Control method and apparatus, and intelligent driving device

Abstract

A control method and apparatus, and an intelligent driving device. The method comprises: when there is a risk of collision between an intelligent driving device and an obstacle, determining a second torque at least according to a first torque of a steering wheel, the first torque being a torque applied to the steering wheel by a user of the intelligent driving device, the direction of the second torque being opposite to the direction of the first torque, and the value of the second torque minus the value of the first torque being greater than or equal to a first preset threshold; and controlling the steering wheel according to the first torque and the second torque. The technical solution of the present application may be applied to intelligent driving devices such as electric vehicles and new energy vehicles. When the risk of collision is detected, it is possible to control the torque of the steering wheel in view of the intent of an action of a driver, which may not only make the behavior of the intelligent driving device during obstacle avoidance more human-like, but also avoid high lateral acceleration caused by excessive torque applied when an obstacle avoidance function is triggered, thereby improving the driving and riding experience of the driver and passengers.

Description

Control method, device and intelligent driving equipment

[0001] This application claims priority to the Chinese patent application filed with the State Intellectual Property Office of China on June 15, 2023, with application number 202310713675.X and invention name “Control Method, Device and Intelligent Driving Equipment”, the entire contents of which are incorporated by reference into this application. Technical Field

[0002] The present application relates to the field of intelligent driving, and more specifically, to a control method, device and intelligent driving equipment. Background Art

[0003] The rapid development of the automotive industry has led to the emergence of numerous assisted and autonomous driving technologies, which can reduce driving stress and improve safety and efficiency. Assisted driving features include active safety functions, which proactively assess and implement preventative safety measures in emergency situations, before the driver can react, significantly reducing road traffic accidents and related casualties.

[0004] However, under the current technological background, the timing of triggering active safety functions is very close to the moment of collision, resulting in a large deceleration or lateral acceleration value of the vehicle when the function is triggered, affecting the driving experience of the driver and passengers, and even causing function failure, threatening driving safety.

[0005] Summary of the Invention

[0006] The present application provides a control method, apparatus, and intelligent driving device. When a collision risk is detected, the steering wheel torque can be controlled in combination with the driver's action intention. This can not only make the behavior of the intelligent driving device more human-like during the obstacle avoidance process, but also avoid applying excessive torque when the obstacle avoidance function is triggered, resulting in large lateral acceleration, thereby improving the driving experience of the driver and passengers.

[0007] In a first aspect, a control method is provided, which can be executed by an intelligent driving device; or, it can also be executed by a computing platform of the intelligent driving device; or, it can also be executed by a chip or circuit used for the intelligent driving device, which is not limited in this application.

[0008] The method includes: when there is a risk of collision between the intelligent driving device and a first obstacle, determining a second torque based at least on a first torque of the steering wheel; wherein the first torque is a torque applied to the steering wheel by a user of the intelligent driving device, a direction of the second torque is opposite to a direction of the first torque, and a value of the second torque minus a value of the first torque is greater than or equal to a first preset threshold; and controlling the steering wheel based on the first torque and the second torque.

[0009] It should be noted that the value of the first torque refers to the torque value of the first torque, and the value of the second torque refers to the torque value of the second torque.

[0010] In some possible implementations, the first preset threshold may be a negative number, that is, the value of the second torque may be less than the value of the first torque. For example, the first preset threshold may be -0.5 Newton-meters (N·m), or the first preset threshold may be other values.

[0011] For example, under the action of the first torque, the intelligent driving device moves from the current driving direction toward the first side of the intelligent driving device, and the first obstacle is located on the first side of the intelligent driving device. The first side can be the left side or the right side of the intelligent driving device.

[0012] In this technical solution, when a collision risk is detected, an opposing force can be applied to the steering wheel based on the torque applied by the driver, alerting the driver to the risk of a collision. Furthermore, controlling the steering wheel in accordance with the driver's intended movements can make the intelligent driving device behave more human-like during obstacle avoidance, avoiding excessive torque and causing significant lateral acceleration when the obstacle avoidance function is triggered, thereby improving the driving experience for the driver and passengers.

[0013] It should be noted that, in the present application, the transverse direction refers to a direction perpendicular to the longitudinal symmetry plane of the intelligent driving device, and the longitudinal direction refers to a direction parallel to the longitudinal symmetry plane of the intelligent driving device.

[0014] In combination with the first aspect, in certain implementations of the first aspect, the second torque is determined at least based on the first torque of the steering wheel, including: determining the value of the second torque based on the first collision risk between the intelligent driving device and the first obstacle and the value of the first torque; wherein, when the first collision risk is less than or equal to the first threshold, the value of the second torque minus the value of the first torque is greater than or equal to the first preset threshold and less than the second preset threshold; or, when the first collision risk is greater than the first threshold, the value of the second torque minus the value of the first torque is greater than or equal to the second preset threshold.

[0015] Exemplarily, the second preset threshold may be zero, or may be a positive number.

[0016] For example, the value of the second torque can be determined based on the magnitude of the first collision risk. The greater the first collision risk, the greater the difference between the value of the second torque and the value of the first torque. Furthermore, under the action of the second torque, the lateral acceleration of the intelligent driving device in the direction opposite to the first side is greater.

[0017] In some possible implementations, the first collision risk may be measured according to time to collision (TTC), and the first collision risk may be quantified into at least two levels according to the TTC.

[0018] In some possible implementations, the first collision risk may be measured according to the distance between the first obstacle and the intelligent driving device and the time to react (TTR), and the first collision risk may be quantified into at least two levels.

[0019] In some possible implementations, the first collision risk may be calculated in combination with the position and speed of other obstacles except the first obstacle, and the position and speed of each obstacle may quantify the first collision risk into at least two levels.

[0020] For example, the at least two levels may include level 1 and level 2. The collision risk corresponding to level 1 is smaller than the collision risk corresponding to level 2. The first threshold may be level 1.

[0021] In the above technical solution, steering wheel torque is intervened in stages before a collision occurs, based on the collision risk. When the collision risk is low, an antagonistic torque is generated based on the torque applied by the driver to the steering wheel. This antagonistic torque can promptly alert the driver to the presence of a collision risk, helping to prevent the intelligent driving device from entering a more dangerous driving scenario. When the collision risk is high, a corrective torque can be generated based on the torque applied by the driver to the steering wheel. This corrective torque can avoid a collision and help improve driving safety.

[0022] In combination with the first aspect, in certain implementations of the first aspect, the method further includes: when the second collision risk between the intelligent driving device and the first obstacle is less than or equal to a second threshold, determining a first longitudinal acceleration based on driving comfort, and controlling the intelligent driving device to decelerate based on the first longitudinal acceleration; or, when the second collision risk is greater than the second threshold, determining a second longitudinal acceleration based at least on the distance between the intelligent driving device and the first obstacle, and controlling the intelligent driving device to decelerate based on the second longitudinal acceleration; wherein the absolute value of the second longitudinal acceleration is greater than the absolute value of the first longitudinal acceleration.

[0023] It can be understood that both the first longitudinal acceleration and the second longitudinal acceleration are negative values.

[0024] In some possible implementations, the second collision risk is measured based on TTC, and the second collision risk is quantified into at least two levels based on TTC; or, the second collision risk is measured based on the distance between the first obstacle and the intelligent driving device and TTR, and the second collision risk is quantified into at least two levels.

[0025] In some possible implementations, a method for determining the second collision risk is the same as a method for determining the first collision risk.

[0026] Exemplarily, determining the second longitudinal acceleration based at least on the distance between the intelligent driving device and the first obstacle includes: determining the TTC based on the distance between the intelligent driving device and the first obstacle, and the relative speed between the two, and determining the second longitudinal acceleration based on the TTC and the current speed of the intelligent driving device.

[0027] In the above technical solution, the collision risk of the intelligent driving device is predicted in advance. When the collision risk is small, the intelligent driving device can be controlled to slowly decelerate at an acceleration that does not affect the driving experience. This can prevent the intelligent driving device from entering more dangerous scenarios (such as scenarios with greater collision risks). While ensuring driving safety, it helps to improve the experience of the driver and passengers. In the case of a greater collision risk, it can still be decelerated at a faster acceleration to improve driving safety. In addition, when the collision risk is detected, through joint lateral and longitudinal control, in more complex driving scenarios, it helps to reduce the probability of collision and improve driving safety.

