Steering assistance control method and device, and intelligent driving device

The steering assist control method and device improve vehicle stability and safety by determining desired steering angles and torques based on control phases and road conditions, addressing the limitations of existing ADAS systems in emergency obstacle avoidance.

KR1020260163501APending Publication Date: 2026-11-16YINWANG INTELLIGENT TECHNOLOGIES CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
KR1020267034636
Authority / Receiving Office
KR · KR
Patent Type
Applications
Current Assignee / Owner
Priority Date
2024-03-19
Filing Date
2025-01-14
Publication Date
2026-11-16

AI Technical Summary

Technical Problem

Existing ADAS systems face challenges in handling emergency obstacle avoidance, particularly in situations where the vehicle's braking distance is insufficient, and the braking system is not designed to handle emergency obstacle avoidance effectively, leading to potential vehicle instability and safety issues.

Method used

A steering assist control method and device that determines desired steering angles and torques based on control phases, road surface adhesion, and vehicle stability, adjusting steering torques to prevent instability and ensure safe obstacle avoidance.

Benefits of technology

Enhances vehicle stability and safety by dynamically adjusting steering torques based on control phases and road conditions, reducing the likelihood of vehicle instability during emergency obstacle avoidance.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure PCT00096_ABST
    Figure PCT00096_ABST
Patent Text Reader

Abstract

A steering assist control method is disclosed, comprising the steps of: acquiring control phase information, wherein the control phase information indicates that the control phase experienced by the vehicle is one of a steering phase, a return-to-center phase, and a lane keeping phase; determining a desired steering angle based on the control phase information, wherein the desired steering angle is a steering wheel angle or a road wheel angle required to control the steering of the vehicle; determining a desired torque based on the desired steering angle; and controlling the vehicle to apply the desired torque. The method is applicable to the field of intelligent vehicles such as electric vehicles and new energy vehicles. During steering-based obstacle avoidance of the vehicle, planned trajectory tracking serves as a primary control objective in the steering phase, so that the vehicle drives based on the planned trajectory to avoid obstacles in advance; and vehicle stability serves as a primary control objective in the return-to-center phase, so that the vehicle does not deviate from an adjacent lane. Under the premise that successful obstacle avoidance by the vehicle is guaranteed, the probability of vehicle instability is reduced, thereby improving the safety and reliability of the vehicle in the steering process. A steering assist control device and an intelligent driving device are additionally disclosed.
Need to check novelty before this filing date? Find Prior Art

Description

Technology Field

[0001] The present application claims priority to Chinese patent application No. 202410312120.9, filed with the National Intellectual Property Administration of China on March 19, 2024, with the title of the invention "Steering assist control method and device, and intelligent driving device," the entirety of which is incorporated herein by reference.

[0002] The present application relates to the field of intelligent driving, and more specifically to a steering assistance control method and device, and an intelligent driving device. Background Technology

[0003] With the advancement of vehicles toward intelligence and automation, an increasing number of vehicles are equipped with intelligent driving systems, such as Advanced Driving Assistant Systems (ADAS), to reduce driving pressure and improve safety. ADAS systems include multiple proactive safety features, such as Autonomous Emergency Braking (AEB), Lane Departure Warning (LDW), Emergency Lane Keeping Assist (ELKA), and Emergency Steering Assist (ESA), which enhance driving safety. For example, when a vehicle faces an emergency situation, the aforementioned proactive safety features can make preemptive judgments and take preventive safety measures prior to subjective reactions from the driver. Additionally, ADAS systems include multiple driving assistance features, such as Lane Centering Control (LCC) and Adaptive Cruise Control (ACC), which help reduce driving pressure and alleviate driver fatigue.

[0004] However, current ADAS systems have several limitations in handling emergency obstacle avoidance. For example, in the case of AEB, when a vehicle is traveling at high speeds, the braking distance may be insufficient, and AEB may fail to stop the vehicle in time to avoid a collision. When the braking distance is insufficient, the driver may attempt steering-based obstacle avoidance. During steering control, understeer may occur, leading to a failure of obstacle avoidance. Alternatively, oversteer may occur during steering control, resulting in a loss of vehicle control. When the driver provides insufficient steering input, ESA can control the vehicle to avoid obstacles by applying additional torque to the steering wheel via the electric power steering (EPS) system. However, when ESA is used for obstacle avoidance, the activation process of ESA is prone to causing vehicle instability, thereby affecting driving safety.

[0005] Considering this, it is urgent to develop a safer and more reliable steering assistance control solution.

[0006] The present application provides a steering assist control method and device and an intelligent driving device for improving the stability of a vehicle in a steering process, thereby improving driving safety.

[0007] According to a first embodiment, a steering assistance control method is provided. The method may be performed by an intelligent driving device, or by a computing platform of an intelligent driving device, or by a chip or circuit used in an intelligent driving device. This is not limited in the present application. The intelligent driving device in the present application may be a vehicle.

[0008] The method comprises the steps of: acquiring control phase information, wherein the control phase information indicates that the control phase experienced by the vehicle is one of a steering phase, a return-to-center phase, and a lane-keeping phase; determining a desired steering angle based on the control phase information, wherein the desired steering angle is a steering wheel angle or road wheel angle required to control the steering of the vehicle; determining a desired torque based on the desired steering angle; and controlling the vehicle to apply the desired torque.

[0009] In some implementations, the steering phase may be a phase in which the vehicle changes from the current driving lane to an adjacent lane, for example, a phase in which a first steering torque is applied to the vehicle to cause it to deviate from the current driving lane and change to an adjacent lane in order to avoid an obstacle in advance. The center return phase may be a phase from the moment the vehicle enters the adjacent lane in a specific pose until the moment the vehicle's body corrects its posture in the adjacent lane. The specific pose may be a pose in which the angle between the vehicle's center axis and the lane line is greater than zero. For example, a second steering torque is applied to the vehicle to realign the vehicle's body in the adjacent lane, thereby preventing the vehicle from deviating from the adjacent lane. The lane keeping phase may be a phase in which the vehicle continues to drive in the adjacent lane without crossing the lane line. It may be understood that the second steering torque is in the opposite direction to the first steering torque.

[0010] In the aforementioned technical solution, the desired steering angle applied to the vehicle is determined based on the control phase the vehicle is experiencing, and the vehicle is controlled to apply different types of desired torques. This reduces the probability of vehicle instability in the steering process under the premise that the vehicle's successful avoidance of obstacles is guaranteed, thereby improving the safety and reliability of the vehicle in the steering process.

[0011] Referring to the first embodiment, in some implementations of the first embodiment, when the distance between an obstacle in front of the vehicle and the vehicle is less than or equal to a distance threshold, the step of determining a desired steering angle based on control phase information includes the step of determining a desired steering angle based on a lateral error when the control phase information indicates that the vehicle is in a steering phase—the lateral error is the difference between the actual position of the vehicle and the planned position—; or the step of determining a desired steering angle based on a heading error when the control phase information indicates that the vehicle is in a center return phase—the heading error is the difference between the actual heading angle of the vehicle and the planned heading angle.

[0012] In some implementations, the distance threshold may be a threshold determined based on the time to collision (TTC) or a threshold determined based on the headway. More specifically, the distance threshold may be the minimum distance at which the vehicle can avoid a collision with an obstacle in advance by braking.

