FUNCTIONAL LIMITS FOR TORQUE REQUIREMENTS BASED ON CALCULATING NEURAL NETWORKS

Abstract

Method (300) for calculating at least one functional limit for a requested auxiliary torque in a steering system, wherein the method (300) comprises: Receiving at least one input; Transmitting the at least one input to an artificial neural network (200), wherein the artificial neural network (200) is configured to calculate an auxiliary torque limit corresponding to the requested auxiliary torque; Receiving the auxiliary torque limit corresponding to the requested auxiliary torque from the artificial neural network (200); and Controlling at least one aspect of the steering system using the requested auxiliary torque and the auxiliary torque limit.

Description

[0001] This invention relates to a method, a system and an apparatus for calculating a functional limit for a requested assist torque in a steering system.

[0002] A vehicle, such as a car, truck, sport utility vehicle, crossover, minivan, watercraft, aircraft, off-road vehicle, recreational vehicle, or other suitable means of transportation, typically includes a steering system, such as an electronic power steering (EPS) system, a steer-by-wire (SBW) system, a hydraulic steering system, or other suitable steering system. The steering system of such a vehicle typically controls various aspects of the vehicle's steering, including providing steering assistance to the vehicle's driver, controlling steerable wheels of the vehicle, and the like.

[0003] The steering system typically includes various torque paths for providing torque to various steering system components. Typically, each torque path includes a firewall to provide functional diagnostics and protect the steering system components from erroneous or malicious torque commands.

[0004] DE 10 2016 212 097 A1 discloses a method for estimating a steering wheel torque, in which a current steering wheel torque is estimated using an artificial intelligence (ANN). DE 10 2021 111 140 A1 teaches a method for implementing torque control, in which a simplified pseudo-neural network is used to obtain a requested torque value. DE 10 2021 129 404 A1 describes a method for implementing steering override phases, wherein the DNN classifies a desired path, predicted vehicle dynamics, and information regarding a phase between autonomous and manual steering. DE 10 2019 212 432 B3 discloses a method for estimating a steering wheel torque for mechanical feedback on a steering wheel, in which steering nonlinearities are estimated using an artificial intelligence method.DE 10 2020 208 860 A1 discloses a module for estimating a road friction coefficient for a motor vehicle, wherein the friction coefficient is estimated using a neural network. DE 10 2020 125 982 A1 relates to a system for controlling the steering of a vehicle, in which a neural network is used to identify the obstacle. DE 10 2020 127 049 A1 describes a steering system in which a steering mode change occurs based on a tracked position or posture of a person's limbs, wherein the position or posture of the limbs is detected using a neural network. DE 10 2017 220 973 A1 describes a method for configuring a steering system, in which a steering force and / or a steering torque is specified using a neural network.

[0005] It is an object underlying the invention to provide an improved method, an improved system and an improved apparatus for controlling at least one aspect of a steering system.

[0006] The above-mentioned object is achieved by a method according to claim 1, a system according to claim 10 and a device according to claim 19.

[0007] This invention relates generally to steering systems.

[0008] One aspect of the disclosed embodiments includes a method for calculating at least one functional limit for a requested assist torque in a steering system. The method includes receiving at least one input and communicating the at least one input to an artificial neural network, the artificial neural network configured to calculate an assist torque limit corresponding to the requested assist torque. The method also includes receiving the assist torque limit corresponding to the requested assist torque from the artificial neural network and controlling at least one aspect of the steering system using the requested assist torque and the assist torque limit.

[0009] Another aspect of the disclosed embodiments includes a system for calculating at least one functional limit for a requested assist torque in a steering system. The system includes a processor and a memory. The memory contains instructions that, when executed by the processor, cause the processor to: receive at least one input; communicate the at least one input to an artificial neural network, the artificial neural network configured to calculate an assist torque limit corresponding to the requested assist torque; receive from the artificial neural network the assist torque limit corresponding to the requested assist torque; and control at least one aspect of the steering system using the requested assist torque and the assist torque limit.

