Torque-based vehicle path prediction

Abstract

The steering system includes a motor and a processor configured to perform a method. The method includes calculating, by the processor, a predicted steering angle at a future time step. The method also includes determining, by the processor, a predicted vehicle position at the future time step based on the predicted steering angle. The method also includes detecting, by the processor, a proximity to an object at the future time step based on the predicted vehicle position. The method also includes generating, by the processor, an intervention signal in response to the proximity being below a predetermined threshold.

Description

Background Art

[0001] Advanced driver assistance systems (ADAS) facilitate different levels of automated control of vehicles. The vehicle's steering system plays a key role in enabling multiple ADAS features. For example, lane keeping assist (LKA) uses lane information from sensors (e.g., cameras) to provide steering torque assistance to the driver using the steering system. In these situations, the ADAS function can request steering system torque overlay to stop the driver from unintentionally changing lanes. Summary of the invention

[0002] According to one or more embodiments, a method includes calculating, by a processor, a predicted steering angle at a future time step. The method also includes determining, by the processor, a predicted vehicle position at a future time step based on the predicted steering angle. The method also includes detecting, by the processor, a proximity to an object at a future time step based on the predicted vehicle position. The method also includes generating, by the processor, an intervention signal in response to the proximity being below a predetermined threshold.

[0003] According to one or more embodiments, a steering system includes a motor and a processor configured to perform a method. The method includes calculating, by the processor, a predicted steering angle at a future time step. The method also includes determining, by the processor, a predicted vehicle position at the future time step based on the predicted steering angle. The method also includes detecting, by the processor, a proximity to an object at the future time step based on the predicted vehicle position. The method also includes generating, by the processor, an intervention signal in response to the proximity being below a predetermined threshold.

[0004] According to one or more embodiments, a computer program product includes a memory having one or more computer executable instructions stored thereon, which when executed by a processor causes the processor to perform a method. The method includes calculating, by the processor, a predicted steering angle at a future time step. The method also includes determining, by the processor, a predicted vehicle position at a future time step based on the predicted steering angle. The method also includes detecting, by the processor, a proximity to an object at a future time step based on the predicted vehicle position. The method also includes generating, by the processor, an intervention signal in response to the proximity being below a predetermined threshold.

[0005] These and other advantages and features will become more apparent from the following description taken in conjunction with the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0006] The subject matter of the present invention is particularly pointed out and distinctly claimed in the claims at the conclusion of the specification. The foregoing and other features and advantages of the present invention will become apparent from the following detailed description taken in conjunction with the accompanying drawings, in which:

[0007] Figure 1 depicts an automated driver assistance system in a vehicle according to one or more embodiments;

[0008] Figure 2 depicts an EPS system according to one or more embodiments;

[0009] Figure 3 is an exemplary embodiment of a SbW system 40 for implementing the described embodiments;

[0010] Figure 4 depicts a block diagram depicting torque-based vehicle path prediction according to one or more embodiments;

[0011] Figure 5 depicts an example structure of a steering system prediction module according to one or more embodiments;

[0012] Figure 6 depicts a visual depiction of lane marking detection using predicted vehicle position in accordance with one or more embodiments;

[0013] Figure 7 depicts a block diagram of a steering system control module according to one or more embodiments; and

[0014] Figure 8 A flow chart of an example method for torque-based vehicle trajectory prediction is depicted in accordance with one or more embodiments. DETAILED DESCRIPTION

[0015] As used herein, the terms module and submodule refer to one or more processing circuits (e.g., application specific integrated circuits (ASICs), electronic circuits), processors (shared, dedicated, or grouped) and memories that execute one or more software or firmware programs, combinatorial logic circuits, and / or other suitable components that provide the functionality. It will be appreciated that the submodules described below may be combined and / or further divided.

[0016] Figure 1 An advanced driver assistance system in a vehicle according to one or more embodiments is depicted. It should be understood that the steering system 40 shown and described may be used in an autonomous or semi-autonomous vehicle or a more conventional vehicle. In the vehicle 100, an advanced driver assistance system (ADAS) 110 may be coupled to the steering system 40, one or more wheels 44 (via one or more control units), and other control units in the vehicle 100. The ADAS 110 may include one or more processors 112 and one or more memory devices 114.

[0017] ADAS 110 receives one or more input signals including data and / or commands from a control unit, such as controller 16 of steering system 40. ADAS 110 may also receive one or more input signals 116 from one or more sensors, such as cameras, radars, lidars, or any other sensors. ADAS 110 may also send signals including data and / or commands to a control unit, such as controller 16 of steering system 40. ADAS 110 may also receive inputs from a human driver, such as a destination, one or more preferences, and the like.

