Unmanned vehicle control method and system, electronic equipment, storage medium and product
By combining vehicle state information and sensor data with an incremental nonlinear dynamic inverse method, the problem of lateral and longitudinal control of unmanned vehicles in complex road environments is solved, thereby improving the stability and safety of unmanned vehicles on complex roads.
Patent Information
- Application Number
- CN202411216387.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-30
- Publication Date
- 2026-03-10
AI Technical Summary
Existing unmanned vehicle control methods struggle to achieve effective lateral and longitudinal coupling control in complex road environments, especially on unconventional surfaces such as mud, gravel, rain, snow, or ice, leading to a decline in vehicle stability and safety.
By employing an incremental nonlinear dynamic inverse method, combining vehicle state information and sensor data, integrated control information is obtained by solving the system state equations, reducing the dependence on models and improving adaptability.
It enables integrated lateral and longitudinal control of unmanned vehicles in complex road environments, improving vehicle adaptability and stability, and enhancing the ability to adapt to uncertain road conditions.
Smart Images
Figure CN121626181A_ABST
Abstract
Description
Technical Field
[0001] This disclosure relates to the field of vehicle technology, and more specifically, to an unmanned vehicle control method, system, electronic device, storage medium, and product. Background Technology
[0002] Existing control methods for autonomous vehicles mostly employ decoupled lateral and longitudinal control. While some methods consider both lateral and longitudinal control simultaneously, these are primarily designed for conventional urban roads with minimal environmental changes. However, vehicle operation often involves unconventional road surfaces such as mud, gravel, rain, snow, or ice. The driving environment is uncertain and time-varying, making existing control methods that consider both lateral and longitudinal control difficult to apply directly to complex road driving scenarios. Summary of the Invention
[0003] The purpose of this disclosure is to provide an unmanned vehicle control method, system, electronic device, storage medium, and product that can enhance the adaptability of unmanned vehicle control to different road surfaces and improve the safety and stability of unmanned vehicles under various road conditions.
[0004] According to a first aspect of the present disclosure, an unmanned vehicle control method is provided, comprising:
[0005] Select the target vehicle's status information and control information;
[0006] Establish the system state equations;
[0007] Obtain the reference state derivative information of the target vehicle, the current state information of the target vehicle, the current state derivative information of the target vehicle, and the control information of the target vehicle at the previous moment;
[0008] Based on the obtained reference state derivative information of the target vehicle, the current state information of the target vehicle, the current state derivative information of the target vehicle, and the control information of the target vehicle at the previous moment, the control information of the target vehicle is obtained by solving the system state equation using the incremental nonlinear dynamic inverse method.
[0009] The control information of the target vehicle obtained by the solution is used as the output of the control module to realize the integrated horizontal and vertical control of the target vehicle.
[0010] Optionally, the state information of the target vehicle is the vehicle's lateral and longitudinal coupling state information, and the control information of the target vehicle is the lateral and longitudinal coupling control information.
[0011] Optionally, the lateral and longitudinal coupling state information of the target vehicle includes the longitudinal velocity of the target vehicle, the lateral coordinate of the target vehicle in the inertial coordinate system, the longitudinal coordinate of the target vehicle in the inertial coordinate system, and the heading angle of the target vehicle; the lateral and longitudinal coupling control information of the target vehicle includes the front wheel steering angle of the target vehicle and the longitudinal acceleration of the target vehicle.
[0012] Optionally, the reference state derivative information of the target vehicle is obtained through the motion planning module of the target vehicle.
[0013] Optionally, the current state information, the current state derivative information, and the previous control information of the target vehicle are obtained through the perception module of the target vehicle.
[0014] Optionally, the method of using incremental nonlinear dynamic inverse to solve the system state equations to obtain the control information of the target vehicle specifically includes:
[0015] The system state equation is linearized by Taylor expansion around the current state information of the target vehicle and the control information of the target vehicle at the previous moment;
[0016] Based on the time-scale separation assumption, the system state equation is approximated;
[0017] The target vehicle reference state derivative information is designed as a virtual input.
[0018] The control information of the target vehicle is obtained by solving the problem.