[0010] Another aspect of the disclosed embodiments includes an apparatus for calculating at least one functional limit for a requested assist torque in a steering system. The apparatus includes a processor and a memory.The memory contains instructions that, when executed by the processor, cause the processor to: receive at least one input including at least one of a handwheel torque, a handwheel angle, an engine speed, a vehicle speed, and an estimated engine torque; communicate the at least one input to an artificial neural network trained using data corresponding to one or more steering maneuvers, the artificial neural network configured to calculate an assist torque limit corresponding to the requested assist torque; receive from the artificial neural network the assist torque limit corresponding to the requested assist torque; and control at least one aspect of the steering system using the requested assist torque and the assist torque limit.

[0011] These and other aspects of the present invention are disclosed in the following detailed description of the embodiments, the appended claims and the accompanying figures. Fig. 1 generally shows a vehicle according to the principles of the present invention. Fig. 2A generally shows a steering system control system according to the principles of the present invention. Fig. Figure 2B generally illustrates an artificial neural network according to the principles of the present invention. Fig. 3 is a flowchart generally illustrating a method for calculating an assist torque limit in accordance with the principles of the present invention.

[0012] As described, a vehicle, such as a car, truck, sport utility vehicle, crossover, minivan, watercraft, aircraft, off-road vehicle, recreational vehicle, or other suitable means of transportation, typically includes a steering system, such as an electronic power steering (EPS) system, a steer-by-wire (SbW) steering system, a hydraulic steering system, or other suitable steering system.

[0013] The steering system of such a vehicle typically controls various aspects of the vehicle's steering, including providing steering assistance to the vehicle's driver, controlling the vehicle's steerable wheels, and the like. The steering system typically includes various torque paths for providing torque to various components of the steering system. For example, in open-loop steering systems, the torque paths may include an assist torque path, a dampening torque path, a return torque path, an end-of-travel torque path, other suitable torque paths, or a combination thereof. In closed-loop steering systems, the closed-loop control system may include a global limiter.

[0014] Typically, each torque path includes a firewall to provide functional diagnostics and protect steering system components from erroneous or damaging torque commands. This may require configuring each firewall separately, which can be relatively time-consuming and requires expert knowledge. In closed-loop control systems, the global limiter can be relatively complex and difficult to configure (e.g., because the global limiter considers standard operating characteristics, the dynamic characteristics of the steering system, and the override commands). Additionally, or alternatively, configuring such firewalls can be prone to human error.

[0015] Accordingly, systems and methods, such as those described herein, configured to use a trained artificial neural network to calculate a functional limit for requested assist torque in real-time or near-real-time may be desirable. In some embodiments, the systems and methods described herein may be configured to generate a global limiter from an artificial neural network that automatically responds to all steering system inputs and outputs. The systems and methods described herein may be configured to provide a robust and universal solution for open-loop or closed-loop control systems that can reduce or eliminate firewall tuning and reduce or eliminate the need for specific steering system knowledge or steering system calibration.

[0016] In some embodiments, the systems and methods described herein may be configured to train the artificial neural network (which may include, for example, a deep learning system, machine learning models, artificial intelligence, artificial neural networks, and the like) based on data corresponding to a variety of recorded (e.g., captured, sensed, measured, and the like) vehicle maneuvers (e.g., including steering maneuvers and / or other suitable maneuvers) that consider all aspects of system behavior (e.g., reversal, damping, end of travel, other suitable aspects and / or behaviors, or a combination thereof). The systems and methods described herein may be configured to train and test the artificial neural network offline (e.g., prior to implementation in the vehicle).In some embodiments, the artificial neural network may include a self-tuning network (e.g., the network may self-tune during training procedures), which may reduce or eliminate manual tuning.

[0017] In some embodiments, the systems and methods described herein may be configured to measure various system characteristics (e.g., handwheel torque, motor speed, estimated motor torque command, and the like). The systems and methods described herein may be configured to provide the measured characteristics (e.g., as inputs) to the artificial neural network. The artificial neural network may process the inputs (e.g., including all driving conditions and vehicle dynamics) and generate a final limit value.