[0018] The ADAS 110 may provide notifications to the driver, such as during interaction with the driver, and / or in response to one or more conditions in the vehicle 100. The notifications may include audio notifications, visual notifications, tactile notifications, torque notifications, etc. For example, audio / visual notifications may be sent via a driver-vehicle information unit, a speaker equipped in the vehicle 100, etc. Tactile notifications may be provided via a seat, the steering system 40, etc. Torque notifications may be sent via the steering system 40, such as by generating a torque overlay that is added to an assist torque (generating an assist torque for assisting the driver when operating the vehicle 100).

[0019] In one or more examples, ADAS 110 automatically determines the driving trajectory of vehicle 100. Sensor 116 is used to provide several ADAS features that affect the lateral movement of vehicle 100, such as lane keeping assist, lane centering assist, blind spot assist, etc. These features can help drivers avoid collisions such as side collisions, front collisions, etc. When providing such functions, ADAS 110 evaluates the driver's intentions, such as acceleration, lane changes, etc. ADAS features such as LKA can rely on sensor-based lane information to detect the proximity of the vehicle to the lane marking or the possibility of the vehicle entering other lanes based on lateral movement. However, this information is usually delayed relative to driver input. After the driver applies the hand-held steering wheel torque, there is some delay before the vehicle movement is affected due to physical reasons. For collision avoidance applications, this delay is undesirable because it may be too late to predict potential side collisions and apply the necessary torque superposition.

[0020] The technical solution described herein helps to determine the predicted vehicle trajectory faster than sensor-based trajectory prediction. In order to overcome the technical challenges of sensor-based vehicle trajectory prediction, the technical solution described herein uses steering signals such as hand-held steering wheel torque to predict vehicle trajectory. The predicted trajectory (or path) can be used to identify the driver's intention and act when necessary to mitigate potential collisions (side collisions, front collisions, etc.).

[0021] The technical solution described herein is applicable to EPS (Electric Power Steering) and SbW (Steer by Wire) systems.Referring to the accompanying drawings, the technical solution will be described with reference to specific embodiments without limitation thereto. Figure 2 is an exemplary embodiment of an electric power steering system (EPS) 40 suitable for use in a vehicle 100 for implementation of the disclosed embodiments, and Figure 3 is an exemplary embodiment of a SbW system 40 for implementing the described embodiment. Unless otherwise specifically described, the steering system 40 referred to in this document may be EPS or SbW, or may be any other type of steering system that can use the technical solutions described herein.

[0022] exist Figure 2 , the steering mechanism 36 is a rack-and-pinion type system and includes a rack (not shown) located within a housing 50 and a pinion (also not shown) located below a gear housing 52. With driver input (hereinafter represented as turning the hand-held steering wheel or steering wheel 26), the upper steering shaft 29 rotates and the lower steering shaft 51 connected to the upper steering shaft 29 by a universal joint 34 rotates the pinion. The rotation of the pinion moves the rack, which moves the tie rods 38 (only one shown), which in turn moves the steering knuckles 39 (only one shown), which rotate the steerable wheels or tires 44 (only one shown). Although a rack-and-pinion system is described herein, the EPS in other embodiments may be a column assisted EPS (CEPS), a pinion assisted EPS (PEPS), a dual pinion assisted EPS, or any other type of EPS.

[0023] Electric power steering assistance is provided by a control arrangement generally indicated by reference numeral 24 and comprising a controller 16 and an electric motor 46, which may be a permanent magnet synchronous motor (PMSM), or a permanent magnet direct current motor (PMDC), or any other type of motor, and is hereinafter referred to as motor 46. The controller 16 is powered by a vehicle power supply 10 via line 12. The controller 16 receives a vehicle speed signal 14 representing the vehicle speed from a vehicle speed sensor 17. The steering angle is measured by a position sensor 32, which may be an optically encoded type sensor, a variable resistance type sensor, or any other suitable type of position sensor, and provides a position signal 20 to the controller 16. The motor speed may be measured using a tachometer or any other device, and is transmitted to the controller 16 as a motor speed signal 21. The position sensor 32 may be a position sensor 20, which ... m The motor speed is measured, calculated, or a combination of both. For example, the motor speed ω mcan be calculated as the change in motor position θ, which is measured by the position sensor 32 over a specified time interval. For example, it can be calculated according to the equation ω m =Δθ / ΔtThe motor speed ω m Determined as the derivative of the motor position θ, where Δt is the sampling time and Δθ is the change in position during the sampling interval. Alternatively, the motor speed can be derived from the motor position as the time rate of change of position. It should be appreciated that there are many well-known methods for performing the derivative function.