[0019] According to a second aspect of the present disclosure, an unmanned vehicle control system is provided, comprising:
[0020] A motion planning module, which is used to obtain the reference state derivative information of the target vehicle;
[0021] The perception module is used to acquire the current state information of the target vehicle, the current state derivative information of the target vehicle, and the control information of the target vehicle at the previous moment.
[0022] The control module is configured to obtain the control information of the target vehicle by using an incremental nonlinear dynamic inverse method based on the reference state derivative information of the target vehicle obtained by the motion planning module, and the current state information, the current state derivative information, and the previous control information of the target vehicle obtained by the perception module. The control information of the target vehicle is then used as the output of the control module to achieve integrated lateral and longitudinal control of the target vehicle.
[0023] Optionally, the control module includes:
[0024] A vehicle information selection module, wherein the vehicle information selection module is used to select the status information and control information of the target vehicle;
[0025] A system state equation establishment module is used to establish the system state equations of the control system.
[0026] The system state equation solving module is used to solve the system state equation using an incremental nonlinear dynamic inverse method, based on the system state equation established by the system state equation establishing module, the reference state derivative information of the target vehicle obtained by the motion planning module, the current state information of the target vehicle obtained by the perception module, the current state derivative information of the target vehicle, and the control information of the target vehicle at the previous moment.
[0027] According to a third aspect of the present disclosure, an electronic device is provided, comprising:
[0028] A memory on which computer programs are stored;
[0029] A processor is configured to execute the computer program in the memory to implement the unmanned vehicle control method of the first aspect described above.
[0030] According to a fourth aspect of the present disclosure, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the steps of the unmanned vehicle control method described in the first aspect.
[0031] According to a fifth aspect of the present disclosure, a computer program product is provided that, when executed by a processor, implements the steps of the unmanned vehicle control method described in the first aspect of the present disclosure.
[0032] The above technical solution establishes the system's state equations by selecting the target vehicle's state information and control information. It then acquires the target vehicle's reference state derivative information, current state information, and previous control information. Based on these information, the incremental nonlinear dynamic inverse method is used to solve the system state equations, obtaining the target vehicle's control information. This control information is then used as the output of the control module, achieving integrated lateral and longitudinal control of the target vehicle. Using the incremental nonlinear dynamic inverse method to solve the system state equations not only fully utilizes the acquired vehicle current state data but also reduces the control method's dependence on the model, improving the unmanned vehicle's adaptability to complex road conditions.
[0033] Other features and advantages of this disclosure will be described in detail in the following detailed description section. Attached Figure Description
[0034] The accompanying drawings are provided to further illustrate the present disclosure and form part of the specification. They are used together with the following detailed description to explain the present disclosure, but do not constitute a limitation thereof. In the drawings:
[0035] Figure 1 This is a flowchart illustrating an unmanned vehicle control method according to an exemplary embodiment;
[0036] Figure 2 This is a block diagram illustrating an unmanned vehicle control system according to an exemplary embodiment. Detailed Implementation
[0037] To enable those skilled in the art to better understand the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are merely some, not all, of the embodiments of the present invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative effort should fall within the scope of protection of the present invention.
[0038] It should be noted that all actions involving the acquisition of signals, information, or data in this disclosure are carried out in compliance with the relevant data protection laws and policies of the country where the location is situated, and with authorization from the owner of the relevant device.
[0039] Figure 1This is a flowchart of a control method for an unmanned vehicle provided in Embodiment 1 of the present invention. This embodiment can be used in vehicle control situations. The method can be executed by the vehicle's control system, which can be implemented in hardware and / or software. The vehicle control system can be configured in any electronic device with network communication and computing capabilities.