[0018] In some embodiments, the systems and methods described herein may be configured to provide a single component (e.g., a single firewall mechanism) for use in open-loop and closed-loop control systems, which may enable functional diagnostics and limitation without specific knowledge of the vehicle or vehicle tuning.

[0019] In some embodiments, the systems and methods described herein may be configured to receive at least one input. The at least one input may include a handwheel torque, a handwheel angle, a motor speed, a vehicle speed, an estimated motor torque command, another suitable input, or a combination thereof. The systems and methods described herein may be configured to communicate the at least one input to an artificial neural network. The artificial neural network may be configured to calculate an assist torque threshold corresponding to a requested assist torque. In some embodiments, the artificial neural network may be trained with data corresponding to one or more steering maneuvers.The systems and methods described herein may be configured to receive the assist torque limit corresponding to the requested assist torque from the artificial neural network. The systems and methods described herein may be configured to control at least one aspect of the steering system using the requested assist torque and the assist torque limit.

[0020] Fig. 1 generally illustrates a vehicle 10 according to the principles of the present invention. The vehicle 10 may be any suitable vehicle, such as a car, a truck, a sport utility vehicle, a minivan, a crossover, any other passenger vehicle, any suitable commercial vehicle, or any other suitable vehicle. Although the vehicle 10 is illustrated as a wheeled passenger vehicle for use on roads, the principles of the present invention may also be applied to other vehicles, such as aircraft, boats, trains, drones, or other suitable vehicles.

[0021] The vehicle 10 includes a vehicle body 12 and a hood 14. A passenger compartment 18 is at least partially defined by the vehicle body 12. Another portion of the vehicle body 12 defines an engine compartment 20. The hood 14 may be movably attached to a portion of the vehicle body 12 such that the hood 14 provides access to the engine compartment 20 when the hood 14 is in a first, or open, position, and the hood 14 covers the engine compartment 20 when the hood 14 is in a second, or closed, position. In some embodiments, the engine compartment 20 may be located at a rear portion of the vehicle 10, other than as generally illustrated.

[0022] The passenger compartment 18 may be located behind the engine compartment 20, but may also be located forward of the engine compartment 20 if the engine compartment 20 is located in the rear of the vehicle 10. The vehicle 10 may include any suitable propulsion system, including an internal combustion engine, one or more electric motors (e.g., an electric vehicle), one or more fuel cells, a hybrid propulsion system (e.g., a hybrid vehicle) comprising a combination of an internal combustion engine and one or more electric motors, and / or any other suitable propulsion system.

[0023] In some embodiments, the vehicle 10 may include a gasoline engine, e.g., a spark-ignition engine. In some embodiments, the vehicle 10 may include a diesel engine, such as a compression-ignition engine. The engine compartment 20 houses and / or encloses at least some components of the propulsion system of the vehicle 10. Additionally or alternatively, propulsion controls, such as an accelerator pedal, a brake pedal, a steering wheel, and other such components, are disposed within the passenger compartment 18 of the vehicle 10. The propulsion controls may be actuated or controlled by a driver of the vehicle 10 and may be directly connected to corresponding components of the propulsion system, such as a throttle, a brake, a vehicle axle, a vehicle transmission, and the like. In some embodiments, the propulsion controls may communicate signals to a vehicle computer (e.g.,Drive-by-Wire), which in turn can control the corresponding drive component of the drive system. Thus, in some embodiments, the vehicle 10 can be an autonomous vehicle.

[0024] In some embodiments, the vehicle 10 includes a transmission connected to a crankshaft via a flywheel, a clutch, or a fluid coupling. In some embodiments, the transmission includes a manual transmission. In some embodiments, the transmission includes an automatic transmission. The vehicle 10, in the case of an internal combustion engine or a hybrid vehicle, may include one or more pistons that cooperate with the crankshaft to generate power that is transmitted through the transmission to one or more axles that rotate the wheels 22. If the vehicle 10 includes one or more electric motors, a vehicle battery and / or a fuel cell provides power to the electric motors to rotate the wheels 22.

