CN112265542B - Automatic driving meeting scene processing method and device and vehicle - Google Patents

Automatic driving meeting scene processing method and device and vehicle Download PDF

Info

Publication number
CN112265542B
CN112265542B CN202010951662.2A CN202010951662A CN112265542B CN 112265542 B CN112265542 B CN 112265542B CN 202010951662 A CN202010951662 A CN 202010951662A CN 112265542 B CN112265542 B CN 112265542B
Authority
CN
China
Prior art keywords
vehicle
meeting
type
judging
self
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
CN202010951662.2A
Other languages
Chinese (zh)
Other versions
CN112265542A (en
Inventor
张双琳
颜波
徐成
张放
李晓飞
张德兆
王肖
霍舒豪
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.)
Wuhan Zhixing Technology Co ltd
Original Assignee
Wuhan Zhixing 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 Wuhan Zhixing Technology Co ltd filed Critical Wuhan Zhixing Technology Co ltd
Priority to CN202010951662.2A priority Critical patent/CN112265542B/en
Publication of CN112265542A publication Critical patent/CN112265542A/en
Priority to PCT/CN2021/117764 priority patent/WO2022053026A1/en
Application granted granted Critical
Publication of CN112265542B publication Critical patent/CN112265542B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W30/00—Purposes of road vehicle drive control systems not related to the control of a particular sub-unit, e.g. of systems using conjoint control of vehicle sub-units
    • B60W30/08—Active safety systems predicting or avoiding probable or impending collision or attempting to minimise its consequences
    • B60W30/09—Taking automatic action to avoid collision, e.g. braking and steering
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W30/00—Purposes of road vehicle drive control systems not related to the control of a particular sub-unit, e.g. of systems using conjoint control of vehicle sub-units
    • B60W30/08—Active safety systems predicting or avoiding probable or impending collision or attempting to minimise its consequences
    • B60W30/095—Predicting travel path or likelihood of collision
    • B60W30/0956—Predicting travel path or likelihood of collision the prediction being responsive to traffic or environmental parameters
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W30/00—Purposes of road vehicle drive control systems not related to the control of a particular sub-unit, e.g. of systems using conjoint control of vehicle sub-units
    • B60W30/18—Propelling the vehicle
    • B60W30/18009—Propelling the vehicle related to particular drive situations

Landscapes

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

Abstract

The invention discloses a method for processing an automatic driving meeting scene, which comprises the following steps: step S1, vehicle meeting state judgment: judging whether the vehicle is in a vehicle meeting state, and when the vehicle is in the vehicle meeting state, continuing to execute the step S2; step S2, meeting type determination processing: and classifying the current meeting state, judging the corresponding meeting type, and executing the corresponding meeting processing operation according to the preset corresponding relation between a plurality of different meeting types and a plurality of different meeting processing operations. In addition, the invention also discloses an automatic driving meeting scene processing device and a vehicle. The processing method and the device for the automatic driving meeting scene and the vehicle have scientific design, and can actively adjust the speed and the transverse position of the vehicle when meeting the meeting scene, thereby reducing the vehicle speed at the meeting moment, simultaneously increasing the transverse spacing distance between the vehicle and the opposite vehicle, being beneficial to improving the driving safety and meeting the driving habits of people.

