CN116653963B - Vehicle lane change control method, system and intelligent driving domain controller - Google Patents

Vehicle lane change control method, system and intelligent driving domain controller Download PDF

Info

Publication number
CN116653963B
CN116653963B CN202310950369.8A CN202310950369A CN116653963B CN 116653963 B CN116653963 B CN 116653963B CN 202310950369 A CN202310950369 A CN 202310950369A CN 116653963 B CN116653963 B CN 116653963B
Authority
CN
China
Prior art keywords
information
planning
vehicle
lane
target
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.)
Active
Application number
CN202310950369.8A
Other languages
Chinese (zh)
Other versions
CN116653963A (en
Inventor
吴鹏
邹欣
计晨
邓晟伟
战策
刘翎予
唐杰
李小刚
潘文博
白颖
陈少佳
陈永春
赵红军
马时骏
刘家辉
李鲁昭
汪锦文
郭璧玺
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.)
Foss Hangzhou Intelligent Technology Co Ltd
Original Assignee
Foss Hangzhou Intelligent Technology Co Ltd
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 Foss Hangzhou Intelligent Technology Co Ltd filed Critical Foss Hangzhou Intelligent Technology Co Ltd
Priority to CN202310950369.8A priority Critical patent/CN116653963B/en
Publication of CN116653963A publication Critical patent/CN116653963A/en
Application granted granted Critical
Publication of CN116653963B publication Critical patent/CN116653963B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • BPERFORMING OPERATIONS; TRANSPORTING
    • B60VEHICLES IN GENERAL
    • B60WCONJOINT 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
    • B60W30/00Purposes 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
    • B60W30/18Propelling the vehicle
    • B60W30/18009Propelling the vehicle related to particular drive situations
    • B60W30/18163Lane change; Overtaking manoeuvres
    • BPERFORMING OPERATIONS; TRANSPORTING
    • B60VEHICLES IN GENERAL
    • B60WCONJOINT 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
    • B60W50/00Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
    • B60W50/0098Details of control systems ensuring comfort, safety or stability not otherwise provided for
    • BPERFORMING OPERATIONS; TRANSPORTING
    • B60VEHICLES IN GENERAL
    • B60WCONJOINT 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
    • B60W50/00Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
    • B60W2050/0001Details of the control system
    • B60W2050/0043Signal treatments, identification of variables or parameters, parameter estimation or state estimation

Landscapes

  • Engineering & Computer Science (AREA)
  • Automation & Control Theory (AREA)
  • Transportation (AREA)
  • Mechanical Engineering (AREA)
  • Human Computer Interaction (AREA)
  • Control Of Driving Devices And Active Controlling Of Vehicle (AREA)
  • Traffic Control Systems (AREA)

Abstract

The application relates to a vehicle lane change control method, a system and an intelligent driving domain controller. The method comprises the following steps: under the condition of triggering and generating a lane change request instruction, acquiring a target junction distance interval for safely converging a driving vehicle into a target lane; determining at least one first time window for the target vehicle to reach the candidate lane sink point and a second time window for the driving vehicle to reach the candidate lane sink point based on the target sink point distance interval; according to the minimum time point in the feasible region time window, determining longitudinal planning information of the driving vehicle and a converging point of a target lane; performing transverse planning by taking the longitudinal planning information as a reference to obtain transverse planning information; and under the condition of generating the re-planning request information, determining the transverse and longitudinal planning track for driving the vehicle to change the track according to the longitudinal planning information, the transverse planning information, the current running track and the conventional planning track based on the re-planning request information. By adopting the method, the accuracy and the safety of lane change decision can be improved.