[0028] In combination with the first aspect, in certain implementations of the first aspect, the method further includes: when the third collision risk between the intelligent driving device and the first obstacle is greater than or equal to a third threshold, determining a first motion trajectory based on control information input by a user of the intelligent driving device and an obstacle boundary, the control information including at least one of the following: opening information of an accelerator pedal of the intelligent driving device, opening information of a decelerator pedal of the intelligent driving device, and a first torque, and the obstacle boundary is determined by multiple obstacles including the first obstacle; the above-mentioned determining the second torque based on at least the first torque of the steering wheel includes: determining the second torque based on the first motion trajectory and the first torque, so that when the steering wheel is controlled based on the second torque, the intelligent driving device travels along the first motion trajectory.

[0029] In some possible implementations, the method for determining the third collision risk is the same as the method for determining the first and second collision risks. For example, the third collision risk is determined based on TTC, and the third threshold is smaller than the first and second thresholds.

[0030] In some possible implementations, the first collision risk and the second collision risk are determined by the first motion trajectory.

[0031] In the above technical solution, trajectory planning based on user-input control information helps generate an obstacle avoidance trajectory (such as the first motion trajectory) that matches the driver's driving behavior, thereby improving the driver's driving experience. Furthermore, lateral control based on the obstacle avoidance trajectory that matches the driver's driving behavior helps improve the human-like lateral control of the intelligent driving device.

[0032] In combination with the first aspect, in certain implementations of the first aspect, the method further includes: determining multiple motion trajectories based on the driver's reaction time and a reachable set of control parameters, where the reachable set of control parameters is a set of motion parameters that can be achieved by the intelligent driving device under user control; determining a third collision risk based on the multiple motion trajectories and the position and speed of the first obstacle.

[0033] Exemplarily, determining a third collision risk based on multiple motion trajectories and the position and speed of the first obstacle includes: determining the collision risk of each of the multiple motion trajectories based on the position and speed of the first obstacle; assigning different weights to the collision risk of each motion trajectory and then summing them up to obtain the third collision risk.

[0034] For example, the weight may be determined according to the lateral offset of the motion trajectory, where the larger the lateral offset, the smaller the weight.

[0035] In the above technical solution, multiple motion trajectories are determined based on the driver's reaction time and the reachable set of control parameters. This allows for early detection of potential collision risks, allowing for lateral and / or longitudinal control of the intelligent driving device based on these potential collision risks. This prevents the intelligent driving device from entering scenarios with a higher collision risk, thereby improving the driving experience for the driver and passengers. Predicting collision risks based on multiple motion trajectories helps reduce the probability of misjudgment of collision risks and increases the detection rate of potential collision risks in complex scenarios, thereby enhancing driving safety.

[0036] In combination with the first aspect, in certain implementations of the first aspect, the first obstacle includes at least one of the following: a motor vehicle, a non-motor vehicle, a general obstacle, and a pedestrian.

[0037] In the above technical solution, when performing collision risk detection, in addition to motor vehicles, the impact of other types of obstacles on intelligent driving equipment is also considered, which helps to improve driving safety.

[0038] In combination with the first aspect, in certain implementations of the first aspect, the second torque is determined at least based on the first torque of the steering wheel, including: determining the value of the second torque based on the TTC between the intelligent driving device and the first obstacle and the value of the first torque; wherein, when the TTC is greater than or equal to the first time length, the value of the second torque minus the value of the first torque is greater than or equal to the first preset threshold and less than the second preset threshold; or, when the TTC is less than the first time length, the value of the second torque minus the value of the first torque is greater than or equal to the second preset threshold.

[0039] Exemplarily, the first duration may be 1.5 seconds, or the first duration may be other values.

[0040] In combination with the first aspect, in certain implementations of the first aspect, the method further includes: when the remaining distance between the intelligent driving device and the first obstacle is greater than or equal to a preset distance, determining a first longitudinal acceleration based on driving comfort, and controlling the intelligent driving device to decelerate based on the first longitudinal acceleration; or, when the remaining distance is less than the preset distance, determining a second longitudinal acceleration based at least on the distance between the intelligent driving device and the first obstacle, and controlling the intelligent driving device to decelerate based on the second longitudinal acceleration; wherein the absolute value of the second longitudinal acceleration is greater than the absolute value of the first longitudinal acceleration.

[0041] For example, the remaining distance may be the actual longitudinal distance between the intelligent driving device and the first obstacle minus the product of the speed of the intelligent driving device and the driver's reaction time.

[0042] Exemplarily, the preset distance may be 2 meters, or the preset distance may be other values.

[0043] In a second aspect, a control method is provided, comprising: when a second collision risk between the intelligent driving device and a first obstacle is less than or equal to a second threshold, determining a first longitudinal acceleration based on driving comfort, and controlling the intelligent driving device to decelerate based on the first longitudinal acceleration; or, when the second collision risk is greater than the second threshold, determining a second longitudinal acceleration based at least on the distance between the intelligent driving device and the first obstacle, and controlling the intelligent driving device to decelerate based on the second longitudinal acceleration; wherein the absolute value of the second longitudinal acceleration is greater than the absolute value of the first longitudinal acceleration.

[0044] In combination with the second aspect, in certain implementations of the second aspect, the method further includes: determining a value of a second torque based on a first collision risk between the intelligent driving device and the first obstacle and a value of a first torque of the steering wheel; wherein the first torque is a torque applied to the steering wheel by a user of the intelligent driving device, and a direction of the second torque is opposite to that of the first torque; when the first collision risk is less than or equal to a first threshold, the value of the second torque minus the value of the first torque is greater than or equal to a first preset threshold and less than a second preset threshold; or, when the first collision risk is greater than the first threshold, the value of the second torque minus the value of the first torque is greater than or equal to a second preset threshold; and controlling the steering wheel based on the first torque and the second torque.

[0045] In combination with the second aspect, in certain implementations of the second aspect, the method further includes: when the third collision risk between the intelligent driving device and the first obstacle is greater than or equal to a third threshold, determining a first motion trajectory based on control information input by a user of the intelligent driving device and an obstacle boundary, the control information including at least one of the following: opening information of an accelerator pedal of the intelligent driving device, opening information of a decelerator pedal of the intelligent driving device, and a first torque, and the obstacle boundary is determined by multiple obstacles including the first obstacle; the above-mentioned determining the second torque based on at least the first torque of the steering wheel includes: determining the second torque based on the first motion trajectory and the first torque, so that when the steering wheel is controlled based on the second torque, the intelligent driving device travels along the first motion trajectory.

[0046] In combination with the second aspect, in certain implementations of the second aspect, the method also includes: determining multiple motion trajectories based on the driver's reaction time and a reachable set of control parameters, where the reachable set of control parameters is a set of motion parameters that can be achieved by the intelligent driving device under user control; determining a third collision risk based on the multiple motion trajectories and the position and speed of the first obstacle.

[0047] In combination with the second aspect, in certain implementations of the second aspect, the first obstacle includes at least one of the following: a motor vehicle, a non-motor vehicle, a general obstacle, and a pedestrian.

[0048] In a third aspect, a control device is provided, which includes: a first determination unit, used to determine a second torque based on at least a first torque of the steering wheel when there is a risk of collision between the intelligent driving device and a first obstacle; wherein the first torque is the torque applied to the steering wheel by a user of the intelligent driving device, the direction of the second torque is opposite to the direction of the first torque, and the value of the second torque minus the value of the first torque is greater than or equal to a first set threshold; and a processing unit, used to control the steering wheel based on the first torque and the second torque.

