Vehicle control method, system and device and storage medium

Abstract

The invention provides a vehicle control method, system and device and a storage medium. Wherein the vehicle comprises a tractor and a trailer connected with the tractor, the tractor is provided with a tractor control subsystem and a decision control subsystem, and the trailer is provided with a trailer control subsystem. The decision control subsystem generates a tractor control signal and a trailer control signal based on a driving track obtained by path planning; and the tractor control signal and the trailer control signal are respectively sent to the tractor control subsystem and the trailer control subsystem, so that the trailer control subsystem can control the motion state of the trailer according to the trailer control signal. By means of the control framework, the trailer can adjust the motion state and is matched with the tractor to run, the control freedom degree of the vehicle is increased, the motion state of the vehicle is better controlled, and the stability of the motion state is improved.

Description

Technical Field

[0001] The present disclosure relates to the field of autonomous driving technology, and in particular to a vehicle control method, system, device and storage medium. Background Art

[0002] Autonomous driving vehicles are developing rapidly as a combination of artificial intelligence and the automotive industry. In this field, commercial autonomous driving applications are particularly eye-catching. Commercial autonomous driving can not only improve traffic safety and reduce traffic congestion, but also improve transportation efficiency and save energy.

[0003] Currently, commercial self-driving vehicles are mainly used for freight transportation. This type of vehicle generally consists of a tractor and a trailer, with the rear of the tractor connected to the front of the trailer. At present, the control logic for the vehicle is mostly based on the tractor, that is, the control logic is designed only for the tractor, and the tractor tows the trailer to control the movement state of the tractor and trailer. However, in scenarios such as curves and reversing, due to the large differences in parameters such as weight and length of the tractor and trailer, and the long distance between the axles of the tractor and trailer, only designing the control logic for the tractor will result in poor stability of the vehicle's movement state. Summary of the invention

[0004] In view of this, the present disclosure provides a vehicle control method, system, device and storage medium to improve the stability of the vehicle's motion state during driving.

[0005] According to a first aspect of the present disclosure, a vehicle control method is provided, wherein the vehicle comprises a tractor and a trailer connected to the tractor, the tractor is provided with a tractor control subsystem, and the trailer is provided with a trailer control subsystem; the control method comprises:

[0006] Generate tractor control signals and trailer control signals based on the driving trajectory obtained by path planning;

[0007] The tractor control signal and the trailer control signal are sent to the tractor control subsystem and the trailer control subsystem respectively.

[0008] According to a second aspect of the present disclosure, a vehicle control method is provided, wherein the vehicle comprises a tractor and a trailer connected to the tractor, the tractor is provided with a tractor control subsystem, and the trailer is provided with a trailer control subsystem; the control method comprises:

[0009] receiving trailer control signals from the decision control subsystem;

[0010] The motion state of the trailer is controlled according to the trailer control signal.

[0011] According to a third aspect of the present disclosure, a control system of a vehicle is provided, the vehicle comprising a tractor and a trailer connected to the tractor; the control system comprising: a decision control subsystem, a tractor control subsystem and a trailer control subsystem;

[0012] The decision control subsystem is configured to generate a tractor control signal and a trailer control signal based on the driving trajectory obtained by the path planning, and send the tractor control signal and the trailer control signal to the tractor control subsystem and the trailer control subsystem respectively;

[0013] A tractor control subsystem, configured to control the motion state of the tractor according to the tractor control signal;

[0014] The trailer control subsystem is configured to control the motion state of the trailer according to the trailer control signal.

[0015] According to a fourth aspect of the present disclosure, a control device is provided, the device comprising:

[0016] one or more processors, and

[0017] A memory for storing a program, wherein the program includes instructions, and when the instructions are executed by a processor, the processor executes the method of the first aspect or the second aspect.

[0018] According to a fifth aspect of the present disclosure, a computer-readable storage medium storing a program is provided, wherein the program includes instructions, and when the instructions are executed by one or more processors of a computing device, the computing device executes the method of the first aspect or the second aspect mentioned above.

[0019] It can be seen from the above technical solutions that the present disclosure provides a new control architecture, providing a trailer control subsystem for the trailer, and the decision control subsystem generates a tractor control signal and a trailer control signal based on the driving trajectory obtained by path planning, and provides them to the tractor control subsystem and the trailer control subsystem respectively, so that the trailer control subsystem can control the motion state of the trailer according to the trailer control signal. This control architecture enables the trailer to adjust its motion state and cooperate with the tractor to travel, increasing the control freedom of the vehicle, thereby better controlling the motion state of the vehicle and improving the stability of the motion state. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the embodiments of the present disclosure or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present disclosure. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0021] Figure 1 A schematic diagram of a control system of a vehicle provided by an embodiment of the present disclosure;

[0022] Figure 2 A schematic diagram of a trailer control subsystem provided by an embodiment of the present disclosure;

[0023] Figure 3 A flow chart of a vehicle control method provided by an embodiment of the present disclosure;

[0024] Figure 4 A block diagram of a decision control subsystem provided in an embodiment of the present disclosure;

[0025] Figure 5 A schematic diagram of a tracking strategy in a forward steering mode provided by an embodiment of the present disclosure;

[0026] Figure 6 (a) and (b) are force diagrams of a conventional control method and a control method provided by an embodiment of the present disclosure in a reverse mode, respectively;

[0027] Figure 7 A flow chart of establishing a vehicle dynamics model provided in an embodiment of the present disclosure;

[0028] Figure 8 A flowchart of another vehicle control method provided by an embodiment of the present disclosure;

[0029] Fig. 9 A schematic block diagram of a control device in the form of an electronic device provided in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0030] The following will be combined with the drawings in the embodiments of the present disclosure to clearly and completely describe the technical solutions in the embodiments of the present disclosure. Obviously, the described embodiments are only part of the embodiments of the present disclosure, not all of the embodiments. Based on the embodiments in the present disclosure, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present disclosure.