[0040] In related technologies, the control of unmanned vehicles often employs decoupled lateral and longitudinal control methods. Lateral control handles the vehicle's steering behavior, while longitudinal control manages its speed and acceleration. This separation of lateral and longitudinal control decomposes the trajectory tracking problem into two sub-problems: lateral and longitudinal control. However, vehicle operation often involves interlocking lateral and longitudinal movements. For example, when a vehicle turns, its longitudinal speed affects its lateral turning acceleration, and its turning behavior also influences its longitudinal braking performance. Some related technologies also use nonlinear control methods to simultaneously consider lateral and longitudinal control. However, existing nonlinear control methods are primarily designed for conventional urban roads with minimal changes in road conditions. During vehicle operation, road conditions often involve unconventional surfaces such as mud, rain, snow, ice, or uneven surfaces. The driving environment is highly uncertain and time-varying, making it difficult to directly transfer control methods designed for conventional urban roads to complex road driving scenarios.
[0041] To address the aforementioned issues, this disclosure proposes a control method and system for unmanned vehicles. By employing an incremental nonlinear dynamic inverse method in the system state equation and integrating vehicle operation sensor data acquired by the perception module, the system equation is solved to obtain the input for the control module, thereby achieving integrated lateral and longitudinal control of the vehicle. Furthermore, this control method has a low dependence on the model, thus enabling simultaneous lateral and longitudinal control of the vehicle under complex road conditions.
[0042] Figure 1 This is a flowchart illustrating an unmanned vehicle control method according to an exemplary embodiment, which can be applied to unmanned vehicle control. Figure 1 As shown, the unmanned vehicle control method includes:
[0043] S10, Select the target vehicle's status information and control information.
[0044] In this embodiment, the target vehicle's state information x is the vehicle's lateral and longitudinal coupling state information, and the target vehicle's control information u is the lateral and longitudinal coupling control information. As an optional but not limited implementation, the target vehicle's lateral and longitudinal coupling state information includes the target vehicle's longitudinal velocity, the target vehicle's abscissa in the inertial coordinate system, the target vehicle's ordinate in the inertial coordinate system, and the target vehicle's heading angle; the target vehicle's lateral and longitudinal coupling control information includes the target vehicle's front wheel steering angle and the target vehicle's longitudinal acceleration.
[0045] In this embodiment of the application, the lateral direction of the vehicle refers to the vehicle's steering behavior, the longitudinal direction of the vehicle refers to the vehicle's speed and acceleration, the vehicle's state information refers to information representing the vehicle's lateral and longitudinal states, and the target vehicle's control information refers to information for achieving lateral and longitudinal control of the vehicle.
[0046] This embodiment specifically implements integrated lateral and longitudinal control for unmanned vehicles. The selection of the target vehicle's state information x and control information u fully considers all or most of the vehicle's lateral and longitudinal coupling. The lateral and longitudinal coupling state information can be, but is not limited to, vehicle position, yaw angle, and longitudinal velocity. For example, it can be the vehicle's yaw rate, the angle between the vehicle's velocity and body, and the vehicle's velocity. In this embodiment, the vehicle's lateral and longitudinal coupling state information specifically includes the vehicle's longitudinal velocity, its abscissa in the inertial coordinate system, its ordinate in the inertial coordinate system, and its heading angle. The lateral and longitudinal coupling control information can be, but is not limited to, lateral steering angle and longitudinal acceleration. For example, it can be tire torque and front wheel steering angle, or tire speed and front wheel steering angle. In this embodiment, the lateral and longitudinal coupling control information specifically uses the front wheel steering angle and longitudinal acceleration. By considering the lateral and longitudinal coupling state and control information, a more realistic lateral and longitudinal joint constraint can be constructed.
[0047] S20, Establish the system state equations.
[0048] Specifically, establish the system state equations. The target vehicle's status information x can be selected as [rβV] T Etc., where V is the vehicle speed, and X and Y are the abscissa and ordinate of the vehicle in the inertial coordinate system, respectively. Let x be the vehicle heading angle, r be the yaw rate, and β be the angle between the vehicle's longitudinal velocity and the vehicle body. In this implementation, x is selected as... Where V x Let be the longitudinal velocity of the target vehicle; the control information u of the target vehicle can be selected as [τδ]. T [ωδ] T [δ,a] T And so on, where δ is the front wheel steering angle, a is the vehicle longitudinal acceleration, τ is the tire torque, ω is the tire rotation speed, and in this implementation, u is selected as u = [δ, a]. T After selecting the vehicle's state information x and control information u, the system state equations are established. middle, Specifically:
[0049]
[0050] L represents the vehicle's wheelbase.