[0049] In combination with the third aspect, in certain implementations of the third aspect, the first determination unit is used to: determine the value of the second torque based on the first collision risk between the intelligent driving device and the first obstacle and the value of the first torque; wherein, when the first collision risk is less than or equal to the first threshold, the value of the second torque minus the value of the first torque is greater than or equal to the first preset threshold and less than the second preset threshold; or, when the first collision risk is greater than the first threshold, the value of the second torque minus the value of the first torque is greater than or equal to the second preset threshold.

[0050] In combination with the third aspect, in certain implementations of the third aspect, the first determination unit is further used to: when the second collision risk between the intelligent driving device and the first obstacle is less than or equal to a second threshold, determine the first longitudinal acceleration based on the driving comfort, and control the intelligent driving device to decelerate based on the first longitudinal acceleration; or, when the second collision risk is greater than the second threshold, determine the second longitudinal acceleration based on at least the distance between the intelligent driving device and the first obstacle, and control the intelligent driving device to decelerate based on the second longitudinal acceleration; wherein the absolute value of the second longitudinal acceleration is greater than the absolute value of the first longitudinal acceleration.

[0051] In combination with the third aspect, in certain implementations of the third aspect, the device also includes a second determination unit, which is used to: when the third collision risk between the intelligent driving device and the first obstacle is greater than or equal to a third threshold, determine the first motion trajectory based on control information input by a user of the intelligent driving device and the obstacle boundary, the control information including at least one of the following: opening information of an accelerator pedal of the intelligent driving device, opening information of a decelerator pedal of the intelligent driving device, and a first torque, and the obstacle boundary is determined by multiple obstacles including the first obstacle; the first determination unit is used to: determine the second torque based on the first motion trajectory and the first torque, so that when the steering wheel is controlled according to the second torque, the intelligent driving device travels along the first motion trajectory.

[0052] In combination with the third aspect, in certain implementations of the third aspect, the device also includes a third determination unit, which is used to: determine multiple motion trajectories based on the driver's reaction time and a reachable set of control parameters, where the reachable set of control parameters is a set of motion parameters that can be achieved by the intelligent driving device under user control; determine a third collision risk based on the multiple motion trajectories and the position and speed of the first obstacle.

[0053] In combination with the third aspect, in certain implementations of the third aspect, the first obstacle includes at least one of the following: a motor vehicle, a non-motor vehicle, a general obstacle, and a pedestrian.

[0054] In a fourth aspect, a control device is provided, comprising a determination unit and a processing unit, for executing the method in any possible implementation of the second aspect.

[0055] In a fifth aspect, a control device is provided, which includes: a memory for storing a computer program; and a processor for executing the computer program stored in the memory, so that the device performs a method in any possible implementation of the first aspect or the second aspect.

[0056] In a sixth aspect, an intelligent driving device is provided, which includes an apparatus as in any possible implementation of the third to fifth aspects.

[0057] In combination with the sixth aspect, in some implementations of the sixth aspect, the intelligent driving device is a vehicle.

[0058] In a seventh aspect, a computer program product is provided, comprising: a computer program code, which, when executed on a computer, enables the computer to execute the method in any possible implementation of the first or second aspect.

[0059] It should be noted that the above-mentioned computer program code may be stored in whole or in part on a first storage medium, wherein the first storage medium may be packaged together with the processor or separately from the processor.

[0060] In an eighth aspect, a computer-readable medium is provided, wherein the computer-readable medium stores instructions. When the instructions are executed by a processor, the processor implements the method in any possible implementation of the first aspect or the second aspect.

[0061] In a ninth aspect, a chip is provided, which includes a circuit for executing the method in any possible implementation of the first aspect or the second aspect. BRIEF DESCRIPTION OF THE DRAWINGS

[0062] FIG1 is a schematic diagram of a driving scenario;

[0063] FIG2 is a functional schematic block diagram of an intelligent driving device provided in an embodiment of the present application;

[0064] FIG3 is a schematic diagram of a system architecture required for implementing the control method provided in an embodiment of the present application;

[0065] FIG4 is a schematic flow chart of a control method provided in an embodiment of the present application;

[0066] FIG5 is a schematic diagram of a driving scenario provided in an embodiment of the present application;

[0067] FIG6 is a schematic diagram of another driving scenario provided in an embodiment of the present application;

[0068] FIG7 is another schematic flow chart of the control method provided in an embodiment of the present application;

[0069] FIG8 is a schematic block diagram of a control device provided in an embodiment of the present application;

[0070] FIG9 is another schematic block diagram of the control device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0071] The technical solution in this application will be described below with reference to the accompanying drawings.

[0072] As mentioned above, the timing of triggering active safety functions is very close to the moment of collision, resulting in a large deceleration or lateral acceleration value of the designed vehicle when the function is triggered, affecting the driving experience of the driver and passengers, and even causing the function to fail, threatening driving safety.

[0073] Furthermore, active safety features struggle to make informed decisions in complex road conditions. For example, in the scenario shown in Figure 1, the autonomous emergency braking (AEB) function typically triggers emergency braking for the nearest preceding vehicle (such as the other vehicle in the image), typically between 0.8 and 1.6 seconds before collision. This indicates that AEB is triggered relatively close to the moment of collision, making it impossible to avoid a collision in certain scenarios. For example, if the preceding vehicle decelerates suddenly, AEB may not be able to prevent the collision. In these situations, evasive steering assist (ESA) can assist the driver in emergency lateral collision avoidance. However, in the scenario shown in Figure 1, if the vehicle takes the lane change path shown, a collision with the obstacle on the right may be unavoidable. In other words, the AEB and ESA functions can only provide longitudinal and lateral control of the vehicle, respectively. Single lateral or longitudinal control alone cannot prevent a collision in the complex scenario shown in Figure 1.

[0074] In view of this, embodiments of the present application provide a control method, apparatus, and intelligent driving device that, when a collision risk is detected, can plan a path in advance based on the driver's driving intent. Through the combined planning of lateral and longitudinal control, the vehicle can be controlled to avoid obstacles and improve driving safety. Furthermore, the control method provided in embodiments of the present application can control the steering wheel torque in stages during lateral control. This not only alerts the driver to the risk of collision early on through steering wheel torque, but also prevents the steering wheel torque from prematurely intervening in the opposite direction of the potential collision, thereby affecting the driver's driving experience.

[0075] The technical solutions in the embodiments of the present application will be described below with reference to the accompanying drawings.

[0076] Figure 2 is a functional block diagram of the intelligent driving device 100 provided in an embodiment of the present application. The intelligent driving device 100 may include a perception system 120, an interaction system 130, and a computing platform 150, wherein the perception system 120 may include one or more sensors for sensing information about the environment surrounding the intelligent driving device 100. For example, the perception system 120 may include a positioning system, which may be a global positioning system (GPS), a Beidou system or other positioning systems, or an inertial measurement unit (IMU). For another example, the perception system 120 may also include one or more of a laser radar, a millimeter wave radar, an ultrasonic radar, and a camera device.

[0077] The interactive system 130 may include a hand force interaction module, which may include a torque detection device for detecting the torque applied by the driver's hand to the steering wheel. The interactive system 130 may also include a human-machine interface (HMI) for providing users with the ability to adjust the triggering timing of the driver assistance system's collision avoidance function to suit different driver styles. For example, the interactive system 130 may also include a speaker, audio device, or other sound-generating device for broadcasting information to the user.

[0078] Some or all functions of the intelligent driving device 100 can be controlled by the computing platform 150. The computing platform 150 may include one or more processors, such as processors 151 to 15n (n is a positive integer). A processor is a circuit capable of processing instructions. In one implementation, the processor can be a circuit capable of reading and executing instructions, such as a central processing unit (CPU), a microprocessor, a graphics processing unit (GPU) (which can be understood as a microprocessor), or a digital signal processor (DSP). In another implementation, the processor can implement certain functions through the logical relationships of hardware circuits. The logical relationships of the hardware circuits are fixed or reconfigurable. For example, the processor is a hardware circuit implemented by an application-specific integrated circuit (ASIC) or a programmable logic device (PLD), such as a field programmable gate array (FPGA). In a reconfigurable hardware circuit, the process of the processor loading a configuration file to implement the hardware circuit configuration can be understood as the process of the processor loading instructions to implement the functions of some or all of the above units. In addition, it can also be a hardware circuit designed for artificial intelligence, which can be understood as an ASIC, such as a neural network processing unit (NPU), a tensor processing unit (TPU), a deep learning processing unit (DPU), etc. In addition, the computing platform 150 can also include a memory for storing instructions. Some or all of the processors 151 to 15n can call the instructions in the memory and execute the instructions to achieve corresponding functions.

