Intelligent auxiliary driving hierarchical decision method and system, electronic device and storage medium

Abstract

This invention provides a hierarchical decision-making method, system, electronic device, and storage medium for intelligent assisted driving. The method includes: acquiring the on / off signal of the vehicle's assisted driving mode; determining the assisted driving mode's working state (including active and standby) based on the driver's driving state and intentions; when the assisted driving mode is active, determining the vehicle's motion mode based on the driver's steering intentions and the vehicle's surrounding environment; determining the vehicle's driving behavior based on the determined motion mode, the vehicle's motion state, the surrounding environment, and the driver's historical following and lane-keeping preferences; making a safety prediction based on the determined driving behavior, and outputting the decision result under safety conditions that meet the safety prediction. This application ensures the safety and comfort of vehicle assisted driving while increasing driver acceptance of the intelligent assisted driving system.

Description

Technical Field

[0001] This invention belongs to the technical field of intelligent driving, and specifically relates to an intelligent assisted driving hierarchical decision-making method, system, electronic device and storage medium. Background Technology

[0002] With the increasing incidence of traffic accidents year by year, road safety, as a crucial component of modern transportation, has attracted widespread attention. Intelligent driving technology is considered a solution to improve the driving safety of intelligent vehicles. Driver assistance systems (ADAS) are the main manifestation of current intelligent driving technology, assisting drivers in controlling the vehicle to a certain extent. Due to the complexity and uncertainty of driving scenarios, different drivers have different perceptions of the same scenario. Therefore, how to achieve safe and reasonable driving behavior decisions is a key research focus in the field of driver assistance systems.

[0003] Currently, most research on intelligent vehicle driving behavior selection in driver assistance systems (ADAS) relies on environmental information within the driving scenario to make driving behavior decisions. For example, patent CN115061747A discloses an ADAS method for vehicles that makes driving behavior decisions based on acquired vehicle status and surrounding environmental information. However, the driver is a crucial component of the ADAS; therefore, the driver's status and driving intentions should be considered as factors influencing driving behavior decisions to avoid traffic accidents caused by driver distrust or over-reliance on ADAS. Furthermore, as intelligent vehicles develop diverse ADAS functions, the coordination of switching between functions is becoming increasingly prominent. For instance, patent CN110834637A discloses a driving mode switching method that switches between congestion-prone autonomous driving mode and advanced autonomous driving mode based on road traffic conditions. However, the same driving behaviors may exist between different driving modes, and switching between driving modes may lead to frequent switching of the same driving behavior state between different driving modes.

[0004] Therefore, how to further reduce the frequent switching between states of the driver assistance system based on a full consideration of factors such as the driver's state and driving intentions and the surrounding environment of the vehicle is an issue that urgently needs to be addressed by those skilled in the art. Summary of the Invention

[0005] To address the aforementioned technical problems, this invention provides a hierarchical decision-making method, system, electronic device, and storage medium for intelligent assisted driving, which can ensure the safety and comfort of vehicle assisted driving while increasing the driver's acceptance of the intelligent assisted driving system.

[0006] Firstly, this application provides a hierarchical decision-making method for intelligent assisted driving, including:

[0007] The signals collected from the vehicle's driver assistance mode switching are used.

[0008] Based on the driver's driving state and driving intention, the driver assistance mode is determined to be in one of the following working states: active or standby. The driving state includes at least one abnormal state among hands-free, distracted, fatigued, and yawning. The driving intention includes at least one driving operation request among acceleration, braking, deceleration, and turning the steering wheel.

[0009] When the assisted driving mode is activated, the vehicle's motion mode is determined based on the driver's steering intention and the vehicle's surrounding environment; wherein, the motion mode includes one of longitudinal motion mode, lateral motion mode, and combined longitudinal and lateral motion mode;

[0010] Based on the determined motion mode, the vehicle's motion state, and the surrounding environment, and combined with the driver's historical following and lane-keeping preferences, the vehicle's driving behavior is determined; wherein, the driving behavior includes one or two of the following: adaptive cruise control, increasing longitudinal following distance, decreasing longitudinal following distance, longitudinal following, lane keeping, and lateral following.

[0011] The system makes a safety prediction based on the determined driving behavior and outputs the decision result under the safety conditions that meet the safety prediction.

[0012] Preferably, the step of determining the working state of the assisted driving mode, including activation and standby, based on the driver's driving state and driving intention specifically includes:

[0013] Determine whether the switching from standby to activation of the assisted driving mode meets the switching control conditions;

[0014] If so, it means that there is a suppressive condition for the assisted driving mode to switch from standby to active state;

[0015] If not, it means that there is no suppression condition for the assisted driving mode to switch from standby to active state;

[0016] The switching conditions are as follows: ① The driver's state is abnormal; ② The driver's intention to accelerate is greater than the control request output by the driver assistance system; ③ The driver requests to brake and decelerate; ④ The driver's intention to turn the steering wheel is greater than the control request output by the driver assistance system. The condition is expressed as follows:

[0017] C 11 =(x∈Driver's abnormal state)∨(T) driver >T ADAS )∨(T brake >0)∨(δ driver >δADAS ),

[0018] In the formula, if C 11 If the statement is true, it means the switching condition is met; otherwise, it means the switching condition is not met. x represents the driver's current state, where abnormal driver state = {hands off, distracted, fatigued, yawning}; T driver T indicates the torque requested by the driver for acceleration. ADAS Indicates the requested torque for drive control of the driver assistance system; T brake Indicates the driver's requested brake pedal opening value; δ driver Indicates the driver's requested steering wheel angle value, δ ADAS This indicates the amount of control request for steering wheel angle from the driver assistance system.

[0019] Preferably, the step of determining the vehicle's motion mode based on the driver's steering intention and the vehicle's surrounding environment when the assisted driving mode is active specifically includes:

[0020] Obtain a signal indicating that the assisted driving mode is active;

[0021] The driver's steering intention is identified based on whether the left or right turn signal is activated;

[0022] Determine whether the driver's steering intention meets the first lane change feasibility setting condition;

[0023] If so, then the vehicle's motion mode is directly determined to be lateral motion mode;

[0024] If not, then the vehicle's motion mode is determined to be a combined lateral and longitudinal motion state;

[0025] The first condition for lane-changing feasibility is: ① the number of lanes in the direction the driver requests a lane change is not less than 1; ② the lane lines in the direction the driver requests a lane change are visible; ③ the lane line type in the direction the driver requests a lane change is a lane-changing type. All three propositions must be true simultaneously, as follows:

[0026] C 21 =(N LC ≥1)∧(VIS LC =1)∧(LT LC =1)

[0027] In the formula, if C 21 If the statement is true, it means that changing lanes does not meet the conditions for feasibility of changing lanes; otherwise, it means that it meets the conditions for feasibility of changing lanes. LC Indicates the number of lanes in the direction the driver requests to change lanes; VIS LC The visibility of the lane markings indicating the direction the driver requests to change lanes, and VISLC ∈{0,1}, where 0 and 1 represent invisible and visible, respectively; LT LC This indicates the lane change capability of the driver requesting the direction of lane change and the lane marking type, and LT LC ∈{0,1}, where 0 and 1 represent lane change not allowed and lane change allowed, respectively.

[0028] Preferably, after the step of determining that the vehicle's motion mode is in a combined lateral and longitudinal motion state, the method further includes:

[0029] Determine whether the vehicle in a combined lateral and longitudinal motion state meets the second lane change feasibility setting conditions;

[0030] If so, then the vehicle's motion mode is directly determined to be longitudinal motion mode;

[0031] If not, then the vehicle's motion mode is directly determined to be a combined lateral and longitudinal motion mode;

[0032] The second lane-changing feasibility assumption condition is: ① the lane lines on both sides of the vehicle's lane are not fully visible; ② there is no vehicle in front, or there is a vehicle in front but the vehicle's speed is higher than a set threshold. Both propositions must be true simultaneously, as follows:

[0033] C 22 =(VIS L +VIS R ≤1)∧((N PV =0)∨((N PV >0)∧(v>v0)))

[0034] In the formula, if C 22 If the statement is true, it means that the conditions for the second lane change feasibility assumption are met; otherwise, it means that the conditions for the second lane change feasibility assumption are not met. (VIS) L and VIS R VIS indicates the visibility of the left and right lane lines of the lane where the vehicle is located. L and VIS R ∈{0, 1}, where 0 and 1 represent invisible and visible, respectively; N PV This indicates the number of vehicles ahead of the vehicle in its lane; v and v0 represent the vehicle's speed and the maximum speed threshold for lateral following, respectively.