[0031] The terms used in the embodiments of the present invention are only for the purpose of describing specific embodiments, and are not intended to limit the present invention. The singular forms "a", "said" and "the" used in the embodiments of the present invention and the appended claims are also intended to include plural forms, unless the context clearly indicates other meanings.

[0032] It should be understood that the term "and / or" used in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship.

[0033] The word "if" as used herein may be interpreted as "at the time of" or "when" or "in response to determining" or "in response to detecting", depending on the context. Similarly, the phrases "if it is determined" or "if (stated condition or event) is detected" may be interpreted as "when it is determined" or "in response to determining" or "when detecting (stated condition or event)" or "in response to detecting (stated condition or event)", depending on the context.

[0034] The vehicle involved in the embodiments of the present disclosure is a type of truck consisting of a tractor and a trailer, and the rear of the tractor is connected to the front of the trailer. According to the shape of the trailer and the relationship between it and the tractor, the vehicle can be divided into two types: full-trailer type and semi-trailer type. Among them, the full-trailer type is that the tractor in front tows the carriage behind, and the carriage is not placed on the tractor, and the total weight of the trailer is borne by itself. The semi-trailer is towed by the tractor and part of the weight of the trailer is borne by the tractor. The vehicle may include one or more trailers. When multiple trailers are included, the tractor is connected to one of the trailers, and the trailers are connected in sequence.

[0035] Usually, manually driven vehicles can only be controlled by controlling the tractor due to the fixed cockpit. As described in the background technology, traditional self-driving vehicles also follow the design concept of manual driving, and only design control logic for the tractor, which tows the trailer to control the motion state of the tractor and trailer. However, in scenarios such as curves and reversing, due to the large differences in parameters such as weight and length of the tractor and trailer, and the long distance between the axles of the tractor and trailer, only designing control logic for the tractor will result in poor stability of the vehicle's motion state and poor path following ability. In fact, the concepts of tractor and trailer are not equivalent to their meanings for manual driving for the automatic driving system.

[0036] In view of this, the embodiments of the present disclosure provide a new control architecture. Figure 1 A schematic diagram of a vehicle control system provided by an embodiment of the present disclosure, such as Figure 1 As shown in , the control system may include: a decision control subsystem 110 , a tractor control subsystem 120 and a trailer control subsystem 130 .

[0037] The decision control subsystem 110 is responsible for the overall decision and control of the vehicle, and is configured to generate a tractor control signal and a trailer control signal based on the driving trajectory obtained by path planning, and send the tractor control signal and the trailer control signal to the tractor control subsystem 120 and the trailer control subsystem 130 respectively.

[0038] The tractor control subsystem 120 is configured to control the motion state of the tractor according to the tractor control signal.

[0039] The trailer control subsystem 130 is configured to control the motion state of the trailer according to the trailer control signal.

[0040] As one of the possible implementations, the decision control subsystem 110 and the tractor control subsystem 120 can be arranged in the tractor, and the trailer control subsystem 130 can be arranged in the trailer. The trailer control subsystem 130 and the decision control subsystem 110 perform signal interaction via a bus or NFC (Near Field Communication) or the like.

[0041] Furthermore, the control system may further include: a first sensor group 140 disposed on the tractor and a second sensor group 150 disposed on the trailer.

[0042] The first sensor group 140 may include more than one sensor, which may be arranged at the top, front, side and rear of the tractor to collect environmental data around the tractor. The second sensor group 150 may also include more than one sensor, which may be arranged at the front, side and rear of the trailer to collect environmental data around the trailer. The sensors may include but are not limited to Radar (Radio detection and ranging), LiDAR (Light Detection And Ranging), camera, gyroscope, accelerometer, IMU (Inertial Measurement Unit), GPS (Global Positioning System), etc. Radar may include ultrasonic radar, millimeter wave radar, etc. Cameras may include monocular cameras, binocular cameras, etc.

[0043] Accordingly, the decision control subsystem 110 can be further configured to obtain environmental data collected by the first sensor group 140 and the second sensor group 150, perform path planning based on the environmental data, and obtain a driving trajectory. The decision control subsystem 110 can fuse the environmental data collected by the first sensor group 140 and the second sensor group 150, and perform path planning based on the fused environmental data. This will be described in detail in subsequent embodiments.

[0044] In order to facilitate the understanding of the technical solution of the present disclosure, the composition of the trailer control subsystem 130 is first described in detail through an embodiment. Figure 2 A schematic diagram of a trailer control subsystem 130 provided in an embodiment of the present disclosure is shown in FIG. Figure 2 As shown in , the trailer control subsystem 130 mainly includes a power component 131 , a trailer controller 132 and a drive component 133 .

[0045] The power assembly 131 is configured to provide power to the trailer controller and the drive assembly.

[0046] The power assembly 131 may include a battery pack consisting of more than one battery cell and supporting electrical components. The electrical components may include BMS (Battery Management System), DC / DC (Direct Current / Direct Current) converter, DC / AC (Direct Current / Alternating Current) converter, etc. BMS is to manage and maintain each battery cell, prevent the battery from overcharging, over-discharging, etc., extend the battery life, and monitor the battery status. Since these are relatively common electrical components, they will not be described in detail here.

[0047] The trailer controller 132 is configured to control the driving component 133 according to the trailer control signal.

[0048] Specifically, the trailer controller 132 is responsible for parsing the trailer control signal from the decision control subsystem 110, obtaining trailer control parameter information, and controlling the driving component 133 according to the trailer control parameter information. The trailer controller 132 may receive the trailer control signal from the decision control subsystem 110 via a bus or NFC.

[0049] The driving assembly 133 is configured to control the wheels of the trailer, for example, to control the torque of at least one wheel of the trailer.

[0050] As one possible implementation, the drive assembly 133 may be a power motor. Figure 2As shown in , power motors can be respectively provided for the two rear wheels of the trailer to achieve individual control of each rear wheel.