[0013] In the aforementioned technical solution, when the vehicle avoids an obstacle in advance by steering, the planned trajectory tracking serves as a primary control objective in the steering phase, allowing the vehicle to drive based on the planned trajectory and avoid the obstacle in advance; and vehicle stability serves as a primary control objective in the center return phase, preventing the vehicle from deviating from the adjacent lane.

[0014] Referring to the first embodiment, in some implementations of the first embodiment, the step of obtaining control phase information includes the step of determining control phase information based on the position of the vehicle for a planned trajectory—the planned trajectory is a steering-based lane change trajectory planned for the vehicle.

[0015] More specifically, the planned trajectory may be a trajectory in which the vehicle is controlled to perform steering-based lane changes to avoid obstacles in advance.

[0016] Referring to the first embodiment, in some implementations of the first embodiment, the step of determining a desired steering angle based on control phase information includes road surface information and the step of determining a desired steering angle based on control phase information—the road surface information includes the road surface adhesion coefficient of the road on which the vehicle is currently traveling.

[0017] In some implementations, the road surface adhesion coefficient of the road the vehicle is currently traveling on is determined based on a measured road surface adhesion coefficient determined based on the road surface type and dynamics perceived by the vehicle.

[0018] In the aforementioned technical solution, vehicle steering is controlled based on the actual road surface adhesion coefficient of the road where the vehicle is positioned, which helps improve the degree of matching between the determined desired torque and the actual road surface condition. For different road surfaces, when the vehicle needs to adjust the same pose, different desired steering angles are calculated, and the vehicle can be controlled to apply different steering torques based on the different desired steering angles. This helps improve the stability of the vehicle in the steering process and improves the intelligence and safety of the vehicle.

[0019] Referring to the first embodiment, in some embodiments of the first embodiment, the method further includes the step of controlling the steering torque of the vehicle based on the control phase the vehicle is experiencing when the vehicle becomes unstable.

[0020] In the aforementioned technical solution, when the vehicle becomes unstable, the vehicle's steering torque is differentially controlled based on the control phase the vehicle is experiencing, which helps ensure vehicle stability and improve driving safety.

[0021] Referring to the first embodiment, in some implementations of the first embodiment, the step of controlling the steering torque of a vehicle based on a control phase that the vehicle is experiencing includes the step of controlling the vehicle to apply a first torque when the vehicle is experiencing a steering phase—the first torque is used to offset the steering torque, the first torque is zero, or the first torque is a non-zero torque opposite in direction to the steering torque.

[0022] In the aforementioned technical solution, when the vehicle becomes unstable during the steering phase, the steering torque of the vehicle is controlled to decrease rapidly to zero, which can help prevent the deterioration of vehicle instability and improve driving safety.

[0023] Referring to the first embodiment, in some implementations of the first embodiment, the step of controlling the steering torque of a vehicle based on a control phase experienced by the vehicle comprises: a step of obtaining the actual pose of the vehicle when the control phase experienced by the vehicle is a center return phase or a lane keeping phase; and a step of controlling the vehicle to apply a second torque when the angle difference between the actual pose and the desired pose is greater than or equal to an angle threshold, the second torque being used to offset the torque currently applied to the vehicle; or a step of ceasing to control the steering torque of the vehicle and inducing the driver of the vehicle to take over control of the vehicle when the angle difference between the actual pose and the desired pose is less than an angle threshold, wherein the desired pose is the pose of the vehicle when the vehicle travels to a preset position along a planned trajectory, and the planned trajectory is a steering-based lane change trajectory planned for the vehicle.

[0024] For example, a preset location may be any location along a planned trajectory where the vehicle is in the lane-keeping phase, or a preset location may be a location along a planned trajectory where the angle of indentation between the vehicle's progress and the lane is less than or equal to an angle of indentation threshold (e.g., 2°, 3°, or another value).

[0025] For example, the angle threshold can be 5°, 10°, or another value.

[0026] For example, ceasing control of the vehicle's steering torque can be understood as ceasing active control of the vehicle's steering torque while still allowing the vehicle to apply steering torque applied by the driver through the steering wheel. For example, ceasing control of the vehicle's steering torque may include terminating the active state of the steering assist function. It can be understood that after active control of the vehicle's steering torque is ceased, if the driver does not take over control of the vehicle, the vehicle's steering torque may gradually ramp down to zero.

[0027] In the aforementioned technical solution, when the vehicle becomes unstable during the center return phase or lane keeping phase, the vehicle's steering torque is controlled based on the angular difference between the vehicle's actual pose and the planned pose. When the angular difference exceeds an angular threshold, the torque currently applied to the vehicle is controlled to rapidly decrease to zero to prevent deterioration of vehicle instability. When the angular difference is below the angular threshold, active control of the vehicle's steering torque is stopped to prevent deterioration of vehicle instability, provided that the vehicle's energy consumption is reduced.

[0028] Referring to the first embodiment, in some implementations of the first embodiment, the step of determining a desired steering angle based on control phase information includes the step of determining a desired steering angle based on control phase information when the road surface adhesion coefficient of the road on which the vehicle is currently traveling is greater than or equal to a coefficient threshold.

[0029] In some implementations, when the road surface adhesion coefficient is low, the operation of the steering assist function is suppressed or the steering assist function is disabled.

[0030] In the technical solution described above, when the road adhesion coefficient is appropriately large, the steering assist function provided herein is enabled; or when the road surface adhesion coefficient is small, the operation of the steering assist function is suppressed or the steering assist function is disabled. This helps to reduce the probability of vehicle instability in the steering process and improve driving safety.

[0031] According to a second embodiment, a steering assist control device is provided. The device includes an acquisition unit and a processing unit. The acquisition unit is configured to acquire control phase information—the control phase information indicates that the control phase the vehicle is experiencing is one of a steering phase, a centering phase, and a lane keeping phase. The processing unit is configured to determine a desired steering angle based on the control phase information—the desired steering angle is a steering wheel angle or road wheel angle required to control the steering of the vehicle—; to determine a desired torque based on the desired steering angle; and to control the vehicle to apply the desired torque.

[0032] Referring to the second embodiment, in some implementations of the second embodiment, when the distance between the vehicle and an obstacle in front of the vehicle is less than or equal to a distance threshold, the processing unit is configured to determine a desired steering angle based on a lateral error when the control phase information indicates that the vehicle is in the steering phase—the lateral error is the difference between the actual position of the vehicle and the planned position—or to determine a desired steering angle based on a heading error when the control phase information indicates that the vehicle is in the center return phase—the heading error is the difference between the actual heading angle of the vehicle and the planned heading angle.

[0033] Referring to the second embodiment, in some implementations of the second embodiment, the processing unit is configured to determine control phase information based on the position of the vehicle with respect to a planned trajectory—the planned trajectory is a steering-based lane change trajectory planned for the vehicle.

[0034] Referring to the second embodiment, in some implementations of the second embodiment, the processing unit is configured to determine a desired steering angle based on road surface information and control phase information, wherein the road surface information includes the road surface adhesion coefficient of the road on which the vehicle is currently traveling.

[0035] Referring to the second embodiment, in some implementations of the second embodiment, the processing unit is further configured to control the steering torque of the vehicle based on the control phase the vehicle is experiencing when the vehicle becomes unstable.