[0035] Preferably, the step of determining the driving behavior of the vehicle based on the determined motion mode, the vehicle's motion state, and the surrounding environment, combined with the driver's historical following and lane-keeping preferences, specifically includes:

[0036] When the determined motion mode is a lateral motion mode, the driving behavior of the vehicle is directly determined as a left lane change or a right lane change based on the driver's steering intention.

[0037] When the determined motion mode is longitudinal motion mode, it is determined whether the longitudinal following condition is met; if not, the driving behavior of the vehicle is determined to be adaptive cruise driving behavior; if it is met, the driving behavior of the vehicle is determined to be longitudinal following behavior of increasing distance, longitudinal following behavior of decreasing distance, or longitudinal following behavior of longitudinal following, depending on whether the driver's historical following preference is captured.

[0038] When the determined motion mode is a combined lateral and longitudinal motion mode, it is determined whether the longitudinal following condition is met; if not, the driving behavior of the vehicle is determined to be adaptive cruise control; if it is met, the driving behavior of the vehicle is determined to be longitudinal following and lane keeping driving behavior, longitudinal following and lateral following driving behavior, or lane keeping driving behavior, depending on the driver's lane keeping preference and whether the lane lines on both sides of the vehicle's lane are clear.

[0039] The longitudinal following conditions are: ① there is a vehicle ahead of the vehicle in its lane, and ② the time distance between vehicles is less than a set threshold. Both conditions must be met simultaneously, as expressed as:

[0040] C 23 =(N PV >0)∧(THW≤τ0)

[0041] In the formula, if C 23 If the statement is true, it means that the longitudinal following condition is met; otherwise, it means that the longitudinal following condition is not met. PV THW represents the distance between the vehicle and the vehicle in front, and τ0 represents the maximum distance threshold for following other vehicles.

[0042] Preferably, the driver's historical following and lane-keeping preferences specifically include:

[0043] When the vehicle is driving stably with longitudinal following behavior, if the driver's intention to accelerate is greater than the control request output by the driver assistance system, and the longitudinal following distance when the driver ends the acceleration request is smaller than before intervention, it is inferred that the driver has a driving preference to reduce the longitudinal following distance.

[0044] When the vehicle is driving stably with longitudinal following behavior, if the driver's intention to brake and decelerate is greater than the control request output by the driver assistance system, and the longitudinal following distance when the driver ends the braking and deceleration request is greater than before intervention, it is inferred that the driver has a driving preference to increase the longitudinal following distance.

[0045] When the vehicle is driving stably with lane keeping behavior, if the driver's intention to turn is greater than the control request output by the driver assistance system, and the lane keeping center shifts to the left or right when the driver ends the steering intervention compared to before the intervention, it is inferred that the driver has a driving preference for keeping the lane to the left or right.

[0046] Preferably, the safety conditions are: ① the collision risk in the current lane is less than a certain threshold, ② the collision risk in the target decision lane is less than a certain threshold, and both propositions are true simultaneously, expressed as:

[0047] C 31 =(F1<F e )∧(F2<F0)

[0048] In the formula, if C 31 If a statement is true, it means that the safety conditions are met; otherwise, it means that the driving behavior does not meet the safety conditions. (F1 and F...) e F1 and F2 represent the collision risk and corresponding collision risk threshold of the current lane, respectively. F3 and F4 represent the collision risk and corresponding collision risk threshold of the target decision lane, respectively. F5 is defined if and only if the target decision lane and the current lane are the same lane. e =F0; where the collision risk of the current lane is represented as:

[0049]

[0050] In the formula, M represents the equivalent mass of the vehicle; e represents the natural base; k1 and k2 represent the distance coefficient and speed coefficient, respectively; v represents the vehicle speed; i = 1 and 2 represent obstacles located in front of and behind the vehicle in the lane where the vehicle is located or the target decision lane, respectively; r i ∈{0,1} are direction coefficients, representing the front and rear positions of the target obstacle in the direction of the vehicle's travel, respectively; G represents a constant coefficient; M i d represents the equivalent mass of obstacle i; i v represents the relative distance between the vehicle and obstacle i; i Let θ represent the speed of obstacle i. i This represents the angle between the velocity direction of obstacle i and the vector distance direction of the vehicle.

[0051] Secondly, this application provides an intelligent assisted driving hierarchical decision-making system, comprising:

[0052] The data acquisition module is used to acquire the on / off signals of the vehicle's assisted driving mode;

[0053] The first decision module is used to decide on one of the working states of the assisted driving mode, including activation and standby, based on the driver's driving state and driving intention; wherein the driving state includes at least one abnormal state among hands-free, distracted, fatigued, and yawning, and the driving intention includes at least one driving operation request among acceleration, braking and deceleration, and turning the steering wheel.

[0054] The second decision module, when the assisted driving mode is activated, determines the vehicle's motion mode based on the driver's steering intention and the vehicle's surrounding environment; wherein the motion mode includes one of longitudinal motion mode, lateral motion mode, and combined longitudinal and lateral motion mode;

[0055] The third decision module determines the driving behavior of the vehicle based on the determined motion mode, the vehicle's motion state and surrounding environment, and in conjunction with the driver's historical following and lane keeping preferences; wherein the driving behavior includes one or two of the following: adaptive cruise control, increasing longitudinal following distance, decreasing longitudinal following distance, longitudinal following, lane keeping, and lateral following.

[0056] The output module is used to make a safety prediction based on the determined driving behavior, and output the decision result under the safety conditions that meet the safety prediction.

[0057] Preferably, the first decision module specifically includes:

[0058] The first judgment unit is used to determine whether the switching from standby to activation of the assisted driving mode meets the switching preconditions; wherein, the switching preconditions are: ① the driver's state is abnormal, ② the driver's intention to accelerate is greater than the control request amount output by the assisted driving system, ③ the driver has a braking and deceleration request, ④ the driver's intention to turn the steering wheel is greater than the control request amount output by the assisted driving system. The fulfillment of any one of these four propositions is expressed as:

[0059] C 11 =(x∈Driver's abnormal state)∨(T) driver >T ADAS )∨(T brake >0)∨(δ driver >δ ADAS ),

[0060] In the formula, if C 11 If the statement is true, it means the switching condition is met; otherwise, it means the switching condition is not met. x represents the driver's current state, where abnormal driver state = {hands off, distracted, fatigued, yawning}; T driver T indicates the torque requested by the driver for acceleration. ADAS Indicates the requested torque for drive control of the driver assistance system; Tbrake Indicates the driver's requested brake pedal opening value; δ driver Indicates the driver's requested steering wheel angle value, δ ADAS This indicates the control request amount for the steering wheel angle of the driver assistance system.

[0061] The first imitation unit is configured to indicate that there is a suppression condition for the assisted driving mode to switch from standby to active if the switching imitation condition is met.

[0062] The first decision unit is configured to indicate that there is no suppression condition for the assisted driving mode to switch from standby to active if the switching restriction condition is not met.

[0063] Preferably, the second decision module specifically includes:

[0064] The acquisition unit is used to acquire a signal that the assisted driving mode is in an active state;

[0065] The recognition unit is used to identify the driver's turning intention based on whether the left or right turn signal is activated.

