WO2025255992A1 - 换道轨迹控制方法、装置、设备、存储介质及程序产品 - Google Patents

换道轨迹控制方法、装置、设备、存储介质及程序产品

Info

Publication number
WO2025255992A1
WO2025255992A1 PCT/CN2024/120834 CN2024120834W WO2025255992A1 WO 2025255992 A1 WO2025255992 A1 WO 2025255992A1 CN 2024120834 W CN2024120834 W CN 2024120834W WO 2025255992 A1 WO2025255992 A1 WO 2025255992A1
Authority
WO
WIPO (PCT)
Prior art keywords
trajectory
vehicle
lane
changing
driving
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
PCT/CN2024/120834
Other languages
English (en)
French (fr)
Inventor
谢泽宇
马欢
罗逍
赵德芳
刘斌
孙连明
王超
郑震
陈薪宇
祁旭
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
FAW Group Corp
Original Assignee
FAW Group Corp
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by FAW Group Corp filed Critical FAW Group Corp
Publication of WO2025255992A1 publication Critical patent/WO2025255992A1/zh
Pending legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W30/00—Purposes of road vehicle drive control systems not related to the control of a particular sub-unit, e.g. of systems using conjoint control of vehicle sub-units
    • B60W30/18—Propelling the vehicle
    • B60W30/18009—Propelling the vehicle related to particular drive situations
    • B60W30/18163—Lane change; Overtaking manoeuvres