[0051] The trailer control parameter information may include control parameter values ​​for controlling the trailer. As one possible implementation, the trailer control parameter information may include wheel torque information. Figure 2 As shown in the figure, by applying wheel torque to each wheel, traction control, braking force control and steering control can be performed on the wheel. Among them, the steering control effect can be generated by applying different wheel torques to the wheels on both sides; if the trailer is expected to keep moving in a straight line, the same wheel torque can be applied to the wheels on both sides, or zero torque (in this case, the trailer moves passively with the tractor).

[0052] As one of the feasible ways, the power assembly 131 may have an external charging function, and the power assembly 131 may be charged when the vehicle stops driving.

[0053] Furthermore, a more preferred implementation can be provided here. In addition to generating driving force or steering for the wheels of the trailer, the drive assembly 133 can also brake the wheels of the trailer in some scenarios. When the drive assembly 133 brakes the wheels of the trailer, the kinetic energy of the wheels can be converted into electric current to charge the power assembly 131 in reverse.

[0054] Correspondingly, the tractor subsystem may also include a tractor controller, a tractor power assembly and a tractor drive assembly for controlling the tractor. The specific implementation method may refer to the above trailer subsystem, or those skilled in the art may configure it according to actual needs, which is not limited here.

[0055] The control process performed by the decision control subsystem is described in detail below in conjunction with the embodiments. Figure 3 The flowchart of a vehicle control method provided by an embodiment of the present disclosure is executed by a decision control subsystem. Figure 3 As shown in , the method may include the following steps:

[0056] Step 301: Generate a tractor control signal and a trailer control signal based on the driving trajectory obtained by path planning.

[0057] Step 303: Send the tractor control signal and the trailer control signal to the tractor control subsystem and the trailer control subsystem respectively.

[0058] In order to facilitate the understanding of this process, first combine Figure 4 The composition of the decision control subsystem 110 is described. Figure 4As shown in , the decision control subsystem mainly includes: a path planning unit 401 and a control signal generating unit 402 , and may further include a data fusion unit 403 .

[0059] The data fusion unit 403 is used to obtain environmental data collected by the first sensor group 140 disposed on the tractor and the second sensor group 150 disposed on the trailer, and to perform fusion processing on the obtained environmental data.

[0060] The above fusion processing includes fusing the environmental data around the tractor and the trailer to expand the perception range, and also includes fusing the environmental data collected by different types of sensors to enrich the perception. When performing fusion processing, the acquired environmental data can be cross-validated, detected and blinded, etc., to improve the reliability and accuracy of perception and decision-making.

[0061] The above cross-validation can be to use environmental data collected by different sensors to perform target detection respectively, and verify the detection results with each other to obtain the final target information. The above detection blind spot filling can be to use environmental data collected by sensors of different locations and types to make up for the detection blind spots of the sensors, thereby increasing the overall field of view of the sensor group and improving the autonomous driving vehicle's perception range of the environment.

[0062] The path planning unit 401 is used to perform path planning and obtain the driving trajectory of the vehicle by using the environmental data obtained after fusion by the data fusion unit 403 before the above step 301.

[0063] Specifically, when performing path planning, the path planning unit 401 performs real-time planning based on the information of the departure point and the destination, and combines the above-mentioned environmental data, traffic rules and other factors to obtain the vehicle's driving path. The driving path can ensure efficient arrival from the departure point to the destination while being able to avoid obstacles in a timely manner based on environmental data and traffic rules, etc., where the environmental data may include obstacle information, road information (such as lane lines, congestion conditions), etc.

[0064] For ordinary vehicles, most path planning is based on vehicle mass points. However, for vehicles including tractors and trailers involved in the embodiments of the present disclosure, due to the large size of the vehicles, path planning based on the vehicle mass point method can easily cause the vehicle to deviate from the path constraints when turning. Therefore, in the embodiments of the present disclosure, path planning needs to consider the constraints on the front and rear positions of the tractor and trailer, and use the front center, rear center and rear center of the tractor as reference points for path planning, so as to ensure efficient arrival from the departure point to the destination, and timely avoid obstacles during driving to obtain a driving trajectory. In other words, the driving trajectory obtained by path planning is the reference trajectory that the front center, rear center and rear center of the tractor and trailer need to follow during driving.

[0065] The specific implementation of the path planning unit 401 in the present disclosure may use the existing path planning method for trailer vehicles, which will not be described in detail here.

[0066] The control signal generating unit 402 is used to execute Figure 3 Step 301 and step 303 shown in FIG.

[0067] In the above step 301, when generating the tractor control signal and the trailer control signal based on the driving trajectory obtained by path planning, the target motion state of the vehicle can be determined based on the driving trajectory obtained by path planning; and the tractor control signal including the tractor control parameter information and the trailer control signal including the trailer control parameter information are determined by using the pre-established vehicle dynamics model and the target motion state of the vehicle.

[0068] During the driving process of the vehicle, each driving trajectory corresponds to a target motion state of the vehicle, that is, what kind of motion state is appropriate for driving on this driving trajectory, so that the vehicle is controlled accordingly, so that the vehicle drives in the target motion state on this driving trajectory.

[0069] The motion state mainly includes vehicle speed, acceleration, yaw rate, hitch angle rate, etc. In the disclosed embodiment, the tractor control parameters mainly include wheel torque and steering wheel angle, and the trailer control parameters mainly include wheel torque.

[0070] The vehicle dynamics model is actually a model that establishes the relationship between the control parameter information and the vehicle's motion state information, and is the basis for decision-making control in the field of autonomous driving. The input of the vehicle dynamics model is usually the control parameters of the vehicle (the vehicle including the tractor and trailer in this disclosure), and the output is usually the vehicle's motion state. After the target motion state of the vehicle is determined, the main task of step 301 is to use the vehicle dynamics model to find a set of control parameters to make the motion state output by the vehicle dynamics model consistent with the target motion state as much as possible. For example, a 2-degree-of-freedom bicycle model, a vehicle longitudinal dynamics model, a 7-degree-of-freedom vehicle dynamics model, etc. can also be used.