[0066] The second judgment unit is used to determine whether the driver's steering intention meets the first lane-changing feasibility assumption condition; wherein, the first lane-changing feasibility assumption condition is: ① the number of lanes in the direction the driver requests to change lanes is not less than 1, ② the lane lines in the direction the driver requests to change lanes are visible, ③ the lane line type in the direction the driver requests to change lanes is a lane-changing type. All three propositions must be true simultaneously, as expressed as:

[0067] C 21 =(N LC ≥1)∧(VIS LC =1)∧(LT LC =1)

[0068] In the formula, if C 21 If the statement is true, it means that changing lanes does not meet the conditions for feasibility of changing lanes; otherwise, it means that it meets the conditions for feasibility of changing lanes. LC Indicates the number of lanes in the direction the driver requests to change lanes; VIS LC The visibility of the lane markings indicating the direction the driver requests to change lanes, and VIS LC ∈{0,1}, where 0 and 1 represent invisible and visible, respectively; LT LC This indicates the lane change capability of the driver requesting the direction of lane change and the lane marking type, and LT LC ∈{0,1}, where 0 and 1 represent lane change not allowed and lane change allowed, respectively;

[0069] The second decision unit is used to directly decide that the vehicle's motion mode is a lateral motion mode if the driver's steering intention meets the first lane change feasibility setting condition.

[0070] The third decision unit is used to decide that the vehicle's motion mode is in a combined lateral and longitudinal motion state if the driver's steering intention does not meet the first lane change feasibility setting condition.

[0071] Preferably, the second decision module further includes:

[0072] The third judgment unit is used to determine whether the vehicle in a combined lateral and longitudinal motion state meets the second lane-changing feasibility assumption condition; wherein, the second lane-changing feasibility assumption condition is: ① the lane lines on both sides of the lane where the vehicle is located are not completely visible, ② there is no vehicle in front or there is a vehicle in front but the vehicle speed is higher than a set threshold, and both propositions are true at the same time, which is expressed as:

[0073] C 22 =(VIS L +VIS R ≤1)∧((N PV =0)∨((N PV >0)∧(v>v0)))

[0074] In the formula, if C 22 If the statement is true, it means that the conditions for the second lane change feasibility assumption are met; otherwise, it means that the conditions for the second lane change feasibility assumption are not met. (VIS) L and VIS R VIS indicates the visibility of the left and right lane lines of the lane where the vehicle is located. L and VIS R ∈{0, 1}, where 0 and 1 represent invisible and visible, respectively; N PV This indicates the number of vehicles ahead of the vehicle in its lane; v and v0 represent the vehicle's speed and the maximum speed threshold for lateral following, respectively.

[0075] The fourth decision unit is used to directly decide that the movement mode of the vehicle is longitudinal movement mode if the vehicle in the combined lateral and longitudinal movement state meets the second lane change feasibility setting condition.

[0076] The fifth decision unit is used to directly decide that the movement mode of the vehicle is the lateral and longitudinal integrated movement mode if the vehicle in the lateral and longitudinal integrated movement state does not meet the second lane change feasibility setting conditions.

[0077] Thirdly, this application provides an electronic device including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the intelligent assisted driving hierarchical decision-making method as described in the first aspect.

[0078] Fourthly, this application provides a storage medium having a computer program stored thereon, which, when executed by a processor, implements the intelligent assisted driving hierarchical decision-making method as described in the first aspect.

[0079] Compared with existing technologies, the intelligent assisted driving hierarchical decision-making method, system, electronic device, and storage medium provided in this application have the following beneficial effects:

[0080] 1. Based on fully considering the driver's state and effectively utilizing the driver's operational intentions to infer the driver's driving preferences, a hierarchical finite state machine is adopted to realize the decision-making process of the assisted driving system, which can reduce the frequent switching between states of the assisted driving system; thereby improving the driver's acceptance of the intelligent assisted driving system while ensuring the safety and comfort of the vehicle's assisted driving.

[0081] 2. A finite state machine approach is used to implement hierarchical decision-making for the working state, motion mode, and driving behavior of the assisted driving mode. The algorithm has clear logic and a complete structure, with good interpretability and scalability. As the number of functional states increases, the hierarchical decision-making method can reduce the frequent switching between states in different assisted driving scenarios, thereby improving the comfort of vehicle driving.

[0082] 3. Taking full account of driver status and intentions, when there is an abnormal driver status or a strong driver intervention intention, the system will hand over driving control to the driver to ensure vehicle driving safety. Based on the driver's intervention intention, the system infers the driver's driving preferences and adjusts the vehicle's driving behavior accordingly to improve driver acceptance of the driver assistance system. Attached Figure Description

[0083] To more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0084] Figure 1 A schematic diagram of an intelligent assisted driving system provided in an embodiment of the present invention;

[0085] Figure 2A flowchart for summarizing intelligent assisted driving behavior decisions provided in an embodiment of the present invention;

[0086] Figure 3 A flowchart of the intelligent assisted driving hierarchical decision-making method provided in Embodiment 1 of the present invention;

[0087] Figure 4 This is a block diagram of the intelligent assisted driving hierarchical decision-making system corresponding to the method in Embodiment 1, provided in Embodiment 2 of the present invention;

[0088] Figure 5 This is a flowchart of the intelligent assisted driving hierarchical decision-making method provided in Embodiment 3 of the present invention;

[0089] Figure 6 This is a block diagram of the intelligent assisted driving hierarchical decision-making system corresponding to the method in Embodiment 3, provided in Embodiment 4 of the present invention;

[0090] Figure 7 A flowchart of the intelligent assisted driving hierarchical decision-making method provided in Embodiment 5 of the present invention;

[0091] Figure 8 This is a block diagram of the intelligent assisted driving hierarchical decision-making system corresponding to the method in Embodiment 5, provided in Embodiment 6 of the present invention;

[0092] Figure 9 A flowchart of the intelligent assisted driving hierarchical decision-making method provided in Embodiment 7 of the present invention;

[0093] Figure 10 This is a block diagram of the intelligent assisted driving hierarchical decision-making system structure corresponding to the method in Embodiment 7, provided in Embodiment 8 of the present invention;

[0094] Figure 11 This is a schematic diagram of the hardware structure of the electronic device provided in Embodiment 9 of the present invention.

[0095] Explanation of reference numerals in the attached figures:

[0096] 10 - Data Acquisition Module;

[0097] 20 - First Decision Module, 21 - First Judgment Unit, 22 - First Drafting Unit, 23 - First Decision Unit;

[0098] 30-Second Decision Module, 31-Acquisition Unit, 32-Identification Unit, 33-Second Judgment Unit, 34-Second Decision Unit, 35-Third Decision Unit, 36-Third Judgment Unit, 37-Fourth Decision Unit, 38-Fifth Decision Unit;

[0099] 40 - Third Decision Module;

[0100] 50 - Output Module;

[0101] 60-Bus, 61-Processor, 62-Memory, 63-Communication interface. Detailed Implementation

[0102] Exemplary embodiments will now be described more fully with reference to the accompanying drawings. However, these exemplary embodiments can be implemented in many forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that this disclosure will be more thorough and complete, and will fully convey the concept of the exemplary embodiments to those skilled in the art.

[0103] Furthermore, the described features, structures, or characteristics can be combined in any suitable manner in one or more embodiments. Numerous specific details are provided in the following description to give a thorough understanding of embodiments of this disclosure. However, those skilled in the art will recognize that the technical solutions of this disclosure can be practiced without one or more of the specific details, or other methods, components, apparatuses, steps, etc., can be employed. In other instances, well-known methods, apparatuses, implementations, or operations are not shown or described in detail to avoid obscuring various aspects of this disclosure.

[0104] The block diagrams shown in the accompanying drawings are merely functional entities and do not necessarily correspond to physically independent entities. That is, these functional entities can be implemented in software, in one or more hardware modules or integrated circuits, or in different network and / or processor devices and / or microcontroller devices.

[0105] The flowcharts shown in the accompanying drawings are merely illustrative and do not necessarily include all content and operations / steps, nor do they necessarily have to be performed in the described order. For example, some operations / steps can be broken down, while others can be combined or partially combined; therefore, the actual execution order may change depending on the specific circumstances.