Definitions

  • This application relates to the field of vehicle technology, and in particular to a lane-changing trajectory control method, device, equipment, storage medium, and program product.
  • advanced cruise control is highly popular and frequently used due to its ability to provide significant assistance to drivers during driving.
  • the introduction of lateral control undoubtedly reduces the difficulty of driving in most scenarios.
  • the lane change lever function aims to achieve smooth driving on straight and curved roads and complete comfortable lane changes, assisting the driver in safe and comfortable lane-changing operations.
  • a well-coordinated and reasonable lane-changing plan can not only guide the control algorithm to complete the lane-changing operation but also improve lane-changing comfort and safety.
  • This application provides a lane change trajectory control method, device, equipment, storage medium, and program product to solve the problems of low accuracy in lane change trajectory execution in related technologies, resulting in a poor driving experience.
  • the formula for calculating the error distance is:
  • v is the vehicle speed at the current moment
  • t0 is the current moment
  • ⁇ is the included angle
  • serr is the error distance
  • the method before calculating the angle between the predicted trajectory and the vehicle's desired driving trajectory, the method further includes: obtaining the vehicle's planned trajectory; segmenting the vehicle's planned trajectory to obtain a first planned trajectory before lane change and a second planned trajectory after lane change, wherein the first planned trajectory is planned using a first preset function and the second planned trajectory is planned using a second preset function; and fusing the first preset function and the second preset function to obtain the desired driving trajectory.
  • controlling the vehicle to move closer to the desired driving trajectory according to the error distance includes: if the error distance is less than or equal to a preset threshold, then stopping the control of the vehicle to move closer to the desired driving trajectory.
  • a second aspect of this application provides a lane-changing trajectory control device, comprising: an acquisition module for acquiring driving data at the current moment during a lane-changing process; a prediction module for predicting the vehicle position at the next moment based on the driving data; a determination module for determining the predicted trajectory based on the vehicle position at the current moment and the vehicle position at the next moment; and a control module for calculating the angle between the predicted trajectory and the vehicle's desired driving trajectory, calculating the error distance between the vehicle position at the next moment and the desired position based on the angle, and controlling the vehicle to move closer to the desired driving trajectory according to the error distance.
  • the formula for calculating the error distance is:
  • v is the vehicle speed at the current moment
  • t0 is the current moment
  • ⁇ is the included angle
  • serr is the error distance
  • a fusion module used to obtain the planned trajectory of the vehicle before calculating the angle between the predicted trajectory and the vehicle's desired driving trajectory; to segment the planned trajectory of the vehicle to obtain a first planned trajectory before lane change and a second planned trajectory after lane change, wherein the first planned trajectory is planned using a first preset function and the second planned trajectory is planned using a second preset function; and to fuse the first preset function and the second preset function to obtain the desired driving trajectory.
  • the driving data includes vehicle speed, driving direction, and steering angle
  • the prediction module is further used to predict the vehicle position at the next moment based on the vehicle speed, driving direction, and steering angle.
  • control module is further configured to: obtain the first endpoint position of the predicted trajectory and the second endpoint position of the desired driving trajectory; and calculate the included angle based on the first endpoint position and the second endpoint position.
  • control module is further configured to: if the error distance is less than or equal to a preset threshold, then stop controlling the vehicle to approach the desired driving trajectory.
  • a third aspect of this application provides an electronic device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor.
  • the processor executes the program to perform the lane-changing driving trajectory control method as described above.
  • a fourth aspect of this application provides a computer-readable storage medium having a computer program or instructions stored thereon, which, when executed by a processor, performs the lane-changing driving trajectory control method as described above.
  • a fifth aspect of this application provides a computer program product, including a computer program or instructions, which, when executed, implement the lane-changing trajectory control method as described in the above embodiments.
  • This application's embodiments can calculate the angle between the predicted trajectory and the desired driving trajectory of the vehicle, calculate the error between the vehicle's position and the desired position at the next moment based on the angle, and control the vehicle to move closer to the desired driving trajectory according to the error distance, making the actual driving trajectory closer to the desired driving trajectory, thereby reducing lane-changing trajectory errors, improving lane-changing trajectory execution accuracy, and thus improving the user's driving experience.
  • This solves the technical problems in related technologies such as low lane-changing trajectory execution accuracy, leading to a poor driving experience.
  • Figure 1 is a flowchart of a lane-changing trajectory control method provided according to an embodiment of this application;
  • Figure 2 is a schematic diagram of the error distance provided according to an embodiment of this application.
  • Figure 3 is a schematic diagram of the lane-changing trajectory provided according to an embodiment of this application.
  • Figure 4 is a schematic diagram of the rate of change of the B-spline curve according to an embodiment of this application.
  • Figure 5 is a schematic diagram of the rate of change of a fifth-order polynomial according to an embodiment of this application.
  • Figure 6 is a schematic diagram of the hyperbolic fusion rate of change provided according to an embodiment of this application.
  • Figure 7 is a schematic diagram of the gradient descent control lane-changing trajectory provided according to an embodiment of this application.
  • Figure 8 is a schematic diagram of lane-changing trajectory control provided according to an embodiment of this application.
  • Figure 9 is a schematic diagram of a lane-changing trajectory control device provided according to an embodiment of this application.
  • Figure 10 is a schematic diagram of the structure of an electronic device provided according to an embodiment of this application.
  • the information such as the vehicle's position, heading angle, lateral and longitudinal velocity and acceleration are compared with the expected value.
  • the error information is used as a boundary condition and substituted into the curve equation.
  • PID Proportional Integral Derivative
  • Other control methods are used to reduce the error.
  • the curve is sampled according to the time interval to obtain the path points at each time.
  • the A and B matrices can then be solved to determine the curve.
  • polynomials are widely used in trajectory planning, they are based on ground coordinates and are not suitable for autonomous driving applications. In addition, once the variables in matrices A and B are determined, the trajectory planning path is also determined, lacking flexibility. Finally, lane changing based on polynomials cannot achieve human-like planning with slow start and fast convergence, affecting the driving experience.
  • a lane-changing trajectory control method proposes a lane-changing trajectory control method, apparatus, device, storage medium, and program product.
  • the lane-changing trajectory control method, apparatus, device, storage medium, and program product of this application are described below with reference to the accompanying drawings.
  • This application provides a lane-change trajectory control method. In this method, the angle between the predicted trajectory and the desired trajectory of the vehicle is calculated. Based on the angle, the error between the vehicle's position and the desired position at the next moment is calculated. The vehicle is then controlled to move closer to the desired trajectory according to the error distance, making the actual trajectory more closely resemble the desired trajectory. This solves the problem of low accuracy in lane-change trajectory execution in related technologies, which leads to a poor driving experience.
  • Figure 1 is a flowchart of a lane-changing trajectory control method provided in an embodiment of this application.
  • the lane-changing trajectory control method includes the following steps:
  • step S101 the driving data at the current moment during the vehicle lane change process is obtained.
  • the driving data may include at least one of the following: vehicle speed, driving direction and steering angle, which can be obtained through sensors in the vehicle.
  • step S102 the vehicle position at the next moment is predicted based on the driving data.
  • predicting the vehicle position at the next moment based on driving data includes: predicting the vehicle position at the next moment based on vehicle speed, driving direction and steering angle.
  • a vehicle For example, if a vehicle is traveling at 60 km/h, heading east, and turning 3 degrees to the left, it is predicted that the vehicle will be positioned to the right of the left lane of its current lane at the next moment. Similarly, if a vehicle is traveling at 50 km/h, heading east, and turning 5 degrees to the right, it is predicted that the vehicle will be positioned in the center of the right lane of its current lane at the next moment.
  • step S103 the predicted trajectory is determined based on the vehicle position at the current time and the vehicle position at the next time.
  • the embodiments of this application can determine the predicted trajectory based on the vehicle position at the current moment and the vehicle position at the next moment, that is, the predicted trajectory of the actual driving of the vehicle.
  • the predicted trajectory can be determined by curve fitting between the vehicle position at the current moment and the vehicle position at the next moment.
  • a coordinate system can be established based on the vehicle's current position, with the current position as the origin and the driving direction as the Y-axis.
  • the vehicle's current position, turning angle, speed, and turning direction are all set to the left.
  • the arc length can be derived using the speed and time, and the turning angle at the next moment can be derived using the time interval.
  • the circle and the circle angle can be derived using the arc length, turning angle, current position, and current angle to determine the vehicle's position coordinates and rotation angle at the next moment, thereby generating a predicted trajectory.
  • step S104 the angle between the predicted trajectory and the vehicle's desired driving trajectory is calculated. Based on the angle, the error distance between the vehicle's position and the desired position at the next moment is calculated. The vehicle is then controlled to move closer to the desired driving trajectory according to the error distance.
  • v is the vehicle speed at the current moment
  • t0 is the current moment
  • ⁇ is the included angle
  • serr is the error distance
  • the embodiments of this application can calculate the angle between the predicted trajectory and the vehicle's expected driving trajectory, and calculate the error distance between the vehicle's position and the expected position at the next moment based on the angle.
  • the vehicle is controlled to move closer to the expected driving trajectory according to the error distance, that is, the vehicle is controlled to continuously approach the expected driving trajectory along the angle that decreases, so as to improve the accuracy of the vehicle's lane-changing trajectory planning.