[0024] When the manual steering wheel 26 is turned, the torque sensor 28 senses the torque applied to the manual steering wheel 26 by the vehicle operator. The torque sensor 28 may include a torsion bar (not shown) and a variable resistor type sensor (also not shown) that outputs a variable torque signal 18 to the controller 16 relative to the amount of twist on the torsion bar. Although this is a torque sensor, any other suitable torque sensing device used with known signal processing techniques can be used. In response to various inputs, the controller sends a command 22 to the electric motor 46, which provides torque assistance to the steering system through a worm 47 and a worm gear 48, thereby providing torque assistance for vehicle steering.

[0025] In the control system 24 shown in the figure, the controller 16 uses torque, position, speed, etc. to calculate the command to deliver the required output power. The controller 16 is configured to communicate with various systems and sensors of the motor control system. The controller 16 receives signals from each system sensor, quantifies the received information, and provides an output command signal in response thereto, in this example, for example, the output command signal is provided to the motor 46. The controller 16 is configured to generate a corresponding voltage from an inverter (not shown) so that when applied to the motor 46, a desired torque or position is generated, wherein the inverter can be optionally combined with the controller 16 and referred to as the controller 16 in this article. In one or more examples, the controller 24 operates in a feedback control mode to generate the command 22 as a current regulator. Alternatively, in one or more examples, the controller 24 operates in a feedforward control mode to generate the command 22. Because these voltages are related to the position and speed of the motor 46 and the desired torque, the position and / or speed of the rotor and the torque applied by the driver are determined. The position encoder is connected to the steering shaft 51 to detect the angular position θ. The encoder can sense the rotational position based on optical detection, magnetic field changes, or other methods. Typical position sensors include potentiometers, resolvers, synchronizers, encoders, and the like, as well as combinations comprising at least one of the foregoing. The position encoder outputs a position signal 20 that indicates the angular position of the steering shaft 51 , and thereby the angular position of the motor 46 .

[0026] The desired torque may be determined by one or more torque sensors 28 that transmit a torque signal 18 indicative of the applied torque. One or more exemplary embodiments include such torque sensors 28 and torque signals 18 derived therefrom as they may be responsive to a compliant torsion bar, T-bar, spring, or similar device (not shown) configured to provide a response indicative of the applied torque.

[0027] In one or more examples, the temperature sensor 23 can be located at the motor 46. Preferably, the temperature sensor 23 is configured to directly measure the temperature of a sensing portion of the motor 46. The temperature sensor 23 transmits a temperature signal 25 to the controller 16 to facilitate processing and compensation as specified herein. Typical temperature sensors include thermocouples, thermistors, thermostats, etc., and combinations including at least one of the foregoing sensors, which provide a calibratable signal proportional to a specific temperature when properly placed.

[0028] Position signal 20, speed signal 21 and torque signal 18 are applied to controller 16. Controller 16 processes all input signals to generate values ​​corresponding to each of these signals, thereby generating rotor position values, motor speed values ​​and torque values ​​that can be used for processing in the algorithm specified in this article. Measurement signals such as the above are also usually linearized, compensated and filtered as needed to enhance the characteristics or eliminate undesirable characteristics of the acquired signal. For example, the signal can be linearized to increase the processing speed or to solve a large signal dynamic range. In addition, frequency or time-based compensation and filtering can be used to eliminate noise or avoid undesirable spectral characteristics. Controller 16 uses a control method to generate a torque command sent to motor 46. Motor 46 generates motor torque according to the command.

[0029] In order to perform the specified functions and the desired processing and the resulting calculations (e.g., identification of motor parameters, control algorithms, etc.), the controller 16 may include, but is not limited to, a processor, a computer, a DSP, a memory, a storage device, a register, a timing, an interrupt, a communication interface, and an input / output signal interface, etc., and a combination including at least one of the foregoing items. For example, the controller 16 may include input signal processing and filtering so that such signals from the communication interface can be accurately sampled and transformed or acquired. Additional features of the controller 16 and some of the processing therein are discussed in detail later in this article.

[0030] Figure 3An exemplary SbW system according to one or more embodiments is depicted. The SbW system 40 includes a hand-held steering wheel actuator (HWA) 70 and a wheel actuator (RWA) 80. The controller 16 is divided into two blocks, namely a controller 16A and a controller 16B associated with the HWA 70 and the RWA 80, respectively. In other examples, the controller 16 can be distributed in any other manner.

[0031] The HWA 70 includes one or more mechanical components, such as a hand-held steering wheel 26 (steering wheel), a steering column, a motor / inverter attached to the steering column through a gear mechanism or a direct drive system. The HWA 70 also includes a microcontroller 16A that controls the operation of the mechanical components. The microcontroller 16A receives and / or generates torque through one or more mechanical components. For example, the microcontroller 16A can send a torque command request to the motor / inverter that will generate such torque.