[0079] The intelligent driving device 100 may include an advanced driving assistant system (ADAS). ADAS uses multiple sensors on the intelligent driving device (including but not limited to: lidar, millimeter wave radar, camera device, ultrasonic sensor, global positioning system, inertial measurement unit) to obtain information from the surroundings of the intelligent driving device, and analyzes and processes the obtained information to achieve functions such as obstacle perception, target recognition, intelligent driving device positioning, path planning, user monitoring / reminder, etc., thereby improving the safety, automation and comfort of driving the intelligent driving device.

[0080] From a logical function perspective, ADAS systems generally include three main functional modules: perception module, decision module and execution module. The perception module perceives the surrounding environment of the vehicle body through sensors and inputs corresponding real-time data to the decision-making layer processing center. The perception module mainly includes on-board cameras / ultrasonic radars / millimeter-wave radars / lidars, etc.; the decision module uses computing devices and algorithms to make corresponding decisions based on the information obtained by the perception module; the execution module takes corresponding actions after receiving decision instructions from the decision module, such as driving, changing lanes, steering, braking, warnings, etc.

[0081] In an embodiment of the present application, the computing platform 150 can generate multiple predicted trajectories based on the driver's intention, and then evaluate the current collision risk based on the multiple predicted trajectories and information such as the position and speed of obstacles around the intelligent driving device collected by the perception system 120. When the collision risk is greater than or equal to a preset threshold, the anti-collision function is activated, and the intelligent driving device is laterally and longitudinally controlled based on the above-mentioned multiple predicted trajectories and relevant information of the obstacles. The lateral control can be performed in combination with the hand torque applied to the steering wheel by the user collected by the interactive system 130.

[0082] The intelligent driving devices involved in this application may include road vehicles, water vehicles, air vehicles, industrial equipment, agricultural equipment, or entertainment equipment, etc. For example, the intelligent driving device can be a vehicle, which is a vehicle in a broad sense and can be a transportation tool (such as a commercial vehicle, a passenger car, a motorcycle, a flying car, a train, etc.), an industrial vehicle (such as a forklift, a trailer, a tractor, etc.), an engineering vehicle (such as an excavator, a bulldozer, a crane, etc.), agricultural equipment (such as a lawn mower, a harvester, etc.), amusement equipment, a toy vehicle, etc. The embodiments of this application do not specifically limit the type of vehicle.

[0083] FIG2 is a schematic diagram of the system architecture required to implement the control method provided in an embodiment of the present application. As shown in FIG2 , the system includes a perception module 210, an activation decision module 220, a horizontal and vertical planning module 230, and an interaction module 240. The perception module 210 may include one or more sensors in the perception system 120 shown in FIG1 , the activation decision module 220 and the horizontal and vertical planning module 230 may each include one or more processors in the computing platform 150 shown in FIG1 , and the interaction module 240 may include one or more modules in the interaction system 130 shown in FIG1 .

[0084] The perception module 210 is used to collect real-time operating parameters of the intelligent driving device (such as driving speed, power information, and steering wheel angle), as well as the location and speed of obstacles around the intelligent driving device. The perception module 210 transmits the relevant information it perceives to the activation decision module 220 and the lateral and longitudinal planning module 230.

[0085] The activation decision module 220 generates multiple predicted trajectories based on the real-time operating parameters of the intelligent driving device and the driver's reaction time. Furthermore, the activation decision module 220 assesses the collision risk of the intelligent driving device based on the multiple predicted trajectories and the location and speed information of obstacles surrounding the intelligent driving device. When the collision risk is greater than or equal to a preset threshold, the activation decision module 220 activates the lateral and longitudinal planning module 230 to control the lateral and longitudinal directions of the intelligent driving device to avoid a collision. The lateral and longitudinal planning module 230 includes a path planning module 231, a speed planning module 232, and a trajectory selection module 233. The path planning module 231 generates multiple lateral paths based on state space sampling. The speed planning module 232 plans the longitudinal speed of the lateral paths based on information such as the speed and acceleration of the intelligent driving device to generate multiple planned trajectories. The trajectory selection module 233 determines a planned trajectory from the multiple trajectories output by the speed planning module 232 and inputs it to the interaction module 240. For example, the planned trajectory determined by the trajectory selection module 233 may be the trajectory that best matches the driver's intent.

[0086] The interaction module 240 includes a longitudinal control module 241, a torque calculation module 242, and a torque interaction module 243. The longitudinal control module 241 determines the planned speed of the intelligent driving device based on the planned trajectory. The torque calculation module 242 determines the preliminary planned steering wheel torque based on the planned trajectory and inputs the preliminary planned torque to the torque interaction module 243. Furthermore, the torque interaction module 243 determines the final planned torque based on the force applied to the steering wheel by the user and the collision risk. When the intelligent driving device executes these planned speeds and final planned torques, it can travel along the planned trajectory.

[0087] It should be understood that the above modules are only examples, and in actual applications, the above modules may be added or deleted according to actual needs. For example, in the system architecture shown in Figure 3, the path planning module 231 and the speed planning module 232 can be combined into one module.

[0088] FIG4 shows a schematic flow chart of a control method provided by an embodiment of the present application. This method can be applied to the intelligent driving device shown in FIG2 , or the method can be executed by the system shown in FIG3 . For example, the following description uses the intelligent driving device as a vehicle and the method as executed by the vehicle's computing platform as an example. The method 400 may include:

[0089] S401, when at least one obstacle is detected within a preset range of the vehicle, a plurality of predicted trajectory lines are generated according to control information input by the driver and a control parameter reachable set.

[0090] The control parameter reachable set is the set of motion parameters that the vehicle can achieve under user control, for example, the longitudinal acceleration and lateral offset that the vehicle can achieve under user control.

[0091] For example, the preset range may be a range of 100 meters from the outer contour of the vehicle, or a range that may affect the driving safety of the vehicle, or other ranges.

[0092] For example, the at least one obstacle may be stationary or movable, and may include, but is not limited to, motor vehicles, non-motor vehicles, general obstacles, and pedestrians. General obstacles may include roadblocks such as cones and warning triangles, temporary road signs, and other obstacles such as guardrails, walls, and stone piers.

[0093] It should be noted that the at least one obstacle may include an obstacle in front of the vehicle, and may also include obstacles located behind and to the side of the vehicle within a preset range.

[0094] For example, the control information may include, but is not limited to, information on the opening degree of the vehicle's accelerator pedal, information on the opening degree of the vehicle's decelerator pedal, and steering wheel torque, wherein the opening degree information includes the opening degree size and the opening degree change rate.

[0095] In some possible implementations, to generate multiple predicted trajectory lines, lateral path deduction and longitudinal trajectory deduction may be performed separately. Furthermore, multiple predicted trajectory lines with time information are generated based on the lateral path and longitudinal trajectory.

[0096] For example, the lateral path of the vehicle can be deduced by the following formula:

[0097] Among them, s e is the longitudinal position of the vehicle, l(s e ) is the vehicle longitudinal position s e The corresponding lateral offset. The first distance is calculated based on the driver's reaction time and the vehicle's current speed. The vehicle's longitudinal starting position can be understood as the vehicle's current position in a direction parallel to the vehicle's longitudinal symmetry plane. For example, It can be the length of the TTR interval as shown in Figure 5, that is, the distance from the head of the vehicle to point a; to It can be the reachable interval as shown in Figure 5. cur is the lateral offset of the vehicle at the current moment, lateralOffset re is the lateral offset corresponding to the end of the cubic curve connection, which can be determined based on the torque applied by the driver to the steering wheel and / or the lateral acceleration that the vehicle can achieve under user control; The vertical position where the cubic curve ends can be preset by the system. In practice, it can be dynamically adjusted according to the vehicle model and the degree of aggressiveness of the driver. For example, if the vehicle model is a large vehicle or the driver drives more aggressively, The value of is larger. arrive Use cubic curves to connect the paths, and the cubic curves are The tangent direction at is parallel to the driving direction of the vehicle, where a, b, c, and d are coefficients of a cubic polynomial, and their specific values ​​can be determined according to the control information input by the driver. This application does not limit their specific values.