[0025] Vehicle 10 may include automatic vehicle propulsion systems, such as cruise control, adaptive cruise control, automatic braking control, other automatic vehicle propulsion systems, or a combination thereof. Vehicle 10 may be an autonomous or semi-autonomous vehicle or another suitable vehicle type. Vehicle 10 may include additional or fewer features than those generally illustrated and / or disclosed herein.

[0026] In some embodiments, the vehicle 10 may include an Ethernet component 24, a CAN bus (Controller Area Network) bus 26, a MOST component (Media Oriented Systems Transport) component 28, a FlexRay component 30 (e.g., a brake-by-wire system and the like), and a LIN component (Local Interconnect Network) component 32. The vehicle 10 may use the CAN bus 26, the MOST component 28, the FlexRay component 30, the LIN component 32, other suitable networks or communication systems, or a combination thereof to communicate various information from, e.g., sensors inside or outside the vehicle to, e.g., various processors or control units inside or outside the vehicle. The vehicle 10 may include additional or fewer features than those generally illustrated and / or disclosed herein.

[0027] In some embodiments, the vehicle 10 may include a steering system, such as an EPS system, a steer-by-wire steering system (which may, for example, include or communicate with one or more controllers that control components of the steering system without the use of a mechanical connection between the handwheel and the wheels 22 of the vehicle 10), a hydraulic steering system (which may, for example, include a magnetic actuator integrated into a valve assembly of the hydraulic steering system), or other suitable steering system.

[0028] The steering system may comprise an open-loop control system or mechanism, a closed-loop control system or mechanism, or a combination thereof. The steering system may be configured to receive various inputs, including, but not limited to, a handwheel position, an input torque, positions of one or more road wheels, other suitable inputs or information, or a combination thereof.

[0029] Additionally or alternatively, the inputs may include a handwheel torque, a handwheel angle, a motor speed, a vehicle speed, an estimated motor torque command, another suitable input, or a combination thereof. The steering system may be configured to provide a steering function and / or control of the vehicle 10. For example, the steering system may generate assist torque based on the various inputs. The steering system may be configured to selectively control a motor of the steering system using the assist torque to provide steering assistance to the driver of the vehicle 10.

[0030] In some embodiments, the steering system may include a steering system controller, such as controller 100, generally described in Fig. 2A. The controller 100 may include any suitable controller. The controller 100 may be configured to, for example, control the various functions of the steering system. The controller 100 may include a processor 102 and a memory 104. The processor 102 may be any suitable processor as described herein. Additionally or alternatively, the controller 100 may include any suitable number of processors in addition to the processor 102 or other processors. The memory 104 may include a single disk or a plurality of disks (e.g., hard drives) and includes a memory management module that manages one or more partitions within the memory 104. In some embodiments, the memory 104 may include flash memory, solid state memory, or the like.Memory 104 may be random access memory (RAM), read-only memory (ROM), or a combination thereof. Memory 104 may contain instructions that, when executed by processor 102, cause processor 102 to control at least various functions of the steering system.

[0031] Controller 100 may receive one or more signals from various gauges or sensors 106 indicative of sensed or measured characteristics of vehicle 10. Sensors 106 may include any suitable sensors, gauges, and / or other suitable mechanisms. For example, sensors 106 may include one or more torque sensors or devices, one or more handwheel position sensors or devices, one or more motor position sensors or devices, one or more position sensors or devices, other suitable sensors or devices, or a combination thereof. The one or more signals may indicate handwheel torque, handwheel angle, motor speed, vehicle speed, other suitable information, or a combination thereof.

[0032] In some embodiments, controller 100 may estimate motor torque using the one or more signals. In some embodiments, controller 100 generates a requested assist torque based on the one or more signals. The assist torque may correspond to an amount of torque to be applied to one or more components of the steering system, for example, to assist the operator in turning the handwheel. In some embodiments, controller 100 may receive the requested assist torque from one or more different sources within vehicle 10.

[0033] In some embodiments, the controller 100 may communicate with an artificial neural network 200. The artificial neural network 200 may be located within the vehicle 10 or at a remote location (e.g., on a computer, such as a mobile computer or other suitable computer, or on a remote server or other suitable remote computer). The artificial neural network 200 may comprise any suitable neural network and may include one or more layers, such as the hidden layers generally described in Fig. 2B are shown.