Description

Vehicle lane change control method, system and intelligent driving domain controller
Technical Field
The application relates to the technical field of driving, in particular to a vehicle lane change control method, a system and an intelligent driving domain controller.
Background
Along with the development of automatic driving technology and auxiliary driving, the vehicle is provided with a certain degree of auxiliary driving function, and the auxiliary driving in simple road conditions can be completed, so that the efficiency of a traffic system is improved, the driving safety is improved, and the traffic jam and the energy consumption are reduced. However, there are complex situations such as huge traffic flow, large speed change, special road conditions between the entrance and the ramp of the expressway, and in order to ensure driving safety, higher requirements are put on the safety and reliability of autonomous lane changing of the vehicle.
However, the conventional autonomous lane change of the vehicle adopts various sensor technologies such as radar, laser radar, a camera, an ultrasonic sensor and the like, and the optimal driving route is judged by collecting the environmental information around the vehicle for sensing and analyzing so as to realize the autonomous lane change of the vehicle. Based on the vehicle-mounted sensor and the vehicle-mounted chip calculation force of the vehicle, when the lane change is carried out on complex road conditions by utilizing the traditional vehicle autonomous lane change mode, the problems of inaccurate lane change decision and safety exist.
Disclosure of Invention
In view of the foregoing, it is desirable to provide a vehicle lane change control method, system and intelligent driving area controller that can solve the problems of inaccurate lane change decisions and safety.
In a first aspect, the present application provides a vehicle lane change control method. The method comprises the following steps:
acquiring vehicle information of a driving vehicle, target state information of a target vehicle, road structure information and lane reference line information;
acquiring a target junction distance interval of the driving vehicle safely converging into the target lane under the condition that the lane changing condition is met and the lane changing request command is triggered to be generated according to the vehicle information, the target state information, the road structure information and the lane reference line information; the target sink-in point distance interval comprises a plurality of candidate sink-in point distances, and each candidate sink-in point distance has a corresponding candidate lane sink-in point;
traversing the alternative lane sink point according to the vehicle information, the target state information and the target sink point distance interval, and determining at least one first time window for the target vehicle to reach the alternative lane sink point;
longitudinally planning the driving vehicle according to the vehicle information, the target state information and the power constraint condition, and determining a second time window for the driving vehicle to reach an alternative lane sink point;
The method comprises the steps that the alternative lane junction is traversed under the condition that a feasible region time window exists according to at least one first time window and at least one second time window, and if longitudinal planning information of a driving vehicle is determined according to the minimum time point in the feasible region time window, the alternative lane junction corresponding to the feasible region time window is determined to be a target lane junction;
taking the longitudinal planning information as a reference, and carrying out transverse planning according to the vehicle information, the target junction distance interval and the target lane junction to obtain transverse planning information;
determining re-planning request information according to the vehicle information, the target state information, the current running track of the driving vehicle and the at least one first time window;
and determining a transverse and longitudinal planning track of the lane change of the driving vehicle according to the longitudinal planning information, the transverse planning information, the current running track and the conventional planning track based on the re-planning request information.
In one embodiment, based on the re-planning request information, determining a transverse and longitudinal planned trajectory of the lane change of the driving vehicle according to the longitudinal planning information, the transverse planning information, the current driving trajectory and a conventional planned trajectory includes:
And if the re-planning request information is that re-planning is needed, determining the real-time transverse and longitudinal planning track as the transverse and longitudinal planning track of the driving vehicle lane change if the real-time transverse and longitudinal planning track determined based on the longitudinal planning information and the transverse planning information exists, and controlling the driving vehicle to execute the transverse and longitudinal planning track.
In one embodiment, the method further comprises:
and under the condition that the re-planning request information is that re-planning is needed, triggering to generate a take-over request if the real-time transverse and longitudinal planning track does not exist and the conventional planning track does not exist.
In one embodiment, the method further comprises:
and under the condition that the re-planning request information is that re-planning is needed, if the real-time transverse and longitudinal planning track does not exist and the conventional planning track exists, determining the conventional planning track as the transverse and longitudinal planning track of the lane change of the driving vehicle, and controlling the driving vehicle to execute the conventional planning track.
In one embodiment, the determining, based on the re-planning request information, a transverse and longitudinal planned trajectory of the lane change of the driving vehicle according to the longitudinal planned information, the transverse planned information, the current driving trajectory and a conventional planned trajectory includes:
And under the condition that the re-planning request information is that re-planning is not needed, determining the current running track as a transverse and longitudinal planning track of the lane change of the driving vehicle, and controlling the driving vehicle to execute the current planning track.
In one embodiment, the determining the feasible region time window for the driving vehicle to change lanes according to the at least one first time window and the second time window includes:
if the at least one first time window and the second time window have coincident time windows, determining the coincident time windows as feasible region time windows; the feasible region time window is used for representing a safety time period for the driving vehicle to sink into the target lane.
In one embodiment, the obtaining a target junction distance interval in which the driving vehicle safely merges into the target lane when the vehicle information, the state information, the road structure information, and the lane reference information satisfy a lane change condition and trigger generation of a lane change request command includes:
determining an initial junction distance interval in which the driving vehicle converges into the target lane under the condition that lane changing conditions are met according to the vehicle information, the state information, the road structure information and the lane reference line information and a lane changing request command is triggered to be generated;
And responding to the lane change request instruction, and performing transverse preprocessing on the initial sink point distance interval according to the road structure information, the lane reference line information and the vehicle information to obtain a target sink point distance interval for safely converging the driving vehicle into the target lane.
In one embodiment, the acquiring vehicle information of the driving vehicle, target state information of the target vehicle, road structure information, and lane reference line information includes:
acquiring vehicle information of a driving vehicle, and sensing fusion information, a map and positioning information of a sensor arranged on the driving vehicle;
carrying out vehicle prediction according to the perception fusion information, the map, the positioning information and the vehicle information to obtain target state information of a target vehicle; the target state information comprises tag information of the target vehicle and target predicted track information of the target vehicle;
and processing according to the perception fusion information, the map, the positioning information and the vehicle information to obtain road structure information and lane reference line information based on the driving vehicle.
In a second aspect, the application further provides a vehicle lane change control system. The system comprises:
The data acquisition module is used for acquiring vehicle information of a driving vehicle, target state information of a target vehicle, road structure information and lane reference line information;
the planning module is used for acquiring a target sink distance interval of the driving vehicle safely converging into the target lane under the condition that the lane changing condition is met and the lane changing request instruction is triggered to be generated according to the vehicle information, the state information, the road structure information and the lane reference line information; the target sink-in point distance interval comprises a plurality of candidate sink-in point distances, and each candidate sink-in point distance has a corresponding candidate lane sink-in point;
the time window determining module is used for traversing the candidate lane sink point according to the vehicle information, the target state information and the target sink point distance interval and determining at least one first time window for the target vehicle to reach the candidate lane sink point;
the longitudinal planning module is used for longitudinally planning the driving vehicle according to the vehicle information, the target state information and the power constraint condition, and determining a second time window for the driving vehicle to reach an alternative lane sink point;
A feasible region determining module, configured to end traversing the candidate lane entry point if a feasible region time window exists according to the at least one first time window and the second time window;
the screening module is used for determining the candidate lane sink point corresponding to the feasible time window as a target lane sink point if the longitudinal planning information of the driving vehicle is determined according to the minimum time point in the feasible time window;
the transverse planning module is used for carrying out transverse planning according to the vehicle information, the target junction distance interval and the target lane junction by taking the longitudinal planning information as a reference to obtain transverse planning information;
the re-planning module is used for determining re-planning request information according to the vehicle information, the target state information, the current running track of the driving vehicle and the at least one first time window;
and the track stitching module is used for determining a transverse and longitudinal planning track of the lane change of the driving vehicle according to the longitudinal planning information, the transverse planning information, the current running track and the conventional planning track based on the re-planning request information.
In a third aspect, the present application also provides an intelligent driving domain controller. The intelligent driving domain controller comprises a memory and a processor, wherein the memory stores a computer program, and the processor realizes the following steps when executing the computer program:
acquiring vehicle information of a driving vehicle, target state information of a target vehicle, road structure information and lane reference line information;
acquiring a target junction distance interval of the driving vehicle safely converging into the target lane under the condition that the lane changing condition is met and the lane changing request command is triggered to be generated according to the vehicle information, the target state information, the road structure information and the lane reference line information; the target sink-in point distance interval comprises a plurality of candidate sink-in point distances, and each candidate sink-in point distance has a corresponding candidate lane sink-in point;
traversing the alternative lane sink point according to the vehicle information, the target state information and the target sink point distance interval, and determining at least one first time window for the target vehicle to reach the alternative lane sink point;
longitudinally planning the driving vehicle according to the vehicle information, the target state information and the power constraint condition, and determining a second time window for the driving vehicle to reach an alternative lane sink point;
The method comprises the steps that the alternative lane junction is traversed under the condition that a feasible region time window exists according to at least one first time window and at least one second time window, and if longitudinal planning information of a driving vehicle is determined according to the minimum time point in the feasible region time window, the alternative lane junction corresponding to the feasible region time window is determined to be a target lane junction;
taking the longitudinal planning information as a reference, and carrying out transverse planning according to the vehicle information, the target junction distance interval and the target lane junction to obtain transverse planning information;