[0036] Referring to the second embodiment, in some implementations of the second embodiment, the processing unit is configured to control the vehicle to apply a first torque when the vehicle is in the steering phase—the first torque is used to offset the steering torque, the first torque is zero, or the first torque is a non-zero torque opposite in direction to the steering torque.

[0037] Referring to the second embodiment, in some implementations of the second embodiment, the processing unit is configured to obtain the actual pose of the vehicle when the vehicle is in the center return phase or the lane keeping phase; and when the angle difference between the actual pose and the desired pose is greater than or equal to an angle threshold, to control the vehicle to apply a second torque—the second torque is used to offset the torque currently applied to the vehicle—or when the angle difference between the actual pose and the desired pose is less than an angle threshold, to stop controlling the steering torque of the vehicle and induce the driver of the vehicle to take over control of the vehicle, the desired pose is the pose of the vehicle when the vehicle is traveling to a preset position along a planned trajectory, and the planned trajectory is a steering-based lane change trajectory planned for the vehicle.

[0038] Referring to the second embodiment, in some implementations of the second embodiment, the processing unit is further configured to determine a desired steering angle based on control phase information when the road surface adhesion coefficient of the road on which the vehicle is currently traveling is below a coefficient threshold.

[0039] According to a third embodiment, a steering assist control device is provided. The device includes a processor configured to execute a computer program stored in memory so that the device performs a method according to any possible implementation of the first embodiment.

[0040] Referring to the third embodiment, in some implementations of the third embodiment, the steering assist control device further includes memory.

[0041] According to a fourth embodiment, an intelligent driving device is provided. The intelligent driving device includes a device according to any possible implementation of the second and third embodiments.

[0042] Referring to the fourth embodiment, in some implementations of the fourth embodiment, the intelligent driving device is a vehicle.

[0043] According to a fifth embodiment, a computer program product is provided. The computer program product includes computer program code. When the computer program product is executed on a computer or processor, the computer is enabled to perform a method according to any possible implementation of the first embodiment.

[0044] It should be noted that all or part of the computer program code may be stored on a storage medium. The storage medium may be packaged together with the processor or packaged separately from the processor.

[0045] According to a sixth embodiment, a computer-readable medium is provided. The computer-readable medium stores instructions. When the instructions are executed by a processor, the processor is enabled to implement a method according to any possible implementation of the first embodiment.

[0046] According to a seventh embodiment, a chip is provided. The chip includes a circuit, and the circuit is configured to perform a method according to any possible implementation of a first embodiment. Brief explanation of the drawing

[0047] FIG. 1 is a functional block diagram of an intelligent driving device according to an embodiment of the present application. FIGS. 2a and 2b are drawings of application scenarios of a steering assist control solution according to an embodiment of the present application. FIG. 3 is a diagram of the architecture of a steering assist control system according to an embodiment of the present application. FIG. 4 is a diagram of divided control phases according to an embodiment of the present application. FIG. 5 is a schematic flowchart of a steering assist control method according to an embodiment of the present application. FIG. 6 is a diagram of a change in steering torque in the case of vehicle instability according to an embodiment of the present application. FIG. 7 is another diagram of a change in steering torque in the case of vehicle instability according to an embodiment of the present application. FIG. 8 is another schematic flowchart of a steering assist control method according to an embodiment of the present application. FIG. 9 is a block diagram of a steering assist control device according to an embodiment of the present application. FIG. 10 is another block diagram of a steering assist control device according to an embodiment of the present application. Specific details for implementing the invention

[0048] The technical solutions of the present application are described below with reference to the attached drawings.

[0049] FIG. 1 is a functional block diagram of an intelligent driving device according to an embodiment of the present application. As illustrated in FIG. 1, the intelligent driving device (100) may include a perception system (120) and a computing platform (150). The perception system (120) may include several sensors configured to detect information regarding the surrounding environment of the intelligent driving device (100). For example, the perception system (120) may include a positioning system. The positioning system may be a global positioning system (GPS), a BeiDou system, or another positioning system. In another example, the perception system (120) may additionally include one or more of an inertial measurement unit (IMU), lidar, millimeter-wave radar, ultrasonic radar, and camera device.

[0050] Some or all of the functions of the intelligent driving device (100) may be controlled by a computing platform (150). The computing platform (150) may include processors (151 to 15n). A processor is a circuit having signal processing capabilities. In an implementation, the processor may be a circuit having instruction reading and execution capabilities, for example, a central processing unit (CPU), a microprocessor, a graphics processing unit (GPU) (which may be understood as a microprocessor), or a digital signal processor (DSP). In another implementation, the processor may implement specific functions based on logical relationships of hardware circuits. Logical relationships of hardware circuits may be 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), for example, a field programmable gate array (FPGA). In a reconfigurable hardware circuit, the process of a processor loading a configuration file to implement the hardware circuit configuration can be understood as the process of a processor loading instructions to implement some or all of the functions of the aforementioned units. Additionally, the processor may alternatively be a hardware circuit designed for artificial intelligence and may be understood as an ASIC, for example, a neural network processing unit (NPU), a tensor processing unit (TPU), or a deep learning processing unit (DPU).Additionally, the computing platform (150) may additionally include memory. The memory is configured to store instructions. Some or all of the processors (151 to 15n) may call instructions from memory to implement corresponding functions.

[0051] The intelligent driving device (100) may include ADAS. The ADAS acquires information around the intelligent driving device by using a plurality of sensors on the intelligent driving device (including, but not limited to, lidar, millimeter-wave radar, camera device, ultrasonic sensor, global positioning system, and inertial measurement unit), and analyzes and processes the acquired information to implement functions such as obstacle detection, target recognition, intelligent driving device positioning, path planning, and driver monitoring / reminders. This improves the driving safety, automation, and comfort of the intelligent driving device.

[0052] In terms of logical functions, an ADAS system generally includes three main functional modules: a perception module, a decision module, and an actuation module. The perception module perceives the environment surrounding the vehicle body using sensors and inputs corresponding real-time data from the decision layer to the processing center. The perception module primarily includes vehicle-mounted cameras, ultrasonic radar, millimeter-wave radar, lidar, etc. The decision module makes corresponding decisions based on the information acquired by the perception module by using computing devices and algorithms. After receiving a decision signal from the decision module, the actuation module takes a corresponding action, such as driving, changing lanes, steering, braking, or issuing a warning.

[0053] At different autonomous driving levels (L0 to L5), ADAS can implement different levels of autonomous driving assistance based on information obtained by utilizing artificial intelligence algorithms and multiple sensors. The aforementioned autonomous driving levels (L0 to L5) are based on the grading standards of the Society of Automotive Engineers (SAE). Level L0 indicates no automation, Level L1 indicates driving assistance, Level L2 indicates partial automation, Level L3 indicates conditional automation, Level L4 indicates high automation, and Level L5 indicates full automation. At Levels L1 to L3, tasks involving monitoring road conditions and responding to them are completed jointly by the driver and the system, and the driver needs to take over dynamic driving tasks. Levels L4 and L5 allow the driver to completely switch to the role of a passenger. Currently, the functions that can be implemented by ADAS primarily include, but are not limited to, adaptive cruise, automatic emergency braking, automatic parking, blind spot monitoring, traffic warning / braking at forward intersections, traffic warning / braking at rear intersections, forward collision warning, lane departure warning, lane keeping assist, rear collision avoidance warning, traffic sign recognition, traffic jam assist, highway assist, etc. It should be understood that the aforementioned functions may have specific modes at different autonomous driving levels (L0 to L5). Higher autonomous driving levels correspond to more intelligent modes.