[0034] In some embodiments, artificial neural network 200 may receive the one or more signals from sensors 106. As described, the one or more signals may indicate a handwheel torque, a handwheel angle, an engine speed, a vehicle speed, other suitable information, or a combination thereof. Artificial neural network 200 may receive the estimated assist torque from controller 100 or another suitable source.

[0035] In some embodiments, controller 100 may receive at least one input. The at least one input may include a handwheel torque, a handwheel angle, a motor speed, a vehicle speed, an estimated motor torque command, another suitable input, or a combination thereof. Controller 100 may transmit the at least one input to artificial neural network 200.

[0036] In some embodiments, the at least one input from the sensors 106 may be communicated to the artificial neural network 200. Additionally or alternatively, the artificial neural network 200 may receive the estimated engine torque from the controller 100 or another suitable source. The artificial neural network 200 may be configured to calculate an assist torque limit corresponding to a requested assist torque generated by the controller 100 or another suitable source. In some embodiments, the artificial neural network 200 may be trained with data corresponding to one or more steering maneuvers, as described.

[0037] Controller 100 may receive the assist torque limit corresponding to the requested assist torque from artificial neural network 200. Controller 100 may control at least one aspect of the steering system using the requested assist torque and the assist torque limit.

[0038] In some embodiments, controller 100 may perform the methods described herein. However, the methods described herein as being performed by controller 100 are not intended to be limiting, and any type of software executing on a controller or processor may perform the methods described herein without departing from the scope of this disclosure. For example, a controller, such as a processor executing software in a computing device, may perform the methods described herein.

[0039] Fig.3 is a flowchart generally illustrating a method 300 for calculating the assist torque limit according to the principles of the present invention. At 302, the method 300 receives at least one input. For example, controller 100 may receive the at least one input.

[0040] At 304, method 300 may transmit the at least one input to an artificial neural network. For example, controller 100 may transmit the at least one input to artificial neural network 200. In some embodiments, artificial neural network 200 may receive the at least one input from sensors 106 or another suitable source.

[0041] At 306, method 300 receives an assist torque limit corresponding to a requested assist torque from the artificial neural network. For example, controller 100 may receive the assist torque limit (e.g., generated by artificial neural network 200 as described) corresponding to the requested assist torque from artificial neural network 200.

[0042] At 308, method 300 controls at least one aspect of the steering system using the requested assist torque and the assist torque limit. For example, controller 100 may control the at least one aspect of the steering system using at least the requested assist torque and the assist torque limit.

[0043] In some embodiments, a method for calculating at least one functional limit for a requested assist torque in a steering system comprises receiving at least one input and providing the at least one input to an artificial neural network, the artificial neural network configured to calculate an assist torque limit corresponding to the requested assist torque. The method also includes receiving the assist torque limit corresponding to the requested assist torque from the artificial neural network, and controlling at least one aspect of the steering system using the requested assist torque and the assist torque limit.

[0044] In some embodiments, the at least one input includes at least one of a handwheel torque, a handwheel angle, an engine speed, a vehicle speed, and / or an estimated engine torque. In some embodiments, the artificial neural network is trained using data corresponding to one or more steering maneuvers. In some embodiments, the data corresponding to the one or more steering maneuvers includes at least one of the following: return torque path data, damping torque path data, and end-of-travel torque path data. In some embodiments, the steering system includes an open-loop control system. In some embodiments, the steering system includes a closed-loop control system. In some embodiments, the steering system includes an electronic power steering system. In some embodiments, the steering system includes a steer-by-wire steering system.In some embodiments, the steering system includes a hydraulic steering system.

[0045] In some embodiments, a system for calculating at least one functional limit for a requested assist torque in a steering system comprises a processor and a memory. The memory contains instructions that, when executed by the processor, cause the processor to: receive at least one input; communicate the at least one input to an artificial neural network, the artificial neural network configured to calculate an assist torque limit corresponding to the requested assist torque; receive from the artificial neural network the assist torque limit corresponding to the requested assist torque; and control at least one aspect of the steering system using the requested assist torque and the assist torque limit.