[0071] As one of the achievable methods, the vehicle dynamics model may include a forward vehicle dynamics model and a backward vehicle dynamics model. The forward vehicle dynamics model is based on the tractor body coordinate system, that is, the target coordinate system used is the tractor body coordinate system. The backward vehicle dynamics model is based on the trailer body coordinate system, that is, the target coordinate system used is the trailer body coordinate system.

[0072] Among them, the body-attached coordinate system, also known as the position coordinate system or Lagrangian coordinate system, refers to a coordinate system that moves with the object and remains relatively stationary with the object. In solid mechanics, this coordinate system is often used to describe the state of an object, which is called Lagrangian description. The characteristic of this coordinate system is that the coordinate system itself changes with the movement of the object. Therefore, the tractor body-attached coordinate system is a coordinate system that moves with the tractor and remains relatively stationary with the tractor; the trailer body-attached coordinate system is a coordinate system that moves with the trailer and remains relatively stationary with the trailer.

[0073] If it is determined that the target motion state of the vehicle corresponds to forward driving, such as straight forward driving, turning during forward driving, etc., the forward vehicle dynamics model is used to determine the tractor control parameter information and the trailer control parameter information.

[0074] If it is determined that the target motion state of the vehicle corresponds to backward driving, such as reversing, etc., the backward vehicle dynamics model is used to determine the tractor control parameter information and the trailer control parameter information.

[0075] It should be noted that the "first" and "second" in the present disclosure do not have limitations on size, order, quantity, etc., and are only used to distinguish in name. For example, "first wheel torque information", "second wheel torque information", etc. are only used to distinguish different wheel torque information in name. For another example, "first steering angle information", "second steering angle information", etc. are only used to distinguish different steering angle information in name.

[0076] The following uses several typical driving modes corresponding to the target motion state as examples to explain the generated control parameters:

[0077] 1) Straight forward driving mode

[0078] If it is determined that the target motion state of the vehicle corresponds to the straight forward driving mode, the tractor control parameter is mainly generated, that is, the tractor is the main control object. As one of the achievable methods, the generated tractor control signal includes the second wheel torque information of the tractor so that the tractor generates driving force.

[0079] If a braking task is performed in the straight forward driving mode, such as emergency braking due to an obstacle or vehicle abnormality, in order to perform the braking task more quickly and reliably, both the tractor and the trailer can be controlled. As one possible implementation, the generated tractor control signal includes the first wheel torque information of the tractor to brake the tractor, and the generated trailer control signal includes the first wheel torque information of the trailer to brake the trailer. For example, the power motor can be used to apply wheel torque to the wheels of the tractor and the trailer, so that the wheels of the tractor and the trailer both generate braking force opposite to the driving direction.

[0080] If an abnormal yaw rate of the trailer is detected in the straight forward driving mode, the yaw rate is detected by, for example, data collected by sensors such as GPS and IMU installed on the trailer. If it is detected that the yaw rate exceeds the normal range, a trailer control signal including the second wheel torque information of the trailer can be further generated, that is, while the tractor is taken as the main control object, the trailer is auxiliary controlled. The second wheel torque information causes the wheels of the trailer to generate a yaw moment in the opposite direction to the abnormal yaw rate, so as to offset the abnormal yaw rate and enhance the driving stability of the vehicle.

[0081] 2) Forward steering mode

[0082] If it is determined that the target motion state of the vehicle corresponds to the forward steering mode, that is, steering is performed during forward driving, such as turning, changing lanes, driving on a ramp, or driving out of a side parking space, etc. In particular, during low-speed and high-rate steering, the tractor and trailer can be coordinated to control the vehicle to steer.

[0083] As one of the achievable ways, the generated tractor control signal includes the first steering angle information and the third wheel torque information of the tractor. The first steering angle information is used to control the steering wheel angle of the tractor, so as to realize the steering of the tractor. The third wheel torque information is used to generate driving force for the tractor. In other words, the control of the tractor includes providing traction and controlling steering. The generated trailer control signal includes the third wheel torque information of the trailer to control the steering of the trailer. The third wheel torque information of the trailer can be different wheel torques applied to the wheels on both sides (left and right sides) of the trailer to control the steering of the trailer.

[0084] Since the axle distance between the tractor and the trailer is relatively long, the vehicle needs a larger turning radius, which may cause a large difference between the tractor trajectory and the trailer trajectory, affecting the path following ability of the vehicle. In view of this, the embodiment of the present disclosure provides a more preferred implementation method, when determining the tractor control parameters and the trailer control parameters in the forward steering mode, the first steering angle information and the third wheel torque information of the tractor and the third wheel torque information of the trailer can be determined based on a preset tracking strategy.

[0085] The above tracking strategy includes: minimizing the sum of the distances from the head center, the tail center of the tractor and the tail center of the trailer to the driving trajectory. This tracking strategy actually provides an evaluation standard for the trajectory tracking effect, so that the control of the tractor and trailer can effectively improve the path following ability of the vehicle.

[0086] like Figure 5 As shown in , point A, point B and point C are the head center, tail center and trailer tail center respectively. The change rate of the distance from each point to the driving track can be established with the target state information of the vehicle based on the geometric relationship. Taking point C as an example, the change rate of the distance from point C to the driving track is The following formula can be used:

[0087]

[0088] Where γ is the yaw angle of the tractor, is the yaw rate of the tractor. φ is the towing angle, i.e. the angle between the longitudinal centerline of the tractor and the trailer, which is usually formed at the towing point H. The so-called towing point refers to the connection point between the tractor and the trailer, through which the tractor can apply force to the trailer to affect the motion state of the trailer. is the traction angular velocity. l is the distance from the trailer tail C to the traction point H, and h is the distance from the traction point H to the origin O of the tractor coordinate system.

[0089] Point A and point B can also generate formulas similar to formula (1) by replacing the value of l with the distance from point A or point B to the towing point H. These formulas are then applied to the vehicle dynamics model in combination with the tracking strategy to obtain the first steering angle information, the third wheel torque information of the tractor, and the third wheel torque information of the trailer.