[0054] The intelligent driving device in the embodiments of the present application may include road transport tools, water transport tools, air transport tools, industrial devices, agricultural devices, recreational devices, etc. For example, the intelligent driving device may be a vehicle. A vehicle is defined in a broad sense and may be a transport tool (e.g., commercial vehicle, passenger car, motorcycle, flying vehicle, or train), an industrial vehicle (e.g., forklift, trailer, or tractor), an engineering vehicle (e.g., excavator, bulldozer, or crane), an agricultural device (e.g., lawn mower or harvester), a recreational device, a toy vehicle, etc. The type of vehicle is not specifically limited in the embodiments of the present application. For ease of understanding, the following uses an example where the intelligent driving device is a vehicle for illustrative purposes.

[0055] As previously mentioned, during steering-based obstacle avoidance, when the steering wheel angle input by the driver is insufficient, the ESA can provide additional torque to the steering wheel. However, during the activation of the ESA, the vehicle is prone to instability, which affects driving safety.

[0056] Generally, the causes of vehicle instability during ESA activation can be classified into two types. The first type of cause is illustrated in Fig. 2a. During steering for obstacle avoidance, the steering wheel rotates at an excessively large angle in a short period, causing the front wheels to lose steering ability. In this case, it becomes impossible to control the vehicle to correct its posture via the steering wheel, leading to the vehicle leaving its lane. The second type of cause is illustrated in Fig. 2b. During the centering process, the steering wheel rotates at an excessively large angle, leading to a reduction in the lateral adhesion of the vehicle's rear wheels. This causes the rear wheels to slip earlier or more significantly than the front wheels, resulting in "fishtailing" of the vehicle. Furthermore, because different road surfaces have different road adhesion coefficients, the vehicle's limited lateral acceleration varies depending on the road surface, even at the same vehicle speed and steering wheel angle. This results in varying obstacle avoidance capabilities for the vehicle on different road surfaces. When the driver is assisted by the ESA based on the same road surface adhesion coefficient (i.e., when additional torque is provided), cases of oversteer or understeer may occur, which can lead to vehicle instability or failure to avoid obstacles.

[0057] With this in mind, embodiments of the present application provide a steering assist control method and device and an intelligent driving device, wherein a desired steering angle can be determined based on different control phases, and a steering torque can be adjusted based on the desired steering angle and the actual steering angle, thereby controlling the stability of the vehicle during obstacle avoidance. Additionally, when the vehicle becomes unstable, the vehicle torque can be further corrected based on the steering control phase in which the vehicle is located, thereby controlling the vehicle to recover a stable state as quickly as possible. The steering assist control method provided in the present application can be deployed on a vehicle's computing platform as a novel preemptive safety function.

[0058] It should be noted that the steering angle in the embodiments of the present application may be the steering wheel angle or the road wheel angle.

[0059] FIG. 3 is a diagram of the architecture of a steering assist control system according to an embodiment of the present application. As illustrated in FIG. 3, the system includes a planning module (210), a preprocessing module (220), a control module (230), and an actuator (240). The preprocessing module (220) includes a road adhesion system estimation module (221) and a stability determination module (222). The control module (230) includes a control phase splitting module (231), a steering angle computing module (232), and a steering torque computing module (233). Optionally, the system illustrated in FIG. 3 may further include a perception module (250). The planning module (210), the preprocessing module (220), and the control module (230) may individually include one or more processors within the computing platform (150) illustrated in FIG. 1, and the perception module (250) may include one or more sensors in the perception system (120) illustrated in FIG. 1.

[0060] Specifically, the planning module (210) plans a trajectory based on information regarding obstacles in front of the ego vehicle and information obtained by the perception module (250), so that the ego vehicle can avoid obstacles by changing lanes. The control module (230) calculates a corresponding control variable (e.g., steering torque, degree of opening of the accelerator pedal, or degree of opening of the brake pedal) based on the planned trajectory input by the planning module (210) and outputs the control variable to the actuator (240). When the actuator (240) applies the control variable, the vehicle can drive along the planned trajectory. In some possible implementations, the actuator may include a steering and braking control system in the intelligent driving device (100).

[0061] For example, the control phase division module (231) can divide the control phases into a steering phase, a center return phase, and a lane keeping phase based on the planned trajectory. As illustrated in FIG. 4, in order to control the vehicle to drive along the planned trajectory, a steering torque that enables the vehicle to rotate counterclockwise needs to be applied to the vehicle at position ②. When the vehicle drives to position ③, in order to prevent the vehicle from deviating from the target lane, a steering torque that enables the vehicle to rotate clockwise needs to be applied to the vehicle at position ③ until the angle between the vehicle's center axis and the road boundary line becomes below the angle threshold (e.g., to position ④). After the angle between the vehicle's center axis and the road boundary line becomes below the angle threshold, the vehicle can continue to drive in the target lane. Referring to FIG. 4, the control phase corresponding to positions ② to ③ can be designated as a steering phase, the control phases corresponding to positions ③ to ④ can be designated as a center return phase, and the phase after position ④ until the vehicle reaches a stable state can be designated as a lane keeping phase.

[0062] After dividing the control phases, the control phase division module (231) determines the control phase currently experienced by the ego vehicle based on the locations of the ego vehicle and obstacles and the locations obtained by the perception module (250), and transmits the control phase information to the steering angle computing module (232). The steering angle computing module (232) can determine a desired steering angle that allows the ego vehicle to be controlled to drive along a planned trajectory based on the control phase currently experienced by the ego vehicle and the road surface adhesion coefficient of the road currently being driven by the ego vehicle and calculated by the road surface adhesion coefficient estimation module (221), and can input the desired steering angle to the steering torque calculation module (233). The steering torque calculation module (233) determines a desired steering torque (hereinafter simply referred to as the desired torque) based on the desired steering angle.

[0063] In some implementations, vehicle instability may occur during the steering process (e.g., vehicle instability caused by the activation of a steering assist function). When the vehicle becomes unstable, the steering torque computing module (233) may, alternatively, determine the desired torque based on the desired steering angle, the current actual steering torque of the ego vehicle, and the control node currently experienced by the ego vehicle. Information regarding whether the vehicle becomes unstable may be determined by the stability determination module (222) and transmitted to the steering torque computing module (233).

[0064] In addition, a desired torque is input to the actuator (240), and when the actuator (240) applies the desired torque, the vehicle moves along a planned trajectory.

[0065] For example, the stability determination module (222) can determine whether the vehicle becomes unstable based on the vehicle's chassis state information. For example, the chassis state information includes the vehicle's actual yaw angle. When the vehicle's actual yaw angle exceeds the desired yaw angle, it is determined that the vehicle becomes unstable. When the vehicle's actual yaw angle is less than or equal to the desired yaw angle, it is determined that the vehicle is stable. The vehicle's desired yaw angle It can satisfy the following equation (1):

[0066] (1)

[0067] In this specification, is the longitudinal speed of the vehicle, and is the steering wheel angle, and is the vehicle's wheelbase, and is the characteristic speed of the vehicle, where the characteristic speed is the vehicle speed at which the vehicle's steady-state rate gain reaches its maximum value.