[0051] S30, acquire the reference state derivative information of the target vehicle, the current state information of the target vehicle, the current state derivative information of the target vehicle, and the control information of the target vehicle at the previous moment.
[0052] Specifically, obtain the reference state derivative information of the target vehicle. This information is obtained through the target vehicle's motion planning module. The motion planning module can be understood as a vehicle path generation module. It generates a vehicle path based on a preset driving target and the surrounding environment, specifically involving path planning and obstacle avoidance, ensuring that the autonomous vehicle can intelligently plan its path. The target vehicle's reference state information can be understood as the lateral and longitudinal coupled state information of the desired destination, including the target vehicle's reference state derivative information. Specifically in It is the rate of change of the longitudinal velocity of the vehicle at the desired destination, obtained from the motion planning module; It is the rate of change of the vehicle's x-coordinate in the inertial coordinate system at the desired destination, obtained from the motion planning module; It is the rate of change of the vehicle's ordinate in the inertial coordinate system at the desired destination, obtained from the motion planning module; It is the rate of change of the vehicle heading angle at the expected destination, obtained from the motion planning module.
[0053] Specifically, obtain the current state information x0 of the target vehicle and the current state derivative information of the target vehicle. This information is obtained through the target vehicle's perception module. The perception module can be understood as a sensor monitoring module. Autonomous vehicles acquire data through sensors to accurately present the environment around the vehicle, specifically involving technologies such as sensor monitoring and sensor data fusion. The target vehicle's current state information can be understood as the vehicle's lateral and longitudinal state information during its current driving process. Specifically, the target vehicle's current state information is... Where V0 is the vehicle's current speed obtained from the sensing module; X0 is the vehicle's horizontal coordinate in the inertial coordinate system obtained from the sensing module; and Y0 is the vehicle's vertical coordinate in the inertial coordinate system obtained from the sensing module. This is the vehicle's current heading angle, obtained from the perception module. It also includes the target vehicle's current state derivative information. Specifically in It is the rate of change of the vehicle's current speed obtained from the sensing module; It is the rate of change of the abscissa of the vehicle in the inertial coordinate system, obtained from the perception module. It is the rate of change of the vehicle's ordinate in the inertial coordinate system, obtained from the perception module; It is the rate of change of the vehicle's heading angle during its current movement, obtained from the perception module.
[0054] Specifically, the control information u of the target vehicle at the previous moment is obtained through the target vehicle's perception module, which acquires the vehicle's lateral and longitudinal control information in the previous time domain, specifically u0 = [δ0a0]. T δ0 is the front wheel steering angle of the vehicle at the previous moment, obtained from the perception module of the target vehicle; a0 is the longitudinal acceleration of the vehicle at the previous moment, obtained from the perception module.
[0055] S40, based on the obtained reference state derivative information of the target vehicle, the current state information of the target vehicle, the current state derivative information of the target vehicle, and the control information of the target vehicle at the previous moment, the control information of the target vehicle is obtained by solving the system state equation using an incremental nonlinear dynamic inverse method.
[0056] As an optional but not limited implementation, the incremental nonlinear dynamic inverse method is used to solve the system state equations to obtain the control information of the target vehicle, including the following steps:
[0057] S401, Linearize the system state equation by performing a Taylor expansion near the current state information of the target vehicle and the previous control information of the target vehicle.
[0058] Specifically, the state equation contains nonlinear terms and needs to be linearized. In this embodiment, the current state information x0 of the target vehicle and the control information u0 of the target vehicle at the previous moment are selected as base points. The nonlinear state equation is expanded in first order Taylor at the base points to obtain:
[0059]
[0060] because The above formula can be expressed as:
[0061]
[0062] in,
[0063] This method ensures that within a short time domain (e.g., 0.01 seconds), the target vehicle's state information x and control information u will essentially change around the base point. Therefore, the linearized model obtained at that point has sufficient descriptive accuracy.
[0064] S402, based on the time-scale separation assumption, approximates the system state equation.