[0106] Currently, research on decision-making for intelligent vehicle driving behavior in driver assistance systems (ADAS) takes several approaches: some consider the complex surrounding environment in driving scenarios, others consider the surrounding environment, driver state, and driving intentions, and still others consider driver preferences. This demonstrates the complexity and uncertainty of driving scenarios, the influence of driver state and intentions, and the varying perceptions of the same scenario among different drivers. Therefore, safe, comfortable, and acceptable driving behavior decisions are a key research focus in the field of ADAS. Figure 1 and Figure 2As shown, the intelligent assisted driving system of this application uses a finite state machine method to realize hierarchical decision-making of the working state, motion mode and driving behavior of the assisted driving mode based on factors such as driver state, driving intention, driving consultation, surrounding environment and driving preferences. This can reduce the frequent switching between states in different assisted driving scenarios, thereby improving the driver's acceptance of the intelligent assisted driving system while ensuring the safety and comfort of vehicle assisted driving.

[0107] Example 1

[0108] Specifically, Figure 3 The diagram shown is a flowchart of a hierarchical decision-making method for intelligent assisted driving provided in this embodiment.

[0109] like Figure 3 As shown, the intelligent assisted driving hierarchical decision-making method of this embodiment includes the following steps:

[0110] S101 collects the on / off signal of the vehicle's assisted driving mode.

[0111] Specifically, the switch signal for the assisted driving mode is either on or off. When the driver turns off the intelligent assisted driving system switch, the assisted driving system enters the off state; otherwise, the decision command generated by this application is output to the planning and control execution unit of the assisted driving system.

[0112] S102, based on the driver's driving state and driving intention, decide on one of the working states of the assisted driving mode, including active and standby.

[0113] The driving state includes at least one abnormal state among hands-free, distracted, fatigued, and yawning, and the driving intention includes at least one driving operation request among acceleration, braking, deceleration, and turning the steering wheel.

[0114] Furthermore, the specific steps of S102 in this embodiment include:

[0115] S1021, determine whether the switching from standby to activation of the assisted driving mode meets the switching control conditions.

[0116] The switching conditions are as follows: ① The driver's state is abnormal; ② The driver's intention to accelerate is greater than the control request output by the driver assistance system; ③ The driver requests to brake and decelerate; ④ The driver's intention to turn the steering wheel is greater than the control request output by the driver assistance system. The condition is expressed as follows:

[0117] C 11 =(x∈Driver's abnormal state)∨(T) driver >T ADAS )∨(Tbrake >0)∨(δ driver >δ ADAS ),

[0118] In the formula, if C 11 If the statement is true, it means the switching condition is met; otherwise, it means the switching condition is not met. x represents the driver's current state, where abnormal driver state = {hands off, distracted, fatigued, yawning}; T driver T indicates the torque requested by the driver for acceleration. ADAS Indicates the requested torque for drive control of the driver assistance system; T brake Indicates the driver's requested brake pedal opening value; δ driver Indicates the driver's requested steering wheel angle value, δ ADAS This indicates the control request amount for the steering wheel angle of the driver assistance system. It should be noted that the driver's current state can be identified through the in-vehicle driver monitoring system.

[0119] S1022, If not, it means that there is no suppression condition for the assisted driving mode to switch from standby to active state.

[0120] Specifically, when there is no suppression condition when the assisted driving mode switches from standby to active state, the assisted driving mode switches to active state.

[0121] S103, when the assisted driving mode is activated, the vehicle's motion mode is determined based on the driver's steering intention and the vehicle's surrounding environment.

[0122] The motion mode includes one of the following: longitudinal motion mode, lateral motion mode, and combined longitudinal and lateral motion mode.

[0123] Furthermore, the specific steps of S103 in this embodiment include:

[0124] S1031, Obtain a signal that the assisted driving mode is in an active state.

[0125] S1032, the driver's steering intention is identified based on whether the left or right turn signal is activated.

[0126] S1033, determine whether the driver's steering intention meets the first lane change feasibility setting condition.

[0127] The first condition for lane-changing feasibility is: ① the number of lanes in the direction the driver requests a lane change is not less than 1; ② the lane lines in the direction the driver requests a lane change are visible; ③ the lane line type in the direction the driver requests a lane change is a lane-changing type. All three propositions must be true simultaneously, as follows:

[0128] C 21=(N LC ≥1)∧(VIS LC =1)∧(LT LC =1)

[0129] In the formula, if C 21 If the statement is true, it means that changing lanes does not meet the conditions for feasibility of changing lanes; otherwise, it means that it meets the conditions for feasibility of changing lanes. LC Indicates the number of lanes in the direction the driver requests to change lanes; VIS LC The visibility of the lane markings indicating the direction the driver requests to change lanes, and VIS LC ∈{0,1}, where 0 and 1 represent invisible and visible, respectively; LT LC This indicates the lane change capability of the driver requesting the direction of lane change and the lane marking type, and LT LC ∈{0,1}, where 0 and 1 represent lane change not allowed and lane change allowed, respectively.

[0130] S1034, if not, then the vehicle's motion mode is determined to be a combined lateral and longitudinal motion state;

[0131] S1035, determine whether the vehicle in the combined lateral and longitudinal motion state meets the second lane change feasibility setting conditions.

[0132] The second lane-changing feasibility assumption condition is: ① the lane lines on both sides of the vehicle's lane are not fully visible; ② there is no vehicle in front, or there is a vehicle in front but the vehicle's speed is higher than a set threshold. Both propositions must be true simultaneously, as follows:

[0133] C 22 =(VIS L +VIS R ≤1)∧((N PV =0)∨((N PV >0)∧(v>v0)))

[0134] In the formula, if C 22 If the statement is true, it means that the conditions for the second lane change feasibility assumption are met; otherwise, it means that the conditions for the second lane change feasibility assumption are not met. (VIS) L and VIS R VIS indicates the visibility of the left and right lane lines of the lane where the vehicle is located. L and VIS R ∈{0, 1}, where 0 and 1 represent invisible and visible, respectively; N PV This indicates the number of vehicles ahead of the vehicle in its lane; v and v0 represent the vehicle's speed and the maximum speed threshold for lateral following, respectively.

[0135] S1036, if so, then directly determine the vehicle's motion mode as longitudinal motion mode.

[0136] S104. Based on the determined motion mode, the vehicle's motion state, and the surrounding environment, and combined with the driver's historical following and lane-keeping preferences, the driving behavior of the vehicle is determined.

[0137] The driving behaviors include one or two of the following: adaptive cruise control, increasing longitudinal following distance, decreasing longitudinal following distance, longitudinal following, lane keeping, and lateral following.

[0138] Specifically, when the determined motion mode is a longitudinal motion mode, it is determined whether the longitudinal following conditions are met; wherein, the longitudinal following conditions are: ① there is a vehicle ahead of the vehicle in its lane, ② the vehicle-to-vehicle distance is less than a set threshold, and both propositions are true simultaneously, expressed as:

[0139] C 23 =(N PV >0)∧(THW≤τ0)

[0140] In the formula, if C 23 If the statement is true, it means that the longitudinal following condition is met; otherwise, it means that the longitudinal following condition is not met. PV THW represents the distance between the vehicle and the vehicle in front, and τ0 represents the maximum distance threshold for following other vehicles.

[0141] If it does not meet the requirements, the decision is that the vehicle's driving behavior is adaptive cruise control.

[0142] If the conditions are met, the system will make decisions on driving behaviors such as increasing the longitudinal following distance, decreasing the longitudinal following distance, and longitudinal following, based on the driver's following driving preferences. If the system does not capture the driver's following driving preference information, the default decision will be longitudinal following.

[0143] S105, make a safety prediction based on the determined driving behavior, and output the decision result under the safety conditions that meet the safety prediction.