[0032] The RWA 80 includes one or more mechanical components, such as a steering rack and / or pinion arrangement coupled to a motor / inverter via a ball nut / ball screw (gear), and the rack is connected to the vehicle wheel / tire 44 via a tie rod. The RWA 80 includes a microcontroller 16B that controls the operation of the mechanical components. The microcontroller 16B receives and / or generates torque via one or more mechanical components. For example, the microcontroller 16B can send a torque command request to the motor / inverter that will generate such torque.

[0033] The microcontrollers 16A and 16B are coupled by electrical connections that allow for sending / receiving signals. As mentioned herein, the controller may include any one of a combination of the HWA controller 16A and the RWA controller 16B or specific microcontrollers.

[0034] In one or more examples, the controllers 16A and 16B of the SbW system 40 communicate with each other via a CAN interface (or other similar digital communication protocol). The steering of the vehicle 100 equipped with the SbW system 40 is performed using a steering gear. The RWA 80 receives an electronic communication signal from the driver rotating the steering wheel. The driver controls the steering wheel to directionally control the vehicle 100. The angle from the HWA 70 is sent to the RWA 80, which performs position control to control the rack travel to guide the wheels. However, due to the lack of a mechanical connection between the steering wheel and the wheels, the driver has no feel for the road without torque feedback (unlike the situation in the EPS described above).

[0035] In one or more examples, the HWA 70 coupled to the steering column and steering wheel simulates the driver's feel for the road. The HWA 70 can apply tactile feedback to the steering wheel in the form of torque. The HWA 70 receives the rack force signal from the RWA 80 to generate an appropriate torque feel for the driver. Alternatively, the hand-held steering wheel angle and vehicle speed can also be used to generate a desired torque feel for the driver.

[0036] As mentioned above, the SbW and EPS described herein are exemplary, and the technical solutions described herein are applicable to any type of steering system, therefore, unless specifically mentioned otherwise, the “steering system 40 ” herein refers to any type of steering system.

[0037] Figure 4 A block diagram describing torque-based vehicle path prediction according to one or more embodiments is depicted. The depicted blocks may be functions implemented by one of the processors, such as the processor 112, and / or may be implemented as modules that receive input data and output results to one or more processors. For example, computer executable instructions may be used to implement the functions.

[0038] The depicted vehicle path prediction system 200 includes, among other components, a steering system (SS) prediction module 420, a path prediction module 430, a SS-based detection module 440, an ADAS function module 450, and a SS function controller 460. The vehicle path prediction system 200 includes / uses sensors 116, such as cameras, radars, lidars, etc., that provide input signals to one or more components.

[0039] In one or more examples, the vehicle path prediction system 200 may also include a sensor-based detection module 410. The sensor-based detection module 410 uses only input signals from one or more sensors 116 (eg, a camera).

[0040] Both the sensor-based detection module 410 and the SS-based detection module 440 detect the proximity of the vehicle 100 to the object. For example, the object may include a lane sign, a traffic sign (e.g., a traffic cone), another vehicle, a railing, a wall, a tree, a pedestrian, or any other object with which the vehicle 100 may collide. In the example described herein, "detection" is described as checking whether the vehicle crosses a predetermined boundary (e.g., lane sign information), but it should be understood that the technical solution described herein can determine and use the proximity to any other object. Detection is usually performed in vehicle coordinates. The ADAS functional module 450 can use the detection result information to determine the proximity to the lane sign or the possibility of lane crossing. The output of one or both detection modules 410, 440 can also be used as an activation signal to the ADAS functional module 450.

[0041] The SS prediction module 420 uses a mathematical model of the dynamics of the steering system 40 to predict the steering angle for future time steps. The prediction is based on the input torque (T), the current steering angle (θ), and the current steering speed (the rate at which the steering angle changes). In one or more examples, the steering speed is derived from the measured motor speed. The input torque (T) can represent the input from the driver (driver torque or hand-held steering wheel torque) or the motor torque (e.g., a command sent to the electric motor 46). The steering speed can be dynamically calculated based on the steering angle at multiple time points.

[0042] The dynamics of the steering system 40 can be represented by a single inertia model or a multi-body model. The single inertia model can be used to represent the dynamics of the steering system 40 in the form of the following second-order discrete transfer function:

[0043]

[0044] Where θ is the steering angle, T is the input torque of the steering system 40 (i.e., the hand-held steering wheel torque or the driver torque), and a0, a1, a2 and b0, b1, b2 are discrete transfer function coefficients obtained by approximating the system dynamics and steering system control. According to the dynamic behavior of the system, a suitable sampling time is selected for the above equation. In the above equation, z -p represents the delay of p sampling time steps. In the case of multi-body or multi-inertia models, the order of the transfer function increases. Those skilled in the art can also use nonlinear functions to obtain the steering angle as a function of the input torque and / or other signals.