  • calculating the angle between the predicted trajectory and the vehicle's desired driving trajectory includes: obtaining the first endpoint position of the predicted trajectory and the second endpoint position of the desired driving trajectory; and calculating the angle based on the first endpoint position and the second endpoint position.
  • the included angle can be calculated based on the first end point position of the predicted trajectory and the second end point position of the desired driving trajectory, and the included angle can be calculated using the coordinates of the first end point position and the coordinates of the second end point position.
  • the coordinate system can be established with the current position of the vehicle as the origin of the coordinate system and the driving direction as the Y-axis, as shown in Figure 2.
  • the included angle is further calculated based on the coordinates of the first endpoint position and the second endpoint position, and then the error distance is calculated based on the included angle.
  • the method before calculating the angle between the predicted trajectory and the vehicle's desired driving trajectory, the method further includes: obtaining the vehicle's planned trajectory; segmenting the vehicle's planned trajectory to obtain a first planned trajectory before lane change and a second planned trajectory after lane change, wherein the first planned trajectory is planned using a first preset function and the second planned trajectory is planned using a second preset function; and fusing the first preset function and the second preset function to obtain the desired driving trajectory.
  • this application's embodiment can segment the vehicle's planned trajectory into a first planned driving trajectory before lane change and a second planned driving trajectory after lane change.
  • the first planned driving trajectory is planned using a first preset function, such as a B-spline function
  • the second planned driving trajectory is planned using a second preset function, such as a fifth-order polynomial function.
  • the first and second preset functions are then fused to obtain the desired driving trajectory.
  • this application utilizes a two-stage piecewise lateral and longitudinal coordinated stability planning based on the fusion of two functions (also known as hyperbolas) to achieve a slow start-fast convergence in the lane-changing process. This ensures both comfort at the start of the lane change and safety at the end.
  • the overall lane-changing trajectory is planned in two stages, as shown in Figure 3.
  • this application introduces B-spline curve planning into the lane-changing trajectory planning. As shown in Figure 4, the B-spline curve has a low rate of change at the beginning of the lane change, and the rate of change increases slowly.
  • the rate of change gradually increases, causing the control module to gradually increase the steering wheel angle, thus achieving a slow start for the lane change. While maintaining the correct lane change timing, it is also crucial to ensure the steering wheel returns to center quickly at the end of the lane change to minimize the risk of overshoot.
  • this application embeds it into the target lane's return-to-center process, fusing it to obtain a hyperbola (as shown in Figure 6). This causes the steering wheel angle to quickly return to center, achieving rapid convergence during the lane change. Furthermore, to avoid vehicle jerking during trajectory switching, a separate adaptive fusion control module is designed and integrated into the overall control logic, seamlessly integrating the entire lane change process and achieving smooth and stable vehicle control, thus improving ride comfort.
  • controlling the vehicle to move closer to the desired driving trajectory according to the error distance includes: if the error distance is less than or equal to a preset threshold, then stopping the control of the vehicle to move closer to the desired driving trajectory.
  • the preset threshold can be set according to specific circumstances, such as being set to 0.
  • the following specific embodiment illustrates the lane-changing trajectory control method of this application, which mainly involves two parts: predictive error control based on the gradient descent idea and two-stage segmented lateral and longitudinal coordinated precise lane-changing planning based on function fusion.
  • this invention introduces the idea of gradient descent into the control process, uses error prediction for vehicle control, and takes the direction of error descent as input to guide the back-end PID algorithm to perform lane-changing control with the position optimization direction.
  • the error distance serr between the vehicle's expected actual position and the planned desired position is:
  • ⁇ is the included angle.
  • the back-end PID control imposes a threshold limit on the rate of change of the vehicle's steering angle.
  • the gradient descent concept is introduced into the error control. Since the error distance shows a continuously decreasing trend in the ⁇ direction angle, this application uses the direction of decreasing ⁇ as the direction of error control gradient descent, as shown in Figure 8. This assists the PID control in continuously approaching the predicted trajectory, preventing overshoot and swaying phenomena in the PID control.
  • This application employs a two-stage planning approach for the overall lane-changing process.
  • this application incorporates B-spline curve planning into the lane-changing trajectory planning.
  • the B-spline curve exhibits a low rate of change at the beginning of the lane change, and the rate of change increases slowly.
  • the rate of change gradually increases, causing the control module to gradually increase the steering wheel angle, achieving a slow start to the lane change while ensuring the reasonableness of the lane-changing time.
  • Second, at the end of the lane change it is necessary to ensure rapid steering wheel return to center to reduce the risk of overshoot.
  • this application embeds it into the target lane's return-to-center process, fusing it to obtain a hyperbola, as shown in Figure 6. This causes the steering wheel angle to return to center quickly, achieving fast convergence of the lane change.
  • a separate adaptive fusion control module was designed and integrated into the overall control logic, seamlessly integrating the entire lane-changing process and achieving smooth vehicle control, thus improving ride comfort.
  • this application does not utilize deep learning algorithms for training and inference, and does not involve deep convolutional calculations; it only uses machine learning methods for trajectory planning, thus requiring low computing power and achieving accurate planning with low computing power.
  • the angle between the predicted trajectory and the desired trajectory of the vehicle can be calculated. Based on the angle, the error between the vehicle position and the desired position at the next moment can be calculated.
  • the vehicle can be controlled to move closer to the desired trajectory according to the error distance, so that the actual trajectory is closer to the desired trajectory, thereby reducing the error of the lane-changing trajectory, improving the accuracy of the lane-changing trajectory execution, and thus improving the user's driving experience.
  • Figure 9 is a block diagram of the lane-changing driving trajectory control device according to an embodiment of this application.
  • the lane-changing driving trajectory control device 10 includes: an acquisition module 100, a prediction module 200, a determination module 300, and a control module 400.
  • the acquisition module 100 is used to acquire the driving data of the vehicle at the current moment during the lane change process; the prediction module 200 is used to predict the vehicle position at the next moment based on the driving data; the determination module 300 is used to determine the predicted trajectory based on the vehicle position at the current moment and the vehicle position at the next moment; and the control module 400 is used to calculate the angle between the predicted trajectory and the vehicle's expected driving trajectory, calculate the error distance between the vehicle position at the next moment and the expected position based on the angle, and control the vehicle to drive closer to the expected driving trajectory according to the error distance.
  • the formula for calculating the error distance is:
  • the apparatus 10 further includes a fusion module.
  • the driving data includes: vehicle speed, driving direction and steering angle
  • the prediction module 200 is further used to: predict the vehicle position at the next moment based on the vehicle speed, driving direction and steering angle.
  • control module 400 is further configured to: obtain the first endpoint position of the predicted trajectory and the second endpoint position of the desired driving trajectory; and calculate the included angle based on the first endpoint position and the second endpoint position.
  • control module 400 is further configured to: if the error distance is less than or equal to a preset threshold, then stop controlling the vehicle to approach the desired driving trajectory.
  • the angle between the predicted trajectory and the desired trajectory of the vehicle can be calculated, the error between the vehicle position and the desired position at the next moment can be calculated based on the angle, and the vehicle can be controlled to move closer to the desired trajectory according to the error distance, so that the actual trajectory is closer to the desired trajectory, thereby reducing the error of the lane-changing trajectory, improving the accuracy of the lane-changing trajectory execution, and thus improving the user's driving experience.
  • the processor 1002 executes the program, it implements the lane-changing driving trajectory control method provided in the above embodiments.
  • electronic devices also include:
  • Communication interface 1003 is used for communication between memory 1001 and processor 1002.
  • the memory 1001 is used to store computer programs that can run on the processor 1002.
  • the memory 1001 may include high-speed RAM memory, and may also include non-volatile memory, such as at least one disk storage device.
  • the bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc.
  • ISA Industry Standard Architecture
  • PCI Peripheral Component Interconnect
  • EISA Extended Industry Standard Architecture
  • Buses can be categorized as address buses, data buses, control buses, etc. For ease of representation, only one thick line is used in Figure 10, but this does not imply that there is only one bus or one type of bus.
  • the memory 1001, processor 1002, and communication interface 1003 are integrated on a single chip, then the memory 1001, processor 1002, and communication interface 1003 can communicate with each other through an internal interface.
  • the processor 1002 may be a central processing unit (CPU), an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of this application.
  • CPU central processing unit
  • ASIC application-specific integrated circuit
  • This application also provides a computer-readable storage medium storing a computer program or instructions thereon, which, when executed by a processor, implements the above-described lane-changing driving trajectory control method.
  • This application also provides a computer program product, including a computer program or instructions, which, when executed, implement the above-described lane-changing trajectory control method.
  • references to terms such as “one embodiment,” “some embodiments,” “example,” “specific example,” or “some examples,” etc. indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this application.
  • the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example.
  • the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.
  • those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.
  • first and second are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Therefore, features defined with “first” and “second” can be explicitly or implicitly indicated. It implicitly includes at least one of these features. In the description of this application, “N” means at least two, such as two, three, etc., unless otherwise explicitly specified.
  • the various parts of this application can be implemented using hardware, software, firmware, or a combination thereof.
  • the N steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system.
  • the N steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system.
  • ASICs application-specific integrated circuits
  • PGAs programmable gate arrays
  • FPGAs field-programmable gate arrays