[0090] In both modes, since the vehicle is moving forward, the forward vehicle dynamics model is used.

[0091] 3) Reverse mode

[0092] If it is determined that the target motion state of the vehicle corresponds to the reverse mode, the trailer is used as the main control object to perform auxiliary control on the tractor. As one of the achievable methods, the generated tractor control signal includes the second steering angle information of the tractor, and the generated trailer control signal includes the fourth wheel torque information of the trailer, and the fourth wheel torque information is used to generate driving force for the trailer. In other words, the tractor does not provide power, but the trailer provides the backward driving force, thereby pulling the tractor backward, and at the same time, the tractor participates in steering control.

[0093] In the reverse mode, since the vehicle is traveling backward, the backward vehicle dynamics model is used. In the process of the vehicle moving from forward to stopping and then to reverse, there is a mode switch, and the vehicle dynamics model on which the tractor control parameter information and trailer control parameter information are generated changes, and the target coordinate system based on them also changes, that is, from the tractor body coordinate system to the trailer body coordinate system.

[0094] The control method in the above-mentioned reversing mode provided by the embodiment of the present disclosure is compared with the traditional control method:

[0095] like Figure 6 As shown in (a), in the conventional control mode, when the vehicle is reversing, the tractor wheels provide driving force. In the absence of driving force for the trailer wheels, the trailer wheels will actually generate resistance at least due to ground friction. If the vehicle is disturbed by external factors during the reversing process, the angle between the tractor and the trailer will continue to increase, and the stability of the motion state, especially the posture, is very poor.

[0096] It should be noted that the external disturbance to the vehicle involved here is a relatively broad concept, which may be the disturbance caused by insufficient execution of control parameters, or the disturbance caused by the deviation between the established vehicle dynamics model and the actual situation, or the abnormal actual condition of one side of the wheel (for example, one side of the wheel runs over water, sand, etc.), resulting in yaw torque on both sides of the tires, etc.

[0097] like Figure 6 As shown in (b), under the control mode provided by the embodiment of the present disclosure, when the vehicle is reversing, the trailer wheels provide driving force, and the tractor wheels are only responsible for yaw angle control (i.e., steering control). If the vehicle is disturbed by the outside world, the traction angle between the tractor and the trailer will gradually decrease due to the reversing of the vehicle, and the stability of the motion state, especially the posture, is significantly improved, and the anti-disturbance ability is stronger.

[0098] Since the vehicle includes a tractor and a trailer, the tractor and the trailer correspond to the tractor body coordinate system and the trailer body coordinate system respectively, so the vehicle dynamics model needs to consider the motion state information and control parameter information of the tractor and the trailer, as well as the two coordinate systems. The process of establishing the vehicle dynamics model is briefly described below in conjunction with the embodiments.

[0099] Figure 7 A flowchart of establishing a vehicle dynamics model is provided in an embodiment of the present disclosure, such as Figure 7 As shown, the process may include the following steps:

[0100] Step 701: Determine the transformation relationship between the target coordinate system and the reference coordinate system.

[0101] The above-mentioned reference coordinate system is another coordinate system in the tractor body coordinate system and the trailer body coordinate system except the target coordinate system.

[0102] If the forward vehicle dynamics model is established, the tractor body coordinate system is used as the target coordinate system, and the trailer body coordinate system is used as the reference coordinate system. If the backward vehicle dynamics model is established, the trailer body coordinate system is used as the target coordinate system, and the tractor body coordinate system is used as the reference coordinate system.

[0103] If the target coordinate system and the reference coordinate system are represented by t0 and t1 respectively, the transformation relationship between t0 and t1 can be expressed by the transformation relationship between the basis vectors of t0 and t1:

[0104]

[0105] Among them, i, j and k are the coordinates of the basis vectors corresponding to the three axes in the three-dimensional coordinate system, and the subscripts represent the coordinate system t0 and t1. t0 Represents the coordinates of the basis vector corresponding to an axis in the target coordinate system t0, i t1 Represents the coordinates of the basis vector corresponding to this axis in the reference coordinate system t1.

[0106] Step 703: Determine the rate of change of the basis vectors with respect to time for the target coordinate system and the reference coordinate system respectively.

[0107] Since t0 and t1 are both non-inertial systems, it is necessary to determine the rate of change of the non-inertial system basis vector relative to time when building the vehicle dynamics model. For the target coordinate system t0, the rate of change of each coordinate in the basis vector relative to time can be expressed as follows:

[0108]

[0109]

[0110]

[0111] For the reference coordinate system t1, the rate of change of each coordinate in the basis vector relative to time can be expressed as follows:

[0112]

[0113]

[0114]

[0115] Among them, ω t0 / n and ω t1 / n is the angular velocity of rotation of the non-inertial coordinate system relative to the inertial coordinate system (geophysical coordinate system), and φ is the rotation angle of the reference coordinate system t1 relative to the target coordinate system t0.

[0116] Step 705: Based on the transformation relationship between the target coordinate system and the reference coordinate system, the expression of the origin of the reference coordinate system in the target coordinate system is determined to prepare for the subsequent construction of the Lagrangian dynamics equation.

[0117] According to the geometric relationship, the origin of the reference coordinate system is selected to be located at the center of gravity (CG) of the trailer, and the origin of the target coordinate system is selected to be located at the center of gravity of the tractor. t When the trailer displacement r s It can be expressed as:

[0118] r s =r t -L1i t0 -L2i t1 (9)

[0119] Where L1 is the distance from the towing point to the tractor CG, with the target coordinate system as the reference; L2 is the distance from the towing point to the trailer CG in the reference coordinate system.

[0120] According to the above equation, the time derivatives of both sides of the equation are:

[0121]

[0122] By using formula (6) and coordinate transformation matrix (2), we can construct the velocity v s The expression in the reference coordinate system can further be used to calculate the kinetic energy of the trailer with the reference coordinate system state as a parameter, in preparation for the subsequent application of the Lagrange equation. t and v s are the speeds of the tractor and trailer respectively.