[0045] The above equation can also be written in a different form:

[0046]

[0047] where k represents the current (kth) time step; k-1 is the previous time step 1 sampling time ago, ... kp is the time step p sampling times ago, and so on.

[0048] Figure 5 Depicted is an example structure of a steering system prediction module in accordance with one or more embodiments. Figure 5 Each box 510 depicted in FIG. 5 performs a calculation of the above equation for θ[k], where the value of k is different for each box. In this calculation, the input torque (T) is assumed to be constant (i.e., the current measured value), and the above equation is applied multiple times (referred to as N times) to obtain a prediction of the steering angle N time steps into the future.

[0049] As shown, the output of the first predictor block 510A is the predicted steering angle at time K, which is used as the input of the second predictor block 510B. The second predictor block outputs the predicted steering at time K+1, and this output is used as the input of the subsequent predictor block (not shown). The sequence continues for N steps to predict the steering angle at K+N. Each predictor block 510A, 510B...510N uses the same input torque value for calculation. It should be noted that in some examples, the input torque can also be predicted and such predicted values ​​used in the corresponding steering angle prediction. In addition, the choice of the number of steps N and the step size depends on the dynamics of the system. As shown in FIG. Figure 5 As shown, the value of T is constant from step K to K+N, and the value at K is the measured value; for θ, its value is previously calculated until it is input to 510A, and the value is estimated dynamically from step K to K+N.

[0050] Return to reference Figure 4 , the path prediction module 430 uses the predicted steering angle from the SS prediction module 420 to calculate the future position of the vehicle 100. The steering angle can be converted into a tire angle (δ) using a steering ratio or other method. In one or more examples, a kinematic vehicle movement model is used for position prediction. Alternatively, in other examples, a dynamic vehicle model can be used to predict the vehicle position based on the predicted steering angle. A constant turning radius model is used. Based on the future steering / tire angle, the position of the vehicle 100 can be predicted at multiple time steps corresponding to the time step n for the prediction of the steering angle.

[0051] The following equations represent calculations that may be performed to predict the vehicle's position, specifically the X and Y coordinates of the vehicle's center of gravity or gravity (CG) and the left and right front angles:

[0052] Radius = L / δ

[0053] ε=U×t * / radius

[0054] x_diameter_cg = radius*sin(ε)

[0055] y_path_cg = sgn * radius * (1-cos(ε))

[0056] x_path_left_angle = x_path_cg + a*cos(ε)-width / 2*sin(ε)

[0057] y_path_left_angle = y_path_cg - (a*sin(ε) + width / 2cos(ε))

[0058] x_path_right_angle=x_path_cg+(a*cos(ε)-width2sin(ε))

[0059] y_path_right_angle = y_path_cg + (a*sin(ε) + width / 2*cos(ε))

[0060] In the above equation, radius = radius of the vehicle path, L = wheelbase, t * = look-ahead distance, U = vehicle speed, ε = arc angle of predicted vehicle path, width = vehicle width.

[0061] The SS-based detection module 440 uses the future position of the vehicle and the lane marking information to check whether the left or right corner of the vehicle is crossing the lane marking. The lane marking can be obtained from the sensor 116 (e.g., a camera). It should be noted that although lane markings are used to describe crossing detection in one or more embodiments of the technical solution described herein, in other embodiments, the detection modules 410 and 440 can use other predetermined landmarks. For example, other landmarks that can be used include other vehicles, road edges, stationary objects, pedestrians, etc.

[0062] Figure 6 A visual depiction of lane marking detection using predicted vehicle positions according to one or more embodiments is depicted. When the vehicle 100 is at position 610, the trajectory of the vehicle is predicted 640 by calculating the vehicle positions at n time steps. Figure 5 The tire angle at time step n of the steering angle calculation described in Figure 6 is shown as δ n One of the predicted vehicle positions includes position 620. Lane marking 630 is detected in conjunction with sensor 116. Whether vehicle 100 crosses lane marking 630 can be mathematically checked by converting the equation for lane marking 630 in vehicle coordinates and using the (x, y) coordinates of the left and right vehicle corners of vehicle 100 from the above equation.

[0063] If the SS-based detection module 440 detects a lane crossing, an activation signal is sent to the ADAS function 460, indicating that the vehicle position 620 may cause a lane crossing. In one or more examples, to make the detection more robust, the following conditions may be checked to set the activation signal to true: the predicted positions of both front vehicle corners cross the left / right lane markings, one front vehicle corner position crosses the left / right lane markings, and the distance of the current vehicle center from the left / right lane markings is less than a threshold. Other conditions may also be used in one or more examples.