[0065] Based on the time-scale separation assumption, since the control information u directly determines... And x is After integration, at very high control frequencies, the rate of change of controller u can be considered significantly lower than the rate of change of x. Therefore, A0(x-x0) << B0(u-u0), which leads to an approximation.
[0066] S403, design the reference state derivative information of the target vehicle as a virtual input.
[0067] Specifically, the target vehicle reference state derivative information is designed as a virtual input as follows:
[0068]
[0069] S404, solve to obtain the control information of the target vehicle.
[0070] Specifically, the control information of the target vehicle is obtained by solving the problem. The control information u of the target vehicle obtained by solving the system state equation using incremental nonlinear dynamic inversion has lower requirements for model dependency and accuracy, and is more robust to model uncertainties. The vehicle controller designed using this method can enhance the adaptability of unmanned vehicles to complex road surfaces. Furthermore, the vehicle control information obtained using the incremental nonlinear dynamic inversion method incorporates sensor data acquired by the vehicle perception module, enabling more accurate control of the target vehicle.
[0071] S50, the control information of the target vehicle obtained by the solution is used as the output of the control module to realize the horizontal and vertical integrated control of the target vehicle.
[0072] Specifically, the control module can be understood as the autonomous vehicle trajectory tracking control module, which controls the autonomous vehicle to drive safely along a planned trajectory. The vehicle's control module involves the lateral and longitudinal control of the vehicle, specifically the input from the vehicle's steering wheel and accelerator pedal.
[0073] Figure 2 This is a schematic diagram of an unmanned vehicle control system provided in Embodiment 2 of this disclosure. This embodiment can be used for the control of unmanned vehicles. The vehicle control system can be implemented in hardware and / or software, and can be configured in any electronic device with network and computing capabilities, such as... Figure 2 As shown, this disclosure provides an unmanned vehicle control system, which includes:
[0074] Motion planning module 10, wherein the motion scale block 10 is used to obtain the reference state derivative information of the target vehicle;
[0075] The sensing module 20 is used to acquire the current state information of the target vehicle, the current state derivative information of the target vehicle, and the control information of the target vehicle at the previous moment.
[0076] The control module 30 is used to solve for the control information of the target vehicle by using an incremental nonlinear dynamic inverse method based on the reference state derivative information of the target vehicle obtained by the motion planning module 10, and the current state information, the current state derivative information, and the previous control information of the target vehicle obtained by the perception module 20. The control information of the target vehicle is then used as the output of the control module 30 to realize the lateral and longitudinal integrated control of the target vehicle.
[0077] Specifically, the motion planning module can be understood as the vehicle driving path generation module. This module generates a driving path based on a preset driving target and the surrounding environment, involving path planning, obstacle avoidance, and other aspects to ensure the autonomous vehicle can intelligently plan its driving path. The perception module can be understood as the sensor module. The autonomous vehicle acquires data through sensors to accurately present the environment around the vehicle, involving technologies such as sensor monitoring and sensor data fusion. The control module can be understood as the autonomous vehicle trajectory tracking and control module. It controls the autonomous vehicle to drive safely along the planned trajectory. The vehicle control module involves lateral and longitudinal control, specifically through inputs from the steering wheel and accelerator pedal.
[0078] Specifically, the reference state derivative information of the target vehicle. Specifically in It is the rate of change of the longitudinal velocity of the vehicle at the desired destination, obtained from the motion planning module; It is the rate of change of the vehicle's x-coordinate in the inertial coordinate system at the desired destination, obtained from the motion planning module; It is the rate of change of the vehicle's ordinate in the inertial coordinate system at the desired destination, obtained from the motion planning module; This is the rate of change of the vehicle's heading angle at the expected arrival point, obtained from the planning module. Current state information of the target vehicle. Specifically Where V0 is the vehicle's current speed obtained from the sensing module; X0 is the vehicle's horizontal coordinate in the inertial coordinate system obtained from the sensing module; and Y0 is the vehicle's vertical coordinate in the inertial coordinate system obtained from the sensing module. This is the vehicle's current heading angle, obtained from the perception module. It also includes the target vehicle's current state derivative information. Specifically in It is the rate of change of the vehicle's current speed obtained from the sensing module; It is the rate of change of the abscissa of the vehicle in the inertial coordinate system, obtained from the perception module. It is the rate of change of the vehicle's ordinate in the inertial coordinate system, obtained from the perception module; This is the rate of change of the vehicle's heading angle during its current movement, obtained from the perception module. The target vehicle's control information u from the previous moment is specifically u0 = [δ0a0]. T δ0 is the front wheel steering angle of the vehicle at the previous moment, obtained from the perception module of the target vehicle; a0 is the longitudinal acceleration of the vehicle at the previous moment, obtained from the perception module.
