calculation result or the judgment that the vehicle ahead exits the lane, the optimal control is executed. After solving the ideal engine torque and gear, the actuator operation command is sent to adjust the driving state of the vehicle.

[0170] It should be noted that the above examples are only for understanding this application and do not constitute a limitation on the anticipatory adaptive cruise control method of this application based on the driving intention of the vehicle ahead. More simple transformations in various forms based on this technical concept are within the protection scope of this application.

[0171] The present application also provides a predictive adaptive cruise control device based on the driving intention of the vehicle ahead. Please refer to Figure 7 , the predictive adaptive cruise control device based on the driving intention of the vehicle ahead includes:

[0172] An intention prediction module 10, configured to predict the potential lane-changing behavior of the vehicle ahead according to the chassis information of the vehicle ahead, and obtain a prediction result of the driving intention of the vehicle ahead;

[0173] A mode switching module 20, configured to determine a vehicle control mode according to the relative distance of the vehicle ahead and / or the prediction result of the driving intention of the vehicle ahead, wherein the vehicle control mode includes a predictive cruise control mode and a following control mode;

[0174] A vehicle control module 30, configured to complete predictive adaptive cruise control according to the vehicle control mode.

[0175] In one embodiment, the vehicle control module 30 is further configured to, when the vehicle control mode is the following control mode, determine a planning time according to the vehicle speed information of the vehicle ahead; determine an expected safety distance according to a first preset safety distance, the relative speed of the vehicle ahead, and the planning time; and complete predictive adaptive cruise control according to the expected safety distance.

[0176] In one embodiment, the vehicle control module 30 is further configured to, when the vehicle control mode is the following control mode, calculate the lane-changing time of the vehicle ahead according to the lane dimension information and the vehicle speed information of the vehicle ahead; calculate the sensor sensing time according to the sensor sensing range information and the vehicle speed information of the vehicle ahead; and calculate the planning time according to the lane-changing time of the vehicle ahead and the sensor sensing time.

[0177] In one embodiment, the vehicle control module 30 is further configured to construct a state quantity according to the actual safety distance, the relative speed of the vehicle ahead, and the acceleration of the host vehicle; calculate the state deviation of the state quantity based on the expected safety distance and the actual safety distance; construct an error control function based on a control quantity and the state deviation, and solve to obtain a target control quantity based on the error control function; and complete predictive adaptive cruise control based on the target control quantity.

[0178] In one embodiment, the vehicle control module 30 is further configured to, when the vehicle control mode is the predictive cruise control mode, construct a target fuel consumption function according to the planned vehicle speed of the road; solve a target speed sequence based on the target fuel consumption function; calculate the engine torque based on the road gradient information and the target speed sequence; and complete predictive adaptive cruise control based on the engine torque.

[0179] In one embodiment, the mode switching module 20 is further configured to determine that the vehicle control mode is the anticipatory cruise control mode when the relative distance of the vehicle ahead is greater than or equal to the second preset safety distance; determine that the vehicle control mode is the anticipatory cruise control mode when the relative distance of the vehicle ahead is less than the second preset safety distance and the predicted result of the driving intention of the vehicle ahead is to accelerate and change lanes; and determine that the vehicle control mode is the following vehicle control mode when the relative distance of the vehicle ahead is less than the second preset safety distance and the predicted result of the driving intention of the vehicle ahead is to decelerate and change lanes.

[0180] In one embodiment, the intention prediction module 10 is further configured to perform temporal encoding on the chassis information of the vehicle ahead to obtain a temporal feature vector; input the temporal feature vector into a long short-term memory network to predict the lane change intention of the vehicle ahead and the speed change intention of the vehicle ahead; and determine the potential lane change behavior of the vehicle ahead according to the lane change intention of the vehicle ahead and the speed change intention of the vehicle ahead to obtain the predicted result of the driving intention of the vehicle ahead.