[0098] For example, the driver reaction time may be preset by the system, or may be set by the user of the vehicle. For example, the driver reaction time may be any value between 0.4 seconds and 1.0 seconds.

[0099] Furthermore, the longitudinal trajectory of the vehicle is determined based on the accelerator pedal opening information, the decelerator pedal opening information, and the longitudinal acceleration that the vehicle can achieve in response to the driver's control in the current operating state.

[0100] It is understood that the longitudinal trajectory includes the longitudinal position (s e ) changes with the time of deduction.

[0101] It should be noted that the lateral acceleration that the vehicle can achieve under user control can be defined as a lateral acceleration range, and the longitudinal acceleration that the vehicle can achieve in response to driver control in its current operating state can be defined as a longitudinal acceleration range. Therefore, the predicted lateral path and longitudinal trajectory can each contain multiple sets of data. In practice, the user can adjust the number of predicted trajectory lines by adjusting the step size of the lateral and longitudinal acceleration ranges.

[0102] S402 : Evaluate collision risk 1 based on multiple predicted trajectory lines and information such as the position and speed of at least one obstacle.

[0103] For example, the collision risk 1 can be determined by the following formula (2): S co =∑ i s i *cost i , (2)

[0104] Among them, S co is the collision risk 1, cost i is the collision risk of trajectory i among multiple predicted trajectories, s i is the weight of the collision risk of trajectory i. Where i is a positive integer, s i It can be a value between 0 and 1, s i The specific value of can be determined according to the lateral offset of the predicted trajectory relative to the current location of the vehicle. The larger the lateral offset, the smaller the weight.

[0105] Among them, cost i Determine according to the following formula (3):

[0106] in, Indicates whether the vehicle will collide with an obstacle when traveling along trajectory line i. If a collision occurs, Take 1, no collision occurs, Take 0. Indicates the degree of consistency between trajectory line i and the driver's driving intention, It can be a value between 0 and 1. The more the trajectory line i matches the driver's driving intention, The smaller. It represents the comfort of the driver in the vehicle when the vehicle is traveling along the trajectory line i, which can be determined by formula (4). w1, w2, and w3 are respectively The weights w1, w2, and w3 take values ​​between 0 and 1, and the sum of w1, w2, and w3 is equal to 1.

[0107] Wherein, jerk represents the acceleration change rate of the vehicle, jerkThresMin represents the lower threshold value of the acceleration change rate of the vehicle; jerkThresMax represents the upper threshold value of the acceleration change rate of the vehicle. For example, when jerk is less than jerkThresMin, cost ve Take 0; when jerk is greater than jerkThresMax, cost ve Take 1.

[0108] It can be understood that the maximum cost of each trajectory line is 1 and the minimum cost is 0.

[0109] S403 : When the collision risk 1 is greater than or equal to the trigger threshold, a horizontal reference line is generated based on the sampling of the state space, and a plurality of planned trajectories are generated according to the obstacle boundary formed by at least one obstacle.

[0110] Exemplarily, the trigger threshold may be 1, or the trigger threshold may be other values.

[0111] For example, multiple trajectories may be generated according to the method of S401 , and then, based on the obstacle boundary, trajectories that exceed the obstacle boundary are removed from the multiple trajectories to obtain multiple planned trajectories.

[0112] S404: determining an obstacle avoidance trajectory from a plurality of planned trajectories according to the control information input by the driver.

[0113] For example, a motion trajectory may be generated based on the control information input by the driver and the current operating parameters of the vehicle, wherein the current operating parameters of the vehicle may include vehicle speed, vehicle attitude angle, etc.

[0114] Furthermore, a matching degree between the motion trajectory and each of the multiple planned trajectories is determined, and a planned trajectory with the highest matching degree among the multiple planned trajectories is determined as the obstacle avoidance trajectory.

[0115] S405: Determine collision risk 2 according to the obstacle avoidance trajectory.

[0116] For example, the collision risk 2 may indicate at least one of the following: a risk of the vehicle colliding with a side obstacle, and a risk of the vehicle colliding with a front obstacle.

[0117] In some possible implementations, when a vehicle is traveling along an obstacle avoidance trajectory and may collide with an obstacle ahead, the risk of the vehicle colliding with the obstacle ahead can be determined based on the longitudinal distance between the vehicle and the obstacle ahead and the vehicle's current speed; alternatively, the risk of the vehicle colliding with the obstacle ahead can be determined based on TTC.

[0118] In some possible implementations, when a vehicle is traveling along an obstacle avoidance trajectory and may collide with a side obstacle, the risk of the vehicle colliding with the side obstacle can be determined based on the lateral distance between the vehicle and the side obstacle and the lateral speed of the vehicle; or, the risk of the vehicle colliding with the side obstacle can be determined based on the TTC; or, the risk of the vehicle colliding with the side obstacle can be determined based on the position, speed and obstacle avoidance trajectory of the side obstacle.

[0119] In some possible implementations, the collision risk 2 may be determined based on the obstacle avoidance trajectory and the positions and speeds of multiple obstacles present while the vehicle is traveling along the obstacle avoidance trajectory. For example, the collision risk 2 may be determined using the above formula (3).

[0120] For example, the collision risk may be divided into levels, for example, into at least two levels, so that the vehicle performs lateral control and / or longitudinal control according to different levels of the collision risk.

[0121] The following example illustrates the classification of collision risk levels using the longitudinal distance between the vehicle and the nearest obstacle and the vehicle's current speed. For example, the remaining distance L is determined based on the longitudinal distance l between the vehicle and the nearest obstacle and the vehicle's current speed v. Different remaining distances correspond to different levels of collision risk. The corresponding relationship between remaining distance and collision risk level is shown in Table 1. Here, L = lv * T, where T is the driver's reaction time.

[0122] Table 1

[0123] The following uses the example of determining the collision risk between a vehicle and a side obstacle based on TTC to illustrate the classification of collision risk levels. For example, TTC is determined based on the lateral component of the vehicle's current velocity v, the lateral distance between the side obstacle and the vehicle, and the speed of the side obstacle. Different TTCs correspond to different levels of collision risk. The corresponding relationship between TTC and collision risk level is shown in Table 2.

[0124] Table 2

[0125] S406 : Determine a target torque based on the collision risk and the hand torque applied by the driver to the steering wheel, and control the steering wheel based on the target torque.

[0126] It is understood that the hand torque applied by the driver to the steering wheel causes the vehicle to deflect in the first direction, thereby creating a risk of collision between the vehicle and at least one obstacle in the first direction. Otherwise, steps S403 through S405 would not be triggered. Therefore, to reduce the risk of collision between the vehicle and at least one obstacle, it is necessary to control the vehicle to have a tendency to travel in the opposite direction of the first direction. In other words, the direction of the target torque is opposite to the direction of the torque generated by the hand torque applied by the driver to the steering wheel. The first direction can be the left side of the vehicle or the right side of the vehicle.

[0127] For example, the target torque can be determined based on the relationship between collision risk 2 and a preset threshold, as well as the hand torque applied by the driver to the steering wheel. Alternatively, the target torque can be determined based on the level of collision risk between the vehicle and obstacle 1, as well as the hand torque applied by the driver to the steering wheel. Obstacle 1 can be the obstacle with the highest probability of colliding with the vehicle among the at least one obstacle in the first direction.