[0079] Specifically, the control module 30 includes:
[0080] Vehicle information selection module 301, the vehicle information selection module 301 is used to select the status information and control information of the target vehicle;
[0081] System state equation establishment module 302, which is used to establish the system state equation of the control system;
[0082] The system state equation solving module 303 is used to solve the system state equation based on the system state equation established by the system state equation establishing module 302, the reference state derivative information of the target vehicle obtained by the motion planning module 10, the current state information of the target vehicle, the current state derivative information of the target vehicle obtained by the sensing module 20, and the control information of the target vehicle at the previous moment, using an incremental nonlinear dynamic inverse method to obtain the control information of the target vehicle.
[0083] Based on the above embodiments, optionally, the target vehicle's state information x is the vehicle's lateral and longitudinal coupled state information, and the target vehicle's control information u is the lateral and longitudinal coupled control information. The lateral aspect of the vehicle refers to its steering behavior, and the longitudinal aspect refers to its speed and acceleration. The target vehicle's state information refers to the information on its lateral and longitudinal states, and the target vehicle's control information refers to the information for implementing lateral and longitudinal control of the vehicle. As an optional but not limited implementation, the target vehicle's lateral and longitudinal coupled state information includes the target vehicle's longitudinal speed, its abscissa in the inertial coordinate system, its ordinate in the inertial coordinate system, and its heading angle; the target vehicle's lateral and longitudinal coupled control information includes the target vehicle's front wheel steering angle and its longitudinal acceleration. By considering the lateral and longitudinal coupled state and control information, a lateral and longitudinal joint constraint that better reflects the real-world driving scenario of unmanned vehicles can be constructed.
[0084] System state equation establishment module 302 is used to establish the state equations of the control system. The specific system state equations are as follows: x represents the state information of the target vehicle, and u represents the control information of the target vehicle.
[0085] Based on the above embodiments, optionally, the state information x of the target vehicle can be selected as... [rβV] T Etc., where V is the vehicle speed, and X and Y are the abscissa and ordinate of the vehicle in the inertial coordinate system, respectively. Let xx be the vehicle heading angle, r be the yaw rate, and β be the angle between the vehicle's longitudinal velocity and the vehicle body. In this embodiment, xx is selected as... Where V x Let u be the longitudinal velocity of the vehicle; the control information u of the target vehicle can be selected as [τδ]. T [ωδ] T [δ,a] T And so on, where δ is the front wheel steering angle, a is the vehicle longitudinal acceleration, τ is the tire torque, ω is the tire rotation speed, and in this implementation, u is selected as u = [δ, a]. T After selecting the vehicle's state information x and the vehicle's control information u, the system state equation is established. middle, Specifically:
[0086]
[0087] L represents the vehicle's wheelbase.
[0088] Based on the above embodiments, optionally, the system state equation solving module 303 uses an incremental nonlinear dynamic inverse method to solve the system state equation to obtain the control information of the target vehicle, including:
[0089] Linearizing the system state equations, and performing a Taylor expansion around the current state information and the previous control information of the target vehicle, we obtain:
[0090]
[0091] Specifically, the state equation contains nonlinear terms and needs to be linearized. In this embodiment, the current state information x0 of the target vehicle and the control input information u0 of the target vehicle at the previous moment are selected as base points. The nonlinear state equation is expanded in first order Taylor at the base points to obtain:
[0092]
[0093] because The above formula can be expressed as:
[0094]
[0095] in,
[0096] This method ensures that within a short time domain (e.g., 0.01 seconds), the target vehicle's state information x and control information u will essentially change around the base point. Therefore, the linearized model obtained at that point has sufficient descriptive accuracy.