[0144] The safety conditions are: ① the collision risk of the current lane is less than a certain threshold, and ② the collision risk of the target decision lane is less than a certain threshold. Both propositions must be true simultaneously, as expressed in the following way:

[0145] C 31 =(F1<F e )∧(F2<F0)

[0146] In the formula, if C 31 If a statement is true, it means that the safety conditions are met; otherwise, it means that the driving behavior does not meet the safety conditions. (F1 and F...) eF1 and F2 represent the collision risk and corresponding collision risk threshold of the current lane, respectively. F3 and F4 represent the collision risk and corresponding collision risk threshold of the target decision lane, respectively. F5 is defined if and only if the target decision lane and the current lane are the same lane. e =F0;

[0147] Furthermore, the collision risk in the current lane is represented as follows:

[0148]

[0149] In the formula, M represents the equivalent mass of the vehicle; e represents the natural base; k1 and k2 represent the distance coefficient and speed coefficient, respectively; v represents the vehicle speed; i = 1 and 2 represent obstacles located in front of and behind the vehicle in the lane where the vehicle is located or the target decision lane, respectively; r i ∈{0,1} are direction coefficients, representing the front and rear positions of the target obstacle in the direction of the vehicle's travel, respectively; G represents a constant coefficient; M i d represents the equivalent mass of obstacle i; i v represents the relative distance between the vehicle and obstacle i; i Let θ represent the speed of obstacle i. i This represents the angle between the velocity direction of obstacle i and the vector distance direction of the vehicle. Wherein, the equivalent mass coefficient M or Mi of the vehicle or obstacle is... i It is related to its own mass m, object type T, and vehicle speed v, and can be expressed as: M=f(m,T,v).

[0150] In summary, by fully considering the driver's state and intention information, the system transfers driving control to the driver to ensure vehicle safety. Furthermore, it infers the driver's driving preferences based on their intervention intentions and adjusts vehicle driving behavior accordingly. Moreover, a finite state machine approach is used to implement hierarchical decision-making for the working state, motion mode, and driving behavior of the assisted driving mode. The algorithm has clear logic, a complete structure, and good interpretability and scalability. As the number of functional states increases, the hierarchical decision-making method reduces frequent state switching between different assisted driving scenarios, thereby improving driver acceptance of the intelligent assisted driving system while ensuring the safety and comfort of vehicle assisted driving.

[0151] Example 2

[0152] This embodiment provides a structural block diagram of a system corresponding to the method described in Embodiment 1. Figure 4 This is a structural block diagram of the intelligent assisted driving hierarchical decision-making system according to this embodiment, such as... Figure 4 As shown, the system includes:

[0153] The acquisition module 10 is used to acquire the on / off signals of the vehicle's assisted driving mode.

[0154] The first decision module 20 is used to decide on one of the working states of the assisted driving mode, including activation and standby, based on the driver's driving status and driving intention.

[0155] Specifically, the first decision module 20 includes:

[0156] The first judgment unit 21 is used to determine whether the switching from standby to activation of the assisted driving mode meets the switching preconditions; wherein, the switching preconditions are: ① the driver's state is abnormal, ② the driver's intention to accelerate is greater than the control request amount output by the assisted driving system, ③ the driver has a braking deceleration request, ④ the driver's intention to turn the steering wheel is greater than the control request amount output by the assisted driving system. The fulfillment of any one of the four propositions is expressed as:

[0157] C 11 =(x∈Driver's abnormal state)∨(T) driver >T ADAS )∨(T brake >0)∨(δ driver >δ ADAS ),

[0158] In the formula, if C 11 If the statement is true, it means the switching condition is met; otherwise, it means the switching condition is not met. x represents the driver's current state, where abnormal driver state = {hands off, distracted, fatigued, yawning}; T driver T indicates the torque requested by the driver for acceleration. ADAS Indicates the requested torque for drive control of the driver assistance system; T brake Indicates the driver's requested brake pedal opening value; δ driver Indicates the driver's requested steering wheel angle value, δ ADAS This indicates the control request amount for the steering wheel angle of the driver assistance system.

[0159] The first decision unit 23 is used to indicate that there is no suppression condition for the assisted driving mode to switch from standby to active if the switching restriction condition is not met.

[0160] The second decision module 30, when the assisted driving mode is activated, determines the vehicle's motion mode based on the driver's steering intention and the vehicle's surrounding environment.

[0161] Specifically, the second decision module 30 includes:

[0162] Acquisition unit 31 is used to acquire a signal that the assisted driving mode is in an active state;

[0163] The identification unit 32 is used to identify the driver's turning intention based on whether the left turn signal or the right turn signal is activated.

[0164] The second judgment unit 33 is used to determine whether the driver's steering intention meets the first lane-changing feasibility assumption condition; wherein, the first lane-changing feasibility assumption condition is: ① the number of lanes in the direction of the lane change requested by the driver is not less than 1, ② the lane line in the direction of the lane change requested by the driver is visible, ③ the lane line type in the direction of the lane change requested by the driver is a lane-changing type, and all three propositions are true simultaneously, as expressed as:

[0165] C 21 =(N LC ≥1)∧(VIS LC =1)∧(LT LC =1)

[0166] In the formula, if C 21 If the statement is true, it means that changing lanes does not meet the conditions for feasibility of changing lanes; otherwise, it means that it meets the conditions for feasibility of changing lanes. LC Indicates the number of lanes in the direction the driver requests to change lanes; VIS LC The visibility of the lane markings indicating the direction the driver requests to change lanes, and VIS LC ∈{0,1}, where 0 and 1 represent invisible and visible, respectively; LT LC This indicates the lane change capability of the driver requesting the direction of lane change and the lane marking type, and LT LC ∈{0,1}, where 0 and 1 represent lane change not allowed and lane change allowed, respectively;

[0167] The third decision unit 35 is used to decide that the vehicle's motion mode is in a combined lateral and longitudinal motion state if the driver's steering intention does not meet the first lane change feasibility setting condition.

[0168] The third judgment unit 36 ​​is used to determine whether the vehicle in a combined lateral and longitudinal motion state meets the second lane-changing feasibility assumption condition; wherein, the second lane-changing feasibility assumption condition is: ① the lane lines on both sides of the lane where the vehicle is located are not completely visible, ② there is no vehicle in front or there is a vehicle in front but the vehicle speed is higher than a set threshold, and both propositions are true at the same time, which is expressed as:

[0169] C 22 =(VIS L +VIS R ≤1)∧((N PV =0)∨((N PV >0)∧(v>v0)))

[0170] In the formula, if C 22 If the statement is true, it means that the conditions for the second lane change feasibility assumption are met; otherwise, it means that the conditions for the second lane change feasibility assumption are not met. (VIS) L and VIS R VIS indicates the visibility of the left and right lane lines of the lane where the vehicle is located. L and VIS R ∈{0, 1}, where 0 and 1 represent invisible and visible, respectively; N PV This indicates the number of vehicles ahead of the vehicle in its lane; v and v0 represent the vehicle's speed and the maximum speed threshold for lateral following, respectively.

[0171] The fourth decision unit 37 is used to directly decide that the movement mode of the vehicle is longitudinal movement mode if the vehicle in the combined lateral and longitudinal movement state meets the second lane change feasibility setting condition.

[0172] The third decision module 40, based on the determined motion mode, the vehicle's motion state and surrounding environment, and combined with the driver's historical following and lane keeping preferences, decides the vehicle's driving behavior.

[0173] Specifically, when the determined motion mode is a longitudinal motion mode, it is determined whether the longitudinal following conditions are met; wherein, the longitudinal following conditions are: ① there is a vehicle ahead of the vehicle in its lane, ② the vehicle-to-vehicle distance is less than a set threshold, and both propositions are true simultaneously, expressed as:

[0174] C 23 =(N PV >0)∧(THW≤τ0)

[0175] In the formula, if C 23 If the statement is true, it means that the longitudinal following condition is met; otherwise, it means that the longitudinal following condition is not met. PV THW represents the distance between the vehicle and the vehicle in front, and τ0 represents the maximum distance threshold for following other vehicles.

[0176] If it does not meet the requirements, the decision is that the vehicle's driving behavior is adaptive cruise control.

[0177] If the conditions are met, the driver's historical following preferences will be captured to determine whether the vehicle's driving behavior is to follow the car with increased distance, follow the car with decreased distance, or follow the car with longitudinal following.

[0178] The output module 50 is used to make a safety prediction based on the determined driving behavior, and output the decision result under the safety conditions that meet the safety prediction.