[0123] In order to facilitate the use of the vehicle dynamics model, all points in the reference coordinate system are unified as the expression of the target coordinate system. It is necessary to first determine the expression of the origin of the reference coordinate system in the target coordinate system, and then use the expression of the origin of the reference coordinate system in the target coordinate system and the coordinates of each point in the reference coordinate system to obtain the coordinates of each point in the reference coordinate system in the target coordinate system.

[0124] Step 707: Determine the equation of acceleration relative to the target coordinate system using the rate of change of the basis vectors with respect to time.

[0125] In this embodiment, the Lagrangian equation is used to construct the vehicle dynamics model. In the process of solving the Lagrangian equation, the equation of acceleration relative to the target coordinate system is used. Therefore, in this step, the rate of change of the basis vector relative to time can be first used to determine the equation of acceleration relative to the target coordinate system.

[0126] In order to facilitate the subsequent calculation using the Lagrange equation, the acceleration involved in this step can use generalized acceleration. Generalized acceleration is the acceleration obtained based on generalized coordinates. Generalized coordinates were proposed by Lagrange and are the minimum parameters required to describe the position and shape of a system. Using a set of generalized coordinates to guide the equation, the answer obtained can be applied to a wider range of problems.

[0127] Step 709: Using the Lagrange equation, the equation of acceleration relative to the target coordinate system, and the expression of the origin of the reference coordinate system in the target coordinate system, a vehicle dynamics model is constructed, and the vehicle dynamics model includes the relationship between the control parameter information and the vehicle's motion state information. For example, a 3-DOF vehicle dynamics model is constructed, and the model uses the vehicle's lateral velocity, the yaw rate of the target coordinate system (the rotation speed around the z-axis), and the relative rotation speed between the target coordinate system and the reference coordinate system as the vehicle's motion state information; and uses the steering wheel angle of the tractor and the wheel torque on both sides of the trailer as the control parameter information.

[0128] In this embodiment, the process of constructing the vehicle dynamics model is the process of solving the Lagrange equation. The kinetic energy and potential energy of the vehicle can be determined first, wherein only the kinetic energy can be considered and the potential energy can be ignored. Then the kinetic energy and potential energy of the vehicle are used to solve the Lagrange equation. The solution process uses the equation of acceleration relative to the target system and the expression of the origin of the reference coordinate system in the target coordinate system.

[0129] The Lagrange equation can be expressed as:

[0130]

[0131] Among them, L is the kinetic energy of the vehicle minus the potential energy, Q is the force on the vehicle, and q is the coordinates of the vehicle (tractor and trailer) expressed in the target coordinate system. Generalized coordinates can be used. It can be generalized acceleration.

[0132] The specific solution process is not described in detail in the embodiment of the present disclosure. Finally, the nonlinear model is linearized and transposed by the Jacobi matrix, and the model can be organized into a state space expression form of a standard linear model, for example:

[0133]

[0134] Among them, x is the variable of motion state, such as speed, acceleration, traction angular velocity, yaw angular velocity, etc. u is the control parameter, such as steering wheel angle, wheel torque, etc.

[0135] The vehicle dynamics model finally obtained actually reflects the relationship between the control parameter information and the vehicle's motion state information. When the target motion state of the vehicle is determined, the control parameter information corresponding to the target motion state can be determined. The control parameters include tractor control parameters and trailer control parameters. In the disclosed embodiment, the tractor control parameters mainly include wheel torque and steering wheel angle, and the trailer control parameters mainly include wheel torque. However, the application is not limited to these control parameters, and other control parameters can also be designed.

[0136] The variables and control parameters of the motion state involved in the above vehicle dynamics model can be adjusted according to actual needs. For example, if the longitudinal speed of the vehicle does not change during the control process, this parameter can be ignored, thereby reducing the state variables and reducing the amount of calculation. For another example, the roll angle can be added to the vehicle dynamics model to consider the control design of anti-rollover during the steering process.

[0137] Figure 7 The manner of establishing the vehicle dynamics model shown is based on the Lagrangian method, but it should be understood that in addition to this method, the vehicle dynamics model may also be established based on other methods.

[0138] Figure 8 FIG. 1 is a flow chart of another vehicle control method provided by an embodiment of the present disclosure, and the control method is executed by a trailer control subsystem. Figure 8 As shown in , the method may include the following steps:

[0139] Step 801: Receive a trailer control signal from the decision control subsystem.

[0140] The decision control subsystem includes the trailer control parameters in the trailer control signal and sends it to the trailer control subsystem via a bus or NFC. After receiving the trailer control signal, the trailer control subsystem parses the trailer control parameters therefrom. In the disclosed embodiment, the trailer control signal may mainly include wheel torque information.

[0141] Step 803: Control the motion state of the trailer according to the trailer control signal.

[0142] The wheel torque information included in the trailer control signal may be wheel torque information for at least one trailer wheel. After receiving and parsing the trailer control signal, the trailer controller in the trailer control subsystem controls the drive assembly according to the parsed trailer control parameter information, for example, according to the wheel torque information of each trailer wheel, controls the power motor to apply a corresponding torque to the corresponding trailer wheel.

[0143] As one of the feasible ways, in the straight forward driving mode, the trailer is towed forward by the tractor. If a braking task is performed, the trailer control signal received by the trailer control subsystem from the decision control subsystem includes first wheel torque information. According to the first wheel torque information, wheel torque is applied to the wheels of the trailer to brake the trailer, that is, a driving force opposite to the driving direction is applied to the wheels of the trailer.

[0144] As another feasible manner, if an abnormal yaw rate of the trailer is detected in the straight forward driving mode, the trailer control signal received by the trailer control subsystem from the decision control subsystem includes second wheel torque information. Based on the second wheel torque information, a wheel torque is applied to the wheels of the trailer to generate a yaw moment in the opposite direction to the abnormal yaw rate of the trailer, so as to offset the abnormal yaw rate and enhance the driving stability of the vehicle.