[0068] It should be understood that the aforementioned system is merely an example. In actual applications, modules within the aforementioned system may be added or removed based on actual requirements. For example, the planning module (210) and the control module (230) may be combined into a single module. As another example, the preprocessing module (220) and the control module (230) may be combined into a single module.

[0069] The system provided in the embodiments of the present application is described above, and the steering assist control method provided in the embodiments of the present application is described in detail below.

[0070] FIG. 5 is a schematic flowchart of a steering assist control method according to an embodiment of the present application. The method may be performed by an intelligent driving device (100) shown in FIG. 1, or by a control module (230) shown in FIG. 2a and FIG. 2b. The method (500) includes some or all of the steps S501 to S504.

[0071] S501: Acquire planned trajectory and road surface information of the vehicle - the road surface information includes the road surface adhesion coefficient of the road the vehicle is currently traveling on.

[0072] In some implementations, if an obstacle appears in front of the vehicle and causes a situation where AEB cannot stop the vehicle in time, steering-based obstacle avoidance is required, and S501 is performed. The planned trajectory may be a trajectory for avoiding an obstacle in front of the vehicle. In some implementations, the road surface adhesion coefficient of the road currently being driven on It can be determined based on road information perceived by the perception system. For example, road surface adhesion coefficient It can be determined based on the following equation (2):

[0073] (2)

[0074] Here, is the perceived road surface adhesion coefficient, and is a measured road surface adhesion coefficient determined based on a vehicle dynamics model, and a and b are weighting coefficients. For example, a and b can be values ​​greater than 0 and less than or equal to 1, and the sum of a and b is 1.

[0075] For example, the measured road surface adhesion coefficient It can be determined based on the following formulas (3) to (5):

[0076] (3)

[0077] (4)

[0078] (5)

[0079] In this specification, is the vehicle mass, and is the longitudinal acceleration of the vehicle measured by the perception system, and is the front wheel steering angle of the vehicle, and , , , and are the longitudinal tire force of the left-front wheel, the longitudinal tire force of the right-front wheel, the longitudinal tire force of the left-rear wheel, and the longitudinal tire force of the right-rear wheel, respectively, and is wheel Represents the longitudinal tire force, is wheel Represents the road adhesion coefficient at, is wheel It is the tire slip ratio, and The value of , , , or And, B, C, D, and E are the stiffness modulus, shape modulus, peak modulus, and curvature modulus, respectively, and is observation noise, and is a weighting coefficient.

[0080] For example, road information can be a road image. The road surface type is determined based on the road image, and the perceived road surface adhesion coefficient of the road currently being driven on. It is determined based on the road surface type. Perceived road surface adhesion coefficient The relationship between and road surface type can be shown in Table 1.

[0081] Road surface type Perceived road surface adhesion coefficient dry asphalt road surface 0.8-1.0 wet asphalt road surface 0.5-0.7 snow-covered road surface 0.2-0.4

[0082] It should be understood that the values ​​and road surface types shown in Table 1 are merely examples. In actual implementation, based on the road surface type, the values ​​shown in Table 1 The value within the range of values It can be determined as such. In addition, in actual implementation, road surface types and value ranges not shown in Table 1 may be additionally included.

[0083] In some implementations, when the road surface adhesion coefficient of the road the vehicle is currently traveling on is below a preset threshold, the operation of the steering assist function is suppressed or the steering assist function is disabled. For example, the preset threshold may be 0.6, 0.7, or another value.

[0084] S502: Determines the desired steering angle based on the planned trajectory and road surface information.

[0085] For example, the desired steering angle γ satisfies the following equations (6) to (8):

[0086] (6)

[0087] (7)

[0088] (8)

[0089] Here, represents the steering angle feedforward term, represents the steering angle feedback term, is the road surface adhesion coefficient of the road the vehicle is currently traveling on, and is the road surface adhesion coefficient It is the yaw angle required for the vehicle to travel along a planned trajectory under, and is a lateral error, and the lateral error may be the difference between the position of the vehicle's front wheels and the distance between the nearest point on the planned trajectory, and is the progression error, that is, the difference between the vehicle's actual progression and planned progression, and and are proportionality constants, and and are integral coefficients, and 1 and are difference coefficients.

[0090] In some implementations, the desired steering angle is determined based on the control phase the vehicle is experiencing. For example, when the vehicle is in the steering phase, Weights for lateral errors in (e.g., , , or 1) is increasing and Weights for the progress error in (e.g., , , or 2) can be reduced, and thus the desired steering angle obtained It can enable the vehicle to drive along a planned trajectory to implement obstacle avoidance. When the vehicle is in the center return phase, Weights for lateral errors in (e.g., , , or 1) is reduced and Weights for the progress error in (e.g., , , or 2) is increased, and thus the desired steering angle obtained It can guarantee vehicle stability. When the vehicle is in the lane keeping phase, if the driver does not take over control of the vehicle, the weighting for lateral error versus In this case, the ratio of weights for the progress error is controlled equally or nearly equally to control the vehicle to drive within the lane and prevent the vehicle from deviating from the lane.

[0091] S503: Determines the desired torque 1 based on the desired steering angle and chassis condition information.

[0092] For example, the desired torque 1 satisfies the following equations (9) to (11):

[0093] (9)

[0094] (10)

[0095] (11)

[0096] Here, T represents the desired torque 1, and represents the torque feedforward term, represents the torque feedback term, represents the torque generated by the driver through the rotation of the steering wheel, and is the rotational inertia of the wheel, and is the second derivative of the desired steering angle, and is the stiffness coefficient of the wheel, and is an angle error, and the angle error can be the difference between the desired steering angle and the actual rotation angle, , , and 3 are the proportionality coefficient, integration coefficient, and difference coefficient, respectively.

[0097] S504: Acquire stable state information - stable state information indicates whether the vehicle has become unstable -, when the vehicle has become unstable, determine the desired torque 2 based on control phase information - control phase information indicates that the vehicle is currently in one of the steering phase, centering phase, and lane keeping phase.

[0098] For example, if stable state information indicates that the vehicle is stable, a desired torque 1 is applied to control the vehicle to drive along a planned trajectory to avoid obstacles. If the vehicle becomes unstable, a control phase in which instability occurs is determined based on an instability signal, and then a desired torque 2 is determined based on the control phase.

[0099] In the example, as illustrated in FIG. 6, when the vehicle becomes unstable during the steering phase, the desired torque 2 is determined based on the obstacle avoidance torque, and the vehicle's obstacle avoidance torque is controlled to rapidly decrease to zero, thereby preventing the deterioration of vehicle instability. The desired torque 2 may be zero, or the desired torque 2 may be a non-zero value in the opposite direction to the obstacle avoidance torque. As illustrated in FIG. 6, a can be viewed as a curve representing the change in the vehicle's actual torque along a planned trajectory after the desired torque 2 is applied to the vehicle.