[0179] The safety conditions are: ① the collision risk of the current lane is less than a certain threshold, and ② the collision risk of the target decision lane is less than a certain threshold. Both propositions must be true simultaneously, as expressed in the following way:

[0180] C 31 =(F1<F e )∧(F2<F0)

[0181] In the formula, if C 31 If a statement is true, it means that the safety conditions are met; otherwise, it means that the driving behavior does not meet the safety conditions. (F1 and F...) e F1 and F2 represent the collision risk and corresponding collision risk threshold of the current lane, respectively. F3 and F4 represent the collision risk and corresponding collision risk threshold of the target decision lane, respectively. F5 is defined if and only if the target decision lane and the current lane are the same lane. e =F0; where the collision risk of the current lane is represented as:

[0182]

[0183] In the formula, M represents the equivalent mass of the vehicle; e represents the natural base; k1 and k2 represent the distance coefficient and speed coefficient, respectively; v represents the vehicle speed; i = 1 and 2 represent obstacles located in front of and behind the vehicle in the lane where the vehicle is located or the target decision lane, respectively; r i ∈{0,1} are direction coefficients, representing the front and rear positions of the target obstacle in the direction of the vehicle's travel, respectively; G represents a constant coefficient; M i d represents the equivalent mass of obstacle i; i v represents the relative distance between the vehicle and obstacle i; i Let θ represent the speed of obstacle i. i This represents the angle between the velocity direction of obstacle i and the vector distance direction of the vehicle.

[0184] It should be noted that the above modules can be functional modules or program modules, and can be implemented through software or hardware. For modules implemented through hardware, the above modules can reside in the same processor; or the above modules can be located in different processors in any combination.

[0185] Example 3

[0186] Specifically, the difference between the intelligent assisted driving hierarchical decision-making method of this embodiment and that of Embodiment 1 lies in the specific steps of step S103. For example... Figure 5 As shown, step S203 of this embodiment is as follows:

[0187] S2031, Obtain a signal that the assisted driving mode is in an active state;

[0188] S2032, The driver's turning intention is identified based on whether the left or right turn signal is activated;

[0189] S2033, determine whether the driver's steering intention meets the first lane change feasibility setting condition;

[0190] S2034, if not, then the vehicle's motion mode is determined to be a combined lateral and longitudinal motion state;

[0191] S2035, determine whether the vehicle in the combined lateral and longitudinal motion state meets the second lane change feasibility setting condition;

[0192] S2036, if not, then directly determine the vehicle's motion mode as a combined lateral and longitudinal motion mode.

[0193] In this embodiment, the determined motion mode is a combined lateral and longitudinal motion mode. The specific steps for subsequent decision-making regarding the vehicle's driving behavior are as follows:

[0194] When the determined motion mode is a combined lateral and longitudinal motion mode, it is determined whether the longitudinal following condition is met. If not, the vehicle's driving behavior is determined to be adaptive cruise control. If it is met: firstly, if the longitudinal following condition is met and the lane lines on both sides are clear, the driving behavior is determined to be longitudinal following + lane keeping; secondly, if the longitudinal following condition is met but the lane lines on both sides are not completely clear, the driving behavior is determined to be longitudinal following + lateral following. It should be noted that the lane keeping driving behavior can be divided into left lane keeping, right lane keeping, and lane keeping based on the driver's lane keeping driving preference. If the system does not collect the driver's lane keeping driving preference information, the default decision is lane keeping driving behavior.

[0195] Example 4

[0196] This embodiment provides a structural block diagram of a system corresponding to the method described in Embodiment 3. The difference between the intelligent assisted driving hierarchical decision-making system of this embodiment and Embodiment 2 lies in the specific structure of the second decision-making module. (See attached diagram). Figure 6 As shown, the structure of the second decision module in this embodiment is as follows:

[0197] Acquisition unit 31 is used to acquire a signal that the assisted driving mode is in an active state;

[0198] The identification unit 32 is used to identify the driver's turning intention based on whether the left turn signal or the right turn signal is activated.

[0199] The second judgment unit 33 is used to judge whether the driver's steering intention meets the first lane change feasibility setting condition;

[0200] The third decision unit 35 is used to decide that the vehicle's motion mode is in a combined lateral and longitudinal motion state if the driver's steering intention does not meet the first lane change feasibility setting condition.

[0201] The third judgment unit 36 ​​is used to judge whether the vehicle in the combined lateral and longitudinal motion state meets the second lane change feasibility simulation conditions.

[0202] The fifth decision unit 38 is used to directly decide that the movement mode of the vehicle is the lateral and longitudinal integrated movement mode if the vehicle in the lateral and longitudinal integrated movement state does not meet the second lane change feasibility setting conditions.

[0203] It should be noted that the above modules can be functional modules or program modules, and can be implemented through software or hardware. For modules implemented through hardware, the above modules can reside in the same processor; or the above modules can be located in different processors in any combination.

[0204] Example 5

[0205] Specifically, the difference between the intelligent assisted driving hierarchical decision-making method of this embodiment and that of Embodiment 1 lies in the specific steps of step S103. For example... Figure 7 As shown, step S303 of this embodiment is as follows:

[0206] S3031, Obtain a signal that the assisted driving mode is in an active state;

[0207] S3032, The driver's turning intention is identified based on whether the left or right turn signal is activated;

[0208] S3033, determine whether the driver's steering intention meets the first lane change feasibility setting condition;

[0209] S3034, if so, then directly determine the vehicle's motion mode as lateral motion mode.

[0210] In this embodiment, the determined motion mode is a combined lateral and longitudinal motion mode. The specific steps for subsequent decision-making regarding the vehicle's driving behavior are as follows:

[0211] When the determined motion mode is a lateral motion mode, the driving behavior of the vehicle is directly determined as a left lane change or a right lane change based on the driver's steering intention.

[0212] Example 6

[0213] This embodiment provides a structural block diagram of a system corresponding to the method described in Embodiment 5. The difference between the intelligent assisted driving hierarchical decision-making system of this embodiment and Embodiment 2 lies in the specific structure of the second decision-making module. (See attached diagram). Figure 8 As shown, the structure of the second decision module in this embodiment is as follows:

[0214] Acquisition unit 31 is used to acquire a signal that the assisted driving mode is in an active state;

[0215] The identification unit 32 is used to identify the driver's turning intention based on whether the left turn signal or the right turn signal is activated.

[0216] The second judgment unit 33 is used to judge whether the driver's steering intention meets the first lane change feasibility setting condition;

[0217] The second decision unit 34 is used to directly decide that the vehicle's motion mode is a lateral motion mode if the driver's steering intention meets the first lane change feasibility setting condition.

[0218] It should be noted that the above modules can be functional modules or program modules, and can be implemented through software or hardware. For modules implemented through hardware, the above modules can reside in the same processor; or the above modules can be located in different processors in any combination.

[0219] Example 7

[0220] Specifically, the difference between the intelligent assisted driving hierarchical decision-making method in this embodiment and that in embodiment 1 lies in the specific steps of step S102. For example... Figure 9 As shown, step S402 of this embodiment is as follows:

[0221] S4021, determine whether the switching from standby to activation of the assisted driving mode meets the switching control conditions;

[0222] S4022, if yes, it means that there is a suppression condition for the assisted driving mode to switch from standby to active state;

[0223] Specifically, if there is a suppressive condition when the assisted driving mode switches from standby to active state, the assisted driving mode will not switch and will remain in standby state.

[0224] Example 8

[0225] This embodiment provides a structural block diagram of a system corresponding to the method described in Embodiment 7. The difference between the intelligent assisted driving hierarchical decision-making system of this embodiment and Embodiment 2 lies in the specific structure of the first decision-making module. (See attached diagram). Figure 10As shown, the structure of the first decision module in this embodiment is as follows:

[0226] The first judgment unit 21 is used to determine whether the switching of the assisted driving mode from standby to activation meets the switching control conditions.

[0227] The first imitation unit 22 is used to indicate that there is no suppression condition for the assisted driving mode to switch from standby to active if the switching imitation condition is not met.

[0228] It should be noted that the above modules can be functional modules or program modules, and can be implemented through software or hardware. For modules implemented through hardware, the above modules can reside in the same processor; or the above modules can be located in different processors in any combination.

[0229] Example 9

[0230] Combination Figure 3 , Figure 5 , Figure 7 , Figure 9 The described hierarchical decision-making method for intelligent assisted driving can be implemented by electronic devices. Figure 11 This is a schematic diagram of the hardware structure of an electronic device according to this embodiment.