Landscapes

  • Engineering & Computer Science (AREA)
  • Automation & Control Theory (AREA)
  • Transportation (AREA)
  • Mechanical Engineering (AREA)
  • Steering Control In Accordance With Driving Conditions (AREA)
  • Control Of Driving Devices And Active Controlling Of Vehicle (AREA)

Abstract

本申请涉及车辆技术领域，特别涉及一种换道轨迹控制方法、装置、设备、存储介质及程序产品，其中，方法包括：获取车辆换道过程中当前时刻的行驶数据；根据行驶数据预测下一个时刻的车辆位置；根据当前时刻的车辆位置和下一个时刻的车辆位置确定预测轨迹；计算预测轨迹和车辆的期望行驶轨迹的夹角，根据夹角计算下一个时刻的车辆位置与期望位置的误差距离，按照误差距离控制车辆靠近期望行驶轨迹行驶。由此，解决了相关技术中换道轨迹执行精准度较低，导致驾驶体验感较差等问题。

Description

换道轨迹控制方法、装置、设备、存储介质及程序产品
相关申请的交叉引用
本申请基于申请号为号202410764046.4，申请日为2024年06月13日申请的中国专利申请提出，并要求该中国专利申请的优先权，该中国专利申请的全部内容在此引入本申请作为参考。
技术领域
本申请涉及车辆技术领域，特别涉及一种换道轨迹控制方法、装置、设备、存储介质及程序产品。
背景技术
在诸多L2智能驾驶行车功能中，高级巡航辅助驾驶功能因其可在驾驶过程中为驾驶员提供较多帮助，备受用户关注，使用率较高。其中，横向控制的引入无疑降低了用户在大多数驾驶场景下的驾驶难度。作为高级巡航行车辅助驾驶功能之一，拨杆换道功能意义在于实现车辆在直道、弯道条件下的平稳行驶，并完成舒适换道，辅助驾驶员进行安全、舒适地换道操作，这对智驾功能的横纵向协同运动规划能力提出了较高要求。一份协调合理的换道规划不仅可以引导控制算法完成换道操作，还可提升换道舒适性与安全性。
此外，由于换道过程中需要根据车辆的实时位置进行实时规划，且受整车多传感器误差限制，自车换道动作往往与期望轨迹有差异，换道轨迹规划执行精准度较低，影响换道控制表现，拉低驾驶感受。
发明内容
本申请提供一种换道轨迹控制方法、装置、设备、存储介质及程序产品，以解决相关技术中换道轨迹执行精准度较低，导致驾驶体验感较差等问题。
本申请第一方面实施例提供一种换道轨迹控制方法，包括以下步骤：获取车辆换道过程中当前时刻的行驶数据；根据行驶数据预测下一个时刻的车辆位置；根据当前时刻的车辆位置和下一个时刻的车辆位置确定预测轨迹；计算预测轨迹和车辆的期望行驶轨迹的夹角，根据夹角计算下一个时刻的车辆位置与期望位置的误差距离，按照误差距离控制车辆靠近期望行驶轨迹行驶。
可选地，误差距离的计算公式为：
其中，v为当前时刻的车速，t0为当前时刻，θ为夹角，serr为误差距离。
可选地，在计算预测轨迹和车辆的期望行驶轨迹的夹角之前，还包括：获取车辆的规划轨迹；对车辆的规划轨迹进行分段处理，得到换道前的第一规划轨迹和换道后的第二规划轨迹，其中，第一规划轨迹采用第一预设函数进行规划，第二规划轨迹采用第二预设函数进行规划；对第一预设函数和第二预设函数进行融合得到期望行驶轨迹。
可选地，行驶数据包括：车速、行驶方向和转向角度，根据行驶数据预测下一个时刻的车辆位置，包括：根据车速、行驶方向和转向角度预测下一时刻的车辆位置。
可选地，计算预测轨迹和车辆的期望行驶轨迹的夹角，包括：获取预测轨迹的第一终点位置和期望行驶轨迹的第二终点位置；根据第一终点位置和第二终点位置计算夹角。
可选地，按照误差距离控制车辆靠近期望行驶轨迹行驶，包括：若误差距离小于或等于预设阈值时，则停止控制车辆靠近期望行驶轨迹行驶。
本申请第二方面实施例提供一种换道行驶轨迹控制装置，包括：获取模块，用于获取车辆换道过程中当前时刻的行驶数据；预测模块，用于根据行驶数据预测下一个时刻的车辆位置；确定模块，用于根据当前时刻的车辆位置和下一个时刻的车辆位置确定预测轨迹；控制模块，用于计算预测轨迹和车辆的期望行驶轨迹的夹角，根据夹角计算下一个时刻的车辆位置与期望位置的误差距离，按照误差距离控制车辆靠近期望行驶轨迹行驶。
可选地，误差距离的计算公式为：
其中，v为当前时刻的车速，t0为当前时刻，θ为夹角，serr为误差距离。
可选地，还包括：融合模块，用于在计算预测轨迹和车辆的期望行驶轨迹的夹角之前，获取车辆的规划轨迹；对车辆的规划轨迹进行分段处理，得到换道前的第一规划轨迹和换道后的第二规划轨迹，其中，第一规划轨迹采用第一预设函数进行规划，第二规划轨迹采用第二预设函数进行规划；对第一预设函数和第二预设函数进行融合得到期望行驶轨迹。
可选地，行驶数据包括：车速、行驶方向和转向角度，预测模块进一步用于：根据车速、行驶方向和转向角度预测下一时刻的车辆位置。
可选地，控制模块进一步用于：获取预测轨迹的第一终点位置和期望行驶轨迹的第二终点位置；根据第一终点位置和第二终点位置计算夹角。
可选地，控制模块进一步用于：若误差距离小于或等于预设阈值时，则停止控制车辆靠近期望行驶轨迹行驶。
本申请第三方面实施例提供一种电子设备，包括：存储器、处理器及存储在存储器上并可在处理器上运行的计算机程序，处理器执行程序，以执行如上述实施例的换道行驶轨迹控制方法。
本申请第四方面实施例提供一种计算机可读存储介质，其上存储有计算机程序或指令，计算机程序或指令被处理器执行时，以执行如上述实施例的换道行驶轨迹控制方法。
本申请第五方面实施例提供一种计算机程序产品，包括计算机程序或指令，计算机程序或指令被执行时，以实现如上述实施例的换道轨迹控制方法。
由此，本申请至少具有如下有益效果：
本申请实施例可以计算车辆的预测轨迹和期望行驶轨迹的夹角，根据夹角计算下一个时刻车辆位置与期望位置的误差，按照误差距离控制车辆靠近期望行驶轨迹，使实际的行驶轨迹更加贴近期望行驶轨迹，以减少换道轨迹的误差，提高换道轨迹执行精准度，进而提高用户的驾驶体验感。由此，解决了相关技术中换道轨迹执行精准度较低，导致驾驶体验感较差等技术问题。
本申请附加的方面和优点将在下面的描述中部分给出，部分将从下面的描述中变得明显，或通过本申请的实践了解到。
附图说明
本申请上述的和/或附加的方面和优点从下面结合附图对实施例的描述中将变得明显和容易理解，其中：
图1为根据本申请实施例提供的换道轨迹控制方法的流程图；
图2为根据本申请实施例提供的误差距离的示意图；
图3为根据本申请实施例提供的换道轨迹的示意图；
图4为根据本申请实施例提供的B样条曲线变化率的示意图；
图5为根据本申请实施例提供的五次多项式变化率的示意图；
图6为根据本申请实施例提供的双曲线融合变化率的示意图；
图7为根据本申请实施例提供的梯度下降控制换道轨迹的示意图；
图8为根据本申请实施例提供的换道轨迹控制的示意图；
图9为根据本申请实施例提供的换道轨迹控制装置的示意图；
图10为根据本申请实施例提供的电子设备的结构示意图。
具体实施方式
下面详细描述本申请的实施例，所述实施例的示例在附图中示出，其中自始至终相同或类似的标号表示相同或类似的元件或具有相同或类似功能的元件。下面通过参考附图描述的实施例是示例性的，旨在用于解释本申请，而不能理解为对本申请的限制。
下面将先对相关技术中车辆的换道轨迹的控制进行阐述，具体如下：
在现实调试过程中，多数主机厂针对换道过程的轨迹规划均以三次/五次多项式进行方程拟合，虽然应用广泛，但其算法机动性较低，设计逻辑并不符合驾驶员的驾驶习惯；另一部分主机厂利用深度学习网络进行换道轨迹规划，虽然提高了规划算法的机动性，但车载芯片算力较低，深度学习网络占用算力较高，仅用于换道轨迹规划中易抢占其他功能算力，影响整体智驾功能表现。
以传统五次多项式曲线插值为例，根据自车位置、航向角、横纵向速度及加速度等信息与期望值作对比，将误差信息作为边界条件带入曲线方程，进行相关系数求解的同时利用PID(Proportional Integral Derivative，比例积分微分)等控制方法减小误差，并按照时间间隔对曲线进行采样，得到各个时刻的路径点。
横纵向位置关于时间t的五次多项式如下：
X(t)＝a0+a1t+a2t2+a3t3+a4t4+a5t5；