determining re-planning request information according to the vehicle information, the target state information, the current running track of the driving vehicle and the at least one first time window;
and determining a transverse and longitudinal planning track of the lane change of the driving vehicle according to the longitudinal planning information, the transverse planning information, the current running track and the conventional planning track based on the re-planning request information.
According to the vehicle lane change control method, the system and the intelligent driving domain controller, under the condition that lane change conditions are met and lane change request instructions are triggered to be generated according to vehicle information, target state information, road structure information and lane reference line information, namely, under the condition that a driving vehicle is about to change lanes, a target junction distance interval of the driving vehicle safely converging into a target lane is obtained first, a first time window when the driving vehicle reaches an alternative lane junction is determined according to the vehicle information of the driving vehicle, the target state information of the target vehicle and the target junction distance interval, a second time window when the driving vehicle reaches the same alternative lane junction is determined, according to whether a feasible region exists in the first time window and the second time window, and under the condition that longitudinal planning information of the driving vehicle can be determined according to the minimum time point of the feasible region time window, the optimal time and the optimal junction position of the lane change are determined. Furthermore, only the longitudinal planning information for driving the vehicle to reach the destination lane entry point in the shortest time is determined according to the feasible time window, so that the storage and calculation force are saved; and taking the longitudinal planning information as a reference, and carrying out transverse planning according to the vehicle information, the target junction distance interval and the target lane junction to obtain transverse planning information. When the longitudinal planning and the transverse planning are completed, whether the vehicle needs to be subjected to re-planning judgment or not is judged, namely, re-planning request information is determined according to vehicle information, target state information, the current running track of the driving vehicle and at least one first time window, the transverse and longitudinal planning track of the driving vehicle is determined according to the longitudinal planning information, the transverse planning information, the current running track and the conventional planning track based on the re-planning request information, so that the transverse and longitudinal planning control of the driving vehicle is completed, the vehicle can keep stable decision and planning, lane changing can be conducted more intelligently and safely and is converged into the target lane, and the success rate of lane changing of the vehicle is further improved.
Drawings
FIG. 1 is an application environment diagram of a vehicle lane change control method in one embodiment;
FIG. 2 is a flow chart of a method of controlling lane change of a vehicle according to one embodiment;
FIG. 3 is a flow chart of a reprofiling step in one embodiment;
FIG. 4 is a flow chart of a method for determining a target sink distance interval in one embodiment;
FIG. 5 is a schematic diagram of an embodiment of an sink distance interval;
FIG. 6 is a schematic diagram illustrating an application of a lane-change control method for a vehicle according to another embodiment;
FIG. 7 is a block diagram of a vehicle lane change control system in one embodiment;
fig. 8 is an internal structural diagram of the intelligent driving domain controller in one embodiment.
Detailed Description
The present application will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present application more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the application.
The lane change control method for the vehicle provided by the embodiment of the application can be applied to an application environment shown in fig. 1. The application environment includes a driving vehicle 102 and a cloud 104. The driving vehicle 102 is an autonomous vehicle having a manual driving mode, and may be operated in the automatic driving mode or in the manual driving mode during actual traveling. The driving vehicle may include sensors, intelligent driving area controllers, on-board communication devices, high precision positioning devices, other controllers for the vehicle, and human-machine interaction systems. Wherein the sensor comprises one or more of the following: at least one millimeter wave radar, at least one lidar, and at least one camera.
The millimeter wave radar can be used for collecting the transmission time of the light beam reaching the obstacle and the speed of the light beam, and sending collected data to the intelligent driving domain controller. The lidar is a radar system that detects a characteristic quantity such as a position, a speed, etc. of a target by emitting a laser beam. The working principle is that a detection signal (laser beam) is emitted to a target, then a received signal (target echo) reflected from the target is compared with the emission signal, and after proper processing, relevant data of the target, such as parameters of the distance, the azimuth, the altitude, the speed, the gesture, even the shape and the like of the target, can be obtained. The camera is used for collecting surrounding images or videos and sending the collected images or videos to the intelligent driving area controller. The high-precision positioning equipment collects the accurate position information (error is smaller than 20 cm) of the current vehicle and the time information of a global positioning system (global positioning system, GPS) corresponding to the accurate position information, and sends the collected information to the intelligent driving domain controller.
The other controllers of the vehicle can execute control commands of the intelligent driving domain controller and send relevant information such as steering, gear, acceleration, deceleration and the like of the vehicle to the intelligent driving domain controller. The man-machine interaction system can provide an audio-video mode of message interaction between the intelligent vehicle and the driver, and can display the tracks of the vehicle and other vehicles by utilizing the display screen. The intelligent driving domain controller can be arranged in the vehicle, and is specifically realized by a processor, and the processor comprises a central processing unit (central processing unit, CPU) or a device or a module with a processing function. For example, the intelligent driving domain controller may be an on-board mobile data center (mobile data center, MDC). When the automatic driving function is executed, namely in an automatic driving mode, the intelligent driving domain controller sends track planning information to the vehicle-mounted communication equipment, and sends self position information and predicted tracks of other surrounding vehicles to the human-computer interaction system. The vehicle-mounted communication device is used for communicating with other vehicles, receiving other vehicle track prediction information (also described as predicted tracks, track information and the like) and sending the information to the intelligent driving area controller, and sending the track of the vehicle-mounted communication device to other surrounding vehicles; and the cloud communication module is used for sending the sensor information, the positioning information and other controller information on the vehicle to the cloud and receiving the model parameters trained by the cloud.
Based on the application environment, the driving vehicle obtains own vehicle information, target state information of a target vehicle, road structure information and lane reference line information based on devices such as a sensor, vehicle-mounted communication equipment and high-precision positioning equipment; under the condition that the lane changing condition is met and the lane changing request instruction is triggered to be generated according to the vehicle information, the target state information, the road structure information and the lane reference line information, a target junction distance interval for safely converging the driving vehicle into a target lane is obtained; the target sink-point distance interval comprises a plurality of candidate sink-point distances, and each candidate sink-point distance has a corresponding candidate lane sink-point; traversing the alternative lane entry point according to the vehicle information, the target state information and the target entry point distance interval, and determining at least one first time window for the target vehicle to reach the alternative lane entry point; the method comprises the steps that the alternative lane junction is traversed under the condition that a feasible region time window exists according to at least one first time window and at least one second time window, and if longitudinal planning information of a driving vehicle is determined according to the minimum time point in the feasible region time window, the alternative lane junction corresponding to the feasible region time window is determined to be a target lane junction; taking the longitudinal planning information as a reference, and carrying out transverse planning according to the vehicle information, the target junction distance interval and the target lane junction to obtain transverse planning information; determining re-planning request information according to the vehicle information, the target state information, the current running track of the driving vehicle and at least one first time window; and determining the transverse and longitudinal planning track of the lane change of the driving vehicle according to the longitudinal planning information, the transverse planning information, the current driving track and the conventional planning track based on the re-planning request information.
In one embodiment, as shown in fig. 2, a vehicle lane change control method is provided, and the method is applied to the driving vehicle in fig. 1 for illustration, and includes the following steps:
step 202, acquiring vehicle information of a driving vehicle, target state information of a target vehicle, road structure information and lane reference line information.
Wherein the vehicle information of the driving vehicle includes a vehicle speed and a pitch rate; the target vehicle is a vehicle which is converged into the target lane in a preset range, and the target state information comprises target information and target predicted track information. The vehicle information of the driving vehicle, the target state information of the target vehicle, the road structure information and the data acquisition mode of the lane reference line information may be acquired by the existing mode, and will not be described herein.
Step 204, under the condition that the lane changing condition is met and the lane changing request instruction is triggered to be generated according to the vehicle information, the target state information, the road structure information and the lane reference line information, a target junction distance interval for safely converging the driving vehicle into a target lane is obtained; the target sink distance interval comprises a plurality of candidate sink distances, and each candidate sink distance has a corresponding candidate lane sink.
The lane change request instruction carries a lane change type, for example, lane change to the left, lane change to the right, and the like. The lane change condition includes judging a proper lane change timing according to vehicle information, target state information, road structure information and lane reference line information, in other words, judging a proper lane change timing according to information such as a map, a road environment, surrounding vehicle conditions, a vehicle state and the like, and sending lane change request instructions such as lane keeping, lane change to the left, lane change to the right and the like to a subsequent track planning and vehicle control module to execute when the lane change condition is met. The lane change in the present embodiment will be described by taking a vehicle upper ramp as an example.
The target junction distance interval refers to the upper limit and the lower limit of the junction distance of a driving vehicle from a current lane to safely junction into a target lane. The target sink distance interval is determined based on vehicle information of the driving vehicle, road structure information and lane reference line information, and the initial sink distance interval. The initial junction distance interval can be determined based on the acquired map information according to two intersection points of the current lane where the driving vehicle is located and the target lane, and the specific determination mode can be realized in an existing mode. The target junction distance interval comprises a plurality of alternative junction distances, each alternative junction distance has a corresponding alternative lane junction, and each alternative lane junction is on the same straight line.
Step 206, traversing the candidate lane entry point according to the vehicle information, the target state information and the target entry point distance interval, and determining at least one first time window for the target vehicle to reach the candidate lane entry point.