[0064] As previously described, in addition, the sensor-based detection module 410 can perform lane crossing detection. The sensor-based detection module 410 can also use the camera sensor signal for lane marking information in vehicle coordinates. The sensor-based detection module 410 uses this information to determine the proximity of the predicted position 620 of the vehicle to the lane marking 630 for potential lane crossings. The output of the sensor-based detection module 410 can be a second activation signal provided to the ADAS functional module 450.

[0065] The ADAS function module 450 depicts any one or more features provided by the ADAS that can be implemented by the processor 112 of the ADAS system 110. Alternatively or additionally, features can be implemented by one or more separate modules of the ADAS 110. For example, the ADAS function 450 can be a lane keeping assist function or a side collision avoidance assist function. The ADAS function 450 uses the activation signal and other information (e.g., the position and speed of the target vehicle in the other lane or the collision time (TTC), etc.) to generate a steering intervention signal. The intervention signal can be an input / output torque overlay or a position control signal or an auxiliary scaling factor, or any other such signal that changes the driver's manipulation of the trajectory of the vehicle 100 toward the predicted position 620. In one or more examples, the intervention signal at least causes the driver to be notified that the ADAS 110 recommends not maneuvering the vehicle 100 along the predicted vehicle trajectory 640 leading to the predicted position 620.

[0066] Figure 7A block diagram of a steering system control module according to one or more embodiments is depicted. The steering system module 450 includes, among other components, an assist torque calculator 710 and a position controller 720. The assist torque calculator 710 calculates an amount of assist torque based on an input torque provided by the driver to provide the driver's manipulation. The intervention signal can be used as an input overlay torque 712 to adjust the input torque provided by the driver. For example, the input overlay torque 712 can increase / decrease an input torque value that is used to calculate the amount of assist torque to be generated by the motor 46. In one or more examples, the intervention signal can be used as an input to a lookup table to determine the input overlay torque 712.

[0067] Alternatively or additionally, the intervention signal is used as a scaling factor 714, which adjusts the amount of assist torque calculated by the assist torque calculator 710. Alternatively, the intervention signal is used as an input to a lookup table to determine the scaling factor 714. The scaling factor 714 can increase / decrease the amount of assist torque calculated. In one or more examples, the scaling factor 714 is used as a multiplier to adjust the amount of assist torque calculated. After adjustment, the amount of assist torque is used to generate an assist torque command, which is applied to the motor 46 to generate a corresponding assist torque.

[0068] In one or more examples, the intervention signal may be used as an output overlay torque command 716 that is blended into the assist torque command generated by the assist torque calculator 710 .

[0069] Additionally, the intervention signal can be used as a position command 722 to the position controller 720. The position controller 720 generates a position torque command to adjust the position of the steering wheel 26. The position torque command is applied to the motor 46 to generate a corresponding amount of position torque that adjusts the position of the steering wheel 26. By applying an additional position command 722, the intervention signal changes the position of the steering wheel 26 from the desired position to which the driver is moving the steering wheel 26. In one or more examples, the intervention signal can be used as the position command 722 itself, or the intervention signal can be used as an input to a lookup table that provides a position command.

[0070] As described herein, the activation signal calculation and subsequent intervention signal calculation and use improve the performance of the ADAS 110. For example, the predicted steering angle and activation signal calculated using the input torque have a faster response time during the execution of the test compared to the activation signal calculation based only on the signal from the sensor 116 (e.g., a camera). In addition, a test was conducted to compare the activation of lane crossings based only on the sensor 116 (e.g., a camera) with the activation based on the torque-based method. It was found that the lane crossing detection using the torque-based method was faster. The lead time caused by the use of the input torque and the steering angle is an improvement over the generation of the sensor-only activation signal, because in the case of a sensor-only system, ADAS functions (such as lane keeping or lane centering) may not update their outputs quickly for fast yaw rate change events. In this case, the steering-based technical solution described herein can improve the performance of the above-mentioned ADAS functions and can also be used for ADAS functions such as side collision avoidance.

[0071] Figure 8 A flow chart of an example method for torque-based vehicle trajectory prediction according to one or more embodiments is depicted. The method can be implemented by one or more processors in the vehicle 100. In one or more examples, the processor is associated with the steering system 40 to send / receive steering signals and torque commands. The method includes, at 802, calculating a predicted steering angle at a future time step t+k, where t is the current time step. As described herein, the steering system prediction module 420 can predict the steering angle based on the input torque, the steering speed, and the current steering angle.

[0072] The method also includes determining a predicted vehicle position at a future time step (t+k) based on the predicted steering angle at 804 (620). The path prediction module 430 can predict the future vehicle position 620 using the vehicle model described herein.