[0181] The anticipatory adaptive cruise control device based on the driving intention of the vehicle ahead provided by the present application adopts the anticipatory adaptive cruise control method based on the driving intention of the vehicle ahead in the above embodiment, and can solve the technical problem of how to plan a safe and economical vehicle speed by considering the vehicle change situation in the front lane. Compared with the prior art, the beneficial effects of the anticipatory adaptive cruise control device based on the driving intention of the vehicle ahead provided by the present application are the same as those of the anticipatory adaptive cruise control method based on the driving intention of the vehicle ahead provided by the above embodiment, and other technical features in the anticipatory adaptive cruise control device based on the driving intention of the vehicle ahead are the same as the features disclosed in the method of the above embodiment, and will not be elaborated here.

[0182] The present application provides an anticipatory adaptive cruise control device based on the driving intention of the vehicle ahead. The anticipatory adaptive cruise control device based on the driving intention of the vehicle ahead includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the anticipatory adaptive cruise control method in the first embodiment above.

[0183] Refer to the following Figure 8, which shows a schematic structural diagram of a predictive adaptive cruise control device suitable for implementing the embodiment of the present application based on the driving intention of the vehicle ahead. The predictive adaptive cruise control device in the embodiment of the present application may include, but is not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions, tablet computers), PMPs (Portable Media Players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 8 The shown predictive adaptive cruise control device based on the driving intention of the vehicle ahead is merely an example and should not impose any limitations on the functions and usage scope of the embodiment of the present application.

[0184] As Figure 8 shown, the predictive adaptive cruise control device based on the driving intention of the vehicle ahead may include a processing device 1001 (such as a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to the program stored in the ROM (Read Only Memory) 1002 or the program loaded from the storage device 1003 into the RAM (Random Access Memory) 1004. In the RAM 1004, various programs and data required for the operation of the predictive adaptive cruise control device based on the driving intention of the vehicle ahead are also stored. The processing device 1001, the ROM 1002, and the RAM 1004 are connected to each other through a bus 1005. The input / output (I / O) interface 1006 is also connected to the bus. Generally, the following systems may be connected to the I / O interface 1006: an input device 1007 including, for example, a touch screen, a touchpad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; an output device 1008 including, for example, an LCD (Liquid Crystal Display), a speaker, a vibrator, etc.; a storage device 1003 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 1009. The communication device 1009 can allow the predictive adaptive cruise control device based on the driving intention of the vehicle ahead to communicate with other devices wirelessly or wiredly to exchange data. Although the figure shows a predictive adaptive cruise control device with various systems, it should be understood that it is not required to implement or have all the shown systems. More or fewer systems may be implemented or had alternatively.

[0185] In particular, according to the embodiments disclosed in the present application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, the embodiments disclosed in the present application include a computer program product that includes a computer program carried on a computer-readable medium, and the computer program includes program codes for executing the methods shown in the flowcharts. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by a processing device 1001, the above-mentioned functions defined in the methods of the embodiments disclosed in the present application are executed.

[0186] The anticipatory adaptive cruise control device based on the driving intention of the preceding vehicle provided by the present application adopts the anticipatory adaptive cruise control method based on the driving intention of the preceding vehicle in the above-mentioned embodiment, and can solve the technical problem of how to consider the vehicle changes in the front lane and plan a safe and economical vehicle speed. Compared with the prior art, the beneficial effects of the anticipatory adaptive cruise control device based on the driving intention of the preceding vehicle provided by the present application are the same as those of the anticipatory adaptive cruise control method based on the driving intention of the preceding vehicle provided in the above-mentioned embodiment, and other technical features in the anticipatory adaptive cruise control device based on the driving intention of the preceding vehicle are the same as the features disclosed in the method of the previous embodiment, and will not be elaborated herein.

[0187] It should be understood that the various parts disclosed in the present application can be implemented by hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in a suitable manner in any one or more embodiments or examples.

[0188] As described above, only the specific embodiments of the present application are provided, but the protection scope of the present application is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed in the present application, and all should be covered by the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

[0189] The present application provides a computer-readable storage medium having computer-readable program instructions (i.e., computer programs) stored thereon, and the computer-readable program instructions are used to execute the anticipatory adaptive cruise control method based on the driving intention of the preceding vehicle in the above-mentioned embodiment.