The method for traversing the candidate lane entry point may be based on a target entry point distance interval, traversing and acquiring the candidate lane entry point at a fixed distance interval according to the sequence of the entry point distance from small to large in the target entry point distance interval, determining the arrival time of the target vehicle on the target lane to the candidate lane entry point corresponding to the traversed candidate entry point distance, and determining a window time pair according to the arrival time of the adjacent target vehicle, thereby obtaining the first time window. For example, when 6 target vehicles are on the target lane and travel to the candidate lane sink 1 corresponding to the candidate sink distance 1, a window time pair with 5 sink windows, i.e. 5 first time windows, is obtained.
Further, in order to ensure the safety of the lane change of the vehicle, the offset processing can be performed on the basis of each obtained pair of time windows, so as to obtain a pair of time windows after the safety redundancy processing.
And step 208, longitudinally planning the driving vehicle according to the vehicle information, the target state information and the power constraint condition, and determining a second time window for the driving vehicle to reach the candidate lane sink point.
The power constraint conditions comprise a preset maximum speed, a preset minimum speed, a preset maximum acceleration, a preset minimum acceleration, a preset maximum jerk and a preset minimum jerk of the vehicle. The second time window may be the arrival time of the driving vehicle at the fastest speed and the slowest speed to reach the alternative lane sink corresponding to the traversed alternative sink distance. It will be appreciated that the first time window and the second time window are determined for the same alternate lane entry point.
Specifically, under the condition of triggering generation of a lane change request instruction, longitudinal planning is performed on the driving vehicle according to vehicle information, target state information, a target junction distance interval and power constraint conditions, and a second time window for the driving vehicle to reach an alternative lane junction and longitudinal planning of upper and lower limits of the junction are determined. The longitudinal planning of the upper and lower limits of the afflux points can be understood as follows: in the longitudinal planning of the upper limit and the lower limit of the junction point, the upper limit and the lower limit of the junction point refer to the maximum and the minimum height limit of the vehicle at the junction point, so that the height limit at the junction point is required to be used as a constraint condition when the longitudinal planning is carried out, the height of the vehicle cannot exceed a preset range, and the safety and the traffic efficiency of road traffic are ensured.
And step 210, finishing traversing the candidate lane sink points under the condition that the feasible region time window exists according to at least one of the first time window and the second time window, and determining the candidate lane sink point corresponding to the feasible region time window as a target lane sink point if the longitudinal planning information of the driving vehicle is determined according to the minimum time point in the feasible region time window.
The feasible region time window for driving the vehicle lane change is determined according to at least one first time window and at least one second time window, and the fact that the first time window and the second time window are overlapped is understood to be that a feasible region exists. If at least one first time window and at least one second time window do not overlap, continuing to traverse the next alternative lane sink. And in the case of a feasible region, taking the minimum time point in a time window of the feasible region as the expected time for reaching the sink point, and solving the longitudinal track according to the minimum time point. If the effective longitudinal track is obtained through solution, namely longitudinal planning information is obtained, the candidate lane sink corresponding to the feasible region time window is determined to be an effective optimal sink, namely a target lane sink. The longitudinal track can be calculated by estimating the average vehicle speed under the minimum time of reaching the current traversed candidate lane sink point according to the acquired expected minimum time, and iteratively calculating one longitudinal track based on a JLT algorithm (Jerk limited Trajectory) and the average vehicle speed as a terminal speed constraint and a highest speed limit.
And 212, carrying out transverse planning according to the vehicle information, the target junction distance interval and the target lane junction by taking the longitudinal planning information as a reference to obtain transverse planning information.
The longitudinal planning information comprises a speed spectrum from the current position of the driving vehicle to the destination lane converging point.
Specifically, longitudinal planning information is taken as a reference, each control point of Bessel is calculated according to vehicle information, a target junction distance interval and a target lane junction, and transverse planning information can be further calculated by using a Bernstein basis function according to the calculated control points.
Step 214, determining re-planning request information according to the vehicle information, the target state information, the current driving track of the driving vehicle and at least one first time window.
The re-planning request information comprises re-planning and non-re-planning. The first time window is a real-time window.
Specifically, determining whether a re-planning is required according to the vehicle information, the target state information, the current driving track of the driving vehicle and at least one first time window includes the following cases:
if the driving vehicle has a front vehicle, determining a safety distance value between the driving vehicle and the front vehicle according to the vehicle information, the target state information and the current running track of the driving vehicle, and if the safety distance value is smaller than the target safety distance value, re-planning is needed.
If the driving vehicle has a front vehicle, determining a first time length of the driving vehicle running to the target lane converging point according to the vehicle information, the target state information and the current running track of the driving vehicle, and a second time length of the driving vehicle running to the target lane converging point, wherein the time length difference is larger than a preset time difference, and when the front vehicle possibly changes lanes or is in a speed increasing state, re-planning is needed.
If the time window of the driving vehicle which is determined according to the original planning parameters and runs to the target lane converging point does not coincide with at least one first time window which is acquired in real time, re-planning is needed.
Step 216, based on the re-planning request information, determining a transverse and longitudinal planning track for driving the vehicle to change the track according to the longitudinal planning information, the transverse planning information, the current driving track and the conventional planning track.
Specifically, a real-time transverse and longitudinal planning track is determined according to longitudinal planning information and transverse planning information, track stitching processing is performed according to the real-time transverse and longitudinal planning track, the current running track and a conventional planning track based on re-planning request information, and a transverse and longitudinal planning track of a driving vehicle lane change and a transverse and longitudinal track execution state corresponding to the transverse and longitudinal planning track are determined. Further, the transverse and longitudinal states are determined according to the lane change request instruction, the vehicle information, the transverse and longitudinal planning track and the transverse and longitudinal track execution state corresponding to the transverse and longitudinal planning track, and the state information of the upper ramp, the common driving and the takeover scene is determined.
In the vehicle lane change control method, when lane change conditions are met and lane change request instructions are triggered to be generated according to vehicle information, target state information, road structure information and lane reference line information, namely, when a driving vehicle is about to change lanes, a target junction distance interval of the driving vehicle safely converging into a target lane is acquired, a first time window when the driving vehicle reaches an alternative lane junction is determined according to the vehicle information of the driving vehicle, the target state information of the driving vehicle and the target junction distance interval, a second time window when the driving vehicle reaches the same alternative lane junction is determined, and the optimal opportunity and the optimal junction position of the lane change are determined according to whether a feasible region exists in the first time window and the second time window and when longitudinal planning information of the driving vehicle can be determined according to the minimum time point of the feasible region time window. Furthermore, only the longitudinal planning information for driving the vehicle to reach the destination lane entry point in the shortest time is determined according to the feasible time window, so that the storage and calculation force are saved; and taking the longitudinal planning information as a reference, and carrying out transverse planning according to the vehicle information, the target junction distance interval and the target lane junction to obtain transverse planning information. When the longitudinal planning and the transverse planning are completed, whether the vehicle needs to be subjected to re-planning judgment or not is judged, namely, re-planning request information is determined according to vehicle information, target state information, the current running track of the driving vehicle and at least one first time window, the transverse and longitudinal planning track of the driving vehicle is determined according to the longitudinal planning information, the transverse planning information, the current running track and the conventional planning track based on the re-planning request information, so that the transverse and longitudinal planning control of the driving vehicle is completed, the vehicle can keep stable decision and planning, lane changing can be conducted more intelligently and safely and is converged into the target lane, and the success rate of lane changing of the vehicle is further improved.
Optionally, in one embodiment, determining a feasible region time window for driving the vehicle to change lanes according to at least one first time window and a second time window includes: if the at least one first time window and the second time window have coincident time windows, determining the coincident time windows as feasible region time windows; the feasible region time window is used to characterize a safe period of time for a driving vehicle to merge into a target lane. It can be understood that a window capable of being imported is formed between every 2 vehicles on the target lane, the arrival time of the 2 vehicles is the upper limit and the lower limit of the window time, namely, a first time window is obtained, and if at least one first time window and a second time window have a superposition time window, the fact that the currently selected alternative lane import point can be used as the import point is indicated.
In the running process of the vehicle, the driving environment is complex and changeable, and the situations of unexpected deceleration of the front vehicle, unexpected deceleration of the target front vehicle, unexpected acceleration of the target rear vehicle and the like exist, so that the running planning result cannot meet the safety constraint requirement. Therefore, in order to ensure that the vehicle is stable by keeping a stable decision and planning under the condition of small environmental change, and ensure that the vehicle can be accurately regulated under the condition of large environmental change, the success rate of the ramp-up is increased, and the ramp-up of the vehicle is required to be re-planned.
In one embodiment, as shown in FIG. 3, a schematic diagram of a reprofiling step is provided, comprising:
step 302, determining re-planning request information according to the vehicle information, the target state information, the current driving track of the driving vehicle and at least one first time window.
Step 304, if a re-planning is needed, executing step 306; if yes, judging whether an effective real-time transverse and longitudinal planning track exists, and if yes, executing step 308; if no effective real-time horizontal-vertical planning track exists, judging whether a conventional planning track exists, and if the conventional planning track does not exist, executing step 310; if a conventional planned trajectory exists, step 312 is performed.
The conventional planning track is determined according to a lane keeping planning module and a following speed planning module of the driving vehicle. The heel-and-toe planning module (Follow Speed Planning Module) and the lane-keeping planning module (Lane Keeping Planning Module) are both important modules in an automatic driving system.