[0097] Based on the timescale separation assumption, the state equation is approximated as follows:
[0098]
[0099] Based on the time-scale separation assumption, since the control information u directly determines... And x is After integration, at very high control frequencies, the rate of change of controller u can be considered significantly lower than the rate of change of x. Therefore, A0(x-x0) << B0(u-u0), which leads to an approximation.
[0100] The reference state derivative information of the target vehicle is used as virtual input:
[0101]
[0102] The control information of the target vehicle is obtained by solving the problem.
[0103]
[0104] The control information u of the target vehicle obtained by solving the system state equation using incremental nonlinear dynamic inversion has lower requirements for model dependency and accuracy, and is more robust to model uncertainties. The vehicle controller designed using this method can enhance the adaptability of unmanned vehicles to complex road surfaces. Furthermore, the vehicle control information obtained using the incremental nonlinear dynamic inversion method incorporates sensor data acquired by the vehicle perception module, enabling more accurate control of the target vehicle.
[0105] The control information u of the target vehicle is used as the output of the control module 30 to achieve integrated horizontal and vertical control of the target vehicle.
[0106] Specifically, the control module can be understood as the autonomous vehicle trajectory tracking control module, which controls the autonomous vehicle to drive safely along a planned trajectory. The vehicle's control module involves the lateral and longitudinal control of the vehicle, specifically the input from the vehicle's steering wheel and accelerator pedal.
[0107] Regarding the apparatus in the above embodiments, the specific manner in which each module performs its operation has been described in detail in the embodiments related to the method, and will not be elaborated upon here.
[0108] In another exemplary embodiment, an electronic device is also provided, comprising:
[0109] A memory on which computer programs are stored;
[0110] A processor is configured to execute the computer program in the memory to implement the unmanned vehicle control method described in Embodiment 1.
[0111] The electronic device can vary considerably depending on its configuration or performance. It may include one or more processors and one or more memories, wherein the memory stores at least one computer program, which is loaded and executed by the processor to implement the unmanned vehicle control method provided in the above-described method embodiment. The electronic device may also include other components for implementing its functions; for example, it may have wired or wireless network interfaces and input / output interfaces for data input and output. Details will not be elaborated upon in this embodiment.
[0112] In another exemplary embodiment, a computer-readable storage medium including program instructions is also provided, which, when executed by a processor, implement the steps of the unmanned vehicle control method described above. For example, the computer-readable storage medium may be a memory including program instructions that can be executed by a processor of the unmanned vehicle control system to complete the steps of the unmanned vehicle control method in the above embodiments. The computer-readable storage medium may be a read-only memory, random access memory, read-only optical disk, magnetic tape, floppy disk, or optical data storage device, etc.
[0113] In another exemplary embodiment, a computer program product is also provided, comprising a computer program executable by a programmable device, the computer program having a code portion for performing the unmanned vehicle control method in the above embodiments when executed by the programmable device.
[0114] In the various embodiments of this application, the sequence number of each process does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.
[0115] In the above embodiments, all or part of the implementation can be achieved through software, hardware, firmware, or any other combination thereof. When implemented using software, the above embodiments can be implemented in whole or in part as a computer program product. A computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, all or part of the flow or function according to the embodiments of the invention is generated. Those skilled in the art will recognize that the steps of the various examples described in conjunction with the embodiments disclosed in this invention can be implemented in electronic hardware or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this invention.
[0116] The preferred embodiments of this disclosure have been described in detail above with reference to the accompanying drawings. However, this disclosure is not limited to the specific details of the above embodiments. Within the scope of the technical concept of this disclosure, various simple modifications can be made to the technical solutions of this disclosure, and these simple modifications all fall within the protection scope of this disclosure.
[0117] It should also be noted that the various specific technical features described in the above specific embodiments can be combined in any suitable manner without contradiction. In order to avoid unnecessary repetition, this disclosure will not describe the various possible combinations separately.