Y(t)＝b0+b1t+b2t2+b3t3+b4t4+b5t5；
求解可知：
可知
A＝T-1X,B＝T-1Y；
即可求解A、B矩阵，确定曲线。
虽然多项式在轨迹规划中应用广泛，然而其以地面坐标为基础，不适用于自动驾驶应用；另外，随着矩阵A、B中变量的确定，轨迹规划路径也随之确定，缺乏机动性；最后，基于多项式的换道无法达成慢启动—快收敛的拟人规划，影响驾驶体验。
为解决上述问题，本申请实施例提出了换道轨迹控制方法、装置、设备、存储介质及程序产品，下面参考附图描述本申请实施例的换道轨迹控制方法、装置、设备、存储介质及程序产品。针对上述背景技术中提到的自车换道动作往往与期望轨迹有差异，换道轨迹 规划执行精准度较低，影响换道控制表现，拉低驾驶感受的问题，本申请提供了一种换道轨迹控制方法，在该方法中，可以计算车辆的预测轨迹和期望行驶轨迹的夹角，根据夹角计算下一个时刻车辆位置与期望位置的误差，按照误差距离控制车辆靠近期望行驶轨迹，使实际的行驶轨迹更加贴近期望行驶轨迹。由此，解决了相关技术中换道轨迹执行精准度较低，导致驾驶体验感较差等问题。
具体而言，图1为本申请实施例所提供的一种换道轨迹控制方法的流程图。
如图1所示，该换道轨迹控制方法包括以下步骤：
在步骤S101中，获取车辆换道过程中当前时刻的行驶数据。
其中，行驶数据可以包括：车速、行驶方向和转向角度的至少一种，具体可以通过车辆中的传感器进行获取。
在步骤S102中，根据行驶数据预测下一个时刻的车辆位置。
可以理解的是，本申请实施例可以根据行驶数据预测下一个时刻的车辆位置，具体如下进行阐述。
在本申请实施例中，根据行驶数据预测下一个时刻的车辆位置，包括：根据车速、行驶方向和转向角度预测下一时刻的车辆位置。
可以理解的是，本申请实施例可以根据车速、行驶方向和转向角度预测下一时刻的车辆位置。
比如，车辆的车速为60km/h，行驶方向为向东正前方行驶，转向角度为向左3度，则预测车辆下一时刻在车辆当前车道的左侧车道的靠右边的位置；再比如车辆的车速为50km/h，行驶方向为向东正前方行驶，转向角度为向右5度，则预测车辆下一时刻在车辆当前车道的右侧车道的居中位置。
在步骤S103中，根据当前时刻的车辆位置和下一个时刻的车辆位置确定预测轨迹。
可以理解的是，本申请实施例可以根据当前时刻的车辆位置和下一时刻的车辆位置确定预测轨迹，即车辆实际行驶的预测轨迹，具体可以将当前时刻的车辆位置和下一时刻的车辆位置进行曲线拟合确定预测轨迹。
比如可以以当前时刻的车辆位置建立坐标系，当前位置为原点，行驶方向为Y轴，车辆当前时刻的位置，转向角度为a，车速为b，转向方向为左，利用车速和时间求导弧长利用间隔时间求导下一时刻的转向角度，利用弧长和转向角度，当前时刻的位置，当前角度求导圆形、圆形角，确定下一时刻车辆的位置坐标和旋转角度，进而生成预测轨迹。
在步骤S104中，计算预测轨迹和车辆的期望行驶轨迹的夹角，根据夹角计算下一个时刻的车辆位置与期望位置的误差距离，按照误差距离控制车辆靠近期望行驶轨迹行驶。
其中，误差距离的计算公式为：
其中，v为当前时刻的车速，t0为当前时刻，θ为夹角，serr为误差距离。
可以理解的是，本申请实施例可以计算预测轨迹和车辆的期望行驶轨迹的夹角，并根据夹角计算下一个时刻的车辆位置与期望位置的误差距离，按照误差距离控制车辆靠近期望行驶轨迹行驶，即沿着夹角减小的角度去控制车辆不断贴近期望行驶轨迹，以提高车辆换道轨迹规划的精准度。
在本申请实施例中，计算预测轨迹和车辆的期望行驶轨迹的夹角，包括：获取预测轨迹的第一终点位置和期望行驶轨迹的第二终点位置；根据第一终点位置和第二终点位置计算夹角。
可以理解的是，本申请实施例可以根据预测轨迹的第一终点位置和期望行驶轨迹的第二终点位置计算夹角，通过第一终点位置坐标和第二终点位置坐标计算夹角。
需要说明的是，本申请实施例可以以当前时刻车辆的位置为坐标系的原点，行驶方向为Y轴建立坐标系，如图2所示，进一步根据第一终点位置坐标和第二终点位置坐标计算夹角，进而根据夹角计算误差距离。
在本申请实施例中，在计算预测轨迹和车辆的期望行驶轨迹的夹角之前，还包括：获取车辆的规划轨迹；对车辆的规划轨迹进行分段处理，得到换道前的第一规划轨迹和换道后的第二规划轨迹，其中，第一规划轨迹采用第一预设函数进行规划，第二规划轨迹采用第二预设函数进行规划；对第一预设函数和第二预设函数进行融合得到期望行驶轨迹。
由于目前针对换道过程的轨迹规划大多使用三次多项式进行方程拟合，虽然应用广泛，但驾驶感受的不充分调研导致算法机动性较低，设计逻辑不符合驾驶习惯，且车辆换道开启不应过快，影响驾驶体验。因此本申请实施例可以将车辆的规划轨迹进行分段处理，分为换道前的第一规划行驶轨迹和换道后的第二规划行驶轨迹，对第一规划行驶轨迹采用第一预设函数进行规划，比如采用B样条函数，对第二规划行驶轨迹采用第二预设函数进行规划，比如采用五次多项式函数，对第一预设函数和第二预设函数进行融合得到期望行驶轨迹。
举例而言，本申请基于双函数(也可称作双曲线)融合的两阶段分段横纵向协调稳定规划，实现了换道过程的慢启动—快收敛，保证换道起步舒适性的同时提供了换道结束安全性的保障，对换道轨迹整体过程进行了两阶段规划，其中，换道轨迹如图3所示。首先，换道启动时，与传统多项式规划方程不同，本申请将B样条曲线规划引入到换道轨迹规划中。如图4所示，B样条曲线在换道开始时具有较低的变化率，且变化率增长速度缓慢。行驶一段时间之后，变化率逐渐变大，带动控制模块逐步增加方向盘转角，实现换道慢启 动的同时保证了换道时间的合理性。其次，换道结束时，需保证方向盘快速回正，降低超调风险。
因传统五次多项式在换道结束时变化率较大，如图5所示，本申请将其嵌入至目标车道回正过程中，融合得到双曲线，如图6所示，带动方向盘转角快速回正，实现换道的快收敛带动方向盘转角快速回正，实现换道的快收敛。另外，为避免轨迹切换过程中整车顿挫，单独的适应性融合控制模块被设计并植入到整体控制逻辑中，将整个换道过程融会贯通，实现了整车控制的平稳丝滑，提高乘车舒适性。
需要说明的是，本申请实施例未利用深度学习算法进行训练及推理，不涉及深层次的卷积计算，仅利用机器学习方法进行轨迹规划，因此占用算力不高，实现了在低算力下的精准规划。
在本申请实施例中，按照误差距离控制车辆靠近期望行驶轨迹行驶，包括：若误差距离小于或等于预设阈值时，则停止控制车辆靠近期望行驶轨迹行驶。
其中，预设阈值可以依据具体情况进行设定，比如可以设定为0。
可以理解的是，本申请实施例在误差距离小于或等于预设阈值时，表明此时误差距离已经较小，则停止控制车辆靠近期望行驶轨迹行驶。
下面通过一个具体实施例来阐述本申请的换道轨迹控制方法，主要涉及到两个部分：基于梯度下降思想的预测性误差控制和基于函数融合的两阶段分段横纵向协调精准换道规划。
一、基于梯度下降思想的预测性误差控制
因换道过程中需要根据车辆的实时位置进行实时规划，且受整车多传感器误差限制，自车换道动作往往与期望轨迹有差异，影响换道控制表现，拉低驾驶感受。同时，PID算法应用在换道过程中极易发生换到超调，极端情况下将导致自车冲出目标车道，影响驾驶安全。针对以上问题，为提高换道轨迹规划执行精准度，本申请将基于误差控制的梯度下降思想引入到传统PID控制中，对自车当前位置进行的实时规划结果(期望结果)与自车下帧能够到达的位置(实际预测结果)进行差异性比对，在行车舒适性约束条件下向误差减小的方向进行PID控制，提出了基于梯度下降思想的预测性误差控制，算法示意图如图7所示。
图7中，自车无法在转角变化率的约束下达到期望轨迹位置，以当前方向继续行驶将导致实际轨迹与目标位置存在误差，为减小误差，增加期望轨迹的控制准确率，本发明将梯度下降思想引入控制过程中，利用误差预测进行整车控制，并将误差下降的方向作为输入，引导后端PID算法进行具备位置寻优方向的换道控制。
在当前时刻的车辆坐标系下，自车以速度v行驶，受整车反应时间或传感器表现误差影响，在单位时间t0(一帧，20ms)后，整车预计实际位置与规划期望位置误差距离serr为：
其中，θ为夹角。然而，为保证整车行驶舒适度，后端PID控制对车辆转向角变化率进行了阈值限制。为解决此问题，梯度下降思想被引入到误差控制中。因在θ方向角度中，误差距离呈现不断减小的趋势，本申请将θ减小的方向作为误差控制梯度下降的方向，如图8所示，辅助PID控制不断贴近预测轨迹，防止PID出现超调、晃动等现象。