The following speed planning module is used for controlling the distance, speed and motion state between the vehicle and the vehicle in front so as to realize intelligent following and following speed running of the vehicle. In the running process, the module can predict the movement track and the running intention of the front vehicle according to the speed and the distance of the front vehicle, so that the running speed and the running direction of the vehicle are adjusted to ensure the safe distance and the proper speed difference with the front vehicle and ensure the stable traffic between vehicles. The lane keeping planning module is used for keeping the vehicle to run along the lane, and aims to ensure that the vehicle runs in the lane and ensure the comfort and safety of the running. The module can sense the lane and surrounding environment of the vehicle in real time through equipment such as a visual sensor, a laser radar, other sensing devices and the like, and formulate a driving strategy and control instructions so as to follow the lane driving rules and avoid traffic accidents. The specific determination mode of the conventional planning track is realized by the prior art, and is not described in detail herein.
And 306, determining the current running track as a transverse and longitudinal planned track of the lane change of the driving vehicle, and controlling the driving vehicle to execute the current planned track.
The track planning of the vehicle is a real-time planning process, and the current planned track is determined by track recursion according to the planned historical track.
And 308, determining the real-time transverse and longitudinal planned track as the transverse and longitudinal planned track of the lane change of the driving vehicle, and controlling the driving vehicle to execute the transverse and longitudinal planned track.
Step 310, triggering generation of a take over request.
Step 312, determining the routine planned track as a transverse and longitudinal planned track of the lane change of the driving vehicle, and controlling the driving vehicle to execute the routine planned track.
In the above embodiment, the re-planning request information is determined according to the vehicle information, the target state information, the current running track of the driving vehicle and at least one first time window, and the optimal planned running track is determined from the real-time horizontal and vertical planning track, the conventional planning track and the current running track based on the re-planning request information, so that the stable decision and planning are ensured under the condition that the environment is not changed greatly, the vehicle is stable, the condition that the environment is changed greatly is also ensured, the vehicle can be regulated, and the success rate of the ramp is increased.
In one embodiment, as shown in fig. 4, a method for determining a target sink distance interval is provided, including the following steps:
step 402, determining an initial junction distance interval for driving the vehicle to junction into the target lane when the lane changing condition is satisfied according to the vehicle information, the state information, the road structure information and the lane reference line information and the lane changing request command is triggered to be generated.
Wherein the initial sink distance interval may be determined based on the map information. Fig. 5 is a schematic diagram of an initial sink distance interval for driving a lane change of a vehicle according to an embodiment, wherein a is a lower limit of the sink distance of the initial sink distance interval, and B is a lower limit of the sink distance of the initial sink distance interval, i.e. the sink distance a is smaller than the sink distance B.
The determining modes of the vehicle information, the state information, the road structure information and the lane reference line information comprise: acquiring vehicle information of a driving vehicle, and sensing fusion information, a map and positioning information of a sensor arranged on the driving vehicle; carrying out vehicle prediction according to the perception fusion information, the map, the positioning information and the vehicle information to obtain target state information of a target vehicle; the target state information comprises label information of a target vehicle and target prediction track information of the target vehicle; and processing according to the perception fusion information, the map, the positioning information and the vehicle information to obtain road structure information and lane reference line information based on the driving vehicle. Vehicle information for driving the vehicle may be obtained through the chassis of the vehicle.
And step 404, responding to the lane change request instruction, and performing transverse preprocessing on the initial junction distance interval according to the road structure information, the lane reference line information and the vehicle information to obtain a target junction distance interval for safely converging the driving vehicle into the target lane.
The transverse preprocessing is to determine a maximum sink point and a minimum sink point of the safe sink, wherein the determination of the maximum sink point can be determined according to the acquired map information, and the sink point distance corresponding to the maximum sink point is the termination distance of the lane change, as shown by C in fig. 5; determination of the minimum sink: the designated entry point may be determined from the initial entry point distance interval, the minimum entry time for driving the vehicle to the lateral displacement of the designated entry point may be calculated, the corresponding minimum longitudinal distance may be determined according to the minimum entry time, the obtained entry point corresponding to the minimum longitudinal distance is the minimum entry point, the minimum longitudinal distance is the starting distance of the lane change, as shown in fig. 5D, and the distance determined by the starting distance and the ending distance is different from the distance determined by the target entry point distance interval. In the above embodiment, when the lane change condition is satisfied according to the vehicle information, the state information, the road structure information and the lane reference line information and the lane change request command is triggered to be generated, the initial junction distance section of the driving vehicle entering the target lane is determined, and the upper limit and the lower limit of the junction distance of the driving vehicle which can safely enter are determined by performing the transverse preprocessing on the initial junction distance section, so that the lane change safety of the vehicle is improved. It should be understood that, although the steps in the flowcharts related to the embodiments described above are sequentially shown as indicated by arrows, these steps are not necessarily sequentially performed in the order indicated by the arrows. The steps are not strictly limited to the order of execution unless explicitly recited herein, and the steps may be executed in other orders. Moreover, at least some of the steps in the flowcharts described in the above embodiments may include a plurality of steps or a plurality of stages, which are not necessarily performed at the same time, but may be performed at different times, and the order of the steps or stages is not necessarily performed sequentially, but may be performed alternately or alternately with at least some of the other steps or stages.
Based on the same inventive concept, the embodiment of the application also provides a vehicle lane change control system for realizing the vehicle lane change control method. The implementation of the solution provided by the system is similar to that described in the above method, so the specific limitation in one or more embodiments of the lane-changing control system for a vehicle provided below may be referred to as the limitation of the lane-changing control method for a vehicle hereinabove, and will not be repeated herein.
The following is an application of the vehicle lane change control method, which is applied to a lane change system for driving a vehicle, and the driving vehicle becomes an up-ramp as shown in fig. 6. The driving vehicle obtains vehicle information of the vehicle through a vehicle chassis, obtains sensing fusion data through equipment such as a sensor arranged on the vehicle end, and obtains map and positioning data, wherein the sensing fusion data comprises target and lane line information. Inputting the acquired perception fusion data, map and positioning information and vehicle information into a prediction module to perform target selection and target track prediction to obtain vehicle information of a target vehicle and target predicted track information of the target vehicle; inputting the acquired perception fusion information, map and positioning information and vehicle information into an environment information module to perform environment information comprehensive processing to obtain road structure information and reference line information based on the vehicle; the obtained vehicle information, target prediction track information, road structure information and reference line information are input into a decision module to carry out an on-ramp decision, and when the on-ramp condition is met, an on-ramp request is generated, and the upper limit and the lower limit of the converging point distance based on the map and the vehicle position, namely an initial converging point distance interval, can be also understood as constraint condition 1.
Before the ramp is not on, ramp planning is needed, and the obtained initial sink distance interval, ramp on request, vehicle information, target state information of a target vehicle, road structure information and lane reference line information are input into a planning module of a ramp system. And based on the determined initial junction distance interval, carrying out transverse pretreatment on the initial junction distance interval according to the road structure information, the lane reference line information and the vehicle information to obtain a target junction distance interval for safely converging the driving vehicle into the target lane, namely, superposing constraint condition 2. According to the vehicle information, the target state information and the target junction distance interval, traversing the alternative lane junction, and performing window searching to obtain at least one first time window for determining that the target vehicle reaches the alternative lane junction, and obtaining window pair information. Outputting longitudinal planning of upper and lower limits of the afflux points and determining a second time window for the driving vehicle to reach the alternative lane afflux point through the longitudinal planner based on the vehicle information, the target information and the target predicted track information, the up-ramp request instruction, the target afflux point distance interval and the dynamic constraint of the driving vehicle. And finishing traversing the candidate lane sink points under the condition that a feasible region time window exists according to at least one first time window and at least one second time window, and determining the candidate lane sink point corresponding to the feasible region time window as a target lane sink point if the longitudinal planning information of the driving vehicle is determined according to the minimum time point in the feasible region time window.
And carrying out transverse planning according to the vehicle information, the target junction distance interval and the target lane junction by using the longitudinal planning information as a reference through a transverse planner to obtain transverse planning information, and carrying out transverse and longitudinal combination according to the determined transverse planning information and the longitudinal planning information to determine a real-time transverse and longitudinal planning track and a corresponding planning state. And carrying out re-planning judgment according to the vehicle information, the target state information, the current running track of the driving vehicle and at least one first time window, and outputting re-planning request information.
If the re-planning request information is that re-planning is needed, determining an effective real-time transverse and longitudinal planning track based on longitudinal planning information and transverse planning information, and determining the real-time transverse and longitudinal planning track as a transverse and longitudinal planning track for driving a vehicle to change lanes; under the condition that the re-planning request information is that re-planning is needed, triggering to generate a take-over request if no real-time transverse and longitudinal planning track exists and no conventional planning track exists; under the condition that the re-planning request information is that re-planning is needed, if the real-time transverse and longitudinal planning track does not exist and the conventional planning track exists, determining the conventional planning track as the transverse and longitudinal planning track for driving the vehicle to change the track; and under the condition that the re-planning request information is that re-planning is not needed, determining the current running track as a transverse and longitudinal planning track for driving the vehicle to change lanes. And determining a transverse and longitudinal planned track of the lane change of the driving vehicle and executing a state on the transverse and longitudinal track corresponding to the transverse and longitudinal planned track. And inputting the execution state of the track corresponding to the track planned in the transverse direction and the longitudinal direction into a state machine according to the track changing request instruction, the vehicle information, the track planned in the transverse direction and the longitudinal direction, outputting the state information of the transverse direction and the longitudinal direction, and outputting the state information of the ramp, the ordinary driving and the takeover scene. Further, the lane keeping planning module outputs lane keeping transverse planning information, and the following speed planning module outputs following speed longitudinal planning information.