[0046] In some embodiments, the at least one input includes at least one of a handwheel torque, a handwheel angle, an engine speed, a vehicle speed, and / or an estimated engine torque. In some embodiments, the artificial neural network is trained using data corresponding to one or more steering maneuvers. In some embodiments, the data corresponding to the one or more steering maneuvers includes at least one of the following: return torque path data, damping torque path data, and end-of-travel torque path data. In some embodiments, the steering system includes an open-loop control system. In some embodiments, the steering system includes a closed-loop control system. In some embodiments, the steering system includes an electronic power steering system. In some embodiments, the steering system includes a steer-by-wire steering system.In some embodiments, the steering system includes a hydraulic steering system.

[0047] In some embodiments, an apparatus for calculating at least one functional limit for a requested assist torque in a steering system comprises a processor and a memory.The memory contains instructions that, when executed by the processor, cause the processor to: receive at least one input including at least one of a handwheel torque, a handwheel angle, an engine speed, a vehicle speed, and an estimated engine torque; communicate the at least one input to an artificial neural network trained using data corresponding to one or more steering maneuvers, the artificial neural network configured to calculate an assist torque limit corresponding to the requested assist torque; receive from the artificial neural network the assist torque limit corresponding to the requested assist torque; and control at least one aspect of the steering system using the requested assist torque and the assist torque limit.

[0048] In some embodiments, the data corresponding to the one or more steering maneuvers includes at least one of the following: return torque path data, damping torque path data, and end-of-travel torque path data.

[0049] The word "example" is used herein to serve as an example, instance, or illustration. Any aspect or design described herein as an "example" is not necessarily preferred or advantageous over other aspects or designs. Rather, the use of the word "example" is intended to illustrate concepts in a concrete manner. As used in this application, the term "or" is intended to mean an inclusive "or" rather than an exclusive "or." That is, unless otherwise stated or clear from the context, "X includes A or B" means any of the natural inclusive permutations. That is, if X includes A, X includes B, or X includes both A and B, then "X includes A or B" is satisfied in each of the foregoing cases.Furthermore, as used in this application and the appended claims, the articles "a / an / an" should generally be interpreted to mean "one or more" unless otherwise indicated or the context clearly indicates a singular form. Furthermore, the use of the term "an implementation" or "an implementation" is not synonymous with the same embodiment or implementation unless described as such.

[0050] The systems, algorithms, methods, instructions, etc., described herein may be implemented in hardware, software, or any combination thereof. The hardware may include, for example, computers, intellectual property (IP) cores, application-specific integrated circuits (ASICs), programmable logic arrays, optical processors, programmable logic controllers, microcode, microcontrollers, servers, microprocessors, digital signal processors, or any other suitable circuitry. In the claims, the term "processor" is to be understood to include any of the foregoing hardware units, either individually or in combination. The terms "signal" and "data" are used interchangeably.

[0051] As used herein, the term module can include a packaged functional hardware unit designed for use with other components, a set of instructions that can be executed by a controller (e.g., a processor executing software or firmware), processing circuitry configured to perform a specific function, and a self-contained hardware or software component that interfaces with a larger system. For example, a module can include an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), a circuit, a digital logic circuit, an analog circuit, a combination of discrete circuits, gates, and other types of hardware, or a combination thereof.In other embodiments, a module may include memory storing instructions that can be executed by a controller to implement a feature of the module.

[0052] In one aspect, the systems described herein may further be implemented, for example, with a general-purpose computer or a general-purpose processor having a computer program that, when executed, carries out the respective methods, algorithms, and / or instructions described herein. Additionally or alternatively, for example, a special-purpose computer / processor may be used, which may include other hardware for executing the methods, algorithms, or instructions described herein.

[0053] Furthermore, all or part of the implementations of the present invention may take the form of a computer program product, accessible, for example, from a computer-usable or computer-readable medium. A computer-usable or computer-readable medium may be any device that can, for example, tangibly contain, store, transmit, or transport the program for use by or in connection with any processor. The medium may be, for example, an electronic, magnetic, optical, electromagnetic, or semiconductor device. Other suitable media are also available.