二、基于函数融合的两阶段分段横纵向协调精准换道规划
当前，针对换道过程的轨迹规划大多使用三次多项式进行方程拟合，虽然应用广泛，但驾驶感受的不充分调研导致算法机动性较低，设计逻辑不符合驾驶习惯。为解决此问题，提高行驶舒适性，首先，本申请对驾驶经验丰富的司机进行了广泛调研，得出结论：换道开启不应过快，影响驾驶体验。其次，设计师通过多方查阅，解析并融合多源信息，对换道曲线进行了贴合司机驾驶习惯的重新设计，提出了基于曲线融合的两阶段分段横纵向协调稳定规划，实现了换道过程的慢启动—快收敛，保证换道起步舒适性的同时提供了换道结束安全性的保障。
本申请对换道整体过程进行了两阶段规划。首先，换道启动时，与传统多项式规划方程不同，本申请将B样条曲线规划引入到换道轨迹规划中。如图4所示，B样条曲线在换道开始时具有较低的变化率，且变化率增长速度缓慢。行驶一段时间之后，变化率逐渐变大，带动控制模块逐步增加方向盘转角，实现换道慢启动的同时保证了换道时间的合理性。其次，换道结束时，需保证方向盘快速回正，降低超调风险。因传统五次多项式在换道结束时变化率较大，如图5所示，本申请将其嵌入至目标车道回正过程中，融合得到双曲线，如图6所示，带动方向盘转角快速回正，实现换道的快收敛带动方向盘转角快速回正，实现换道的快收敛。另外，为避免轨迹切换过程中整车顿挫，单独的适应性融合控制模块被设计并植入到整体控制逻辑中，将整个换道过程融会贯通，实现了整车控制的平稳丝滑，提高乘车舒适性。最后，本申请未利用深度学习算法进行训练及推理，不涉及深层次的卷积计算，仅利用机器学习方法进行轨迹规划，因此占用算力不高，实现了在低算力下的精准规划。
根据本申请实施例提出的换道行驶轨迹控制方法，可以计算车辆的预测轨迹和期望行驶轨迹的夹角，根据夹角计算下一个时刻车辆位置与期望位置的误差，按照误差距离控制车辆靠近期望行驶轨迹，使实际的行驶轨迹更加贴近期望行驶轨迹，以减少换道轨迹的误差，提高换道轨迹执行精准度，进而提高用户的驾驶体验感。
其次参照附图描述根据本申请实施例提出的换道行驶轨迹控制装置。
图9是本申请实施例的换道行驶轨迹控制装置的方框示意图。
如图9所示，该换道行驶轨迹控制装置10包括：获取模块100、预测模块200、确定模块300和控制模块400。
其中，获取模块100用于获取车辆换道过程中当前时刻的行驶数据；预测模块200用于根据行驶数据预测下一个时刻的车辆位置；确定模块300用于根据当前时刻的车辆位置和下一个时刻的车辆位置确定预测轨迹；控制模块400用于计算预测轨迹和车辆的期望行驶轨迹的夹角，根据夹角计算下一个时刻的车辆位置与期望位置的误差距离，按照误差距离控制车辆靠近期望行驶轨迹行驶。
在本申请实施例中，误差距离的计算公式为：
其中，v为当前时刻的车速，t0为当前时刻，θ为夹角，serr为误差距离。
在本申请实施例中，本申请实施例的装置10还包括：融合模块。
其中，融合模块，用于在计算预测轨迹和车辆的期望行驶轨迹的夹角之前，获取车辆的规划轨迹；对车辆的规划轨迹进行分段处理，得到换道前的第一规划轨迹和换道后的第二规划轨迹，其中，第一规划轨迹采用第一预设函数进行规划，第二规划轨迹采用第二预设函数进行规划；对第一预设函数和第二预设函数进行融合得到期望行驶轨迹。
在本申请实施例中，行驶数据包括：车速、行驶方向和转向角度，预测模块200进一步用于：根据车速、行驶方向和转向角度预测下一时刻的车辆位置。
在本申请实施例中，控制模块400进一步用于：获取预测轨迹的第一终点位置和期望行驶轨迹的第二终点位置；根据第一终点位置和第二终点位置计算夹角。
在本申请实施例中，控制模块400进一步用于：若误差距离小于或等于预设阈值时，则停止控制车辆靠近期望行驶轨迹行驶。
需要说明的是，前述对换道行驶轨迹控制方法实施例的解释说明也适用于该实施例的换道行驶轨迹控制装置，此处不再赘述。
根据本申请实施例提出的换道行驶轨迹控制装置，可以计算车辆的预测轨迹和期望行驶轨迹的夹角，根据夹角计算下一个时刻车辆位置与期望位置的误差，按照误差距离控制车辆靠近期望行驶轨迹，使实际的行驶轨迹更加贴近期望行驶轨迹，以减少换道轨迹的误差，提高换道轨迹执行精准度，进而提高用户的驾驶体验感。
图10为本申请实施例提供的电子设备的结构示意图。该电子设备可以包括：
存储器1001、处理器1002及存储在存储器1001上并可在处理器1002上运行的计算机程序。
处理器1002执行程序时实现上述实施例中提供的换道行驶轨迹控制方法。
进一步地，电子设备还包括：
通信接口1003，用于存储器1001和处理器1002之间的通信。
存储器1001，用于存放可在处理器1002上运行的计算机程序。
存储器1001可能包含高速RAM存储器，也可能还包括非易失性存储器(non-volatile memory)，例如至少一个磁盘存储器。
如果存储器1001、处理器1002和通信接口1003独立实现，则通信接口1003、存储器1001和处理器1002可以通过总线相互连接并完成相互间的通信。总线可以是工业标准体系结构(Industry Standard Architecture，简称为ISA)总线、外部设备互连(Peripheral ComponentInterconnect，简称为PCI)总线或扩展工业标准体系结构(Extended Industry Standard Architecture，简称为EISA)总线等。总线可以分为地址总线、数据总线、控制总线等。为便于表示，图10中仅用一条粗线表示，但并不表示仅有一根总线或一种类型的总线。
可选的，在具体实现上，如果存储器1001、处理器1002及通信接口1003，集成在一块芯片上实现，则存储器1001、处理器1002及通信接口1003可以通过内部接口完成相互间的通信。
处理器1002可能是一个中央处理器(Central Processing Unit，简称为CPU)，或者是特定集成电路(Application Specific Integrated Circuit，简称为ASIC)，或者是被配置成实施本申请实施例的一个或多个集成电路。
本申请实施例还提供一种计算机可读存储介质，其上存储有计算机程序或程序，计算机程序或指令被处理器执行时，以实现上述的换道行驶轨迹控制方法。
本申请实施例还提供一种计算机程序产品，包括计算机程序或指令，计算机程序或指令被执行时，以实现上述的换道轨迹控制方法。
在本说明书的描述中，参考术语“一个实施例”、“一些实施例”、“示例”、“具体示例”、或“一些示例”等的描述意指结合该实施例或示例描述的具体特征、结构、材料或者特点包含于本申请的至少一个实施例或示例中。在本说明书中，对上述术语的示意性表述不必须针对的是相同的实施例或示例。而且，描述的具体特征、结构、材料或者特点可以在任一个或N个实施例或示例中以合适的方式结合。此外，在不相互矛盾的情况下，本领域的技术人员可以将本说明书中描述的不同实施例或示例以及不同实施例或示例的特征进行结合和组合。
此外，术语“第一”、“第二”仅用于描述目的，而不能理解为指示或暗示相对重要性或者隐含指明所指示的技术特征的数量。由此，限定有“第一”、“第二”的特征可以明示或者 隐含地包括至少一个该特征。在本申请的描述中，“N个”的含义是至少两个，例如两个，三个等，除非另有明确具体的限定。
流程图中或在此以其他方式描述的任何过程或方法描述可以被理解为，表示包括一个或N个用于实现定制逻辑功能或过程的步骤的可执行指令的代码的模块、片段或部分，并且本申请的优选实施方式的范围包括另外的实现，其中可以不按所示出或讨论的顺序，包括根据所涉及的功能按基本同时的方式或按相反的顺序，来执行功能，这应被本申请的实施例所属技术领域的技术人员所理解。
应当理解，本申请的各部分可以用硬件、软件、固件或它们的组合来实现。在上述实施方式中，N个步骤或方法可以用存储在存储器中且由合适的指令执行系统执行的软件或固件来实现。如，如果用硬件来实现和在另一实施方式中一样，可用本领域公知的下列技术中的任一项或多项的组合来实现：具有用于对数据信号实现逻辑功能的逻辑门电路的离散逻辑电路，具有合适的组合逻辑门电路的专用集成电路，可编程门阵列(PGA)，现场可编程门阵列(FPGA)等。
本技术领域的普通技术人员可以理解实现上述实施例方法携带的全部或部分步骤是可以通过程序来指令相关的硬件完成，所述的程序可以存储于一种计算机可读存储介质中，该程序在执行时，包括方法实施例的步骤之一或其组合。