In one embodiment, as shown in fig. 7, there is provided a vehicle lane change control system including: a data acquisition module 702, a planning module 704, a time window determination module 706, a longitudinal planning module 708, a feasible region determination module 710, a screening module 712, a lateral planning module 714, a re-planning module 716, and a trajectory stitching module 718, wherein:
the data acquisition module 702 is configured to acquire vehicle information of a driving vehicle, target state information of a target vehicle, road structure information, and lane reference line information.
The planning module 704 is configured to obtain a target junction distance interval in which the driving vehicle safely merges into the target lane when it is determined that the lane changing condition is satisfied and the lane changing request command is triggered to be generated according to the vehicle information, the state information, the road structure information and the lane reference line information; the target sink distance interval comprises a plurality of candidate sink distances, and each candidate sink distance has a corresponding candidate lane sink.
The time window determining module 706 is configured to traverse the candidate lane entry point according to the vehicle information, the target state information, and the target entry point distance interval, and determine at least one first time window for the target vehicle to reach the candidate lane entry point.
The longitudinal planning module 708 is configured to perform longitudinal planning on the driving vehicle according to the vehicle information, the target state information, and the power constraint condition, and determine a second time window when the driving vehicle reaches the candidate lane sink point.
The feasible region determination module 710 is configured to end traversing the candidate lane entry point if a feasible region time window exists according to at least one of the first time window and the second time window.
And the screening module 712 is configured to determine, if the longitudinal planning information of the driving vehicle is determined according to the minimum time point in the feasible time window, an alternative lane sink corresponding to the feasible time window as the target lane sink.
The lateral planning module 714 is configured to perform lateral planning according to the vehicle information, the target junction distance interval, and the target lane junction with reference to the longitudinal planning information, so as to obtain lateral planning information.
The re-planning module 716 is configured to determine re-planning request information according to the vehicle information, the target state information, the current driving track of the driving vehicle, and at least one first time window.
The track stitching module 718 is configured to determine a transverse and longitudinal planned track for driving the vehicle to change the track according to the longitudinal planned information, the transverse planned information, the current driving track and the regular planned track based on the re-planning request information.
According to the vehicle lane change control system, when lane change conditions are met and lane change request instructions are triggered to be generated according to vehicle information, target state information, road structure information and lane reference line information, namely, when a driving vehicle is about to change lanes, a target junction distance interval of the driving vehicle safely converging into a target lane is acquired, a first time window when the driving vehicle reaches an alternative lane junction is determined according to the vehicle information of the driving vehicle, the target state information of the driving vehicle and the target junction distance interval, a second time window when the driving vehicle reaches the same alternative lane junction is determined, and the optimal opportunity and the optimal junction position of the lane change are determined according to whether a feasible region exists in the first time window and the second time window or not and when longitudinal planning information of the driving vehicle can be determined according to the minimum time point of the feasible region time window. Furthermore, only the longitudinal planning information for driving the vehicle to reach the destination lane entry point in the shortest time is determined according to the feasible time window, so that the storage and calculation force are saved; and taking the longitudinal planning information as a reference, and carrying out transverse planning according to the vehicle information, the target junction distance interval and the target lane junction to obtain transverse planning information. When the longitudinal planning and the transverse planning are completed, whether the vehicle needs to be subjected to re-planning judgment or not is judged, namely, re-planning request information is determined according to vehicle information, target state information, the current running track of the driving vehicle and at least one first time window, the transverse and longitudinal planning track of the driving vehicle is determined according to the longitudinal planning information, the transverse planning information, the current running track and the conventional planning track based on the re-planning request information, so that the transverse and longitudinal planning control of the driving vehicle is completed, the vehicle can keep stable decision and planning, lane changing can be conducted more intelligently and safely and is converged into the target lane, and the success rate of lane changing of the vehicle is further improved.
Optionally, in another embodiment, a lane-change control system for a vehicle is provided, which includes, in addition to the data acquisition module 702, the planning module 704, the time window determination module 706, the longitudinal planning module 708, the feasible region determination module 710, the screening module 712, the lateral planning module 714, the re-planning module 716, and the trajectory stitching module 718: planning module, horizontal preprocessing module, data acquisition module, prediction module and environmental information module, wherein:
the track stitching module 718 is further configured to, if the re-planning request information is that re-planning is required, determine an effective real-time transverse and longitudinal planning track based on the longitudinal planning information and the transverse planning information, determine the real-time transverse and longitudinal planning track as a transverse and longitudinal planning track of the driving vehicle for lane change, and control the driving vehicle to execute the transverse and longitudinal planning track.
And the planning module is used for triggering and generating a take-over request if the real-time transverse and longitudinal planning track does not exist and the conventional planning track does not exist under the condition that the re-planning request information is that re-planning is needed.
The track stitching module 718 is further configured to determine, if the re-planning request information indicates that the re-planning is needed, the normal planned track as the planned track of the driving vehicle, and control the driving vehicle to execute the normal planned track if the real-time planned track is not available and the normal planned track is available.
The track stitching module 718 is further configured to determine, when the re-planning request information indicates that re-planning is not needed, the current driving track as a transverse and longitudinal planned track of the lane change of the driving vehicle, and control the driving vehicle to execute the current planned track.
The feasible region determining module 710 is further configured to determine the overlapping time window as a feasible region time window if there is an overlapping time window in the at least one first time window and the second time window; the feasible region time window is used to characterize a safe period of time for a driving vehicle to merge into a target lane.
The time window determining module 706 is further configured to determine an initial junction distance interval in which the driving vehicle is junction into the target lane, when the lane changing condition is satisfied according to the vehicle information, the state information, the road structure information, and the lane reference line information and the lane changing request command is triggered to be generated;
and the transverse preprocessing module is used for responding to the lane changing request instruction, and carrying out transverse preprocessing on the initial sink distance interval according to the road structure information, the lane reference line information and the vehicle information.
The time window determining module 706 is further configured to perform a lateral preprocessing on the initial sink distance interval according to the lateral preprocessing module, so as to obtain a target sink distance interval where the driving vehicle safely sinks into the target lane.
The data acquisition module is used for acquiring vehicle information of a driving vehicle, and sensing fusion information, a map and positioning information of a sensor arranged on the driving vehicle.
The prediction module is used for predicting the vehicle according to the perception fusion information, the map, the positioning information and the vehicle information to obtain the target state information of the target vehicle; the target state information includes tag information of the target vehicle and target predicted trajectory information of the target vehicle.
And the environment information module is used for processing according to the perception fusion information, the map, the positioning information and the vehicle information to obtain road structure information and lane reference line information based on driving vehicles.
The various modules in the vehicle lane change control system described above may be implemented in whole or in part in software, hardware, or a combination thereof. The above modules may be embedded in hardware or independent of a processor in the intelligent driving domain controller, or may be stored in software in a memory in the intelligent driving domain controller, so that the processor may call and execute operations corresponding to the above modules.
In one embodiment, an intelligent driving domain controller is provided, the internal structure of which may be as shown in fig. 8. The computer device includes a processor, a memory, and a network interface connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The database of the computer device is used for storing related data such as perception fusion information, maps, positioning information, vehicle information and the like. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a vehicle lane change control method.
It will be appreciated by those skilled in the art that the structure shown in fig. 8 is merely a block diagram of a portion of the structure associated with the present inventive arrangements and is not limiting of the intelligent driving domain controller to which the present inventive arrangements are applied, and that a particular intelligent driving domain controller may include more or fewer components than shown, or may combine certain components, or have a different arrangement of components.
In one embodiment, an intelligent driving domain controller is provided, including a memory and a processor, where the memory stores a computer program, and the processor implements the steps of the method embodiments described above when the processor executes the computer program.
It should be noted that, the data related to the vehicle related to the present application are all information and data authorized by the user or fully authorized by each party, and the collection, use and processing of the related data are required to comply with the related laws and regulations and standards of the related country and region.
Those skilled in the art will appreciate that implementing all or part of the above described methods may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed, may comprise the steps of the embodiments of the methods described above. Any reference to memory, database, or other medium used in embodiments provided herein may include at least one of non-volatile and volatile memory. The nonvolatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical Memory, high density embedded nonvolatile Memory, resistive random access Memory (ReRAM), magnetic random access Memory (Magnetoresistive Random Access Memory, MRAM), ferroelectric Memory (Ferroelectric Random Access Memory, FRAM), phase change Memory (Phase Change Memory, PCM), graphene Memory, and the like. Volatile memory can include random access memory (Random Access Memory, RAM) or external cache memory, and the like. By way of illustration, and not limitation, RAM can be in the form of a variety of forms, such as Static Random access memory (Static Random access memory AccessMemory, SRAM) or dynamic Random access memory (Dynamic Random Access Memory, DRAM), and the like. The databases referred to in the embodiments provided herein may include at least one of a relational database and a non-relational database. The non-relational database may include, but is not limited to, a blockchain-based distributed database, and the like. The processor referred to in the embodiments provided in the present application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic unit, a data processing logic unit based on quantum computing, or the like, but is not limited thereto.
The technical features of the above embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.
The foregoing examples illustrate only a few embodiments of the application and are described in detail herein without thereby limiting the scope of the application. It should be noted that it will be apparent to those skilled in the art that several variations and modifications can be made without departing from the spirit of the application, which are all within the scope of the application. Accordingly, the scope of the application should be assessed as that of the appended claims.