[0128] For example, when the collision risk level is less than or equal to a preset threshold level 1, the electric power steering (EPS) assistance characteristic curve is queried based on the driver's hand torque applied to the steering wheel and the current vehicle speed. A preliminary counteracting torque is determined based on the EPS assistance characteristic curve. This counteracting torque is then slope-limited and filtered to obtain a target torque. Slope limiting refers to limiting the rate of change of torque output based on the torque change slope control. The torque resulting from the driver's hand torque applied to the steering wheel is greater than or equal to a preset threshold 1 and less than or equal to a preset threshold 2. This ensures that the driver can feel resistance while continuing to turn the steering wheel in the first direction, thereby alerting the driver to the collision risk and providing them with sufficient time to maneuver the vehicle to avoid a collision. For example, preset threshold 1 can be -0.5 N·m, and preset threshold 2 can be 0 N·m. Alternatively, preset thresholds 1 and 2 can be other values.

[0129] For example, when the collision risk level is greater than a preset level threshold of 1, the EPS assist characteristic curve is queried based on the torque applied by the driver to the steering wheel and the current vehicle speed to determine a preliminary target torque. The value of this preliminary target torque may be the same as the value of the torque generated by the driver's hand torque applied to the steering wheel. Furthermore, an additional torque is determined based on the vehicle's speed and the lateral and longitudinal distances between the vehicle and the obstacle. This additional torque is used to correct the vehicle's lateral position to prevent the vehicle from colliding with the obstacle. The sum of this additional torque and the preliminary target torque is the target torque. If the value of this target torque minus the torque generated by the driver's hand torque applied to the steering wheel is greater than a preset threshold of 2, the vehicle is controlled to steer in a direction opposite to the first direction to avoid collision with the obstacle in the first direction.

[0130] Exemplarily, the preset level threshold 1 may be level one or level two.

[0131] In some possible implementations, when the collision risk level is less than or equal to a preset level threshold of 1, in addition to controlling the steering wheel through target torque to alert the driver of the collision risk, the driver may also be alerted through an HMI, speaker, etc. For example, the speaker may announce "Beware of obstacles in the first direction" as a reminder.

[0132] S407: Determine a longitudinal acceleration based on the collision risk and driving comfort or longitudinal distance, and control vehicle deceleration based on the longitudinal acceleration.

[0133] For example, the longitudinal acceleration can be determined based on the relationship between collision risk 2 and a preset threshold, as well as driving comfort or the longitudinal distance between the vehicle and the nearest obstacle ahead. Alternatively, the longitudinal acceleration can be determined based on the level of collision risk between the vehicle and the nearest obstacle ahead, as well as driving comfort or the longitudinal distance between the vehicle and the nearest obstacle ahead.

[0134] For example, when the collision risk level is less than or equal to a preset level threshold of 2, the longitudinal acceleration of 1 is determined based on driving comfort, allowing the vehicle to slowly decelerate before entering a state with a higher collision risk, thereby improving driving safety and passenger comfort. For different collision risk levels, different longitudinal accelerations can also be used to control vehicle deceleration while ensuring driving comfort. For example, when the collision risk level is less than or equal to a preset level threshold of 2, a lower longitudinal acceleration is used to control vehicle deceleration when the collision risk level is low, and a higher longitudinal acceleration is used to control vehicle deceleration when the collision risk level is high.

[0135] For example, when the level of the collision risk is greater than or equal to a preset level threshold 2, the longitudinal acceleration 2 is determined according to the longitudinal distance between the vehicle and the nearest obstacle in front and the speed of the vehicle.

[0136] For example, the absolute value of the longitudinal acceleration 1 may be less than or equal to 4 m / s 2 , the absolute value of the longitudinal acceleration 2 can be greater than 4m / s 2 .

[0137] Exemplarily, the preset level threshold 2 may be level one or level two.

[0138] In a specific implementation, not all operations in FIG4 need to be executed. For example, S406 or S407 may be executed. For example, when there is no risk of a lateral collision, only S407 may be executed, and when there is no risk of a longitudinal collision, only S406 may be executed. In addition, the operations shown in FIG4 may not be executed in the order shown in the figure. For example, S406 and S407 may be executed simultaneously, or S407 may be executed before S406.

[0139] FIG6 shows an application scenario of an embodiment of the present application. As shown in FIG6 (a), when a vehicle 601 is in human driving mode and driving in lane 2, the driver applies torque to the steering wheel, causing the vehicle 601 to drive to the right compared to the center line of the lane line. In this case, the vehicle 601 may collide with an obstacle 603. The steering wheel of the vehicle 601 can be controlled according to the above method 400 to avoid the collision. As shown in FIG6 (b), when the vehicle 601 is in human driving mode and driving in lane 2, the front vehicle 604 suddenly decelerates, causing the vehicle 601 and the front vehicle 604 to have a collision risk. When the vehicle 601 decelerates at the maximum deceleration and cannot avoid the collision, the target torque can be determined based on the torque applied by the driver to the steering wheel to cause the vehicle 601 to drive to the right to avoid the vehicle 601 from colliding with the front vehicle 604. In the process of determining the target torque, the speed and position of the obstacle 605 are taken into consideration to avoid the vehicle 601 from colliding with the obstacle 605 during the obstacle avoidance process. As shown in (c) of Figure 6, when vehicle 601 is in human driving mode and traveling in lane 2, the driver applies torque to the steering wheel, causing vehicle 601 to travel to the right of the center line of the lane. At this time, vehicle 601 may collide with vehicle 607 to its right rear. The collision risk level can be determined based on the position and speed of vehicle 601 and the position and speed of vehicle 607. The target torque can be determined based on the collision risk level and the torque applied to the steering wheel by the driver, and then the steering wheel of vehicle 601 can be controlled based on the target torque to avoid a collision. Alternatively, when the vehicle 601 is in the posture as shown in (c) in Figure 6, the driver applies torque to the steering wheel to cause the vehicle 601 to deviate from the current posture to the left relative to the center line of the lane line. At this time, the vehicle 601 may collide with the preceding vehicle 606. The collision risk level can be determined based on the position and speed of the vehicle 601 and the position and speed of the vehicle 606. The target torque is determined based on the collision risk level and the torque applied to the steering wheel by the driver, and the steering wheel of the vehicle 601 is controlled based on the target torque. At the same time, the longitudinal acceleration can be determined based on the collision risk level, and the vehicle 601 can be controlled to decelerate based on the longitudinal acceleration to avoid a collision.

[0140] FIG7 shows a control method provided by an embodiment of the present application, which can be applied to the intelligent driving device shown in FIG2 , or can be executed by the system shown in FIG3 . The method includes:

[0141] S701: When there is a risk of collision between the intelligent driving device and a first obstacle, determine a second torque based on at least a first torque of the steering wheel, wherein the first torque is a torque applied to the steering wheel by a user of the intelligent driving device, a direction of the second torque is opposite to a direction of the first torque, and a value of the second torque minus a value of the first torque is greater than or equal to a first preset threshold.

[0142] Exemplarily, the intelligent driving device may be the intelligent driving device 100 , for example, and may include the above-mentioned vehicle.

[0143] For example, the first obstacle may include the nearest obstacle in front of the intelligent driving device; or it may include an obstacle on a first side of the intelligent driving device, such as the aforementioned obstacle 1. The first side is the side toward which the intelligent driving device is biased by the first torque, such as the right side of vehicle 601 shown in FIG6(a).

[0144] For example, the method for determining whether there is a collision risk between the intelligent driving device and the first obstacle can refer to the description in S401 and S402, which will not be repeated here.

[0145] Optionally, determining the second torque based on at least the first steering wheel torque includes determining the second torque based on a relationship between a first collision risk between the intelligent driving device and the first obstacle and a first threshold. For example, the second torque value is determined based on the value of the first torque; wherein, when the first collision risk between the intelligent driving device and the first obstacle is less than or equal to the first threshold, the value of the second torque minus the value of the first torque is greater than or equal to a first preset threshold and less than a second preset threshold; or, when the first collision risk is greater than the first threshold, the value of the second torque minus the value of the first torque is greater than or equal to the second preset threshold.

[0146] For example, the first collision risk may include the above-mentioned collision risk 2, or the first collision risk may include the collision risk between the intelligent driving device and a lateral obstacle. The method for determining the first collision risk may refer to the description in S405 and will not be repeated here.