Claims (10)

  1. 一种换道轨迹控制方法，其特征在于，包括以下步骤：
    获取车辆换道过程中当前时刻的行驶数据；
    根据所述行驶数据预测下一个时刻的车辆位置；
    根据当前时刻的车辆位置和所述下一个时刻的车辆位置确定预测轨迹；
    计算所述预测轨迹和所述车辆的期望行驶轨迹的夹角，根据所述夹角计算下一个时刻的车辆位置与期望位置的误差距离，按照所述误差距离控制所述车辆靠近所述期望行驶轨迹行驶。
  2. 根据权利要求1所述的换道轨迹控制方法，其特征在于，所述误差距离的计算公式为：
    其中，v为当前时刻的车速，t0为当前时刻，θ为夹角，serr为误差距离。
  3. 根据权利要求1所述的换道轨迹控制方法，其特征在于，在计算所述预测轨迹和所述车辆的期望行驶轨迹的夹角之前，还包括：
    获取车辆的规划轨迹；
    对所述车辆的规划轨迹进行分段处理，得到换道前的第一规划轨迹和换道后的第二规划轨迹，其中，所述第一规划轨迹采用第一预设函数进行规划，所述第二规划轨迹采用第二预设函数进行规划；
    对所述第一预设函数和所述第二预设函数进行融合得到期望行驶轨迹。
  4. 根据权利要求1所述的换道轨迹控制方法，其特征在于，所述行驶数据包括：车速、行驶方向和转向角度，所述根据所述行驶数据预测下一个时刻的车辆位置，包括：
    根据所述车速、所述行驶方向和所述转向角度预测下一时刻的车辆位置。
  5. 根据权利要求1所述的换道轨迹控制方法，其特征在于，所述计算所述预测轨迹和所述车辆的期望行驶轨迹的夹角，包括：
    获取所述预测轨迹的第一终点位置和所述期望行驶轨迹的第二终点位置；
    根据所述第一终点位置和所述第二终点位置计算所述夹角。
  6. 根据权利要求1所述的换道轨迹控制方法，其特征在于，所述按照所述误差距离控制所述车辆靠近所述期望行驶轨迹行驶，包括：
    若所述误差距离小于或等于预设阈值时，则停止控制所述车辆靠近所述期望行驶轨迹行驶。
  7. 一种换道行驶轨迹控制装置，其特征在于，包括：
    获取模块，用于获取车辆换道过程中当前时刻的行驶数据；
    预测模块，用于根据所述行驶数据预测下一个时刻的车辆位置；
    确定模块，用于根据当前时刻的车辆位置和所述下一个时刻的车辆位置确定预测轨迹；
    控制模块，用于计算所述预测轨迹和所述车辆的期望行驶轨迹的夹角，根据所述夹角计算下一个时刻的车辆位置与期望位置的误差距离，按照所述误差距离控制所述车辆靠近所述期望行驶轨迹行驶。
  8. 一种电子设备，其特征在于，包括：存储器、处理器及存储在所述存储器上并可在所述处理器上运行的计算机程序，所述处理器执行所述程序，以实现如权利要求1-6任一项所述的换道轨迹控制方法。
  9. 一种计算机可读存储介质，其上存储有计算机程序或指令，其特征在于，所述计算机程序或指令被处理器执行时，以用于实现如权利要求1-6任一项所述的换道轨迹控制方法。
  10. 一种计算机程序产品，包括计算机程序或指令，其特征在于，所述计算机程序或指令被执行时，以实现如权利要求1-6任一项所述的换道轨迹控制方法。
PCT/CN2024/120834 2024-06-13 2024-09-24 换道轨迹控制方法、装置、设备、存储介质及程序产品 Pending WO2025255992A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202410764046.4 2024-06-13
CN202410764046.4A CN118651223A (zh) 2024-06-13 2024-06-13 换道轨迹控制方法、装置、设备、存储介质及程序产品