Claims (10)

1. A vehicle lane-change control method, characterized by comprising:
acquiring vehicle information of a driving vehicle, target state information of a target vehicle, road structure information and lane reference line information;
acquiring a target junction distance interval of the driving vehicle safely converging into a target lane under the condition that the lane changing condition is met and the lane changing request command is triggered to be generated according to the vehicle information, the target state information, the road structure information and the lane reference line information; the target sink-in point distance interval comprises a plurality of candidate sink-in point distances, and each candidate sink-in point distance has a corresponding candidate lane sink-in point;
Traversing the alternative lane sink point according to the vehicle information, the target state information and the target sink point distance interval, and determining at least one first time window for the target vehicle to reach the alternative lane sink point;
longitudinally planning the driving vehicle according to the vehicle information, the target state information and the power constraint condition, and determining a second time window for the driving vehicle to reach an alternative lane sink point;
the method comprises the steps that the alternative lane junction is traversed under the condition that a feasible region time window exists according to at least one first time window and at least one second time window, and if longitudinal planning information of a driving vehicle is determined according to the minimum time point in the feasible region time window, the alternative lane junction corresponding to the feasible region time window is determined to be a target lane junction;
taking the longitudinal planning information as a reference, and carrying out transverse planning according to the vehicle information, the target junction distance interval and the target lane junction to obtain transverse planning information;
determining re-planning request information according to the vehicle information, the target state information, the current running track of the driving vehicle and the at least one first time window;
And determining a transverse and longitudinal planning track of the lane change of the driving vehicle according to the longitudinal planning information, the transverse planning information, the current running track and the conventional planning track based on the re-planning request information.
2. The method of claim 1, wherein determining a lateral-longitudinal planned trajectory of the driving vehicle lane change based on the re-planning request information from the longitudinal planning information, the lateral planning information, the current travel trajectory, and a conventional planned trajectory comprises:
and under the condition that the re-planning request information is that re-planning is needed, if an effective real-time transverse and longitudinal planning track is determined based on the longitudinal planning information and the transverse planning information, determining the real-time transverse and longitudinal planning track as the transverse and longitudinal planning track of the driving vehicle lane change, and controlling the driving vehicle to execute the transverse and longitudinal planning track.
3. The method according to claim 2, wherein the method further comprises:
and under the condition that the re-planning request information is that re-planning is needed, triggering to generate a take-over request if the real-time transverse and longitudinal planning track does not exist and the conventional planning track does not exist.
4. The method according to claim 2, wherein the method further comprises:
and under the condition that the re-planning request information is that re-planning is needed, if the real-time transverse and longitudinal planning track does not exist and the conventional planning track exists, determining the conventional planning track as the transverse and longitudinal planning track of the lane change of the driving vehicle, and controlling the driving vehicle to execute the conventional planning track.
5. The method of claim 1, wherein the determining a lateral-longitudinal planned trajectory of the driving vehicle lane change based on the re-planning request information from the longitudinal planning information, the lateral planning information, the current driving trajectory, and a regular planned trajectory comprises:
and under the condition that the re-planning request information is that re-planning is not needed, determining the current running track as a transverse and longitudinal planning track of the lane change of the driving vehicle, and controlling the driving vehicle to execute the current running track.
6. The method of claim 1, wherein the determining a feasible region time window for the driving vehicle to change lanes based on the at least one first time window and the second time window comprises:
If the at least one first time window and the second time window have coincident time windows, determining the coincident time windows as feasible region time windows; the feasible region time window is used for representing a safety time period for the driving vehicle to sink into the target lane.
7. The method according to claim 1, wherein the acquiring a target junction distance zone where the driving vehicle safely merges into the target lane in a case where lane change conditions are satisfied according to the vehicle information, the state information, the road structure information, and the lane reference information and a trigger to generate a lane change request instruction, comprises:
determining an initial junction distance interval in which the driving vehicle converges into the target lane under the condition that lane changing conditions are met according to the vehicle information, the state information, the road structure information and the lane reference line information and a lane changing request command is triggered to be generated;
and responding to the lane change request instruction, and performing transverse preprocessing on the initial sink point distance interval according to the road structure information, the lane reference line information and the vehicle information to obtain a target sink point distance interval for safely converging the driving vehicle into the target lane.
8. The method according to claim 1, wherein the acquiring vehicle information of the driving vehicle, target state information of the target vehicle, road structure information, and lane reference line information includes:
acquiring vehicle information of a driving vehicle, and sensing fusion information, a map and positioning information of a sensor arranged on the driving vehicle;
carrying out vehicle prediction according to the perception fusion information, the map, the positioning information and the vehicle information to obtain target state information of a target vehicle; the target state information comprises tag information of the target vehicle and target predicted track information of the target vehicle;
and processing according to the perception fusion information, the map, the positioning information and the vehicle information to obtain road structure information and lane reference line information based on the driving vehicle.
9. A lane-change control system for a vehicle, the system comprising:
the data acquisition module is used for acquiring vehicle information of a driving vehicle, target state information of a target vehicle, road structure information and lane reference line information;
the planning module is used for acquiring a target sink distance interval of the driving vehicle safely converging into a target lane under the condition that the lane changing condition is met and the lane changing request instruction is triggered to be generated according to the vehicle information, the state information, the road structure information and the lane reference line information; the target sink-in point distance interval comprises a plurality of candidate sink-in point distances, and each candidate sink-in point distance has a corresponding candidate lane sink-in point;
The time window determining module is used for traversing the candidate lane sink point according to the vehicle information, the target state information and the target sink point distance interval and determining at least one first time window for the target vehicle to reach the candidate lane sink point;
the longitudinal planning module is used for longitudinally planning the driving vehicle according to the vehicle information, the target state information and the power constraint condition, and determining a second time window for the driving vehicle to reach an alternative lane sink point;
a feasible region determining module, configured to end traversing the candidate lane entry point if a feasible region time window exists according to the at least one first time window and the second time window;
the screening module is used for determining the candidate lane sink point corresponding to the feasible time window as a target lane sink point if the longitudinal planning information of the driving vehicle is determined according to the minimum time point in the feasible time window;
the transverse planning module is used for carrying out transverse planning according to the vehicle information, the target junction distance interval and the target lane junction by taking the longitudinal planning information as a reference to obtain transverse planning information;
The re-planning module is used for determining re-planning request information according to the vehicle information, the target state information, the current running track of the driving vehicle and the at least one first time window;
and the track stitching module is used for determining a transverse and longitudinal planning track of the lane change of the driving vehicle according to the longitudinal planning information, the transverse planning information, the current running track and the conventional planning track based on the re-planning request information.
10. An intelligent driving domain controller comprising a memory and a processor, the memory storing a computer program, characterized in that the processor implements the steps of the method of any one of claims 1 to 8 when the computer program is executed.
CN202310950369.8A 2023-07-31 2023-07-31 Vehicle lane change control method, system and intelligent driving domain controller Active CN116653963B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202310950369.8A CN116653963B (en) 2023-07-31 2023-07-31 Vehicle lane change control method, system and intelligent driving domain controller