[0100] In another example, as illustrated in FIG. 7, when the vehicle becomes unstable during the centering phase, it is determined whether the in-between angle α between the vehicle's actual pose and the planned pose when the vehicle becomes unstable is greater than or equal to an angle threshold, where the planned pose is the pose obtained when the vehicle drives along the planned trajectory in the lane keeping phase. Additionally, when the in-between angle α is greater than or equal to the angle threshold, the desired torque 1 is corrected to the desired torque 2, where the desired torque 2 is 0 or opposite to the direction of the desired torque in the centering phase, thereby controlling the desired torque in the vehicle's centering phase to rapidly decrease to 0, thereby preventing the deterioration of vehicle instability. As illustrated in FIG. 7, b can be viewed as a curve representing the change in the vehicle's actual torque along the planned trajectory after the desired torque 2 is applied to the vehicle. When the in-between angle α is less than the in-between angle threshold, the steering assist function can be controlled to terminate the active state. For example, the angle threshold can be 5°, 10°, or another value.

[0101] According to the steering assist control method provided in the present embodiment of the application, the desired steering angle and desired torque are determined based on the actual road surface adhesion coefficient of the road on which the vehicle is currently traveling, thereby helping to improve the stability of the vehicle during the steering process. Additionally, when the vehicle becomes unstable, the torque of the vehicle is controlled based on the control phase the vehicle is experiencing, thereby helping to improve the stability and safety of the vehicle.

[0102] FIG. 8 is another schematic flowchart of a steering assistance control method according to an embodiment of the present application. The method may be performed by an intelligent driving device (100) shown in FIG. 1, or by a control module (230) shown in FIG. 2a and FIG. 2b. The method (800) includes the following steps.

[0103] S810: Acquire control phase information - The control phase information indicates that the control phase the vehicle is experiencing is one of the steering phase, centering phase, and lane keeping phase.

[0104] In some implementations, control phase information is determined based on the vehicle's position relative to a planned trajectory, and the planned trajectory is a steering-based lane change trajectory planned for the vehicle. For example, when the vehicle travels to the area between position ② and position ③ shown in FIG. 4, the control phase is determined to be a steering phase; when the vehicle travels to the area between position ③ and position ④ shown in FIG. 4, the control phase is determined to be a center return phase; and when the vehicle travels to the area between position ④ and position ⑤ shown in FIG. 4, the control phase is determined to be a lane keeping phase.

[0105] For example, the planned trajectory may include the planned trajectory in method (500).

[0106] S820: Determines the desired steering angle based on control phase information - The desired steering angle is the steering wheel angle or road wheel angle required to control the steering of the vehicle.

[0107] In some implementations, when the distance between the vehicle and an obstacle in front of the vehicle is less than or equal to a distance threshold, the step of determining a desired steering angle based on control phase information includes the step of determining a desired steering angle based on a lateral error when the control phase information indicates that the vehicle is in a steering phase—the lateral error is the difference between the actual position of the vehicle and the planned position—; or the step of determining a desired steering angle based on a heading error when the control phase information indicates that the vehicle is in a center return phase—the heading error is the difference between the actual heading angle of the vehicle and the planned heading angle.

[0108] For example, in an actual implementation, as described in S502, the desired steering angle is determined based on lateral error and travel error. Thus, it can be understood that the desired steering angle is determined based on lateral error as follows: when the desired steering angle is determined, the weight for lateral error is increased, for example, the weight for lateral error in the steering angle feedback term is increased, and the weight for travel error within the steering angle feedback term is decreased. Similarly, it can be understood that the desired steering angle is determined based on travel error as follows: when the desired steering angle is determined, the weight for travel error is increased, for example, the weight for travel error in the steering angle feedback term is increased, and the weight for lateral error within the steering angle feedback term is decreased.

[0109] In some implementations, the step of determining a desired steering angle based on control phase information includes road surface information and the step of determining a desired steering angle based on control phase information - the road surface information includes the road surface adhesion coefficient of the road on which the vehicle is currently traveling.

[0110] For example, the road surface information may include the road surface information described in method (500). For a specific implementation of determining the road surface information, refer to the description in S501. Details are not described again in this specification. Determining a desired steering angle based on the road surface information and control phase information may include determining a steering angle feedforward term based on the road surface information, determining a steering angle feedback term based on the control phase information, and determining a desired steering angle based on the steering angle feedforward term and the steering angle feedback term. For a more specific implementation, refer to the description in S502. Details are not described again in this specification.

[0111] S830: Determines the desired torque based on the desired steering angle.

[0112] For a more specific method for determining the desired torque based on the desired steering angle, refer to the description in S503. Details are not described again in this specification.

[0113] S840: Controls the vehicle to apply the desired torque.

[0114] In some implementations, the method further comprises the step of controlling the steering torque of the vehicle based on the control phase the vehicle is experiencing when the vehicle becomes unstable. More specifically, the step of controlling the steering torque of the vehicle based on the control phase the vehicle is experiencing comprises the step of controlling the vehicle to apply a first torque when the vehicle is experiencing a steering phase—the first torque is used to offset the steering torque, the first torque is zero, or the first torque is a non-zero torque opposite in direction to the steering torque. The step of controlling the steering torque of the vehicle based on the control phase the vehicle is experiencing further comprises the step of acquiring the actual pose of the vehicle when the control phase the vehicle is experiencing is a centering phase or a lane keeping phase; and when the angular difference between the actual pose and the desired pose is greater than or equal to an angular threshold, controlling the vehicle to apply a second torque—the second torque is used to offset the torque currently applied to the vehicle—; Alternatively, when the angle difference between the actual pose and the desired pose is less than an angle threshold, the method may include a step of stopping the control of the vehicle's steering torque and inducing the driver of the vehicle to take over control of the vehicle, wherein the desired pose is the pose of the vehicle when the vehicle travels to a preset position along a planned trajectory, and the planned trajectory is a steering-based lane change trajectory planned for the vehicle.

[0115] For example, the first torque or the second torque may include the desired torque 2 in the method (500), and the angle threshold may be 5°, 10°, or another value.

[0116] In some implementations, when the road surface adhesion coefficient of the road the vehicle is currently traveling on is greater than or equal to the coefficient threshold, the method (800) is performed; or when the road surface adhesion coefficient of the road the vehicle is currently traveling on is less than the coefficient threshold, the steering assist function is disabled.

[0117] For example, the coefficient threshold can be a preset threshold in S501, for example, 0.6 or 0.7, or another value.

[0118] According to the steering assist control method provided in the present embodiment of the present application, the desired steering angle applied to the vehicle is determined based on the control phase the vehicle is experiencing, thereby controlling the vehicle to apply different types of desired torques. When the vehicle avoids an obstacle in advance by steering, tracking the planned trajectory serves as a primary control objective in the steering phase, causing the vehicle to drive based on the planned trajectory to avoid the obstacle in advance; and vehicle stability serves as a primary control objective in the center return phase, preventing the vehicle from deviating from an adjacent lane. Under the premise that the vehicle's successful obstacle avoidance is guaranteed, the probability of vehicle instability in the steering process is reduced, thereby improving the safety and reliability of the vehicle in the steering process. Furthermore, when the vehicle becomes unstable, the vehicle's torque is controlled based on the control phase the vehicle is experiencing, thereby helping to prevent the deterioration of vehicle instability and improve driving safety.

[0119] In the embodiments of the present application, unless otherwise stated or there is a logic conflict, the terms and / or descriptions in the embodiments are consistent and may be cross-referenced, and technical features in different embodiments may be combined based on their internal logical relationships to form new embodiments.