[0190] The computer-readable storage medium provided by this application can be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or components, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections with one or more wires, portable computer disks, hard disks, RAM (Random Access Memory), ROM (Read Only Memory), EPROM (Erasable Programmable Read Only Memory), or flash memory, optical fibers, CD-ROM (CD-Read Only Memory), optical storage devices, magnetic storage devices, or any suitable combination of the above. In this embodiment, the computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, device, or component. The program code contained on the computer-readable storage medium can be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination of the above.

[0191] The above computer-readable storage medium can be included in the anticipatory adaptive cruise control device based on the driving intention of the vehicle ahead; it can also exist independently and not be assembled into the anticipatory adaptive cruise control device based on the driving intention of the vehicle ahead.

[0192] The above computer-readable storage medium carries one or more programs. When the above one or more programs are executed by the anticipatory adaptive cruise control device based on the driving intention of the vehicle ahead, the anticipatory adaptive cruise control device based on the driving intention of the vehicle ahead is caused to: predict the potential lane-changing behavior of the vehicle ahead according to the chassis information of the vehicle ahead to obtain a prediction result of the driving intention of the vehicle ahead; determine the vehicle control mode according to the relative distance of the vehicle ahead and / or the prediction result of the driving intention of the vehicle ahead, where the vehicle control mode includes an anticipatory cruise control mode and a following control mode; and complete anticipatory adaptive cruise control according to the vehicle control mode.

[0193] Computer program code for performing the operations of this application can be written in one or more programming languages or combinations thereof. The above-mentioned programming languages include object-oriented programming languages such as Java, Smalltalk, C++, and also include conventional procedural programming languages such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, executed as an independent software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any kind of network, including a LAN (Local Area Network) or a WAN (Wide Area Network), or it can be connected to an external computer (for example, by connecting through the Internet using an Internet service provider).

[0194] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions, and operations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in the flowchart or block diagram may represent a module, a program segment, or a part of the code, and this module, program segment, or part of the code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than that marked in the accompanying drawings. For example, two consecutive blocks shown may actually be executed substantially in parallel, and they may sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram and / or flowchart, as well as the combination of blocks in the block diagram and / or flowchart, can be implemented by a dedicated hardware-based system for performing the specified functions or operations, or can be implemented by a combination of dedicated hardware and computer instructions.

[0195] The modules involved in the embodiments described in this application can be implemented in software or in hardware. Among them, the name of the module does not constitute a limitation to the unit itself in some cases.

[0196] The readable storage medium provided by this application is a computer-readable storage medium. The computer-readable storage medium stores computer-readable program instructions (i.e., computer programs) for performing the above-mentioned anticipatory adaptive cruise control method based on the driving intention of the vehicle in front, and can solve the technical problem of how to plan a safe and economical vehicle speed considering the vehicle changes in the front lane. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided by this application are the same as those of the anticipatory adaptive cruise control method based on the driving intention of the vehicle in front provided by the above embodiments, and will not be elaborated here.

[0197] The present application also provides a computer program product, including a computer program which, when executed by a processor, implements the steps of the above-described anticipatory adaptive cruise control method based on the driving intention of the vehicle ahead.

[0198] The computer program product provided by the present application can solve the technical problem of how to plan a safe and economical vehicle speed by considering the vehicle changes in the front lane. Compared with the prior art, the beneficial effects of the computer program product provided by the present application are the same as those of the anticipatory adaptive cruise control method based on the driving intention of the vehicle ahead provided in the above embodiments, and will not be elaborated here.

[0199] The above are only some embodiments of the present application, and thus do not limit the patent scope of the present application. Any equivalent structural transformation made under the technical concept of the present application by using the content of the specification and drawings of the present application, or any direct / indirect application in other related technical fields, is included in the patent protection scope of the present application.

Claims

1. A predictive adaptive cruise control method based on the driving intention of the preceding vehicle, characterized in that: The adaptive cruise control method based on the driving intention of the preceding vehicle comprises: Predict the potential lane-changing behavior of the preceding vehicle based on the chassis information of the preceding vehicle, and obtain the predicted result of the preceding vehicle's driving intention; Determining a vehicle control mode according to a relative distance to a preceding vehicle and / or a predicted result of a driving intention of the preceding vehicle, wherein the vehicle control mode includes a predictive cruise control mode and a following vehicle control mode; Predictive adaptive cruise control is performed according to the vehicle control mode.

2. The method according to claim 1, characterized in that The step of completing the predictive adaptive cruise control according to the vehicle control mode includes: When the vehicle control mode is the following vehicle control mode, determining the planning time according to the speed information of the preceding vehicle; Determine the expected safety distance according to the first preset safety distance, the relative speed of the preceding vehicle and the planned time; Predictive adaptive cruise control is performed according to the desired safety distance.

3. The method according to claim 2, characterized in that When the vehicle control mode is the following vehicle control mode, the step of determining the planning time according to the speed information of the preceding vehicle comprises: When the vehicle control mode is the following vehicle control mode, calculating the lane changing time of the preceding vehicle according to the lane dimension information and the preceding vehicle speed information; Calculating the sensor sensing time according to the sensor sensing range information and the vehicle speed information of the preceding vehicle; The planning time is calculated according to the lane changing time of the preceding vehicle and the sensing time of the sensor.

4. The method according to claim 2, characterized in that The step of completing the predictive adaptive cruise control according to the expected safety distance includes: Constructing a state quantity according to the actual safety distance, the relative speed of the preceding vehicle and the acceleration of the own vehicle; Calculating a state deviation of the state quantity based on the expected safety distance and the actual safety distance; Constructing an error control function based on the control amount and the state deviation, and solving the error control function to obtain a target control amount; Predictive adaptive cruise control is performed based on the target control amount.

5. The method according to claim 1, characterized in that The step of completing the predictive adaptive cruise control according to the vehicle control mode includes: When the vehicle control mode is the predictive cruise control mode, constructing a target fuel consumption function according to the road planning vehicle speed; Solving a target speed sequence based on the target fuel consumption function; calculating an engine torque based on the road gradient information and the target speed sequence; Predictive adaptive cruise control is performed based on the engine torque.

6. The method according to claim 1, characterized in that The step of determining the vehicle control mode according to the relative distance to the preceding vehicle and / or the preceding vehicle driving intention prediction result comprises: When the relative distance to the preceding vehicle is greater than or equal to a second preset safety distance, determining that the vehicle control mode is a predictive cruise control mode; When the relative distance to the preceding vehicle is less than the second preset safety distance and the preceding vehicle's driving intention prediction result is an acceleration lane change, determining that the vehicle control mode is a predictive cruise control mode; When the relative distance to the leading vehicle is less than the second preset safety distance and the predicted driving intention result of the leading vehicle is to decelerate and change lanes, the vehicle control mode is determined to be the following vehicle control mode.

7. The method according to any one of claims 1 to 6, characterized in that The step of predicting the potential lane-changing behavior of the preceding vehicle based on the chassis information of the preceding vehicle to obtain the predicted result of the preceding vehicle's driving intention comprises: Perform time series encoding on the chassis information of the preceding vehicle to obtain a time series feature vector; Inputting the time series feature vector into a long short-term memory network to predict the lane change intention and speed change intention of the preceding vehicle; The potential lane changing behavior of the preceding vehicle is determined according to the lane changing intention of the preceding vehicle and the speed changing intention of the preceding vehicle, and a prediction result of the driving intention of the preceding vehicle is obtained.

8. A predictive adaptive cruise control device based on the driving intention of the preceding vehicle, characterized in that: The device comprises: The intention prediction module is used to predict the potential lane-changing behavior of the preceding vehicle based on the chassis information of the preceding vehicle and obtain the prediction result of the preceding vehicle's driving intention; A mode switching module, used for determining a vehicle control mode according to a relative distance to a preceding vehicle and / or a predicted result of a driving intention of the preceding vehicle, wherein the vehicle control mode includes a predictive cruise control mode and a following vehicle control mode; The vehicle control module is used to perform predictive adaptive cruise control according to the vehicle control mode.

9. A predictive adaptive cruise control device based on the driving intention of the preceding vehicle, characterized in that: The device comprises: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the predictive adaptive cruise control method based on the driving intention of the preceding vehicle as described in any one of claims 1 to 7.

10. A storage medium, characterized in that: The storage medium is a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the steps of the predictive adaptive cruise control method based on the driving intention of the preceding vehicle are implemented as described in any one of claims 1 to 7.

Images