Publications (1)

Publication Number Publication Date
WO2025255992A1 true WO2025255992A1 (zh) 2025-12-18

Family

ID=92696692

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2024/120834 Pending WO2025255992A1 (zh) 2024-06-13 2024-09-24 换道轨迹控制方法、装置、设备、存储介质及程序产品

Country Status (2)

Country Link
CN (1) CN118651223A (zh)
WO (1) WO2025255992A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN121409636A (zh) * 2025-12-26 2026-01-27 清华大学 车辆轨迹跟踪控制的评价方法及装置

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN118651223A (zh) * 2024-06-13 2024-09-17 中国第一汽车股份有限公司 换道轨迹控制方法、装置、设备、存储介质及程序产品

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102358287A (zh) * 2011-09-05 2012-02-22 北京航空航天大学 一种用于车辆自动驾驶机器人的轨迹跟踪控制方法
US20160107682A1 (en) * 2014-10-15 2016-04-21 Han-Shue Tan System and method for vehicle steering control
CN110979305A (zh) * 2019-03-18 2020-04-10 长城汽车股份有限公司 车辆异常换道控制方法、装置及系统
CN111123950A (zh) * 2019-12-31 2020-05-08 东软睿驰汽车技术（沈阳）有限公司 行车控制方法、装置及车辆
CN111824181A (zh) * 2020-07-16 2020-10-27 北京经纬恒润科技有限公司 一种轨迹规划方法及装置
CN118651223A (zh) * 2024-06-13 2024-09-17 中国第一汽车股份有限公司 换道轨迹控制方法、装置、设备、存储介质及程序产品

Family Cites Families (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110018632B (zh) * 2018-06-22 2020-10-09 长城汽车股份有限公司 一种车辆变道控制方法和装置
CN111609846A (zh) * 2020-04-08 2020-09-01 延锋伟世通电子科技（上海）有限公司 车辆行驶轨迹预测方法、系统、介质及车载终端
CN112687121A (zh) * 2020-12-21 2021-04-20 苏州挚途科技有限公司 行驶轨迹的预测方法、装置及自动驾驶车辆
CN112874536B (zh) * 2021-01-19 2023-09-12 英博超算(南京)科技有限公司 一种智能车辆拨杆换道方法
CN116001811A (zh) * 2022-12-01 2023-04-25 云控智行科技有限公司 一种自动驾驶车辆的轨迹规划方法、装置及设备
CN115617051B (zh) * 2022-12-16 2023-03-28 禾多科技（北京）有限公司 车辆控制方法、装置、设备和计算机可读介质
CN116659538B (zh) * 2023-07-31 2023-10-31 福思(杭州)智能科技有限公司 变道路径规划方法、装置和车载设备

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102358287A (zh) * 2011-09-05 2012-02-22 北京航空航天大学 一种用于车辆自动驾驶机器人的轨迹跟踪控制方法
US20160107682A1 (en) * 2014-10-15 2016-04-21 Han-Shue Tan System and method for vehicle steering control
CN110979305A (zh) * 2019-03-18 2020-04-10 长城汽车股份有限公司 车辆异常换道控制方法、装置及系统
CN111123950A (zh) * 2019-12-31 2020-05-08 东软睿驰汽车技术（沈阳）有限公司 行车控制方法、装置及车辆
CN111824181A (zh) * 2020-07-16 2020-10-27 北京经纬恒润科技有限公司 一种轨迹规划方法及装置
CN118651223A (zh) * 2024-06-13 2024-09-17 中国第一汽车股份有限公司 换道轨迹控制方法、装置、设备、存储介质及程序产品

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN121409636A (zh) * 2025-12-26 2026-01-27 清华大学 车辆轨迹跟踪控制的评价方法及装置

Also Published As

Publication number Publication date
CN118651223A (zh) 2024-09-17

Similar Documents

Publication Publication Date Title
WO2025255992A1 (zh) 换道轨迹控制方法、装置、设备、存储介质及程序产品
CN111169469B (zh) 一种车辆的轨迹规划方法、装置、存储介质及汽车
CN108725585B (zh) 车辆自主泊车的轨迹跟踪控制方法及装置
CN105292116B (zh) 自动驾驶车辆的车道变换路径规划算法
US9457807B2 (en) Unified motion planning algorithm for autonomous driving vehicle in obstacle avoidance maneuver
CN102495631B (zh) 一种无人驾驶车辆跟踪预定轨迹的智能控制方法
CN110789530B (zh) 一种四轮独立转向-独立驱动车辆轨迹跟踪方法和系统
CN102076541A (zh) 用于自动车道居中和车道变换控制系统的路径生成算法
CN113581167A (zh) 一种基于直线圆弧路径的全自动泊车控制方法及控制器
CN114001739B (zh) 一种路径规划方法、装置、车辆及存储介质
CN111688683B (zh) 车辆行驶状态控制方法、装置、计算机设备和存储介质
CN116853293A (zh) 一种基于自适应预瞄路径的非连续曲率轨迹跟踪控制方法
CN115447615B (zh) 基于车辆运动学模型预测控制的轨迹优化方法
WO2023159839A1 (zh) 换道路径规划方法、装置、智能驾驶汽车及存储介质
CN116215546B (zh) 一种车道中心线的预测方法及相关装置
CN115848493A (zh) 基于横摆角速度的车辆高速循迹控制方法及装置
CN114019962B (zh) 车辆变道控制方法、装置和车辆
CN114834441B (zh) 自动泊车的轨迹跟踪控制方法、装置、系统及存储介质
CN115503759A (zh) 车道线航向角补偿方法、装置、电子设备及存储介质
WO2025251472A1 (zh) 基于模型预测的车道保持方法、装置、车辆及存储介质
CN114291092A (zh) 车辆换道控制方法、装置、电子控制单元及存储介质
CN116142183A (zh) 用于车道偏离辅助的控制方法、装置、设备及存储介质
CN115855089A (zh) 一种绕障路径规划方法及装置
WO2025241367A1 (zh) 自适应巡航车速控制方法、装置、车辆、介质及产品
CN113276835A (zh) 车辆转向稳定控制方法、装置、esc及车辆

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 24943147

Country of ref document: EP

Kind code of ref document: A1