[0073] At 806, sensor-based detection module 440 detects lane crossings at future time steps based on the predicted vehicle position. The prediction uses lane marking information received from sensor 116 (e.g., a camera). The detection is performed by checking whether the predicted vehicle position crosses the lane marking coordinates. In one or more examples, the lane marking coordinates are converted to vehicle coordinates for performing the check. Alternatively, the vehicle's coordinates are converted to lane marking coordinates. Other conversions are also possible.

[0074] At 808, if a (potential) lane crossing is detected at a future time step, an intervention signal is generated by the ADAS functional module 450. The intervention signal is provided to the steering control module 460. The intervention signal can be used by the steering control module 460 in one or more ways to provide notification to the driver and / or change the driver's manipulation being performed by the steering wheel 26. For example, the intervention signal can be used to generate an audio / visual signal to the driver. Alternatively or additionally, a superimposed torque can be generated, which is added to the input torque received from the driver. In one or more examples, the superimposed torque can be added to an auxiliary torque command, which is generated based on the input torque from the driver. In yet another example, the superimposed torque is added to the final torque command, which is applied to the motor 46. In one or more examples, the final torque command can be the addition of the auxiliary torque and the position torque command. A position torque command can be generated based on the input signal to change the angle of the steering wheel 26. In some other examples, the intervention signal is used to change the position torque command itself by generating a position command added to the input steering angle signal.

[0075] Therefore, the technical solution described herein helps to use the steering signal (torque, angle) to predict the vehicle position (or driver intention) over a predetermined duration. The technical solution described herein helps to use the steering model to predict the future steering angle based on the steering torque. In addition, the vehicle model is used to predict the future vehicle path based on the predicted future steering angle and vehicle position. The technical solution described herein also uses the predicted vehicle position to identify lateral vehicle movement. The predicted vehicle position is also used to calculate the activation signal based on the possibility of lane crossing. Lane crossing detection is also based on sensor-based lane information and predicted vehicle position to calculate the activation signal. The activation signal causes the generation of a steering intervention signal, which causes a change in the steering motor torque. For example, the steering intervention signal can be used to modify the steering torque using input torque superposition / output torque superposition / position command / auxiliary scaling factor. In one or more examples, the steering intervention signal is also used to generate an audio / visual warning.

[0076] The technical solution may be a system, method and / or computer program product at any possible level of integration of technical details. The computer program product may include a computer-readable storage medium (or medium) having computer-readable program instructions thereon for causing a processor to execute various aspects of the technical solution.

[0077] This article refers to the flowchart and / or block diagram of the method, device (system) and computer program product according to the embodiment of the technical solution to describe various aspects of the present technical solution. It will be understood that each frame of the flowchart and / or block diagram and the combination of frames in the flowchart and / or block diagram can be implemented by computer-readable program instructions.

[0078] The flow chart and block diagram in the accompanying drawings illustrate the architecture, function and operation of the possible implementation of the system, method and computer program product according to various embodiments of the present technical solution. In this regard, each frame in the flow chart or block diagram can represent a module, a segment or a partial instruction, which includes one or more executable instructions for implementing a specified logical function. In some alternative embodiments, the functions mentioned in the frame may not occur in the order shown in the figure. For example, in fact, the two boxes shown in succession can be executed substantially at the same time, or these boxes can sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each frame of the block diagram and / or flow chart and the combination of the frames in the block diagram and / or flow chart can be implemented by a dedicated hardware type system that performs a specific function or action or performs a combination of dedicated hardware and computer instructions.

[0079] It should also be understood that any module, unit, component, server, computer, terminal or device for executing instructions illustrated herein may include or otherwise access computer-readable media, such as storage media, computer storage media or data storage devices (removable and / or non-removable) (e.g., disks, optical disks or tapes). Computer storage media may include volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information (e.g., computer-readable instructions, data structures, program modules or other data). Such computer storage media may be part of the device or may be accessible to or connected to the device. Any application or module described herein may be implemented using computer-readable / executable instructions that may be stored or otherwise maintained by such computer-readable media.

[0080] Although the technical solution has been described in detail in conjunction with only a limited number of embodiments, it should be readily understood that the technical solution is not limited to these disclosed embodiments. Rather, the technical solution may be modified to include any number of variations, changes, substitutions, or equivalent arrangements not previously described but commensurate with the spirit and scope of the technical solution. Additionally, although various embodiments of the technical solution have been described, it should be understood that various aspects of the technical solution may include only some of the described embodiments. Therefore, the technical solution should not be considered to be limited by the foregoing description.

Claims

1. A method for predicting vehicle trajectory based on torque, comprising: calculating, by the processor, a predicted steering angle at a future time step; determining, by the processor, a predicted vehicle position at a future time step based on the predicted steering angle; detecting, by a processor, proximity to an object at a future time step based on the predicted vehicle position; as well as generating, by the processor, an intervention signal in response to the proximity falling below a predetermined threshold, Therein, the predicted steering angle is calculated based on a measured input torque value applied by the driver to the hand-held steering wheel, a steering speed, and a current steering angle.