[0120] The steering assist control method provided in the embodiments of the present application is described in detail with reference to FIGS. 1 through 8. The apparatus provided in the embodiments of the present application is described in detail below with reference to FIGS. 9 and 10. It should be understood that the descriptions of the apparatus embodiments correspond to the descriptions of the method embodiments. Accordingly, for details not described in detail, reference is made to the method embodiments. For the sake of brevity, details are not described again in this specification.

[0121] FIG. 9 is a block diagram of a steering assist control device (2000) according to an embodiment of the present application. The device (2000) may include units configured to perform method (500) and method (800). Additionally, units within the device (2000) are configured to implement corresponding procedures in the aforementioned method embodiments. The device (2000) includes an acquisition unit (2010). The acquisition unit (2010) may be configured to implement a corresponding data acquisition or reception / transmission function. The device (2000) further includes a processing unit (2020). The processing unit (2020) may be configured to implement a corresponding processing function.

[0122] Optionally, the device (2000) may additionally include a storage unit. The storage unit may be configured to store instructions and / or data. The processing unit (2020) may read instructions and / or data within the storage unit to enable the device to perform the relevant actions in the aforementioned method embodiments.

[0123] It should be understood that the specific process by which the units perform the corresponding steps described above has been described in detail in the aforementioned method embodiments. For the sake of brevity, details are not described again in this specification.

[0124] It should be understood that the device (2000) of this specification is embodied in the form of a functional unit. In this specification, the terms “module” or “unit” may be a custom ASIC, electronic circuit, a processor configured to execute one or more software or firmware programs (e.g., a shared processor, a dedicated processor, or a group processor), and memory, merged logic circuit, and / or other suitable components supporting the described functions.

[0125] The device in the solutions described above has functions for implementing corresponding steps performed by the computing platform (150) in the methods described above. These functions may be implemented by hardware or by hardware that executes corresponding software. The hardware or software includes one or more modules corresponding to the functions described above. For example, the acquisition unit (2010) may be replaced with a transceiver, and other units, such as a processing unit, may be replaced with a processor configured to perform the relevant processing operations in the method embodiments.

[0126] For example, the acquisition unit (2010) and the processing unit (2020) may be placed within the intelligent driving device (100) shown in FIG. 1 or within the system shown in FIG. 3. More specifically, the acquisition unit (2010) and the processing unit (2020) may be placed in the control module (230). For example, operations performed by the acquisition unit (2010) and the processing unit (2020) may be performed by a single processor or by different processors. In a specific implementation process, one or more processors may be processors placed in the intelligent driving device (100) shown in FIG. 1; or the device (2000) may be a chip placed in the intelligent driving device (100).

[0127] In a specific implementation process, all or some of the units within the aforementioned device may be integrated together or implemented independently. In the implementation, the units are integrated and implemented in the form of a system-on-a-chip (SoC).

[0128] FIG. 10 is another block diagram of a steering assist control device according to an embodiment of the present application. The steering assist control device (2100) illustrated in FIG. 10 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 configured to store instructions. The processor (2110) is configured to execute instructions stored in the memory (2130) to implement the methods of the embodiments described above. Optionally, the memory (2130) may be coupled to the processor (2110) via an interface or may be integrated with the processor (2110).

[0129] It should be noted that the transceiver (2120) may include, but is not limited to, a transceiver device such as an input / output interface (input / output interface) to implement communication between the device (2100) and another device or communication network.

[0130] The memory (2130) may be volatile memory and / or non-volatile memory. Non-volatile memory may be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. Volatile memory may be random access memory (RAM). For example, RAM may be used as an external cache. As an example, not a limitation, RAM includes multiple forms such as static random access memory (static RAM, SRAM), dynamic random access memory (dynamic RAM, DRAM), synchronous dynamic random access memory (synchronous DRAM, SDRAM), double data rate synchronous dynamic random access memory (double data rate SDRAM, DDR SDRAM), enhanced synchronous dynamic random access memory (enhanced SDRAM, ESDRAM), synchlink dynamic random access memory (synchlink DRAM, SLDRAM), and direct rambus random access memory (direct rambus RAM, DR RAM).

[0131] The transceiver (2120) uses, for example, a transceiver device such as a transceiver to receive / transmit data / information used to implement the methods in the aforementioned embodiments by implementing communication between the device (2100) and another device or communication network, but is not limited thereto.

[0132] Embodiments of the present application further provide an intelligent driving device. The intelligent driving device includes a steering assist control device (2000) or a steering assist control device (2100) in the above-described embodiment.

[0133] Embodiments of the present application further provide a computer program product. The computer program product includes computer program code. When the computer program code is executed on a computer, the computer is enabled to implement the methods of the embodiments described above of the present application.

[0134] Embodiments of the present application further provide a computer-readable storage medium. The computer-readable medium stores computer instructions. When computer instructions are executed on a computer, the computer is enabled to implement the methods of the embodiments described above of the present application.

[0135] An embodiment of the present application further provides a chip comprising a circuit configured to perform the methods of the embodiments described above of the present application.

[0136] It will be clearly understood by those skilled in the art that, for a convenient and brief explanation of the detailed operation of the aforementioned systems, devices, and units, reference may be made to the corresponding processes in the aforementioned method embodiments. Details are not described again herein.

[0137] In the description of the embodiments of this application, " / " means "or" unless otherwise specified. For example, A / B may represent A or B. In this application, "and / or" merely describes an association between associated objects and indicates that three relationships may exist. For example, "A and / or B" may represent the following three cases: only A exists, both A and B exist, and only B exists. In this application, "at least one" means one or more, and "plural" means two or more. "At least one of the following items (pieces)" or a similar expression means any combination of these items, including a single item (piece) or any combination of plural items (pieces). For example, at least one item (piece) of a, b, or c may represent a, b, c, a and b, a and c, b and c, or a, b, and c, wherein a, b, and c may be singular or plural.

[0138] In the embodiments of this application, prefix words such as "first" and "second" are intended merely to distinguish between different objects and do not impose limitations on the locations, orders, priorities, quantities, contents, etc., of the described objects. In the embodiments of this application, the use of prefix words, for example ordinal numbers, used to distinguish between the described objects does not constitute a limitation on the described objects. For the description of the described objects, refer to the claims or the context of the embodiments. The use of such prefix words should not constitute a redundant limitation.

[0139] It should be understood that in some of the embodiments provided in this application, the disclosed systems, devices, and methods may be implemented in other ways. For example, the described device embodiments are merely examples. For example, the division into units is merely a logical functional division and may be different in actual implementation. For example, multiple units or components may be combined or integrated into different systems, or some features may be ignored or not performed. Additionally, the mutual couplings or direct couplings or communication connections shown or discussed may be implemented through some interfaces. Indirect couplings or communication connections between devices or units may be implemented in electronic, mechanical, or other forms.

[0140] In the embodiments of the present application, unless otherwise stated or there is a logic conflict, the terms and / or descriptions in the embodiments are consistent and may be cross-referenced, and technical features in different embodiments may be combined based on their internal logical relationships to form new embodiments.

[0141] The unit described as a separate part may or may not be physically separated, and the part displayed as a unit may or may not be a physical unit, may be located in a single position, or may be distributed across multiple network units. Some or all of the units may be selected based on actual requirements to achieve the purposes of the solutions of the embodiments.