[0054] The above-described embodiments, implementations, and aspects have been described to facilitate a simple understanding of the present invention and do not limit the present invention. On the contrary, the invention is intended to cover various modifications and equivalent arrangements that fall within the scope of the appended claims, which scope should be interpreted as broadly as possible to encompass all such modifications and equivalent structures permitted by law.

Claims

[1] Method (300) for calculating at least one functional limit for a requested auxiliary torque in a steering system, the method (300) comprising: Receiving at least one input; transmitting the at least one input to an artificial neural network (200), the artificial neural network (200) configured to calculate an assist torque limit corresponding to the requested assist torque; Receiving the auxiliary torque limit corresponding to the requested auxiliary torque from the artificial neural network (200); and Controlling at least one aspect of the steering system using the requested assist torque and the assist torque limit. [2] Method (300) according to claim 1, characterized bythat the at least one input comprises a handwheel torque and / or a handwheel angle and / or an engine speed and / or a vehicle speed and / or an estimated engine torque. [3] Method (300) according to claim 1, characterized by that the artificial neural network (200) is trained using data corresponding to one or more steering maneuvers. [4] Method (300) according to claim 3, characterized by that the data corresponding to the one or more steering maneuvers includes at least one of the following elements: return torque path data, damping torque path data, and end-of-travel torque path data. [5] Method (300) according to claim 1, characterized by that the steering system comprises an open-loop control system. [6] Method (300) according to claim 1, characterized by that the steering system comprises a closed-loop control system. [7] Method (300) according to claim 1, characterized by that the steering system includes an electronic power steering system. [8] Method (300) according to claim 1, characterized by that the steering system includes a steer-by-wire steering system. [9] Method (300) according to claim 1, characterized by that the steering system comprises a hydraulic steering system. [10] System for calculating at least one functional limit for a requested assist torque in a steering system, the system comprising: a processor (102); and a memory (104) containing instructions that, when executed by the processor (102), cause the processor (102) to: to receive at least one input; transmit the at least one input to an artificial neural network (200), the artificial neural network (200) configured to calculate an assist torque limit corresponding to the requested assist torque; receive from the artificial neural network (200) the auxiliary torque limit corresponding to the requested auxiliary torque; and control at least one aspect of the steering system using the requested assist torque and the assist torque limit. [11] System according to claim 10, characterized by that the at least one input comprises a handwheel torque and / or a handwheel angle and / or an engine speed and / or a vehicle speed and / or an estimated engine torque. [12] System according to claim 10, characterized by that the artificial neural network (200) is trained using data corresponding to one or more steering maneuvers. [13] System according to claim 12, characterized by that the data corresponding to the one or more steering maneuvers includes at least one of the following elements: return torque path data, damping torque path data, and end-of-travel torque path data. [14] System according to claim 10, characterized by that the steering system comprises an open-loop control system. [15] System according to claim 10, characterized by that the steering system comprises a closed-loop control system. [16] The system according to claim 10, characterized by that the steering system includes an electronic power steering system. [17] System according to claim 10, characterized by that the steering system includes a steer-by-wire steering system. [18] System according to claim 10, characterized by that the steering system comprises a hydraulic steering system. [19] Apparatus for calculating at least one functional limit for a requested assist torque in a steering system, the apparatus comprising: a processor (102); and a memory (104) containing instructions that, when executed by the processor (102), cause the processor (102) to: receive at least one input including at least one of the following: a handwheel torque, a handwheel angle, an engine speed, a vehicle speed, and an estimated engine torque; transmitting the at least one input to an artificial neural network (200) trained using data corresponding to one or more steering maneuvers, the artificial neural network (200) configured to calculate an assist torque limit corresponding to the requested assist torque; receive from the artificial neural network (200) the auxiliary torque limit corresponding to the requested auxiliary torque; and control at least one aspect of the steering system using the requested assist torque and the assist torque limit. [20] Device according to claim 19, characterized bythat the data corresponding to the one or more steering maneuvers includes at least one of the following elements: return torque path data, damping torque path data, and end-of-travel torque path data

Images