[0118] Furthermore, various different embodiments of this disclosure can be combined in any way, as long as they do not violate the spirit of this disclosure, they should also be regarded as the content disclosed in this disclosure.
Claims
1. A method for controlling an unmanned vehicle, the method comprising: The method comprises the following steps: selecting state information of a target vehicle and control information of the target vehicle; establishing a system state equation; obtaining reference state derivative information of the target vehicle, current state information of the target vehicle, current state derivative information of the target vehicle and control information of the target vehicle at a previous time; solving the system state equation by using an incremental nonlinear dynamic inverse method to obtain the control information of the target vehicle according to the reference state derivative information of the target vehicle, the current state information of the target vehicle, the current state derivative information of the target vehicle and the control information of the target vehicle at the previous time; outputting the control information of the target vehicle obtained by solving as an output of a control module to realize integrated lateral and longitudinal control of the target vehicle.
2. The method of claim 1, wherein, The state information of the target vehicle is vehicle lateral and longitudinal coupling state information, and the control information of the target vehicle is lateral and longitudinal coupling control information.
3. The method of claim 2, wherein, The lateral and longitudinal coupling state information of the target vehicle comprises a longitudinal speed of the target vehicle, a lateral coordinate of the target vehicle in an inertial coordinate system, a longitudinal coordinate of the target vehicle in the inertial coordinate system and a heading angle of the target vehicle, and the lateral and longitudinal coupling control information of the target vehicle comprises a front wheel steering angle of the target vehicle and a longitudinal acceleration of the target vehicle.
4. The method of claim 1, wherein, The reference state derivative information of the target vehicle is obtained by a motion planning module of the target vehicle.
5. The method of claim 1, wherein, The current state information of the target vehicle, the current state derivative information of the target vehicle and the control information of the target vehicle at the previous time are obtained by a perception module of the target vehicle.
6. The method of claim 1, wherein, The control information of the target vehicle is obtained by solving the system state equation by using an incremental nonlinear dynamic inverse method, and specifically comprises the following steps: linearizing the system state equation and Taylor expanding around the current state information of the target vehicle and the control information of the target vehicle at the previous time; approximating the system state equation according to a time scale separation assumption; designing the reference state derivative information of the target vehicle as virtual input; obtaining the control information of the target vehicle.
7. An unmanned vehicle control system, characterized by, The method comprises the following steps: a motion planning module is configured to obtain reference state derivative information of a target vehicle; a perception module is configured to obtain current state information of the target vehicle, current state derivative information of the target vehicle and control information of the target vehicle at a previous time; and a control module is configured to obtain control information of the target vehicle by solving the control module by using an incremental nonlinear dynamic inverse method according to the reference state derivative information of the target vehicle obtained by the motion planning module and according to the current state information of the target vehicle, the current state derivative information of the target vehicle and the control information of the target vehicle at the previous time obtained by the perception module, and output the control information of the target vehicle as an output of the control module to realize integrated lateral and longitudinal control of the target vehicle.
8. The control system of claim 7, wherein, The control module comprises: a vehicle information selection module, configured to select state information and control information of the target vehicle; a system state equation establishment module, configured to establish a system state equation of the control system; a system state equation solving module, configured to solve the system state equation according to the system state equation established by the system state equation establishment module, the reference state derivative information of the target vehicle obtained by the motion planning module, the current state information of the target vehicle obtained by the perception module, the current state derivative information of the target vehicle, and the last-time control information of the target vehicle, and obtain the control information of the target vehicle by using an incremental nonlinear dynamic inverse method.
9. An electronic device, comprising: comprising: a memory having a computer program stored thereon; a processor configured to execute the computer program in the memory to implement the unmanned vehicle control method of any one of claims 1-6.
10. A computer-readable storage medium having stored thereon a computer program, characterized in that, The computer program is executed by the processor to implement the steps of the unmanned vehicle control method of any one of claims 1-6.
11. A computer program product comprising a computer program, characterized in that, The computer program is executed by the processor to implement the steps of the unmanned vehicle control method of any one of claims 1-6. The computer program is executed by the processor to implement the steps of the unmanned vehicle control method of any one of claims 1-6.