2. The method according to claim 1, wherein: The future time step is t+k, where t is the current time and k is a predetermined integer.

3. The method according to claim 1, wherein: The intervention signal is an overlay torque command that is added to the input torque of the steering system.

4. The method according to claim 1, wherein: The intervention signal is a scaling factor used to scale the input torque to the steering system.

5. The method according to claim 1, wherein: The intervention signal is a position command that is added to the input steering angle provided to the steering system.

6. The method according to claim 1, wherein: The intervention signal is a torque command that is added to the assist torque command calculated by the steering system.

7. The method according to claim 6, further comprising: calculating an assist torque command by a motor control system of the steering system to generate a corresponding assist torque using the motor; calculating a position control torque command by a motor control system to position a steering wheel of a steering system; as well as A final torque command is generated by the motor control system by adding the superimposed torque command corresponding to the intervention signal, the assist torque command, and the position control torque command.

8. The method according to claim 1, further comprising: An audiovisual notification corresponding to the intervention signal is generated.

9. The method according to claim 1, wherein: Detecting proximity to an object at a future time step based on the predicted vehicle position includes detecting a lane crossing at a future time step.

10. The method according to claim 9, wherein: Lane crossing detection also includes: receiving, by a processor, lane marking coordinates from a sensor; and The predicted vehicle position crossing the lane marking coordinates is detected by the processor.

11. A steering system comprising: motor; as well as A processor configured to execute a method comprising: determining the predicted steering angle at a future time step; calculating a predicted vehicle position at a future time step based on the predicted steering angle; detecting, by the processor, proximity to the object at a future time step based on the predicted vehicle position; and generating, by the processor, an intervention signal in response to the proximity falling below a predetermined threshold, Therein, the predicted steering angle is determined based on a measured input torque value applied by the driver to the hand-held steering wheel, a steering speed, and a current steering angle.

12. The steering system according to claim 11, wherein: The intervention signal is an overlay torque command that is added to the input torque of the steering system.

13. The steering system according to claim 11, wherein: The intervention signal is a scaling factor used to scale the input torque to the steering system.

14. The steering system according to claim 11, wherein: The intervention signal is a position command that is added to the input steering angle provided to the steering system.

15. The steering system according to claim 11, wherein: The intervention signal is a torque command that is added to the assist torque command calculated by the steering system.

16. The steering system of claim 15, further comprising: calculating an assist torque command by a motor control system of the steering system to generate a corresponding assist torque using the motor; calculating a position control torque command by a motor control system to position a steering wheel of a steering system; as well as A final torque command is generated by the motor control system by adding the superimposed torque command corresponding to the intervention signal, the assist torque command, and the position control torque command.

17. The steering system of claim 11, further comprising: An audiovisual notification corresponding to the intervention signal is generated.

18. The steering system according to claim 11, wherein: Detecting proximity to an object at a future time step based on the predicted vehicle position includes detecting a lane crossing at a future time step.

19. A computer program product comprising a storage device having one or more computer executable instructions stored thereon, the computer executable instructions, when executed by a processor, causing the processor to perform a method, the method comprising: determining the predicted steering angle at a future time step; calculating a predicted vehicle position at a future time step based on the predicted steering angle; detecting, by a processor, proximity to an object at a future time step based on the predicted vehicle position; as well as generating, by the processor, an intervention signal in response to the proximity falling below a predetermined threshold, Therein, the predicted steering angle is determined based on a measured input torque value applied by the driver to the hand-held steering wheel, a steering speed, and a current steering angle.

20. The computer program product of claim 19, wherein: The intervention signal is an overlay torque command that is added to the input torque of the steering system.

21. The computer program product of claim 19, wherein: The intervention signal is a scaling factor used to scale the input torque to the steering system.

22. The computer program product of claim 19, wherein: The intervention signal is a position command that is added to the input steering angle provided to the steering system.

23. The computer program product of claim 19, wherein: The intervention signal is a torque command that is added to the assist torque command calculated by the steering system.

24. The computer program product of claim 23, further comprising: calculating an assist torque command by a motor control system of the steering system to generate a corresponding assist torque using the motor; calculating a position control torque command by a motor control system to position a steering wheel of a steering system; as well as A final torque command is generated by the motor control system by adding the superimposed torque command corresponding to the intervention signal, the assist torque command, and the position control torque command.

25. The computer program product of claim 19, further comprising: An audiovisual notification corresponding to the intervention signal is generated.

26. The computer program product of claim 19, wherein: Detecting proximity to an object at a future time step based on the predicted vehicle position includes detecting a lane crossing at a future time step.

Images