[0145] As another achievable method, in the forward steering mode, that is, steering during forward driving, the trailer control signal received by the trailer control subsystem from the decision control subsystem includes the third wheel torque information, and the wheel torque is applied to the wheels of the trailer according to the third wheel torque information to control the steering of the trailer. This method can effectively improve the stability and path following ability of the vehicle in the turning mode.

[0146] As another feasible manner, in the reversing mode, the trailer control signal received by the trailer control subsystem from the decision control subsystem includes fourth wheel torque information, and wheel torque is applied to the wheels of the trailer based on the fourth wheel torque information to make the trailer generate driving force, thereby making the trailer pull the tractor backwards, and at the same time, the tractor participates in steering control.

[0147] It can be seen that the trailer in the disclosed embodiment is equipped with a trailer control subsystem, and the decision control subsystem considers the coupling relationship between the tractor and the trailer, coordinates the control inputs of the tractor and the trailer, so that the tractor and the trailer in the vehicle can achieve automatic driving in a coordinated manner. This approach weakens the relative concept of the tractor and the trailer, is more in line with the actual driving state of automatic driving, and realizes flexible control allocation through stronger control freedom.

[0148] The trailer control subsystem provided in the embodiment of the present disclosure is arranged on the trailer, and the decision control subsystem and the tractor control subsystem can be arranged on the tractor. Among them, the trailer can be regarded as a "pluggable" structure. If the vehicle replaces the trailer, the replaced trailer can continue to interact with the decision control subsystem arranged on the tractor through bus or NFC, etc., and receive the trailer control signal of the decision control subsystem to realize the coordinated control of the tractor and the trailer.

[0149] If the vehicle is a multi-trailer vehicle, i.e., multiple trailers, the trailer control subsystem may be provided on some of the trailers, or may be provided on all trailers. The decision control subsystem may generate a trailer control signal for each trailer control subsystem, and each trailer control subsystem controls the target motion state of the corresponding trailer according to the received trailer control signal.

[0150] The above is a description of a specific embodiment of the specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0151] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system or system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0152] In addition, an embodiment of the present disclosure further provides a computer-readable storage medium on which a computer program is stored. The program includes instructions. When the instructions are executed by one or more processors of a computing device, the steps of the method described in any one of the aforementioned method embodiments are executed.

[0153] The present disclosure also provides a computer program product, including a computer program, which implements the steps of any one of the methods in the aforementioned method embodiments when executed by a processor.

[0154] The control device provided in the embodiment of the present disclosure may be implemented in the form of an electronic device. In this case, Fig. 9As shown in , the control device includes one or more processors 901 and a memory 902 storing one or more programs, which are executed by the one or more processors 901 to implement the method flow and / or device operation shown in the above embodiments of the present invention. Fig. 9 The above structure can also be used to implement the decision control subsystem.

[0155] The various components are interconnected using different buses and can be mounted on a common mainboard or in other ways as needed. The processor 901 can process instructions executed in the electronic device. In other embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories.

[0156] The processor 901 may include one or more single-core processors or multi-core processors. The processor 901 may include any combination of general-purpose processors or dedicated processors (such as image processors, application processors, baseband processors, etc.).

[0157] The memory 902 is a computer-readable storage medium provided by the present disclosure, which can be used to store non-transient software programs, non-transient computer executable programs and units, such as the following in the embodiments of the present disclosure: Figure 3 or Figure 8 The processor 901 executes the control method shown in the above method embodiment by running the non-transient software program, instructions and units stored in the memory 902. Figure 3 or Figure 8 The control method shown in .

[0158] The control device may further include: an input device 903 and an output device 904. The processor 901, the memory 902, the input device 903 and the output device 904 may be connected via a bus or other means. Fig. 9 The example of connecting through bus is taken in the following.

[0159] The input device 903 can receive input digital or character information and generate signal input related to user settings and function control of the control device. Figure 3 or Figure 8 The results generated by the control method shown in are output to other devices connected to the control device.

[0160] The above-mentioned programs (also referred to as software, software applications, or codes) include machine instructions for programmable processors, and these computer programs can be implemented using object-oriented programming languages, assembly or machine languages.

[0161] With the development of time and technology, the meaning of medium is becoming more and more extensive, and the propagation path of computer programs is no longer limited to tangible media, and can also be downloaded directly from the network, etc. Any combination of one or more computer-readable storage media can be used. Computer-readable storage media can be used but not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or devices, or any combination of the above. More specific examples (non-exhaustive list) of computer-readable storage media include: portable computer disks, hard disks, random access memories (RAM), read-only memories (ROM), erasable programmable read-only memories (EPROM or flash memory), optical fibers, portable compact disk read-only memories (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the above. In this document, computer-readable storage media can be any tangible medium containing or storing programs, which can be used by or in combination with instruction execution systems, devices or devices.

[0162] The technical solution provided by the present disclosure is described in detail above. The principles and implementation methods of the present disclosure are described in detail using specific examples. The description of the above embodiments is only used to help understand the method and core idea of ​​the present disclosure. At the same time, for those skilled in the art, according to the idea of ​​the present disclosure, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting the present disclosure.

[0163] The above description is only a preferred embodiment of the present disclosure and is not intended to limit the present disclosure. Any modifications, equivalent substitutions, etc. made within the spirit and principles of the present disclosure should be included in the protection scope of the present disclosure.

Claims

1. A method for controlling a vehicle, wherein the vehicle comprises a tractor and a trailer connected to the tractor, the tractor is provided with a tractor control subsystem, and the trailer is provided with a trailer control subsystem; characterized in that: The control method comprises: Generate tractor control signals and trailer control signals based on the driving trajectory obtained by path planning; The tractor control signal and the trailer control signal are sent to the tractor control subsystem and the trailer control subsystem respectively.

2. The control method according to claim 1, characterized in that: The control method further comprises: Acquire environmental data collected by a first sensor group and a second sensor group; wherein the first sensor group is disposed on the tractor, and the second sensor group is disposed on the trailer; Performing fusion processing on the environmental data to obtain fused environmental data; The fused environmental data is used to perform path planning to obtain the driving trajectory.