[0231] The electronic device may include a processor 61 and a memory 62 storing program instructions for the electronic device.

[0232] Specifically, the processor 61 may include a central processing unit (CPU), an application specific integrated circuit (ASIC), or one or more integrated circuits that can be configured to implement the present application.

[0233] The memory 62 may include a mass storage device for data or instructions. For example, and not limitingly, the memory 62 may include a hard disk drive (HDD), a floppy disk drive, a solid-state drive (SSD), flash memory, an optical disk drive, a magneto-optical disk drive, magnetic tape, or a Universal Serial Bus (USB) drive, or a combination of two or more of these. Where appropriate, the memory 62 may include removable or non-removable (or fixed) media. Where appropriate, the memory 62 may be internal or external to a data processing device. In a particular embodiment, the memory 62 is non-volatile memory. In a particular embodiment, the memory 62 includes read-only memory (ROM) and random access memory (RAM). Where appropriate, the ROM may be a mask-programmed ROM, a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), an electrically alterable read-only memory (EAROM), or flash memory, or a combination of two or more of these. Where appropriate, the RAM can be Static Random-Access Memory (SRAM) or Dynamic Random-Access Memory (DRAM). DRAM can be Fast Page Mode Dynamic Random-Access Memory (FPMDRAM), Extended Data Out Dynamic Random-Access Memory (EDODRAM), Synchronous Dynamic Random-Access Memory (SDRAM), etc.

[0234] The memory 62 can be used to store or cache various data files that need to be processed and / or communicated, as well as possible electronic device program instructions executed by the processor 61.

[0235] The processor 61 reads and executes the electronic device program instructions stored in the memory 62 to implement the intelligent assisted driving hierarchical decision-making method described in Embodiments 1, 3, 5, and 7.

[0236] In some embodiments, the electronic device may further include a communication interface 63 and a bus 60. For example, Figure 11 As shown, the processor 61, memory 62, and communication interface 63 are connected through bus 60 and complete communication with each other.

[0237] The communication interface 63 is used to enable communication between the various modules, devices, units, and / or equipment in this application. The communication interface 63 can also enable data communication with other components such as external devices, image / data acquisition devices, databases, external storage, and image / data processing workstations.

[0238] Bus 60 includes hardware, software, or both, that couples components of an electronic device together. Bus 60 includes, but is not limited to, at least one of the following: data bus, address bus, control bus, expansion bus, and local bus. For example, and not as a limitation, bus 60 may include an Accelerated Graphics Port (AGP) or other graphics bus, an Extended Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), a Hyper Transport (HT) interconnect, an Industry Standard Architecture (ISA) bus, an InfiniBand interconnect, a Low Pin Count (LPC) bus, a memory bus, a Micro Channel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a Video Electronics Standards Association Local Bus (VLB) bus, or other suitable buses, or a combination of two or more of these. Where appropriate, bus 60 may include one or more buses. Although this application describes and illustrates a specific bus, this application considers any suitable bus or interconnection.

[0239] The electronic device can access the intelligent assisted driving hierarchical decision-making system and execute the intelligent assisted driving hierarchical decision-making methods of Embodiments 1, 3, 5, and 7.

[0240] Furthermore, in conjunction with the intelligent assisted driving hierarchical decision-making methods in Embodiments 1, 3, 5, and 7 described above, this application can provide a storage medium for implementation. This storage medium stores electronic device program instructions; when these electronic device program instructions are executed by a processor, they implement the intelligent assisted driving hierarchical decision-making methods of Embodiments 1, 3, 5, and 7 described above.

[0241] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0242] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. An intelligent assisted driving hierarchical decision method, characterized in that, The method comprises the following steps: Collecting a switch signal of an auxiliary driving mode of a vehicle; According to the driving state and driving intention of the driver, deciding a working state of the auxiliary driving mode, the working state comprising activation and standby; When the auxiliary driving mode is in the activation state, according to the steering intention of the driver and the surrounding environment of the vehicle, deciding a motion mode of the vehicle; wherein the motion mode comprises one of a longitudinal motion mode, a lateral motion mode and a comprehensive lateral-longitudinal motion mode; According to the decided motion mode, the motion state and the surrounding environment of the vehicle, and in combination with the historical following vehicle and lane keeping preference of the driver, deciding a driving behavior of the vehicle; wherein the driving behavior comprises one or two of adaptive cruise, increasing distance longitudinal following, decreasing distance longitudinal following, longitudinal following, lane keeping and lateral following; Performing safety prediction for the decided driving behavior, and outputting a decision result under the safety condition conforming to the safety prediction; The step of deciding the working state of the auxiliary driving mode according to the driving state and driving intention of the driver comprises the following steps: Judging whether the auxiliary driving mode switching from standby to activation conforms to a switching stipulation condition; If yes, it means that there is an inhibition condition for the auxiliary driving mode switching from standby to activation; If no, it means that there is no inhibition condition for the auxiliary driving mode switching from standby to activation; The switching stipulation condition is that any one of the following four propositions is true: C 11 = ( x∈ Driver state abnormal) ∨ ( T driver > T ADAS ) ∨ ( T brake > 0) ∨ ( The driver state is abnormal, the driver's intention action of accelerating is greater than the control request quantity output by the auxiliary driving system, the driver has a braking deceleration request, and the driver's intention action of turning the steering wheel is greater than the control request quantity output by the auxiliary driving system. driver > The step of deciding the motion mode of the vehicle according to the steering intention of the driver and the surrounding environment of the vehicle when the auxiliary driving mode is in the activation state comprises the following steps: ADAS ), In the formula, if C 11 is a true proposition, it indicates that the switching simulation condition is met, otherwise it indicates that the switching simulation condition is not met; x represents the current state of the driver, and the driver state exception = {hands off, distracted, fatigue, yawn}; T driver represents the driver's acceleration request torque, T ADAS represents the request torque of the auxiliary driving system driving control; T brake represents the driver's brake pedal opening request value; Obtaining a signal that the auxiliary driving mode is in the activation state; driver represents the driver's steering wheel angle request value, Identifying the steering intention of the driver according to the activated state of the left or right turn signal; ADAS represents the control request amount of the auxiliary driving system steering wheel angle.