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202310950369.8A CN116653963B (en) 2023-07-31 2023-07-31 Vehicle lane change control method, system and intelligent driving domain controller

Publications (2)

Publication Number Publication Date
CN116653963A CN116653963A (en) 2023-08-29
CN116653963B true CN116653963B (en) 2023-10-20

Family

ID=87724601

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202310950369.8A Active CN116653963B (en) 2023-07-31 2023-07-31 Vehicle lane change control method, system and intelligent driving domain controller

Country Status (1)

Country Link
CN (1) CN116653963B (en)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117698752B (en) * 2024-02-05 2024-05-14 苏州万集车联网技术有限公司 Target screening method and device

Citations (15)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DE102013223428A1 (en) * 2013-11-18 2015-05-21 Robert Bosch Gmbh Method and driver assistance device for supporting lane changes or overtaking maneuvers of a motor vehicle
CN110203202A (en) * 2019-04-29 2019-09-06 长安大学 A kind of lane-change auxiliary method for early warning and device based on Driver intention recognition
CN110532846A (en) * 2019-05-21 2019-12-03 华为技术有限公司 Automatic lane-change method, apparatus and storage medium
CN111923910A (en) * 2020-09-14 2020-11-13 福瑞泰克智能系统有限公司 Method for planning lane change of vehicle, autonomous vehicle and storage medium
CN112477884A (en) * 2020-11-11 2021-03-12 东风汽车集团有限公司 Automatic driving control method and device and vehicle
WO2021116345A1 (en) * 2019-12-13 2021-06-17 Renault S.A.S System and method for predicting the trajectory of a vehicle
CN113366497A (en) * 2018-11-21 2021-09-07 伟摩有限责任公司 Agent prioritization for autonomous vehicles
CN113386795A (en) * 2021-07-05 2021-09-14 西安电子科技大学芜湖研究院 Intelligent decision-making and local track planning method for automatic driving vehicle and decision-making system thereof
CN114364591A (en) * 2019-06-06 2022-04-15 移动眼视觉科技有限公司 Navigation system and method for vehicle
CN115027505A (en) * 2022-07-28 2022-09-09 广州小鹏自动驾驶科技有限公司 Method, device and system for re-planning track of vehicle, vehicle and storage medium
CN115107808A (en) * 2022-07-28 2022-09-27 云控智行科技有限公司 Vehicle running track planning method and device
CN115179949A (en) * 2022-09-13 2022-10-14 毫末智行科技有限公司 Vehicle pressure speed changing control method, device, equipment and storage medium
US11526721B1 (en) * 2020-02-21 2022-12-13 Zoox, Inc. Synthetic scenario generator using distance-biased confidences for sensor data
CN115900738A (en) * 2022-10-17 2023-04-04 广州小鹏自动驾驶科技有限公司 Path planning method, device, vehicle and storage medium
CN115973158A (en) * 2023-03-20 2023-04-18 北京集度科技有限公司 Lane changing track planning method, vehicle, electronic equipment and computer program product

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US11008000B2 (en) * 2017-06-20 2021-05-18 Motional Ad Llc Risk processing for vehicles having autonomous driving capabilities

Patent Citations (15)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DE102013223428A1 (en) * 2013-11-18 2015-05-21 Robert Bosch Gmbh Method and driver assistance device for supporting lane changes or overtaking maneuvers of a motor vehicle
CN113366497A (en) * 2018-11-21 2021-09-07 伟摩有限责任公司 Agent prioritization for autonomous vehicles
CN110203202A (en) * 2019-04-29 2019-09-06 长安大学 A kind of lane-change auxiliary method for early warning and device based on Driver intention recognition
CN110532846A (en) * 2019-05-21 2019-12-03 华为技术有限公司 Automatic lane-change method, apparatus and storage medium
CN114364591A (en) * 2019-06-06 2022-04-15 移动眼视觉科技有限公司 Navigation system and method for vehicle
WO2021116345A1 (en) * 2019-12-13 2021-06-17 Renault S.A.S System and method for predicting the trajectory of a vehicle
US11526721B1 (en) * 2020-02-21 2022-12-13 Zoox, Inc. Synthetic scenario generator using distance-biased confidences for sensor data
CN111923910A (en) * 2020-09-14 2020-11-13 福瑞泰克智能系统有限公司 Method for planning lane change of vehicle, autonomous vehicle and storage medium
CN112477884A (en) * 2020-11-11 2021-03-12 东风汽车集团有限公司 Automatic driving control method and device and vehicle
CN113386795A (en) * 2021-07-05 2021-09-14 西安电子科技大学芜湖研究院 Intelligent decision-making and local track planning method for automatic driving vehicle and decision-making system thereof
CN115027505A (en) * 2022-07-28 2022-09-09 广州小鹏自动驾驶科技有限公司 Method, device and system for re-planning track of vehicle, vehicle and storage medium
CN115107808A (en) * 2022-07-28 2022-09-27 云控智行科技有限公司 Vehicle running track planning method and device
CN115179949A (en) * 2022-09-13 2022-10-14 毫末智行科技有限公司 Vehicle pressure speed changing control method, device, equipment and storage medium
CN115900738A (en) * 2022-10-17 2023-04-04 广州小鹏自动驾驶科技有限公司 Path planning method, device, vehicle and storage medium
CN115973158A (en) * 2023-03-20 2023-04-18 北京集度科技有限公司 Lane changing track planning method, vehicle, electronic equipment and computer program product

Non-Patent Citations (3)

* Cited by examiner, † Cited by third party
Title
基于Frenet坐标系的智能车运动规划研究;王沙晶;陈建业;;移动电源与车辆(第01期);26-33 *
基于深度学习的驾驶员换道行为预测;惠飞;魏诚;;计算机系统应用(第03期);59-67 *
高速场景相邻前车驾驶行为识别及意图预测;张海伦;付锐;;交通运输系统工程与信息(第01期);44-50 *

Also Published As

Publication number Publication date
CN116653963A (en) 2023-08-29

Similar Documents

Publication Publication Date Title
CN108983781B (en) Environment detection method in unmanned vehicle target search system
CN111750886B (en) Local path planning method and device
CN110562258B (en) Method for vehicle automatic lane change decision, vehicle-mounted equipment and storage medium
JP6838241B2 (en) Mobile behavior prediction device
CN111552284A (en) Method, device, equipment and medium for planning local path of unmanned vehicle
US20190018412A1 (en) Control Method for Autonomous Vehicles
Raju et al. Performance of open autonomous vehicle platforms: Autoware and Apollo
CN107664993A (en) A kind of paths planning method
US11467584B2 (en) Multi-layer grid based open space planner
CN116653963B (en) Vehicle lane change control method, system and intelligent driving domain controller
Mandal et al. Lyft 3D object detection for autonomous vehicles
RU2757234C2 (en) Method and system for calculating data for controlling the operation of a self-driving car
US20220153296A1 (en) Trajectory planning with obstacle avoidance for autonomous driving vehicles
KR20230004212A (en) Cross-modality active learning for object detection
KR20210118995A (en) Method and apparatus for generating u-turn path of autonomous vehicle based on deep learning
CN118235180A (en) Method and device for predicting drivable lane
CN115230719A (en) Driving track planning method and device
US20230382368A1 (en) System, Method, and Computer Program Product for Identification of Intention and Prediction for Parallel Parking Vehicles
CN117916682A (en) Motion planning using a time-space convex corridor
US20240230366A1 (en) Handling Unmapped Speed Limit Signs
CN114217601B (en) Hybrid decision method and system for self-driving
CN117826825B (en) Unmanned mining card local path planning method and system based on artificial potential field algorithm
US20230229826A1 (en) Method for assigning a lane relationship between an autonomous vehicle and other actors near an intersection
US11787405B1 (en) Active coasting in traffic
CN117073709B (en) Path planning method, path planning device, computer equipment and storage medium

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant