Vehicle target trajectory constraint determination method and device, equipment and storage medium

Abstract

The embodiment of the invention provides a vehicle target trajectory constraint determination method and device, equipment and a storage medium. The method comprises the steps of calculating potentials of a plurality of actuators of a vehicle based on a road adhesion coefficient, performing dynamic potential conversion of the whole vehicle to obtain dynamic trajectory constraint information of the vehicle, determining comfort trajectory constraint information of the vehicle based on road information, obstacle information and in-vehicle member identification information, and determining the comfort trajectory constraint information of the vehicle according to the determined comfort trajectory constraint information. And carrying out fusion processing on the dynamic trajectory constraint information and the comfort trajectory constraint information to obtain target trajectory constraint information of the vehicle. According to the method, the chassis dynamic characteristics, the comfort requirement, the complex driving environment and other factors of the vehicle are comprehensively considered, and accurate constraint and adjustment of the vehicle driving track are achieved. The driving safety and stability are improved, the driving comfort and the passenger experience are optimized, and meanwhile the intelligent level of the automatic driving system and the vehicle driving efficiency and energy saving performance are improved.

Description

Technical Field

[0001] The present application relates to the field of vehicle autonomous driving technology, and in particular to a method, device, equipment and storage medium for determining vehicle target trajectory constraints. Background Art

[0002] With the continuous advancement of technology, autonomous driving technology brings more convenience and safety to people's travel. Target trajectory constraint determination is one of the key links in autonomous driving technology. It involves how autonomous vehicles determine the optimal driving trajectory based on multiple factors such as road environment, traffic rules, and vehicle status. This technology mainly stems from the pursuit of driving safety and comfort for autonomous vehicles. Through accurate target trajectory constraint determination, autonomous vehicles can better adapt to complex traffic environments and improve driving stability and safety.

[0003] In the prior art, autonomous driving usually constrains the target trajectory and its constraints based on kinematics and obstacle factors.

[0004] However, the constraints of the above method are limited and relatively simple, and cannot achieve intelligent adjustment of the trajectory, resulting in a poor driving experience for the driver. Summary of the invention

[0005] The vehicle target trajectory constraint determination method, device, equipment and storage medium provided in the embodiments of the present application are used to solve the limitation of constraining the vehicle trajectory in the prior art and the problem that the trajectory cannot be intelligently adjusted.

[0006] In a first aspect, an embodiment of the present application provides a method for determining a vehicle target trajectory constraint, comprising:

[0007] Calculating the potential of multiple actuators of the vehicle based on a predetermined road adhesion coefficient;

[0008] Convert the potential of each actuator into the dynamic potential of the whole vehicle to obtain the dynamic trajectory constraint information of the vehicle;

[0009] Determining the comfort trajectory constraint information of the vehicle based on the pre-acquired road surface information, obstacle information, and vehicle occupant identification information;

[0010] The dynamic trajectory constraint information and the comfort trajectory constraint information are fused to obtain the target trajectory constraint information of the vehicle.

[0011] In a possible implementation manner, determining the comfort trajectory constraint information of the vehicle based on pre-acquired road surface information, obstacle information, and vehicle occupant identification information includes:

[0012] Determining a comfort control mode according to the vehicle occupant identification information;

[0013] The comfort trajectory constraint information is obtained through fuzzy control calculation based on the road surface information, the obstacle information and the comfort control mode.

[0014] In a possible implementation manner, obtaining the comfort trajectory constraint information through fuzzy control calculation based on the road surface information, the obstacle information and the comfort control mode includes:

[0015] Based on the road surface information, determining comfort road surface constraint information;

[0016] Based on the obstacle information, determining comfort obstacle constraint information;

[0017] determining a correction coefficient according to the comfort control mode;

[0018] Based on the correction coefficient, the comfort road constraint information and the comfort obstacle constraint information are fused and corrected through a fuzzy control algorithm to obtain the comfort trajectory constraint information.

[0019] In a possible implementation manner, the plurality of actuators include a driving actuator, a braking actuator, a steering actuator, and a suspension actuator, and the potential of the plurality of actuators of the vehicle is calculated based on a predetermined road adhesion coefficient, including:

[0020] calculating the potential of the driving actuator based on the road adhesion coefficient;

[0021] calculating the potential of the brake actuator based on the road adhesion coefficient;

[0022] calculating the potential of the steering actuator based on the road adhesion coefficient;

[0023] Based on the road adhesion coefficient, the potential of the suspension actuator is calculated.

[0024] In a possible implementation manner, determining the comfort control mode according to the vehicle occupant identification information includes:

[0025] If the vehicle occupant identification information indicates that the vehicle occupant includes a child, determining a child mode as the comfort control mode;

[0026] If the vehicle occupant identification information indicates that the vehicle occupants do not include children but include elderly people, determining the elderly mode as the comfort control mode;

[0027] If the vehicle occupant identification information indicates that the vehicle occupants include passengers but do not include children and the elderly, determining the passenger mode as the comfort control mode;

[0028] If the vehicle occupant identification information indicates that the vehicle occupants include only the driver, then based on the driver's characteristic information, the driver model is determined as the comfort control mode, and the driver mode includes a first driver mode, a second driver mode, or a third driver mode, and the first driver mode, the second driver mode, and the third driver mode represent different driving preferences.

[0029] In a possible implementation, the method further includes:

[0030] If the pre-acquired HMI information indicates that the driver has designated a control mode, the control mode designated by the driver is determined as the comfort control mode.

[0031] In one possible implementation, the target trajectory constraint information includes any multiple corresponding maximum and minimum values ​​of longitudinal acceleration, longitudinal acceleration change rate, lateral acceleration, lateral acceleration change rate, target trajectory curvature, target curvature change rate, vehicle speed, body vertical acceleration, body vertical acceleration change rate, yaw angular velocity, yaw angular velocity change rate, pitch angular velocity, pitch angular velocity change rate, roll angular velocity, and roll angular velocity change rate.

[0032] In a second aspect, an embodiment of the present application provides a method for determining a vehicle target trajectory, comprising:

[0033] Constraint adjustment is performed on the planned initial trajectory according to the target trajectory constraint information to obtain the target trajectory, wherein the target trajectory constraint information is determined by the first aspect and / or various possible implementations of the first aspect.

[0034] In a third aspect, an embodiment of the present application provides a device for determining a vehicle target trajectory constraint, comprising:

[0035] A calculation module for calculating the potential of a plurality of actuators of the vehicle based on a predetermined road adhesion coefficient;

[0036] A conversion module, used for converting the potential of each actuator into the dynamic potential of the whole vehicle to obtain the dynamic trajectory constraint information of the vehicle;

[0037] A determination module, configured to determine the comfort trajectory constraint information of the vehicle based on pre-acquired road surface information, obstacle information, and vehicle occupant identification information;

[0038] The fusion module is used to fuse the dynamic trajectory constraint information and the comfort trajectory constraint information to obtain the target trajectory constraint information of the vehicle.

[0039] In a fourth aspect, an embodiment of the present application provides a device for determining a vehicle target trajectory, comprising:

[0040] An adjustment module is used to perform constraint adjustment on the planned initial trajectory according to the target trajectory constraint information to obtain the target trajectory, wherein the target trajectory constraint information is determined by the first aspect and / or various possible implementation methods of the first aspect.

[0041] In a fifth aspect, an embodiment of the present application provides an electronic device, including: a memory, a processor;

[0042] A processor, and a memory communicatively connected to the processor;

[0043] The memory stores computer-executable instructions;

[0044] The processor executes the computer-executable instructions stored in the memory, so that the processor executes the above first aspect and / or various possible implementations of the first aspect and the implementations of the second aspect.

[0045] In a sixth aspect, an embodiment of the present application provides a computer-readable storage medium, in which computer-readable storage medium is stored computer execution instructions, and when the computer execution instructions are executed by a processor, they are used to implement the first aspect and / or various possible implementations of the first aspect and the implementation of the second aspect as described above.

[0046] In a fifth aspect, an embodiment of the present application provides a computer program product, including a computer program, which, when executed by a processor, implements the first aspect and / or various possible implementations of the first aspect and the implementation of the second aspect as described above.

[0047] The method, device, equipment and storage medium for determining the target trajectory constraint of the vehicle provided in the embodiment of the present application calculates the potential of multiple actuators of the vehicle based on a predetermined road adhesion coefficient, converts the potential of each actuator into the dynamic potential of the whole vehicle, obtains the dynamic trajectory constraint information of the vehicle, determines the comfort trajectory constraint information of the vehicle based on the pre-acquired road information, obstacle information, and vehicle occupant identification information, fuses the dynamic trajectory constraint information and the comfort trajectory constraint information to obtain the target trajectory constraint information of the vehicle, and constrains and adjusts the vehicle's driving trajectory based on the target trajectory constraint information to obtain the target trajectory. The above method realizes accurate constraint and adjustment of the vehicle's driving trajectory by comprehensively considering factors such as the chassis dynamic characteristics of the vehicle, comfort requirements, and complex driving environment. It not only improves the safety and stability of driving, but also optimizes driving comfort and passenger experience, while improving the intelligence level of the automatic driving system and the vehicle's driving efficiency and energy saving. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0049] Figure 1 A schematic diagram of the model architecture of an application system of the method for determining vehicle target trajectory constraints provided in this application;

[0050] Figure 2 Schematic diagram of the process of determining the vehicle target trajectory constraint provided in this application Figure 1 ;

[0051] Figure 3 A schematic diagram of a flow chart of a method for determining a vehicle target trajectory provided in this application;

[0052] Figure 4 Schematic diagram of the process of determining the vehicle target trajectory constraint provided in this application Figure 2 ;

[0053] Figure 5 Schematic diagram of the process of determining the vehicle target trajectory constraint provided in this application Figure 3 ;

[0054] Figure 6 Schematic diagram of the process of determining the vehicle target trajectory constraint provided in this application Figure 4 ;

[0055] Figure 7 Schematic diagram of the process of determining the vehicle target trajectory constraint provided in this application Figure 5 ;

[0056] Figure 8A schematic diagram of the structure of a device for determining a vehicle target trajectory constraint provided in the present application;

[0057] Fig. 9 A schematic diagram of the structure of a device for determining a vehicle target trajectory provided by the present application;

[0058] Fig.10 A schematic diagram of the structure of the electronic device provided in this application.

[0059] The above drawings have shown clear embodiments of the present application, which will be described in more detail later. These drawings and text descriptions are not intended to limit the scope of the present application in any way, but to illustrate the concept of the present application to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION

[0060] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present application. Instead, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims.

[0061] With the continuous advancement of technology, autonomous driving technology brings more convenience and safety to people's travel. Target trajectory constraint determination is one of the key links in autonomous driving technology. It involves how autonomous vehicles determine the optimal driving trajectory based on multiple factors such as road environment, traffic rules, and vehicle status. This technology mainly stems from the pursuit of driving safety and comfort for autonomous vehicles. Through accurate target trajectory constraint determination, autonomous vehicles can better adapt to complex traffic environments and improve driving stability and safety. In the prior art, autonomous driving usually constrains the target trajectory and its constraints based on kinematics and obstacle factors to determine the target trajectory. However, the constraints of the above method are limited and relatively single, and cannot achieve intelligent adjustment of the trajectory, resulting in a poor driving experience for the driver.

[0062] In view of the above problems, the present application provides a method, device, equipment and storage medium for determining the target trajectory constraint of a vehicle, so that the determination of the target trajectory constraint is more accurate and flexible, thereby improving the driving experience. Specifically, when planning the target trajectory and its constraints, the current autonomous driving usually only considers kinematics and obstacle factors, and mainly focuses on the X and Y directions. However, the chassis dynamics of the whole vehicle are less considered, and the comfort in the Z direction is not fully considered. As a result, the target trajectory and trajectory constraints of autonomous driving are relatively single, resulting in a lack of personalization in the experience and a lack of good ride comfort. In view of these problems, the inventor studied whether it is possible to calculate the potential of each actuator in the chassis in real time based on intelligent road surface recognition technology and convert it into a constraint on the target trajectory of the entire vehicle. At the same time, it can also intelligently identify the driving mode, the status of the passengers in the car and the intelligent human-computer interaction in real time, so as to realize the real-time intelligent personalization and comfort correction of the target trajectory. Thereby, it not only ensures the full utilization of the chassis capacity of the whole vehicle, improves the accuracy of the target trajectory, but also ensures the comfort of different passengers or drivers, and completely changes the driving experience of autonomous driving.

[0063] Figure 1 A schematic diagram of the model architecture of the application system of the vehicle target trajectory constraint determination method provided in this application, such as Figure 1 As shown, the model architecture includes a road surface and environment recognition module 101, an actuator potential calculation module 102, a vehicle capability constraint calculation module 103, a driver recognition module 104, a passenger recognition module 105, a human-machine interface (HMI) input processing module 106, a comfort comprehensive processing module 107, a trajectory constraint comprehensive processing module 108 and a signal output processing module 109.

[0064] Among them, the road surface and environment recognition module 101 receives the road surface information and obstacle information collected by the vehicle, and then inputs it into the actuator potential calculation module 102. The actuator potential calculation module 102 calculates the potential of each actuator according to the road surface information, and sends the potential of each actuator to the vehicle capability constraint calculation module 103 to calculate the vehicle's dynamic trajectory constraint information.

[0065] The driver identification module 104 collects the driver identification information in the vehicle, the passenger identification module 105 collects the occupant identification information in the vehicle, and the HMI input processing module 106 receives the HMI information input by the driver, and then inputs the driver identification information, the occupant identification information and the HMI information into the comfort comprehensive processing module 107 for processing to obtain the vehicle's comfort trajectory constraint information.

[0066] The trajectory constraint comprehensive processing module 108 performs fusion processing based on the comfort trajectory constraint information, the dynamic trajectory constraint information, and the road surface information to obtain the target trajectory constraint information, and then inputs the target trajectory constraint information to the signal output processing module 109 to adjust and determine the target trajectory.

[0067] The technical solution of the present application and how the technical solution of the present application solves the above-mentioned technical problems are described in detail below with specific embodiments. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present application will be described below in conjunction with the accompanying drawings.

[0068] Figure 2 Schematic diagram of the process of determining the vehicle target trajectory constraint provided in this application Figure 1 ,like Figure 2 As shown, the method includes:

[0069] S201 : Calculate the potential of multiple actuators of the vehicle based on a predetermined road adhesion coefficient.

[0070] In this step, in order to improve the feasibility of trajectory planning, enhance the stability and safety of vehicle driving, optimize vehicle handling performance, improve the overall performance of the autonomous driving system, and adapt to more road conditions and environments, the vehicle's chassis dynamics can be considered when constraining the vehicle trajectory.

[0071] Specifically, after the road adhesion coefficient is determined, the potential of multiple actuators of the vehicle is calculated.

[0072] Exemplarily, the multiple actuators of the vehicle may include a driving actuator, a braking actuator, a steering actuator, and a suspension actuator. Based on the road adhesion coefficient, the potential of the above actuators is calculated respectively.

[0073] S202: Convert the potential of each actuator into the dynamic potential of the entire vehicle to obtain the dynamic trajectory constraint information of the vehicle.

[0074] In this step, once the potential of the chassis actuators is obtained, the potential of all actuators is converted into the dynamic potential of the whole vehicle, and this information can be converted into dynamic constraints on the vehicle trajectory.

[0075] For example, according to the potential of the steering system actuator, the maximum steering angle and steering speed of the vehicle can be limited to ensure that the vehicle can remain stable and avoid loss of control when turning. According to the potential of the braking system actuator, the maximum deceleration and braking distance of the vehicle can be limited to ensure that the vehicle can stop quickly and remain stable during emergency braking. According to the potential of the suspension system actuator, the stiffness and damping of the suspension can be adjusted to cope with different road conditions and driving requirements, thereby maintaining the ride comfort and handling stability of the vehicle. According to the potential of the vehicle's power system (such as the engine or motor), the maximum speed and acceleration of the vehicle can be limited to ensure that the power system's capabilities are not exceeded during driving.

[0076] S203: Determine the comfort trajectory constraint information of the vehicle based on the pre-acquired road surface information, obstacle information, and vehicle occupant identification information.

[0077] In this step, the existing technology usually constrains the target trajectory based on vehicle dynamics and obstacle factors, that is, only focuses on the X and Y directions, and fails to consider the comfort of the Z direction, resulting in a poor driving experience and a relatively simple constraint. Based on road information, obstacle information, and vehicle occupant identification information, the vehicle's comfort trajectory constraint information is determined.

[0078] Specifically, the comfort control mode is determined according to the in-vehicle occupant identification information, and the comfort trajectory constraint information is obtained through fuzzy control calculation based on the road surface information, obstacle information and the comfort control mode.

[0079] S204: Fusing the dynamic trajectory constraint information and the comfort trajectory constraint information to obtain the target trajectory constraint information of the vehicle.

[0080] In this step, after the dynamic trajectory constraint information and the comfort trajectory constraint information are determined, the two types of constraint information are fused to obtain the target trajectory constraint information of the vehicle.

[0081] Exemplarily, the dynamic trajectory constraint information mainly focuses on the physical performance and stability of the vehicle during driving. These constraint information are usually based on the vehicle's dynamic model, including the vehicle's longitudinal acceleration, longitudinal acceleration change rate, lateral acceleration, lateral acceleration change rate, target trajectory curvature, target curvature change rate, vehicle speed, etc. These parameters jointly determine the dynamic response and stability of the vehicle during driving. Comfort trajectory constraint information mainly focuses on the passenger's riding experience and comfort. These constraint information are usually based on factors such as the vehicle's suspension system, seat design, and vibration and acceleration changes during vehicle driving. Including body vertical acceleration, body vertical acceleration change rate, yaw angular velocity, yaw angular velocity change rate, pitch angular velocity, pitch angular velocity change rate, roll angular velocity, roll angular velocity change rate, etc. These parameters jointly determine the passenger's comfort and riding experience during driving. The two types of constraint information are fused, which can be fused in the following way:

[0082] 1. Assign different weights to the dynamic trajectory constraint information and the comfort trajectory constraint information, and then calculate the weighted sum as the final constraint information. The choice of weights can be adjusted according to factors such as vehicle type, passenger needs, and driving environment. For example, for a high-performance racing car, a higher weight may be given to the dynamic constraint; while for a luxury car, more emphasis may be placed on the comfort constraint.

[0083] Optionally, the above weights can also be dynamically adjusted according to changes in the driving environment. For example, when driving on a highway, the weight of the dynamic constraint can be increased to ensure the stability and safety of the vehicle; while when driving on a city road, the weight of the comfort constraint can be increased to improve the passenger's riding experience.

[0084] 2. Use optimization algorithms (such as genetic algorithms, particle swarm algorithms, etc.) to find the optimal trajectory that meets the dynamics and comfort constraints. This method can comprehensively consider multiple constraints and find the optimal solution.

[0085] For example, the objective function is the core of the optimization algorithm, which defines the performance index to be optimized. When integrating dynamics and comfort constraints, a comprehensive objective function can be defined, which considers both dynamics performance and comfort indexes. For example, the objective function can be defined as the minimum difference between the weighted sum of dynamics performance indexes and the weighted sum of comfort indexes.

[0086] The constraints ensure that the optimization algorithm does not violate dynamic and comfort constraints during the search process. These constraints can include physical limitations of the vehicle, passenger comfort requirements, and restrictions of the road and traffic environment.

[0087] 3. Use fuzzy logic to deal with the fuzzy relationship between dynamics and comfort constraints. By defining fuzzy sets and fuzzy rules, the fusion and coordination of the two constraint information can be achieved.

[0088] Optionally, fuzzy sets are the basis of fuzzy logic. When fusing dynamics and comfort constraints, two fuzzy sets can be defined: one for dynamics constraints and another for comfort constraints. The elements in these sets can be different constraint information or performance indicators.

[0089] Fuzzy rules define the relationship between fuzzy sets. When integrating dynamics and comfort constraints, a series of fuzzy rules can be defined to describe the interaction and influence between these constraints. For example, a rule can be defined: if the dynamics constraint is high and the comfort constraint is low, increase the weight of the comfort constraint; if the dynamics constraint is low and the comfort constraint is high, increase the weight of the dynamics constraint.

[0090] Defuzzification is the process of converting fuzzy outputs into clear outputs. After integrating the dynamics and comfort constraints, the fuzzy output results need to be converted into clear vehicle target trajectory constraint information. This can be achieved by using defuzzification methods such as the center of gravity method, maximum membership method, or weighted average method.

[0091] The above is merely a specific example of the fusion processing of dynamic constraint information and comfort constraint information, and the specific implementation method is not specifically limited in the embodiments of this application.

[0092] Optionally, the target trajectory constraint information includes but is not limited to the maximum and minimum values ​​of each of the longitudinal acceleration, the longitudinal acceleration change rate, the lateral acceleration, the lateral acceleration change rate, the target trajectory curvature, the target curvature change rate, the vehicle speed, the body vertical acceleration, the body vertical acceleration change rate, the yaw angular velocity, the yaw angular velocity change rate, the pitch angular velocity, the pitch angular velocity change rate, the roll angular velocity, and the roll angular velocity change rate.

[0093] The method for determining the target trajectory constraint of a vehicle provided in the embodiment of the present application calculates the potential of multiple actuators of the vehicle based on a predetermined road adhesion coefficient, converts the potential of each actuator into the dynamic potential of the whole vehicle, obtains the dynamic trajectory constraint information of the vehicle, determines the comfort trajectory constraint information of the vehicle based on the pre-acquired road information, obstacle information, and vehicle occupant identification information, fuses the dynamic trajectory constraint information and the comfort trajectory constraint information, and obtains the target trajectory constraint information of the vehicle. The above method realizes the precise constraint and adjustment of the vehicle's driving trajectory by comprehensively considering factors such as the chassis dynamics characteristics of the vehicle, comfort requirements, and complex driving environment. It not only improves the safety and stability of driving, but also optimizes driving comfort and passenger experience, while improving the intelligence level of the automatic driving system and the driving efficiency and energy saving of the vehicle.

[0094] Figure 3 A flow chart of a method for determining a vehicle target trajectory provided in this application is shown in FIG. Figure 3 As shown, the method includes:

[0095] S301: Calculating the potential of multiple actuators of the vehicle based on a predetermined road adhesion coefficient.

[0096] S302: Convert the potential of each actuator into the dynamic potential of the entire vehicle to obtain the dynamic trajectory constraint information of the vehicle.

[0097] S303: Determine the comfort trajectory constraint information of the vehicle based on the pre-acquired road surface information, obstacle information, and vehicle occupant identification information.

[0098] S304: The dynamic trajectory constraint information and the comfort trajectory constraint information are integrated to obtain the target trajectory constraint information of the vehicle.

[0099] The specific implementation of steps S301 - S304 is the same as that of steps S201 - S204 in the aforementioned embodiment, and will not be repeated here.

[0100] S305: Constraint adjustment is performed on the vehicle driving trajectory based on the target trajectory constraint information to obtain a target trajectory.

[0101] In this step, in order to ensure that the vehicle drives safely, stably and comfortably according to the expected trajectory, after determining the target trajectory constraint information, it is necessary to preliminarily plan the vehicle's driving trajectory based on this constraint information. This usually involves modeling the vehicle's kinematic model and dynamic model, and predicting and optimizing the vehicle's driving trajectory based on these models. The preliminarily planned driving trajectory is as close to the target trajectory as possible while satisfying all constraints. Based on the preliminarily planned driving trajectory, it is necessary to further adjust the trajectory based on the target trajectory constraint information.

[0102] According to the dynamic constraint information such as the longitudinal acceleration and longitudinal acceleration change rate of the vehicle, the acceleration, deceleration and other motion states of the vehicle are adjusted to ensure the stability and safety of the vehicle's driving.

[0103] According to the comfort constraint information such as the vehicle body vertical acceleration and the rate of change of the vehicle body vertical acceleration, the vehicle's suspension system, seat design, etc. are adjusted to improve the riding comfort of passengers.

[0104] The vehicle's trajectory is dynamically adjusted based on external factors such as road conditions and traffic flow to avoid collisions with obstacles or violations of traffic regulations.

[0105] The method for determining the target trajectory of a vehicle provided in an embodiment of the present application calculates the potential of multiple actuators of the vehicle based on a predetermined road adhesion coefficient, converts the potential of each actuator into the dynamic potential of the entire vehicle, obtains the dynamic trajectory constraint information of the vehicle, determines the comfort trajectory constraint information of the vehicle based on pre-acquired road information, obstacle information, and vehicle occupant identification information, fuses the dynamic trajectory constraint information and the comfort trajectory constraint information to obtain the target trajectory constraint information of the vehicle, and constrains and adjusts the vehicle's driving trajectory based on the target trajectory constraint information to obtain the target trajectory. By comprehensively considering the constraint conditions and obtaining accurate constraint information, the target trajectory is made more accurate, which improves driving stability and safety.

[0106] Figure 4 Schematic diagram of the process of determining the vehicle target trajectory constraint provided in this application Figure 2 ,like Figure 4 As shown, based on the above embodiment, step S203 specifically includes:

[0107] S401. Determine a comfort control mode according to vehicle occupant identification information.

[0108] In this step, in order to improve driving intelligence, after obtaining the information of the occupants in the vehicle, the comfort control mode can be determined based on the identification information of the occupants in the vehicle.

[0109] Specifically, if the pre-acquired HMI information indicates that the driver has specified a control mode, the control mode specified by the driver is determined as the comfort control mode; if the in-car occupant identification information indicates that the in-car occupants include children, the child mode is determined as the comfort control mode; if the in-car occupant identification information indicates that the in-car occupants do not include children but include the elderly, the elderly mode is determined as the comfort control mode; if the in-car occupant identification information indicates that the in-car occupants include passengers but do not include children and the elderly, the passenger mode is determined as the comfort control mode; if the in-car occupant identification information indicates that the in-car occupants include only the driver, then based on the driver's characteristic information, the driver model is determined as the comfort control mode.

[0110] S402 : Based on the road surface information, obstacle information and comfort control mode, obtain comfort trajectory constraint information through fuzzy control calculation.

[0111] In this step, after the road surface information, obstacle information and comfort control mode are acquired in advance, the comfort trajectory constraint information is determined based on the above-mentioned multiple information.

[0112] Specifically, based on the road surface information, the comfort road surface constraint information is determined, based on the obstacle information, the comfort obstacle constraint information is determined, according to the comfort control mode, the correction coefficient is determined, and based on the correction coefficient, the comfort road surface constraint information and the comfort obstacle constraint information are fused and corrected through the fuzzy control algorithm to obtain the comfort trajectory constraint information.

[0113] The method for determining the vehicle target trajectory constraint provided in the embodiment of the present application determines the comfort control mode according to the in-vehicle occupant identification information, and obtains the comfort trajectory constraint information through fuzzy control calculation based on the road surface information, obstacle information and the comfort control mode. The above method calculates the comfort trajectory constraint information using the fuzzy control algorithm by comprehensively considering the in-vehicle occupant identification information, road surface information, obstacle information and the comfort control mode, thereby improving the ride comfort, enhancing driving safety, optimizing the vehicle driving efficiency and improving the intelligence level of the automatic driving system.

[0114] Figure 5 Schematic diagram of the process of determining the vehicle target trajectory constraint provided in this application Figure 3 ,like Figure 5 As shown, based on the above embodiment, step S402 specifically includes:

[0115] S501: Determine comfort road constraint information based on road surface information.

[0116] In this step, after the road surface information is acquired in advance, a match is performed in a preset restriction value set based on the road surface type in the road surface information, thereby obtaining the comfort road surface constraint information.

[0117] The preset limit value set includes limit values ​​of multiple constraint conditions corresponding to multiple road types. The constraint conditions may include but are not limited to longitudinal acceleration, longitudinal acceleration change rate, lateral acceleration, lateral acceleration change rate, target trajectory curvature, target curvature change rate, vehicle speed, vehicle body vertical acceleration, vehicle body vertical acceleration change rate, yaw angular velocity, yaw angular velocity change rate, pitch angular velocity, pitch angular velocity change rate, roll angular velocity, and roll angular velocity change rate.

[0118] Exemplarily, pavement types may include: highway pavement, which usually has high flatness and structural strength and is designed for high-speed driving; urban road pavement, including main roads, secondary roads and branch roads, etc., the design of which needs to consider factors such as traffic flow, pedestrian safety and urban landscape; rural road pavement, which is usually simpler, may have more potholes and unevenness, and is designed for low-speed driving.

[0119] Longitudinal acceleration

[0120] 1. Highway pavement

[0121] Maximum value: usually no more than 0.3m / s² (this value may vary depending on the specific design standards, but generally does not exceed this range to ensure stability during high-speed driving).

[0122] Minimum value: There is no specific minimum value limit, but excessive negative acceleration (i.e. deceleration too quickly) should be avoided so as not to cause discomfort to passengers.

[0123] 2. Urban road surface

[0124] Maximum value: may be slightly higher than that of expressways, but generally does not exceed 0.3m / s² (the specific value depends on factors such as traffic flow and design speed of urban roads).

[0125] Minimum value: There is no specific minimum value limit, but it must ensure the stability of the vehicle and the comfort of passengers when driving at low speeds in the city.

[0126] 3. Rural road surface

[0127] Maximum value: Due to the low driving speed, the maximum value of longitudinal acceleration may be relatively loose, but generally should not exceed 0.4m / s² (to avoid vehicle loss of control or passenger discomfort).

[0128] Minimum value: There is no specific minimum value, but it is necessary to ensure the stability and safety of the vehicle when driving on rural roads.

[0129] Longitudinal deceleration

[0130] 1. Highway pavement

[0131] Maximum value: In emergency braking, the longitudinal deceleration may reach a larger value, but generally does not exceed 0.8g (g is the acceleration due to gravity, about 9.8m / s²). This depends on the braking performance of the vehicle and the friction coefficient of the road surface.

[0132] Minimum value: There is no specific minimum value limit, but it is necessary to ensure that the vehicle can be decelerated to a stop smoothly.

[0133] 2. Urban road surface

[0134] Maximum value: may be slightly lower than on highways to accommodate frequent stopping and starting in cities. Generally, it does not exceed 0.8g, but the specific value depends on the traffic flow and design standards of urban roads.

[0135] Minimum value: There is no specific minimum value limit, but it must ensure the stability of the vehicle and the comfort of passengers when driving at low speeds in the city.

[0136] 3. Rural road surface

[0137] Maximum value: may be relatively lenient, but generally should not exceed 1.0g (to avoid loss of vehicle control or severe discomfort to passengers).

[0138] Minimum value: There is no specific minimum value, but it is necessary to ensure that the vehicle can be safely slowed to a stop on rural roads.

[0139] Curvature

[0140] 1. Highway pavement

[0141] Maximum value: The minimum curvature radius of highways in plains and hilly areas is usually higher, such as 650m (corresponding to a smaller curvature value). Highways in mountainous areas may use a smaller curvature radius, such as 250m (corresponding to a larger curvature value), but special design and reinforcement are required.

[0142] Minimum value: There is no specific minimum value limit, but too small a curvature may cause vehicle instability or passenger discomfort.

[0143] 2. Urban road surface

[0144] Maximum value: depends on the road type and traffic demand. The curvature radius of a curve on a general urban road may be smaller than that on a highway, but the specific value needs to be determined according to the design standards.

[0145] Minimum value: There is no specific minimum value limit, but it is necessary to ensure the stability and safety of the vehicle when driving on urban roads.

[0146] 3. Rural road surface

[0147] Maximum value: may be relatively lenient, but generally should not be too small to avoid vehicle instability or passenger discomfort. The specific value depends on the design standards and traffic demand of rural roads.

[0148] Minimum value: There is no specific minimum value, but it is necessary to ensure that the vehicle can safely negotiate bends on rural roads.

[0149] The above limit values ​​are only examples and are not absolute standard values. In actual road design and maintenance, it is necessary to consider a variety of factors (such as regional characteristics, traffic flow, design speed, etc.) to determine the final comfort limit value.

[0150] S502: Determine comfort obstacle constraint information based on obstacle information.

[0151] In this step, after obtaining obstacle information on the vehicle's driving road in advance, the comfort obstacle constraint information is determined based on the obstacle information.

[0152] Specifically, the comfort obstacle constraint information is calculated according to the obstacle type, distance, and height.

[0153] Illustratively, different types of obstacles have different effects on comfort. For example, fixed buildings and trees have different visual and physical effects than moving vehicles and pedestrians. The distance between the obstacle and the observer (e.g., pedestrian, driver). The greater the distance, the less the effect of the obstacle on comfort is usually. The height of the obstacle relative to the observer's line of sight or the ground. The higher the height, the more conspicuous the obstacle may be and the greater the effect on comfort may be.

[0154] The comfort standard can be a comfort threshold determined based on the sensory perception and psychological reaction of the passengers, such as maximum lateral acceleration, maximum longitudinal deceleration, minimum curvature radius, etc.

[0155] For example, the vehicle type is a family car, the driving speed is 60 km / h (about 16.67 m / s), the road type is a city main road, and the obstacle type is a fixed obstacle on the roadside (such as trees and street lights). The comfort standard is the maximum lateral acceleration of 0.3g (about 3 m / s²), and the visual obstacle limit is that the obstacle shall not block the driver's line of sight by more than 10°.

[0156] Calculation of lateral acceleration limit: Assume that the vehicle needs to go around a curve with a radius of R meters. According to the circular motion formula, lateral acceleration a = v² / R. In order to meet the comfort standard, a≤0.3g, substitute v = 16.67 m / s, and get R≥(16.67 m / s)² / (3 m / s²)≈92.9 m. Therefore, the curve radius must not be less than 92.9 meters to meet the comfort limit of lateral acceleration.

[0157] Calculation of visual obstruction limit value: Assume that the obstacle is located at an angle θ to the vehicle's travel direction, the obstacle height is h meters, and the distance from the vehicle is d meters. According to trigonometric functions, tan(θ) = h / d. In order to meet the visual obstruction limit, θ≤10. Assuming the obstacle height h = 5 meters (such as a street lamp), d≥5 meters / tan(10°)≈28.66 meters. Therefore, the obstacle must be no less than 28.66 meters away from the vehicle to avoid blocking the driver's vision by more than 10°.

[0158] S503: Determine a correction coefficient according to the comfort control mode.

[0159] In this step, after the comfort control mode of the vehicle is determined, the comfort constraint can be corrected and adjusted based on the current comfort control mode of the vehicle, and the correction coefficient is determined according to the comfort control mode.

[0160] Specifically, the comfort control mode is preset in a correction coefficient mapping relationship set, so that after the comfort control mode is determined, the correction coefficient corresponding to the comfort control mode is matched in the mapping relationship set.

[0161] S504: Based on the correction coefficient, the comfort road constraint information and the comfort obstacle constraint information are fused and corrected by a fuzzy control algorithm to obtain the comfort trajectory constraint information.

[0162] In this step, the correction coefficient obtained in the above step is used to adjust the comfort obstacle constraint information and the comfort road constraint information to better meet the comfort requirements in different modes. The fuzzy control algorithm is a control method based on fuzzy logic and fuzzy sets, which can effectively handle uncertainty and fuzziness. In the vehicle control system, the fuzzy control algorithm can calculate the final comfort constraint information based on the input comfort obstacle constraint information and comfort road constraint information, as well as the correction coefficient.

[0163] Specifically, the input variables include comfort obstacle constraint information, comfort road constraint information and correction coefficients. These input variables reflect the comfort requirements and the characteristics of the vehicle driving environment under different control modes. In the fuzzy control algorithm, the input variables are mapped to fuzzy sets, and reasoning and decision-making are performed through fuzzy rules. These fuzzy rules are pre-established to describe the relationship and influence between different input variables. The output variable, namely the comfort constraint information, is calculated by the fuzzy control algorithm based on the input variables and fuzzy rules. It reflects the constraints that the vehicle should comply with when driving while meeting the comfort requirements.

[0164] For example, a family sedan is traveling at a speed of 60 km / h (about 16.67 m / s) on a straight line on a city main road, but there is a slight curve ahead with a radius of 100 meters. The comfort control mode is the passenger mode, which focuses more on the passenger's riding experience.

[0165] In passenger mode, the main focus is on passenger comfort, so the following comfort constraint information is set: Comfort obstacle constraint information: The minimum safe distance between the vehicle and the obstacle in front (such as the shoulder, trees, etc.) is set to 5 meters. Comfort road surface constraint information: The maximum bumpiness of the road surface when the vehicle is driving, measured by the acceleration change rate, is set to 0.2 m / s³ (indicates that the road surface is relatively flat and the acceleration change is small). In passenger mode, it is necessary to increase the requirements for stability, so the correction coefficient is set to 1.2 to adjust the comfort obstacle constraint information and comfort road surface constraint information.

[0166] The corrected comfort constraint information is input into the fuzzy control algorithm: Corrected comfort obstacle constraint information: 6 meters, Corrected comfort road constraint information: 0.24 m / s³.

[0167] The fuzzy control algorithm performs fuzzy reasoning and decision-making based on the input corrected comfort constraint information and the current state of the vehicle (such as speed, acceleration, steering angle, etc.). The following is an example of a simplified fuzzy control rule:

[0168] If the vehicle is moving at a high speed and there is a curve ahead, the safe distance from the obstacle is increased and the bumpiness of the road surface is reduced. If the vehicle is moving at a low speed and the road ahead is flat, the safe distance from the obstacle can be appropriately reduced, but the flatness of the road surface can be maintained. According to these fuzzy rules, the fuzzy control algorithm will output a final comfort constraint information, which takes into account the vehicle state, road conditions and passenger comfort needs. Assume that after reasoning, the fuzzy control algorithm obtains the following final comfort constraint information: Final comfort obstacle constraint information: 7 meters (larger than the corrected 6 meters to ensure safety when driving on curves) Final comfort road surface constraint information: 0.22 m / s³ (slightly smaller than the corrected 0.24 m / s³ to provide a relatively flat driving road surface while maintaining safety).

[0169] It should be noted that the numerical values ​​and fuzzy rules in the above examples are simplified. In actual applications, more complex rules and more accurate numerical values ​​may be required to calculate the final comfort constraint information. In addition, the specific implementation and debugging of the fuzzy control algorithm also need to be customized according to factors such as vehicle type, driving environment and passenger needs.

[0170] The method for determining the vehicle target trajectory constraint provided in the embodiment of the present application determines the comfort road constraint information based on the road surface information, determines the comfort obstacle constraint information based on the obstacle information, determines the correction coefficient according to the comfort control mode, and fuses and corrects the comfort road constraint information and the comfort obstacle constraint information through the fuzzy control algorithm based on the correction coefficient to obtain the comfort trajectory constraint information. The method of determining the comfort constraint information based on the road surface information and the obstacle information, determining the correction coefficient according to the comfort control mode, and fusing and correcting through the fuzzy control algorithm improves driving safety, improves riding comfort, enhances the vehicle intelligence level, and promotes the development of intelligent driving technology.

[0171] Figure 6 Schematic diagram of the process of determining the vehicle target trajectory constraint provided in this application Figure 4 ,like Figure 6 As shown, based on the above embodiment, the multiple actuators include a driving actuator, a braking actuator, a steering actuator, and a suspension actuator, and step S201 specifically includes:

[0172] S601: Calculate the potential of the driving actuator based on the road adhesion coefficient.

[0173] S602: Calculate the potential of the brake actuator based on the road adhesion coefficient.

[0174] S603: Calculate the potential of the steering actuator based on the road adhesion coefficient.

[0175] S604: Calculate the potential of the suspension actuator based on the road adhesion coefficient.

[0176] In order to achieve the constraints and accurate determination of the vehicle's target trajectory, it is necessary to consider the vehicle chassis dynamics and thus construct a vehicle dynamics model.

[0177] Specifically, the road adhesion coefficient is a physical quantity that measures the friction between the road surface and the tire, which directly affects the acceleration, braking, steering and suspension performance of the vehicle. Different road materials (such as asphalt, concrete, wet and slippery roads, icy and snowy roads, etc.) and different road conditions (such as dry, wet, icy, etc.) will cause changes in the adhesion coefficient.

[0178] Based on the road adhesion coefficient, the maximum driving force that a drive actuator (such as an engine or electric motor) can provide can be calculated. This calculation needs to take into account the grip of the tires, that is, the friction between the tires and the road. When the road adhesion coefficient is high, the tire grip is greater and the vehicle can obtain greater driving force; conversely, when the road adhesion coefficient is low, the tire grip is reduced and the vehicle's driving force will also be limited.

[0179] For example, suppose there is a car with a mass of 1500 kg, driving on a dry asphalt road (adhesion coefficient The maximum driving force is about 0.8. The maximum engine output of the car is 150kW and the tire radius is 0.3m. .

[0180] Substituting the above specific values ​​into the calculation, the maximum driving force is 11772 N. Since the driving force provided by the engine cannot exceed the maximum static friction between the tire and the road surface, in this case, the potential of the driving actuator (i.e. the maximum available driving force) is 11772 N.

[0181] Based on the road adhesion coefficient, the maximum braking force that the brake actuator (such as brake pads, brake discs, etc.) can provide is calculated. The calculation of the braking force also needs to take into account the grip of the tires. In emergency braking situations, if the road adhesion coefficient is low, the tires may slip, resulting in increased braking distance or even loss of braking effect. Therefore, when calculating the brake actuator potential, the impact of the road adhesion coefficient on braking performance must be considered.

[0182] For example, the potential of the brake actuator can be expressed by calculating the maximum braking force between the tire and the road surface, which also depends on the road adhesion coefficient and the vehicle mass, that is, the calculation method is the same as the above-mentioned maximum driving force, and the potential of the brake actuator is also 11772N.

[0183] The potential calculation of the steering actuator (such as the steering motor or hydraulic power steering system) needs to take into account the effect of the road adhesion coefficient on the vehicle's steering stability. On roads with a low adhesion coefficient, the vehicle's steering stability may decrease because the friction between the tire and the road surface is reduced. This may cause the vehicle to slip or lose control when turning. Therefore, when calculating the potential of the steering actuator, it is necessary to evaluate the steering stability and controllability on roads with different adhesion coefficients.

[0184] For example, on a road with a low adhesion coefficient, the turning radius of the vehicle will increase because the cornering stiffness of the tire will decrease. Therefore, the potential of the steering actuator itself, that is, the maximum steering torque that can be generated, usually depends on parameters such as the power and reduction ratio of the steering motor.

[0185] The potential calculation of suspension actuators (such as shock absorbers, springs, etc.) involves the impact of the road adhesion coefficient on the performance of the vehicle suspension system. On uneven roads, the suspension system needs to withstand greater impact and vibration. If the road adhesion coefficient is low, the tire may lose its ability to follow the road due to lack of sufficient grip, resulting in a decrease in the performance of the suspension system. Therefore, when calculating the potential of suspension actuators, it is necessary to consider the impact of the road adhesion coefficient on the response speed and shock absorption effect of the suspension system.

[0186] For example, on uneven roads, the suspension system needs to withstand greater impact and vibration. The potential of the suspension actuator can be expressed by the maximum impact energy it can absorb, which depends on parameters such as the damping coefficient and stroke of the shock absorber.

[0187] The method for determining the target trajectory constraint of the vehicle provided in the embodiment of the present application calculates the potential of the driving actuator based on the road adhesion coefficient, calculates the potential of the braking actuator based on the road adhesion coefficient, calculates the potential of the steering actuator based on the road adhesion coefficient, and calculates the potential of the suspension actuator based on the road adhesion coefficient. By accurately calculating the vehicle chassis dynamics and actuator potential based on the road adhesion coefficient, the driving stability and safety of the vehicle are significantly improved, the energy consumption and emissions are optimized, and the intelligence level and the accuracy of the trajectory constraint are improved.

[0188] Figure 7 Schematic diagram of the process of determining the vehicle target trajectory constraint provided in this application Figure 5 ,like Figure 7 As shown, based on the above embodiment, step S401 specifically includes:

[0189] S701: If the pre-acquired HMI information indicates that the driver has specified a control mode, the control mode specified by the driver is determined as a comfort control mode.

[0190] S702: If the vehicle occupant identification information indicates that the vehicle occupants include children, the child mode is determined as the comfort control mode.

[0191] S703: If the vehicle occupant identification information indicates that the vehicle occupants do not include children but include elderly people, the elderly mode is determined as the comfort control mode.

[0192] S704: If the vehicle occupant identification information indicates that the vehicle occupants include passengers but do not include children and the elderly, the passenger mode is determined as the comfort control mode.

[0193] S705: If the vehicle occupant identification information indicates that the vehicle occupants only include the driver, the driver model is determined as a comfort control mode based on the driver's characteristic information.

[0194] In order to intelligently and automatically adjust trajectory constraints according to different drivers, driving preferences and passenger conditions, the driver in the car can interact with the vehicle through the HMI and specify the vehicle comfort control mode through the HMI. If the vehicle electronic equipment detects that the driver has specified the control mode through the HMI, it will determine the mode specified by the driver as the comfort control mode.

[0195] If the driver does not specify, intelligent matching can be performed based on the in-car member identification information. Specifically, if the in-car member identification information indicates that there are children in the car, the vehicle will automatically switch to child mode. In this mode, the vehicle may adopt a more gentle and stable driving strategy, such as limiting the acceleration and deceleration range to reduce the potential impact on children. At the same time, the vehicle may also enable special safety features for children, such as child locks and child seat reminders. If the in-car member identification information indicates that there are elderly people in the car but no children, the vehicle will switch to elderly mode. In this mode, the vehicle may pay more attention to the smoothness and comfort of the ride, such as reducing the bumpy feeling by adjusting the suspension settings, and providing a softer acceleration and braking experience. If the in-car member identification information indicates that there are passengers in the car (excluding children and the elderly), the vehicle will adopt passenger mode. In this mode, the vehicle may balance driving performance and ride comfort to ensure that all passengers can get a good ride experience. If the in-car member identification information indicates that there is only the driver in the car, the vehicle will determine a most suitable comfort control mode based on the driver's characteristic information (such as age, gender, driving habits, etc.). This personalized control mode can further improve the comfort and safety during driving.

[0196] Optionally, the driver mode may be a first driver mode, a second driver mode, or a third driver mode, wherein the first driver mode, the second driver mode, and the third driver mode represent different driving preferences.

[0197] For example, the first driver mode usually represents a driver's specific preferences, which may cover driving style, vehicle settings, safety configuration and other aspects. For example, a driver may prefer a more aggressive driving style, like fast acceleration and high-speed cornering, then the first driver mode can adjust the engine response, steering sensitivity and suspension settings accordingly to meet this preference. At the same time, the mode may also include personalized safety settings for the driver, such as seat position, steering wheel angle and mirror adjustment, to ensure the best driving vision and comfort.

[0198] Compared with the first driver mode, the second driver mode may represent another completely different driving preference. For example, another driver may pay more attention to fuel economy, ride comfort and driving stability. Therefore, the second driver mode may adjust the engine power output, transmission shift logic and suspension system to achieve a more economical and comfortable driving experience. In addition, the mode may also contain specific safety configurations for this driver, such as the enable or disable status of functions such as automatic emergency braking and lane keeping assist.

[0199] The third driver mode may represent a more balanced or universal driving preference. This mode may be designed to meet the general needs of most drivers, neither too aggressive nor too conservative. In the third driver mode, the vehicle may adopt a more neutral setting, such as moderate engine response, stable steering feel and comfortable suspension tuning. This provides a safe and comfortable driving experience suitable for use in different road conditions and driving conditions.

[0200] The method for determining the target trajectory constraint of the vehicle provided in the embodiment of the present application is as follows: if the pre-acquired HMI information indicates that the driver has specified a control mode, the control mode specified by the driver is determined as the comfort control mode; if the in-car occupant identification information indicates that the in-car occupants include children, the child mode is determined as the comfort control mode; if the in-car occupant identification information indicates that the in-car occupants do not include children but include the elderly, the elderly mode is determined as the comfort control mode; if the in-car occupant identification information indicates that the in-car occupants include passengers but do not include children and the elderly, the passenger mode is determined as the comfort control mode; if the in-car occupant identification information indicates that the in-car occupants only include the driver, the driver model is determined as the comfort control mode based on the driver's characteristic information. By integrating HMI information and in-car occupant identification information to determine the comfort control mode, not only the personalized experience of driving and riding is improved, driving safety is enhanced, and vehicle energy utilization and environmental protection performance are optimized, but also the intelligence and automation level of the vehicle, as well as user experience and satisfaction, are improved, and the constraint of the target trajectory is made more intelligent and flexible.

[0201] In one possible implementation, in each of the aforementioned embodiments, road surface information can be collected based on sensors, such as infrared sensors, which can detect objects and obstacles on the road surface and provide real-time road conditions. Radar sensors use radar waves to detect road conditions ahead, including obstacles, vehicles, and pedestrians. LiDAR generates high-precision three-dimensional road surface images by emitting lasers and receiving reflected signals.

[0202] Machine vision can also be used, for example, camera-based image recognition technology, which can identify lane lines, traffic signs, pedestrians and other vehicles on the road by analyzing videos or images captured by the camera. Deep learning algorithms use deep learning technology to train models to more accurately identify and understand complex scenes on the road.

[0203] The global positioning system (GPS) can also provide real-time location information of the vehicle, and combined with map data, the road conditions and traffic rules of the current road can be understood. Map data contains information such as road geometry, slope, curvature, traffic signals, intersection layout, etc. By communicating with other vehicles, road surface information such as congestion, accidents or construction conditions ahead can be shared. Communication between vehicles and infrastructure (such as traffic lights, roadside units, etc.) can obtain more comprehensive road surface information.

[0204] Optionally, the road surface information may include, but is not limited to, road geometry information, traffic information, obstacle information, traffic rule information, road surface condition information, road surface type, environmental information, etc.

[0205] It should be noted that the road adhesion coefficient in the above-mentioned embodiments is calculated based on road surface information. For example, the friction between the wheel and the road surface is directly measured by using sensors (such as acceleration sensors, force sensors, etc.) installed on the wheels, so as to calculate the road adhesion coefficient. It is also possible to analyze the road surface image captured by the camera and use a deep learning model to identify characteristics such as road surface material, texture and wetness, and then estimate the road adhesion coefficient. Alternatively, the road adhesion coefficient of a specific road section can be comprehensively evaluated by combining GPS location information, map data and vehicle network communication data. For example, the friction performance of the current road surface can be predicted based on historical data, weather conditions and real-time traffic information. Alternatively, the vehicle dynamics model and tire mechanics model, combined with sensor data (such as vehicle speed, acceleration, tire pressure, etc.), simulate the interaction process between the wheel and the road surface, and thus calculate the road adhesion coefficient.

[0206] The in-vehicle occupant identification information may include driver identification information and passenger identification information, wherein the driver identification information is obtained by identifying the driver type and preference type through the driver monitoring camera (DMS) system and the identity recognition system. The passenger identification information is obtained by identifying the number and type of occupants through the in-cabin occupant camera, such as children, the elderly, pets, etc. The HMI information may be that the driver can select the comfort mode through the HMI or hard switch or voice system input.

[0207] Figure 8 A schematic diagram of the structure of the vehicle target trajectory constraint determination device provided in this application, such as Figure 8 As shown, the vehicle target trajectory constraint determination device 800 includes:

[0208] The calculation module 801 is used to calculate the potential of multiple actuators of the vehicle based on a predetermined road adhesion coefficient.

[0209] The conversion module 802 is used to convert the potential energy of each actuator into the dynamic potential energy of the whole vehicle to obtain the dynamic trajectory constraint information of the vehicle.

[0210] The determination module 803 is used to determine the comfort trajectory constraint information of the vehicle based on the pre-acquired road surface information, obstacle information, and vehicle occupant identification information.

[0211] The fusion module 804 is used to fuse the dynamic trajectory constraint information and the comfort trajectory constraint information to obtain the target trajectory constraint information of the vehicle.

[0212] In a possible implementation, the determination module 803 is specifically configured to:

[0213] Determine the comfort control mode according to the identification information of the passengers in the vehicle;

[0214] Based on road surface information, obstacle information and comfort control mode, the comfort trajectory constraint information is obtained through fuzzy control calculation.

[0215] In a possible implementation, the determination module 803 obtains the comfort trajectory constraint information through fuzzy control calculation based on the road surface information, obstacle information and comfort control mode, specifically including:

[0216] Based on the road surface information, determining comfort road surface constraint information;

[0217] Based on the obstacle information, determine the comfort obstacle constraint information;

[0218] Determine the correction coefficient according to the comfort control mode;

[0219] Based on the correction coefficient, the comfort road constraint information and the comfort obstacle constraint information are fused and corrected through the fuzzy control algorithm to obtain the comfort trajectory constraint information.

[0220] In a possible implementation, the multiple actuators include a driving actuator, a braking actuator, a steering actuator, and a suspension actuator, and the calculation module 801 is specifically used to:

[0221] Based on the road adhesion coefficient, the potential of the driving actuator is calculated;

[0222] Calculate the potential of the brake actuator based on the road adhesion coefficient;

[0223] Calculate the potential of the steering actuator based on the road adhesion coefficient;

[0224] Based on the road adhesion coefficient, the potential of the suspension actuator is calculated.

[0225] In a possible implementation, the determination module 803 determines the comfort control mode according to the vehicle occupant identification information, specifically including:

[0226] If the vehicle occupant identification information indicates that the vehicle occupants include children, the child mode is determined as the comfort control mode;

[0227] If the vehicle occupant identification information indicates that the vehicle occupants do not include children but include elderly people, the elderly mode is determined as the comfort control mode;

[0228] If the vehicle occupant identification information indicates that the vehicle occupants include passengers but do not include children and the elderly, the passenger mode is determined as the comfort control mode;

[0229] If the in-vehicle occupant identification information indicates that the in-vehicle occupants include only the driver, the driver model is determined as the comfort control mode based on the driver's characteristic information. The driver mode includes the first driver mode, the second driver mode, or the third driver mode. The first driver mode, the second driver mode, and the third driver mode represent different driving preferences.

[0230] In a possible implementation, the determination module 803 determines the comfort control mode according to the vehicle occupant identification information, and further includes:

[0231] If the pre-acquired HMI information indicates that the driver has designated a control mode, the control mode designated by the driver is determined as the comfort control mode.

[0232] In one possible implementation, the target trajectory constraint information includes any multiple corresponding maximum and minimum values ​​of longitudinal acceleration, longitudinal acceleration change rate, lateral acceleration, lateral acceleration change rate, target trajectory curvature, target curvature change rate, vehicle speed, body vertical acceleration, body vertical acceleration change rate, yaw angular velocity, yaw angular velocity change rate, pitch angular velocity, pitch angular velocity change rate, roll angular velocity, and roll angular velocity change rate.

[0233] The device for determining the vehicle target trajectory constraint provided in this embodiment can execute the method for determining the vehicle target trajectory constraint provided in the above method embodiment. Its implementation principle and technical effect are similar, and this embodiment will not be described in detail here.

[0234] Fig. 9 A schematic diagram of the structure of the vehicle target trajectory determination device provided in this application, such as Fig. 9 As shown, the vehicle target trajectory determination device 900 includes:

[0235] The adjustment module 901 is used to perform constraint adjustment on the planned initial trajectory according to the target trajectory constraint information to obtain the target trajectory. The target trajectory constraint information is determined by any of the above-mentioned method embodiments.

[0236] Fig.10 This is a schematic diagram of the structure of the electronic device provided in this application. Fig.10As shown, the electronic device 1000 provided in this embodiment includes: at least one processor 1001 and a memory 1002. Optionally, the electronic device 1000 also includes a communication component 1003. The processor 1001, the memory 1002 and the communication component 1003 are connected via a bus 1004.

[0237] In a specific implementation process, at least one processor 1001 executes computer-executable instructions stored in the memory 1002, so that at least one processor 1001 executes the above-mentioned method for determining the vehicle target trajectory constraint and the method for determining the vehicle target trajectory.

[0238] The specific implementation process of the processor 1001 can be found in the above method embodiment, and its implementation principle and technical effect are similar, so this embodiment will not be repeated here.

[0239] In the above embodiments, it should be understood that the processor can be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), etc. A general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in the invention can be directly implemented as a hardware processor, or can be implemented by a combination of hardware and software modules in the processor.

[0240] The memory may include a high-speed memory (Random Access Memory, RAM), and may also include a non-volatile memory (NVM), such as at least one disk storage.

[0241] The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, the bus in the drawings of this application is not limited to only one bus or one type of bus.

[0242] The present application also provides a computer program product, including a computer program, which, when executed by a processor, implements the above-mentioned method for determining vehicle target trajectory constraints and method for determining vehicle target trajectory.

[0243] The present application also provides a computer-readable storage medium, in which computer-executable instructions are stored. When a processor executes the computer-executable instructions, the above-mentioned method for determining vehicle target trajectory constraints and method for determining vehicle target trajectory are implemented.

[0244] The above-mentioned readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk. The readable storage medium can be any available medium that can be accessed by a general or special-purpose computer.

[0245] An exemplary readable storage medium is coupled to a processor so that the processor can read information from the readable storage medium and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can be located in an application specific integrated circuit (Application Specific Integrated Circuits, referred to as: ASIC). Of course, the processor and the readable storage medium can also exist in the device as discrete components.

[0246] The division of units is only a logical function division, and there may be other divisions in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interface, device or unit, which can be electrical, mechanical or other forms.

[0247] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0248] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0249] If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods of each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0250] Those skilled in the art can understand that all or part of the steps of implementing the above-mentioned method embodiments can be completed by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When the program is executed, the steps of the above-mentioned method embodiments are executed; and the aforementioned storage medium includes: ROM, RAM, disk or optical disk and other media that can store program codes.

[0251] Finally, it should be noted that those skilled in the art will readily conceive of other embodiments of the present invention after considering the specification and practicing the invention disclosed herein. The present invention is intended to cover any variations, uses or adaptations of the present invention, which follow the general principles of the present invention and include common knowledge or customary technical means in the art not disclosed by the present invention, are not limited to the precise structure described above and shown in the drawings, and may be modified and changed in various ways without departing from the scope thereof. The scope of the present invention is limited only by the appended claims.

Claims

1. A method for determining a vehicle target trajectory constraint, characterized in that: include: Calculating the potential of multiple actuators of the vehicle based on a predetermined road adhesion coefficient; Converting the potential of each actuator into the dynamic potential of the entire vehicle to obtain the dynamic trajectory constraint information of the vehicle; Determining the comfort trajectory constraint information of the vehicle based on the pre-acquired road surface information, obstacle information, and vehicle occupant identification information; The dynamic trajectory constraint information and the comfort trajectory constraint information are fused to obtain the target trajectory constraint information of the vehicle.

2. The method according to claim 1, characterized in that The determining of the comfort trajectory constraint information of the vehicle based on the pre-acquired road surface information, obstacle information, and vehicle occupant identification information includes: Determining a comfort control mode according to the vehicle occupant identification information; The comfort trajectory constraint information is obtained through fuzzy control calculation based on the road surface information, the obstacle information and the comfort control mode.

3. The method according to claim 2, characterized in that The obtaining of the comfort trajectory constraint information through fuzzy control calculation based on the road surface information, the obstacle information and the comfort control mode includes: Based on the road surface information, determining comfort road surface constraint information; Based on the obstacle information, determining comfort obstacle constraint information; determining a correction coefficient according to the comfort control mode; Based on the correction coefficient, the comfort road constraint information and the comfort obstacle constraint information are fused and corrected through a fuzzy control algorithm to obtain the comfort trajectory constraint information.

4. The method according to claim 1, characterized in that The multiple actuators include a driving actuator, a braking actuator, a steering actuator, and a suspension actuator. Based on a predetermined road adhesion coefficient, the potential of the multiple actuators of the vehicle is calculated, including: calculating the potential of the driving actuator based on the road adhesion coefficient; calculating the potential of the brake actuator based on the road adhesion coefficient; calculating the potential of the steering actuator based on the road adhesion coefficient; Based on the road adhesion coefficient, the potential of the suspension actuator is calculated.

5. The method according to claim 2, characterized in that: The step of determining the comfort control mode according to the vehicle occupant identification information includes: If the vehicle occupant identification information indicates that the vehicle occupant includes a child, determining a child mode as the comfort control mode; If the vehicle occupant identification information indicates that the vehicle occupants do not include children but include elderly people, determining the elderly mode as the comfort control mode; If the vehicle occupant identification information indicates that the vehicle occupants include passengers but do not include children and the elderly, determining the passenger mode as the comfort control mode; If the vehicle occupant identification information indicates that the vehicle occupants include only the driver, then based on the driver's characteristic information, the driver model is determined as the comfort control mode, and the driver mode includes a first driver mode, a second driver mode, or a third driver mode, and the first driver mode, the second driver mode, and the third driver mode represent different driving preferences.

6. The method according to claim 5, characterized in that The method further comprises: If the pre-acquired human-machine interface HMI information indicates that the driver has specified a control mode, the control mode specified by the driver is determined as the comfort control mode.

7. The method according to any one of claims 1 to 6, characterized in that: The target trajectory constraint information includes any multiple corresponding maximum and minimum values ​​of longitudinal acceleration, longitudinal acceleration change rate, lateral acceleration, lateral acceleration change rate, target trajectory curvature, target curvature change rate, vehicle speed, body vertical acceleration, body vertical acceleration change rate, yaw angular velocity, yaw angular velocity change rate, pitch angular velocity, pitch angular velocity change rate, roll angular velocity, and roll angular velocity change rate.

8. A method for determining a vehicle target trajectory, characterized in that: include: The initial trajectory obtained by planning is constrained and adjusted according to the target trajectory constraint information to obtain the target trajectory, wherein the target trajectory constraint information is determined by the method described in any one of claims 1 to 7.

9. A device for determining a vehicle target trajectory constraint, characterized in that: include: A calculation module for calculating the potential of a plurality of actuators of the vehicle based on a predetermined road adhesion coefficient; A conversion module, used for converting the potential of each actuator into the dynamic potential of the whole vehicle to obtain the dynamic trajectory constraint information of the vehicle; A determination module, configured to determine the comfort trajectory constraint information of the vehicle based on pre-acquired road surface information, obstacle information, and vehicle occupant identification information; The fusion module is used to fuse the dynamic trajectory constraint information and the comfort trajectory constraint information to obtain the target trajectory constraint information of the vehicle.

10. A device for determining a vehicle target trajectory, characterized in that: include: An adjustment module is used to perform constraint adjustment on the initial trajectory obtained by planning according to target trajectory constraint information to obtain the target trajectory, wherein the target trajectory constraint information is determined by the method described in any one of claims 1 to 7.

11. An electronic device, characterized in that: include: A processor, and a memory communicatively connected to the processor; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory, so that the processor executes the method for determining the vehicle target trajectory constraint according to any one of claims 1 to 7 and the method for determining the vehicle target trajectory according to claim 8.

12. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the method for determining the vehicle target trajectory constraints as described in any one of claims 1 to 7 and the method for determining the vehicle target trajectory as described in claim 8.

Images