3. The control method according to claim 1, characterized in that: The generating of the tractor control signal and the trailer control signal based on the driving trajectory obtained by path planning includes: Determining a target motion state of the vehicle based on a driving trajectory obtained through path planning; A tractor control signal including tractor control parameter information and a trailer control signal including trailer control parameter information are determined using a pre-established vehicle dynamics model and a target motion state of the vehicle.

4. The control method according to claim 3, characterized in that: The vehicle dynamics model includes a forward vehicle dynamics model and a backward vehicle dynamics model, wherein the forward vehicle dynamics model uses the tractor body coordinate system as the target coordinate system, and the backward vehicle dynamics model uses the trailer body coordinate system as the target coordinate system; In response to the target motion state of the vehicle corresponding to forward travel, utilizing the forward vehicle dynamics model; In response to the target motion state of the vehicle corresponding to backward travel, the backward vehicle dynamics model is utilized.

5. The control method according to claim 3 or 4, characterized in that: The vehicle dynamics model is pre-established in the following manner: Determine a transformation relationship between a target coordinate system and a reference coordinate system, wherein the reference coordinate system is another coordinate system of the tractor body coordinate system and the trailer body coordinate system except the target coordinate system; Determine the rate of change of the basis vectors with respect to time for the target coordinate system and the reference coordinate system respectively; Based on the transformation relationship, determining the expression of the origin of the reference coordinate system in the target coordinate system; Determining an equation of acceleration relative to a target coordinate system using the rate of change of the basis vectors with respect to time; The vehicle dynamics model is constructed using the Lagrange equation, the equation of the acceleration relative to the target coordinate system, and the expression of the origin of the reference coordinate system in the target coordinate system. The vehicle dynamics model includes the relationship between the control parameter information and the motion state information of the vehicle, wherein the control parameter information includes the tractor control parameter information and the trailer control parameter information.

6. The control method according to claim 3, characterized in that: The tractor control parameter information includes steering angle information or wheel torque information, and the trailer control parameter information includes wheel torque information.

7. The control method according to claim 6, characterized in that: If it is determined that the target motion state of the vehicle corresponds to a straight-forward driving mode, then when performing a braking task, the generated tractor control signal includes first wheel torque information of the tractor to brake the tractor, and the generated trailer control signal includes first wheel torque information of the trailer to brake the trailer; or, If it is determined that the target motion state of the vehicle corresponds to a straight forward driving mode, the generated tractor control signal includes second wheel torque information of the tractor so that the tractor generates a driving force, and when an abnormal yaw rate of the trailer is detected, a trailer control signal including the second wheel torque information of the trailer is further generated, wherein the second wheel torque information generates a yaw moment in a direction opposite to the abnormal yaw rate; or, If it is determined that the target motion state of the vehicle corresponds to a forward steering mode, the generated tractor control signal includes first steering angle information and third wheel torque information of the tractor, the third wheel torque information is used for the tractor to generate driving force, and the generated trailer control signal includes the third wheel torque information of the trailer to control the steering of the trailer; or, If it is determined that the target motion state of the vehicle corresponds to the reversing mode, the generated tractor control signal includes the second steering angle information of the tractor, and the generated trailer control signal includes the fourth wheel torque information of the trailer, and the fourth wheel torque information is used for the trailer to generate driving force.

8. The control method according to claim 7, characterized in that: The control method further comprises: If it is determined that the target motion state of the vehicle corresponds to a forward steering mode, determining first steering angle information and third wheel torque information of the tractor and third wheel torque information of the trailer based on a preset tracking strategy; The tracking strategy includes: minimizing the sum of the distances from the head center, the tail center of the tractor and the tail center of the trailer to the driving track respectively.

9. A method for controlling a vehicle, wherein the vehicle comprises a tractor and a trailer connected to the tractor, the tractor is provided with a tractor control subsystem, and the trailer is provided with a trailer control subsystem; characterized in that: The control method comprises: receiving trailer control signals from the decision control subsystem; The motion state of the trailer is controlled according to the trailer control signal.

10. The control method according to claim 9, characterized in that: The controlling of the motion state of the trailer according to the trailer control signal comprises: Parsing the trailer control signal to obtain trailer control parameter information, wherein the trailer control parameter information includes wheel torque information; The wheels of the trailer are controlled according to the trailer control parameter information.

11. The control method according to claim 10, characterized in that: The controlling the wheels of the trailer according to the trailer control parameter information includes: applying wheel torque to the wheels of the trailer to brake the trailer according to the first wheel torque information obtained by parsing the trailer control signal; or, applying wheel torque to the wheels of the trailer to generate a yaw moment in a direction opposite to the abnormal yaw angular velocity of the trailer based on the second wheel torque information obtained by parsing the trailer control signal; or, applying wheel torque to the wheels of the trailer to control the steering of the trailer according to the third wheel torque information obtained by parsing the trailer control signal; or, According to fourth wheel torque information obtained by parsing the trailer control signal, wheel torque is applied to the wheels of the trailer so that the trailer generates driving force.

12. A control system for a vehicle, the vehicle comprising a tractor and a trailer connected to the tractor; characterized in that: The control system includes: a decision control subsystem, a tractor control subsystem and a trailer control subsystem; The decision control subsystem is configured to generate a tractor control signal and a trailer control signal based on the driving trajectory obtained by path planning, and send the tractor control signal and the trailer control signal to the tractor control subsystem and the trailer control subsystem respectively; The tractor control subsystem is configured to control the motion state of the tractor according to the tractor control signal; The trailer control subsystem is configured to control the motion state of the trailer according to the trailer control signal.

13. A control device, characterized in that: The device comprises: one or more processors, and A memory storing a program, the program comprising instructions which, when executed by the processor, cause the processor to perform the method according to any one of claims 1 to 11.

14. A computer-readable storage medium storing a program, the program comprising instructions, which, when executed by one or more processors of a computing device, cause the computing device to perform the method according to any one of claims 1 to 11.

Images