2. The intelligent assisted driving hierarchical decision method according to claim 1, characterized in that, Judging whether the steering intention of the driver conforms to a first lane changing feasibility stipulation condition; If yes, directly deciding the motion mode of the vehicle as the lateral motion mode; If no, deciding that the motion mode of the vehicle is in the comprehensive lateral-longitudinal motion state; The first lane changing feasibility stipulation condition is that the number of lanes in the direction requested by the driver to change lanes is not less than 1, the lane line in the direction requested by the driver to change lanes has visibility, and the lane line in the direction requested by the driver to change lanes is of a lane changeable type, and the three propositions are true at the same time. The method further comprises the following steps after the step of deciding that the motion mode of the vehicle is in the comprehensive lateral-longitudinal motion state: ​ ​ C 21 =（ N LC ≥1）∧（ ​ LC =1）∧（ ​ LC =1） In the formula, if C 21 is a true proposition, it indicates that the lane change does not meet the lane change feasibility stipulation condition, otherwise it indicates that it meets the lane change feasibility stipulation condition; N LC represents the number of lanes in the direction of the lane change requested by the driver; ​ LC represents the visibility of the lane line in the direction of the lane change requested by the driver, and ​ LC ∈ {0, 1}, where 0 and 1 respectively represent invisible and visible; ​ LC represents the lane change feasibility of the lane line type in the direction of the lane change requested by the driver, and ​ LC ∈ {0, 1}, where 0 and 1 respectively represent lane change line types that are not allowed and lane change line types that are allowed. 3.The intelligent assisted driving hierarchical decision method according to claim 2, characterized in that, ​ determining whether the ego vehicle in the combined lateral and longitudinal motion state meets the second lane-changing feasibility hypothesis condition; if yes, directly determining the motion mode of the ego vehicle as the longitudinal motion mode; if no, directly determining the motion mode of the ego vehicle as the combined lateral and longitudinal motion mode; wherein the second lane-changing feasibility hypothesis condition is that: ①the lane lines on both sides of the lane where the ego vehicle is located are not completely visible, and ②there is no preceding vehicle or there is a preceding vehicle but the speed of the ego vehicle is higher than a set threshold, both of which are true, and is expressed as: C 22 =（ VIS L + VIS R ≤1）∧（（ N PV =0）∨（（ N PV ＞0）∧（ v ＞ v 0））） In the formula, if C 22 is a true proposition, it indicates that the second lane-changing feasibility condition is met, otherwise it indicates that the second lane-changing feasibility condition is not met; VIS L and VIS R respectively represent the visibility of the left and right lane lines of the lane where the ego vehicle is located, VIS L and VIS R ∈ {0, 1}, wherein 0 and 1 respectively represent invisible and visible; N PV represents the number of vehicles in front of the lane where the ego vehicle is located; v and v 0 respectively represent the speed of the ego vehicle and the maximum speed threshold value at which the vehicle can perform lateral following. 4.The intelligent assisted driving hierarchical decision method of claim 1, wherein, The step of determining the driving behavior of the ego vehicle according to the determined motion mode, the motion state of the ego vehicle and the surrounding environment, and the historical following and lane keeping preferences of the driver specifically includes: when the determined motion mode is the lateral motion mode, directly determining the driving behavior of the ego vehicle as left lane-changing driving behavior or right lane-changing driving behavior according to the steering intention of the driver; when the determined motion mode is the longitudinal motion mode, determining whether the longitudinal following condition is met; if not, determining the driving behavior of the ego vehicle as adaptive cruise driving behavior; if so, determining the driving behavior of the ego vehicle as increasing distance longitudinal following, decreasing distance longitudinal following, or longitudinal following driving behavior according to whether the historical following preference of the driver is captured; when the determined motion mode is the combined lateral and longitudinal motion mode, determining whether the longitudinal following condition is met; if not, determining the driving behavior of the ego vehicle as adaptive cruise driving behavior; if so, determining the driving behavior of the ego vehicle as longitudinal following and lane keeping driving behavior, longitudinal following and lateral following driving behavior, or lane keeping driving behavior according to the lane keeping preference of the driver and whether the lane lines on both sides of the lane where the ego vehicle is located are clear; wherein the longitudinal following condition is that: ①there is a vehicle in front of the lane where the ego vehicle is located, and ②the time distance between the vehicles is less than a set threshold, both of which are true, and is expressed as: C 23 =（ N PV ＞0）∧（ THW ≤ τ 0） In the formula, if C 23 is a true proposition, it indicates that the longitudinal following condition is met, otherwise it indicates that the longitudinal following condition is not met; N PV represents the number of vehicles in front of the lane where the ego vehicle is located; THW represents the inter-vehicle time distance between the ego vehicle and the preceding vehicle, τ 0 represents the maximum inter-vehicle time distance threshold for following.

5. The intelligent assisted driving hierarchical decision method according to claim 4, characterized in that, The historical following and lane keeping preferences of the driver specifically include: when the ego vehicle is stably driving in a state containing longitudinal following driving behavior, if the intention action of the driver's acceleration request is greater than the control request output by the auxiliary driving system, and the longitudinal following time distance when the driver ends the acceleration request is smaller than before intervention, it is inferred that the driver has a driving preference of reducing the longitudinal following distance; when the ego vehicle is stably driving in a state containing longitudinal following driving behavior, if the intention action of the driver's braking and deceleration request is greater than the control request output by the auxiliary driving system, and the longitudinal following time distance when the driver ends the braking and deceleration request is greater than before intervention, it is inferred that the driver has a driving preference of increasing the longitudinal following distance; when the ego vehicle is stably driving in a state containing lane keeping driving behavior, if the intention action of the driver's steering request is greater than the control request output by the auxiliary driving system, and the lane keeping center shifts left or right when the driver ends the steering intervention compared to before intervention, it is inferred that the driver has a driving preference of left or right lane keeping.

6. The intelligent assisted driving hierarchical decision method of claim 1, wherein, The safety condition is that: ① the collision risk of the current lane is less than a certain threshold, and ② the collision risk of the target decision lane is less than a certain threshold, both propositions are true, which is expressed as: C 31 =（ F 1＜ F e ）∧（ F 2＜ F 0） In the formula, if C 31 is a true proposition, it indicates that it meets the safety condition, otherwise it indicates that it does not meet the driving behavior safety condition; F 1 and F e respectively represent the collision risk of the current lane and the corresponding collision risk threshold, F 2 and F 0 respectively represent the collision risk of the target decision lane and the corresponding collision risk threshold, and only when the target decision lane is the same as the current lane, F e = F 0; wherein the collision risk of the current lane is represented as: In the formula, M represents the equivalent mass of the ego vehicle; e represents the natural base; k 1 and k 2 respectively represent the distance coefficient and the speed coefficient; v represents the speed of the ego vehicle; i =1, 2 respectively represent the obstacle in front of or behind the ego vehicle in the lane where the ego vehicle is located or the target decision lane; r i ∈ {0, 1} is the direction coefficient, which respectively represents the front or rear position of the target obstacle in the driving direction of the ego vehicle; G represents the constant coefficient; M i represents the equivalent mass of the obstacle i ; d i represents the relative distance between the ego vehicle and the obstacle i ; v i represents the driving speed of the obstacle i , θ i represents the angle between the speed direction of the obstacle i and the vector distance direction of the ego vehicle.

7. An intelligent assisted driving hierarchical decision system characterized by, Comprise: The acquisition module is used for acquiring the switch signal of the auxiliary driving mode of the vehicle; The first decision module is used for deciding the working state of the auxiliary driving mode including activation and standby according to the driving state and driving intention of the driver; wherein the driving state includes at least one abnormal state of hand-off, distraction, fatigue and yawning, and the driving intention includes at least one driving operation request of acceleration, braking and deceleration, and steering the steering wheel; The second decision module is used for deciding the motion mode of the vehicle according to the steering intention of the driver and the surrounding environment of the vehicle when the auxiliary driving mode is in the activated state; wherein the motion mode includes one of longitudinal motion mode, lateral motion mode and comprehensive motion mode of horizontal and vertical directions; The third decision module is used for deciding the driving behavior of the vehicle according to the decided motion mode, motion state and surrounding environment of the vehicle, and combining the historical following and lane keeping preferences of the driver; wherein the driving behavior includes one or two of adaptive cruise, increasing distance longitudinal following, reducing distance longitudinal following, longitudinal following, lane keeping and lateral following; The output module is used for safety pre-judgment for the decided driving behavior, and outputs the decision result under the safety condition conforming to the safety pre-judgment; The first decision module specifically comprises: The first judgment unit is used for judging whether the switching from standby to activation of the auxiliary driving mode conforms to the switching condition; wherein the switching condition is that: ① the driver state is abnormal, ② the intention action of the driver's acceleration request is greater than the control request amount output by the auxiliary driving system, ③ the driver has a braking and deceleration request, and ④ the intention action of the driver's steering the steering wheel is greater than the control request amount output by the auxiliary driving system, any one of the four propositions is true, which is expressed as: C 11 = ( x∈ Driver state abnormal) ∨ ( T driver > T ADAS ) ∨ ( T brake > 0) ∨ ( δ driver > δ ADAS ), In the formula, if C 11 is a true proposition, it indicates that the switching simulation condition is met, otherwise it indicates that the switching simulation condition is not met; x represents the current state of the driver, and the driver state exception = {hands off, distracted, fatigue, yawn}; T driver represents the driver's acceleration request torque, T ADAS represents the request torque of the auxiliary driving system driving control; T brake represents the driver's brake pedal opening request value; δ driver represents the driver's steering wheel angle request value, δ ADAS represents the control request amount of the auxiliary driving system steering wheel angle.

8. An electronic device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, The processor executes the computer program to realize the intelligent auxiliary driving hierarchical decision method according to any one of claims 1 to 6.

9. A storage medium having stored thereon a computer program, characterized in that The program is executed by the processor to realize the intelligent auxiliary driving hierarchical decision method according to any one of claims 1 to 6.

Images