[0147] S702: Control the steering wheel according to the first torque and the second torque.

[0148] Optionally, the method also includes: when the second collision risk between the intelligent driving device and the first obstacle is less than or equal to a second threshold, determining a first longitudinal acceleration based on driving comfort, and controlling the intelligent driving device to decelerate based on the first longitudinal acceleration; or, when the second collision risk is greater than the second threshold, determining a second longitudinal acceleration based at least on the distance between the intelligent driving device and the first obstacle, and controlling the intelligent driving device to decelerate based on the second longitudinal acceleration; wherein the absolute value of the second longitudinal acceleration is greater than the absolute value of the first longitudinal acceleration.

[0149] For example, the second collision risk may include the above-mentioned collision risk 2, or the second collision risk may include the collision risk between the intelligent driving device and the nearest obstacle in front. The method for determining the second collision risk may refer to the description in S405 and will not be repeated here.

[0150] For example, the first collision risk and the second collision risk are determined based on the first motion trajectory, which may include the obstacle avoidance trajectory in the above embodiment. The specific method for determining the first motion trajectory can be referred to the description in the above embodiment and will not be repeated here.

[0151] The control method provided in the embodiments of the present application can apply an opposite force to the steering wheel based on the torque applied by the driver to the steering wheel when the intelligent driving device is in human driving mode and detects a collision risk, thereby alerting the driver to the risk of a collision. Furthermore, controlling the steering wheel in conjunction with the driver's action intention can make the behavior of the intelligent driving device more human-like during obstacle avoidance and avoid applying excessive torque when the function is triggered, resulting in large lateral acceleration, thereby improving the driving experience of the driver and passengers. Furthermore, through combined lateral and longitudinal control, in more complex driving scenarios, it helps reduce the probability of collisions and improve driving safety.

[0152] The method provided in the embodiments of the present application is described in detail above with reference to Figures 1 to 7 . The apparatus provided in the embodiments of the present application will be described in detail below with reference to Figures 8 and 9 . It should be understood that the description of the apparatus embodiment corresponds to the description of the method embodiment. Therefore, for matters not described in detail, reference can be made to the method embodiment above, and for the sake of brevity, no further description will be given here.

[0153] FIG8 shows a schematic block diagram of a control device 2000 provided in an embodiment of the present application. The device 2000 includes a first determining unit 2010 and a processing unit 2020 .

[0154] The apparatus 2000 may include units for executing the method in Figure 4 or Figure 7. Furthermore, each unit in the apparatus 2000 is for implementing a corresponding process of the method embodiment in Figure 4 or Figure 7.

[0155] Exemplarily, when the device 2000 is used to execute method 700, the first determination unit 2010 is used to determine the second torque based on at least the first torque of the steering wheel when there is a risk of collision between the intelligent driving device and the first obstacle; wherein the first torque is the torque applied to the steering wheel by a user of the intelligent driving device, the direction of the second torque is opposite to the direction of the first torque, and the value of the second torque minus the value of the first torque is greater than or equal to a first set threshold; and the processing unit 2020 is used to control the steering wheel based on the first torque and the second torque.

[0156] Optionally, the first determination unit 2010 is used to: determine the value of the second torque based on the first collision risk between the intelligent driving device and the first obstacle and the value of the first torque; wherein, when the first collision risk is less than or equal to the first threshold, the value of the second torque minus the value of the first torque is greater than or equal to the first preset threshold and less than the second preset threshold; or, when the first collision risk is greater than the first threshold, the value of the second torque minus the value of the first torque is greater than or equal to the second preset threshold.

[0157] Optionally, the first determination unit 2010 is further used to: when the second collision risk between the intelligent driving device and the first obstacle is less than or equal to a second threshold, determine the first longitudinal acceleration based on the driving comfort, and control the intelligent driving device to decelerate based on the first longitudinal acceleration; or, when the second collision risk is greater than the second threshold, determine the second longitudinal acceleration based on at least the distance between the intelligent driving device and the first obstacle, and control the intelligent driving device to decelerate based on the second longitudinal acceleration; wherein the absolute value of the second longitudinal acceleration is greater than the absolute value of the first longitudinal acceleration.

[0158] Optionally, the device 2000 also includes a second determination unit, which is used to: when the third collision risk between the intelligent driving device and the first obstacle is greater than or equal to a third threshold, determine the first motion trajectory based on control information input by a user of the intelligent driving device and the obstacle boundary, the control information including at least one of the following: opening information of an accelerator pedal of the intelligent driving device, opening information of a decelerator pedal of the intelligent driving device, and a first torque, and the obstacle boundary is determined by multiple obstacles including the first obstacle; the first determination unit 2010 is used to: determine the second torque based on the first motion trajectory and the first torque, so that when the steering wheel is controlled according to the second torque, the intelligent driving device travels along the first motion trajectory.

[0159] For example, the third collision risk may include the collision risk 1 described above.

[0160] Optionally, the device also includes a third determination unit, which is used to: determine multiple motion trajectories based on the driver's reaction time and the control parameter reachable set, where the control parameter reachable set is a set of motion parameters that can be achieved by the intelligent driving device under user control; determine the third collision risk based on the multiple motion trajectories and the position and speed of the first obstacle.

[0161] Exemplarily, the multiple motion trajectories may include the multiple predicted trajectory lines. The method for determining the multiple motion trajectories may refer to the description in S401 above, which will not be repeated here.

[0162] Optionally, the first obstacle includes at least one of the following: a motor vehicle, a non-motor vehicle, a general obstacle, and a pedestrian.

[0163] For example, the first determination unit 2010 and the processing unit 2020 may be provided in an intelligent driving device. More specifically, the first determination unit 2010 and the processing unit 2020 may be provided in the interaction module 240 shown in FIG3 . For example, the second determination unit may be provided in the lateral and longitudinal planning module 230 shown in FIG3 , and the third determination unit may be provided in the activation decision module 220 shown in FIG3 .

[0164] For example, the operations performed by the first determination unit 2010 and the processing unit 2020 may be performed by a single processor, or by different processors. In a specific implementation, the one or more processors may be the processors provided in the intelligent driving device 100 shown in FIG. 2 ; or the apparatus 2000 may be a chip provided in the intelligent driving device 100.

[0165] In a specific implementation process, all or part of the units in the above apparatus may be integrated together, or may be implemented independently. In one implementation, these units are integrated together and implemented in the form of a system-on-a-chip (SoC).

[0166] Figure 9 is a schematic block diagram of a control device provided in an embodiment of the present application. The device 2100 shown in Figure 9 may include: a processor 2110, a transceiver 2120, and a memory 2130. The processor 2110, the transceiver 2120, and the memory 2130 are connected via an internal connection path. The memory 2130 is used to store instructions, and the processor 2110 is used to execute the instructions stored in the memory 2130 to implement the methods in the above embodiments. Optionally, the memory 2130 can be coupled to the processor 2110 via an interface or integrated with the processor 2110.

[0167] It should be noted that the transceiver 2120 may include but is not limited to a transceiver device such as an input / output interface to implement communication between the device 2100 and other devices or a communication network.

[0168] The memory 2130 may be a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM).

[0169] The transceiver 2120 uses a transceiver device such as but not limited to a transceiver to implement communication between the device 2100 and other devices or communication networks to receive / send data / information used to implement the methods in the above embodiments.

[0170] During the specific implementation process, the device 2100 can be set in the computing platform 150 of the intelligent driving device 100 shown in Figure 2.

[0171] An embodiment of the present application further provides an intelligent driving device, which includes the above-mentioned device 2000 or the above-mentioned device 2100.

[0172] In some possible implementations, the intelligent driving device may be a vehicle.

[0173] An embodiment of the present application further provides a computer program product, which includes computer program code. When the computer program code runs on a computer, the computer implements the methods in the above embodiments of the present application.

[0174] An embodiment of the present application further provides a computer-readable storage medium, which stores computer instructions. When the computer instructions are executed on a computer, the computer implements the methods in the above embodiments of the present application.