[0142] Additionally, the functional units in the embodiments of the present application may be integrated into a single processing unit, each unit may exist physically independently, or two or more units may be integrated into a single unit.

[0143] The foregoing description is merely a specific embodiment of the present application and is not intended to limit the scope of protection of the present application. Any modification or substitution that a person skilled in the art could readily derive within the technical scope disclosed in the present application falls within the scope of protection of the present application. Accordingly, the scope of protection of the present application should be determined based on the scope of protection of the claims.

Claims

Claim 1 A steering assist control method comprising: a step of acquiring control phase information, wherein the control phase information indicates that the control phase experienced by the vehicle is one of a steering phase, a return-to-center phase, and a lane keeping phase; a step of determining a desired steering angle based on the control phase information, wherein the desired steering angle is a steering wheel angle or a road wheel angle required to control the steering of the vehicle; a step of determining a desired torque based on the desired steering angle; and a step of controlling the vehicle to apply the desired torque. Claim 2 A method according to claim 1, wherein when the distance between an obstacle in front of the vehicle and the vehicle is less than or equal to a distance threshold, the step of determining the desired steering angle based on the control phase information comprises: the step of determining the desired steering angle based on a lateral error when the control phase information indicates that the vehicle is in the steering phase—the lateral error being the difference between the actual position of the vehicle and the planned position—; or the step of determining the desired steering angle based on a heading error when the control phase information indicates that the vehicle is in the center return phase—the heading error being the difference between the actual heading angle of the vehicle and the planned heading angle. Claim 3 A method according to claim 1 or 2, wherein the step of acquiring the control phase information comprises the step of determining the control phase information based on the position of the vehicle relative to a planned trajectory—the planned trajectory being a steering-based lane change trajectory planned for the vehicle. Claim 4 A method according to any one of claims 1 to 3, wherein the step of determining the desired steering angle based on the control phase information comprises: determining the desired steering angle based on road surface information and the control phase information—the road surface information includes the road adhesion coefficient of the road on which the vehicle is currently traveling. Claim 5 A method according to any one of claims 1 to 4, wherein the method further comprises the step of controlling the steering torque of the vehicle based on the control phase the vehicle is experiencing when the vehicle becomes unstable. Claim 6 In claim 5, the step of controlling the steering torque of the vehicle based on the control phase experienced by the vehicle comprises the step of controlling the vehicle to apply a first torque when the vehicle is in the steering phase, wherein the first torque is used to offset the steering torque, the first torque is zero, or the first torque is a non-zero torque opposite in direction to the steering torque. Claim 7 The method according to claim 5 or 6, wherein the step of controlling the steering torque of the vehicle based on the control phase the vehicle is experiencing comprises: acquiring the actual pose of the vehicle when the vehicle is in the center return phase or the lane keeping phase; and controlling the vehicle to apply a second torque when the angle difference between the actual pose and the desired pose is greater than or equal to an angle threshold, wherein the second torque is used to offset the torque currently applied to the vehicle; or stopping the control of the steering torque of the vehicle and inducing the driver of the vehicle to take over control of the vehicle when the angle difference between the actual pose and the desired pose is less than the angle threshold, wherein the desired pose is the pose of the vehicle when the vehicle is traveling to a preset position along the planned trajectory, and the planned trajectory is a steering-based lane change trajectory planned for the vehicle. Claim 8 A method according to any one of claims 1 to 7, wherein the step of determining the desired steering angle based on the control phase information includes the step of determining the desired steering angle based on the control phase information when the road surface adhesion coefficient of the road on which the vehicle is currently driving is greater than or equal to a coefficient threshold. Claim 9 A device comprising a steering assist control device, comprising: an acquisition unit configured to acquire control phase information, wherein the control phase information indicates that the control phase experienced by the vehicle is one of a steering phase, a centering phase, and a lane keeping phase; and a processing unit configured to determine a desired steering angle based on the control phase information, wherein the desired steering angle is a steering wheel angle or a road wheel angle required to control the steering of the vehicle; wherein a desired torque is determined based on the desired steering angle; and wherein the processing unit is configured to control the vehicle to apply the desired torque. Claim 10 A device according to claim 9, wherein when the distance between an obstacle in front of the vehicle and the vehicle is less than or equal to a distance threshold, the processing unit determines the desired steering angle based on a lateral error when the control phase information indicates that the vehicle is in the steering phase—wherein the lateral error is the difference between the actual position of the vehicle and the planned position—; or determines the desired steering angle based on a progression error when the control phase information indicates that the vehicle is in the center return phase—wherein the progression error is the difference between the actual progression angle of the vehicle and the planned progression angle. Claim 11 A device according to claim 9 or 10, wherein the processing unit is configured to determine the control phase information based on the position of the vehicle relative to a planned trajectory, wherein the planned trajectory is a steering-based lane change trajectory planned for the vehicle. Claim 12 A device according to any one of claims 9 to 11, wherein the processing unit is configured to determine the desired steering angle based on road surface information and the control phase information, wherein the road surface information includes the road surface adhesion coefficient of the road on which the vehicle is currently traveling. Claim 13 A device according to any one of claims 9 to 12, wherein the processing unit is additionally configured to control the steering torque of the vehicle based on the control phase the vehicle is experiencing when the vehicle becomes unstable. Claim 14 In claim 13, the processing unit is configured to control the vehicle to apply a first torque when the vehicle is in the steering phase, wherein the first torque is used to offset the steering torque, the first torque is zero, or the first torque is a non-zero torque opposite in direction to the steering torque. Claim 15 In claim 13 or 14, the processing unit is configured to obtain the actual pose of the vehicle when the vehicle is in the center return phase or the lane keeping phase; and when the angle difference between the actual pose and the desired pose is greater than or equal to an angle threshold, to control the vehicle to apply a second torque—the second torque being used to offset the torque currently applied to the vehicle—; or when the angle difference between the actual pose and the desired pose is less than the angle threshold, to stop controlling the steering torque of the vehicle and urge the driver of the vehicle to take over control of the vehicle, wherein the desired pose is the pose of the vehicle when the vehicle travels to a preset position along the planned trajectory, and the planned trajectory is a steering-based lane change trajectory planned for the vehicle, the device. Claim 16 A device according to any one of claims 9 to 15, wherein the processing unit is further configured to determine the desired steering angle based on the control phase information when the road surface adhesion coefficient of the road on which the vehicle is currently traveling is below a coefficient threshold. Claim 17 A device comprising a processor configured to execute a computer program stored in memory to enable the device to perform a method according to any one of claims 1 to 8, as a steering assist control device. Claim 18 In paragraph 17, the device further comprises the memory. Claim 19 An intelligent driving device comprising a device according to any one of paragraphs 9 through 18. Claim 20 A computer-readable storage medium, wherein the computer-readable storage medium stores instructions, and when the instructions are executed by a processor, a method according to any one of claims 1 to 8 is implemented. Claim 21 A computer program product, wherein the computer program product comprises computer program code, and when the computer program code is executed by a processor, a method according to any one of claims 1 to 8 is implemented. Claim 22 A chip, wherein the chip comprises a circuit, and the circuit is configured to perform a method according to any one of claims 1 to 8.