[0175] An embodiment of the present application also provides a chip, including a circuit, for executing the methods in the above embodiments of the present application.

[0176] During implementation, each step of the above method can be completed by an integrated logic circuit of the hardware in the processor or by instructions in the form of software. The method disclosed in conjunction with the embodiments of the present application can be directly embodied as being executed by a hardware processor, or can be executed by a combination of hardware and software modules in the processor. The software module can be located in a storage medium mature in the art such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, or a power-on erasable programmable memory, a register, etc. The storage medium is located in the memory, and the processor reads the information in the memory and completes the steps of the above method in combination with its hardware. To avoid repetition, it will not be described in detail here.

[0177] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0178] In the description of the embodiments of the present application, unless otherwise specified, " / " means or, for example, A / B can mean A or B; "and / or" in this article is a kind of association relationship that describes associated objects, indicating that there can be three relationships, for example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. In this application, "at least one" refers to one or more, and "more than one" refers to two or more. "At least one of the following items" or similar expressions refers to any combination of these items, including any combination of single items or plural items. For example, at least one of a, b, or c can mean: a, b, c, ab, ac, bc, or abc, where a, b, c can be single or multiple.

[0179] In the embodiments of this application, prefixes such as "first" and "second" are used only to distinguish different description objects and have no limiting effect on the position, order, priority, quantity, or content of the described objects. The use of prefixes such as ordinal numbers in the embodiments of this application to distinguish description objects does not constitute a limitation on the described objects. For a statement of the described objects, please refer to the description in the context of the claims or embodiments, and the use of such prefixes should not constitute an unnecessary limitation.

[0180] In the several embodiments provided in this application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of the units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0181] In the various embodiments of the present application, unless otherwise specified or there is a logical conflict, the terms and / or descriptions between the various embodiments are consistent and can be referenced by each other. The technical features in different embodiments can be combined to form new embodiments according to their inherent logical relationships.

[0182] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0183] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0184] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

Claims

1. A control method, characterized in that: include: When there is a risk of collision between the intelligent driving device and the first obstacle, determining the second torque at least according to the first torque of the steering wheel; The first torque is a torque applied to the steering wheel by a user of the intelligent driving device, the direction of the second torque is opposite to the direction of the first torque, and the value of the second torque minus the value of the first torque is greater than or equal to a first preset threshold; The steering wheel is controlled according to the first torque and the second torque.

2. The method according to claim 1, characterized in that The determining the second torque at least according to the first torque of the steering wheel comprises: determining a value of the second torque according to a first collision risk between the intelligent driving device and the first obstacle and a value of the first torque; Wherein, when the first collision risk is less than or equal to a first threshold, the value of the second torque minus the value of the first torque is greater than or equal to the first preset threshold and less than a second preset threshold; or, When the first collision risk is greater than the first threshold, the value of the second torque minus the value of the first torque is greater than or equal to the second preset threshold.

3. The method according to claim 1 or 2, characterized in that: The method further comprises: When the second collision risk between the intelligent driving device and the first obstacle is less than or equal to a second threshold, determining a first longitudinal acceleration according to driving comfort, and controlling the intelligent driving device to decelerate according to the first longitudinal acceleration; or When the second collision risk is greater than the second threshold, determining a second longitudinal acceleration at least according to the distance between the intelligent driving device and the first obstacle, and controlling the intelligent driving device to decelerate according to the second longitudinal acceleration; The absolute value of the second longitudinal acceleration is greater than the absolute value of the first longitudinal acceleration.

4. The method according to any one of claims 1 to 3, characterized in that The method further comprises: When a third collision risk between the intelligent driving device and the first obstacle is greater than or equal to a third threshold, determining a first motion trajectory according to control information input by a user of the intelligent driving device and an obstacle boundary, the control information comprising at least one of the following: opening information of an accelerator pedal of the intelligent driving device, opening information of a decelerator pedal of the intelligent driving device, and the first torque, and the obstacle boundary is determined by a plurality of obstacles including the first obstacle; The determining the second torque at least according to the first torque of the steering wheel comprises: The second torque is determined according to the first motion trajectory and the first torque, so that when the steering wheel is controlled according to the second torque, the intelligent driving device travels according to the first motion trajectory.

5. The method according to claim 4, characterized in that The method further comprises: Determining a plurality of motion trajectories according to the driver reaction time and a control parameter reachable set, wherein the control parameter reachable set is a set of motion parameters that can be achieved by the intelligent driving device under the control of the user; The third collision risk is determined according to the multiple motion trajectories and the position and speed of the first obstacle.

6. The method according to any one of claims 1 to 5, characterized in that The first obstacle includes at least one of the following: a motor vehicle, a non-motor vehicle, a general obstacle, and a pedestrian.

7. A control device, characterized in that: include: a first determining unit, configured to determine a second torque at least according to a first torque of a steering wheel when there is a risk of collision between the intelligent driving device and the first obstacle; The first torque is a torque applied to the steering wheel by a user of the intelligent driving device, the direction of the second torque is opposite to the direction of the first torque, and the value of the second torque minus the value of the first torque is greater than or equal to a first set threshold; A processing unit is used to control the steering wheel according to the first torque and the second torque.

8. The device according to claim 7, characterized in that The first determining unit is used for: determining a value of the second torque according to a first collision risk between the intelligent driving device and the first obstacle and a value of the first torque; Wherein, when the first collision risk is less than or equal to a first threshold, the value of the second torque minus the value of the first torque is greater than or equal to the first preset threshold and less than a second preset threshold; or, When the first collision risk is greater than the first threshold, the value of the second torque minus the value of the first torque is greater than or equal to the second preset threshold.

9. The device according to claim 7 or 8, characterized in that The first determining unit is further configured to: When the second collision risk between the intelligent driving device and the first obstacle is less than or equal to a second threshold, determining a first longitudinal acceleration according to driving comfort, and controlling the intelligent driving device to decelerate according to the first longitudinal acceleration; or When the second collision risk is greater than the second threshold, determining a second longitudinal acceleration at least according to the distance between the intelligent driving device and the first obstacle, and controlling the intelligent driving device to decelerate according to the second longitudinal acceleration; The absolute value of the second longitudinal acceleration is greater than the absolute value of the first longitudinal acceleration.

10. The device according to any one of claims 7 to 9, characterized in that The device further includes a second determining unit, wherein the second determining unit is configured to: When a third collision risk between the intelligent driving device and the first obstacle is greater than or equal to a third threshold, determining a first motion trajectory according to control information input by a user of the intelligent driving device and an obstacle boundary, the control information comprising at least one of the following: opening information of an accelerator pedal of the intelligent driving device, opening information of a decelerator pedal of the intelligent driving device, and the first torque, and the obstacle boundary is determined by a plurality of obstacles including the first obstacle; The first determining unit is used for: The second torque is determined according to the first motion trajectory and the first torque, so that when the steering wheel is controlled according to the second torque, the intelligent driving device travels according to the first motion trajectory.

11. The device according to claim 10, characterized in that The device further includes a third determining unit, wherein the third determining unit is configured to: Determining a plurality of motion trajectories according to the driver reaction time and a control parameter reachable set, wherein the control parameter reachable set is a set of motion parameters that can be achieved by the intelligent driving device under the control of the user; The third collision risk is determined according to the multiple motion trajectories and the position and speed of the first obstacle.

12. The device according to any one of claims 7 to 11, characterized in that The first obstacle includes at least one of the following: a motor vehicle, a non-motor vehicle, a general obstacle, and a pedestrian.

13. A control device, characterized in that: include: Memory for storing computer programs; A processor, configured to execute the computer program stored in the memory, so that the apparatus performs the method according to any one of claims 1 to 6.

14. An intelligent driving device, characterized in that: Comprising a device as claimed in any one of claims 7 to 13.

15. A computer-readable storage medium, characterized in that: Instructions are stored thereon, and when the instructions are executed by a processor, the processor implements the method according to any one of claims 1 to 6.

16. A chip, characterized in that: The chip comprises a circuit for executing the method according to any one of claims 1 to 6.

Images