Description

Automatic driving meeting scene processing method and device and vehicle
Technical Field
The invention relates to the technical field of automatic driving, in particular to a method and a device for processing an automatic driving meeting scene and a vehicle.
Background
As the application fields of the autonomous vehicles are increasingly expanded, driving scenes to be processed are also gradually increased. The meeting is a common traffic scene in the driving process, and in the traffic rules, a plurality of systems and regulations are provided for meeting.
The vehicles meeting is that opposite running vehicles (including the self vehicle and the opposite vehicle) pass through in a staggered way at a certain same place at the same time point. The speed of the vehicles is properly controlled according to the conditions of roads, climate, vehicle types and the like during meeting, a sufficient transverse distance is kept, and the relevant meeting regulations are strictly observed. Because certain meeting working conditions have certain collision risks, the psychological and operational confusion of human drivers can be caused.
At present, the existing processing scheme of the automatic driving field for the obstacle can be roughly divided into two types of sampling and optimizing. The method comprises the steps of searching a guide blank area by performing collision detection on sampling points of a state space based on a sampled obstacle processing scheme, and finding a collision-free planning path from a starting point to a target point. Based on the optimized obstacle processing scheme, firstly, behavior decision is carried out on the obstacle, safety, comfort, efficiency and the like are taken as optimization targets, and unknown parameters of kinematics are solved.
However, the obstacle processing scheme based on sampling is not accurate enough in the representation of the environmental information, and there is no flexibility in selecting the search endpoint. However, based on the optimized obstacle handling scheme, the calculation amount is large, and there may be a case of non-convergence.
In addition, the two existing barrier processing schemes have no strategy for adjusting the characteristics of the meeting scene, and are not in line with the driving habits of human beings.
Therefore, at present, there is an urgent need to develop a method for processing meeting scenes, which is safe and conforms to the driving habits of people, and this is of great significance.
Disclosure of Invention
The invention aims to provide an automatic driving meeting scene processing method, an automatic driving meeting scene processing device and a vehicle, aiming at the technical defects in the prior art.
Therefore, the invention provides an automatic driving meeting scene processing method, which comprises the following steps:
step S1, vehicle meeting state judgment: judging whether the vehicle is in a vehicle meeting state, and when the vehicle is in the vehicle meeting state, continuing to execute the step S2;
step S2, meeting type determination processing: and classifying the current meeting state, judging the corresponding meeting type, and executing the corresponding meeting processing operation according to the preset corresponding relation between a plurality of different meeting types and a plurality of different meeting processing operations.
Preferably, after step S2, the method further includes the following steps:
step S3, determining the lateral rightward offset distance and the target speed of the vehicle according to the vehicle meeting type of the current vehicle meeting state judged in the step S2;
step S4, obtaining a planned target end point of the self-vehicle according to the transverse rightward offset distance and the target speed of the self-vehicle determined in the step S3, wherein the planned target end point of the self-vehicle is the end point of the reference path of the self-vehicle;
and step S5, generating a driving track from the current position to the planned target end point according to the current position of the vehicle and the position of the planned target end point of the vehicle determined in the step S4.
Preferably, in step S11, it is first determined whether the vehicle meets a preset vehicle meeting condition, if yes, step S12 is executed, otherwise, it is determined that the vehicle is not in a vehicle meeting state and no processing is performed;
the preset meeting conditions are as follows: the self-vehicle is positioned on the leftmost lane, and no physical shelter exists on the left side of the self-vehicle;
and step S12, screening all the opposite vehicles in front of the own vehicle (namely the vehicles running in opposite directions), if the opposite vehicles run in the opposite lanes adjacent to the own vehicle, judging that the own vehicle is in a vehicle meeting state at the moment, and continuing to execute the step S2, otherwise, judging that the own vehicle is not in the vehicle meeting state and not processing.
Preferably, step S2 specifically includes the following sub-steps:
step S21, first, determining whether there is a collision risk between the predicted trajectory of the oncoming vehicle and the reference path of the own vehicle, and if there is no collision risk, determining that the current meeting state belongs to the speed-limiting type, and performing the meeting processing operation correspondingly as follows: reducing the speed of the vehicle, if the collision risk exists, judging that the current meeting state does not belong to the speed-limiting type, and continuing to execute the step S22;
step S22, determining whether a collision region (i.e. a region that does not allow two vehicles to pass through simultaneously) exists between the host vehicle and the opposite vehicle, and if no collision region exists, determining that the current meeting state belongs to the avoidance type, where the meeting processing operation executed correspondingly is: the collision is avoided by controlling the self-vehicle to do lateral rightward deviation movement, if a collision area exists, the current meeting state is judged to belong to the parking type, and the corresponding meeting processing operation is as follows: and controlling the self vehicle to stop before the conflict area and waiting for the opposite vehicle to pass.
Preferably, in step S21, in order to determine whether there is a collision risk between the predicted trajectory of the oncoming vehicle and the reference path of the own vehicle, the specific operations are:
calculating the distance between any position point of the predicted track of the opposite vehicle and any position point in the reference path of the self vehicle, and if the distance value is smaller than the preset safety distance, indicating that the collision risk exists, otherwise, not existing;
in step S22, the method for determining whether there is a collision area between the host vehicle and the oncoming vehicle specifically includes the following operations:
and when the static obstacle exists on the opposite lane and the width of the left space on the right side of the static obstacle on the opposite lane is smaller than the sum of the width of the vehicle, the width of the opposite vehicle and the preset safety distance, judging that a conflict area exists between the vehicle and the opposite vehicle.
Preferably, in step S3, the method for determining the lateral rightward offset distance of the host vehicle according to the meeting type to which the current meeting state belongs, which is determined in step S2, includes the following steps:
if the current meeting state belongs to the speed-limiting type, the transverse rightward offset distance of the self vehicle is zero;
if the current meeting state belongs to the avoidance type, calculating the transverse right offset distance obtained from the vehicle according to the following calculation formula, wherein the specific formula is as follows:
s＝l+0.5w+d；
wherein l represents a straight-line distance between the rightmost point of the predicted trajectory of the oncoming vehicle and the reference path of the own vehicle;
wherein w represents the width of the vehicle; d represents a preset safety distance, namely a transverse vertical distance kept between a straight line on the left side of the self vehicle and a straight line on the rightmost side of the opposite vehicle;
if the current meeting state belongs to the parking type, calculating the lateral rightward offset distance obtained from the vehicle according to the following calculation formula:
s＝x-d；
wherein x represents the distance from the center of the vehicle to the rightmost side of the road before the conflict area;
d represents a preset safety distance, namely a certain transverse vertical distance is kept between a straight line on the left side of the self vehicle and a straight line on the rightmost side of the opposite vehicle.
Preferably, in step S3, the determining the target speed of the vehicle according to the meeting type to which the current meeting state belongs specifically includes the following steps:
if the current meeting state belongs to the speed limit type, the target speed of the vehicle is a preset first target speed;
if the current meeting state belongs to the avoidance type, the target speed of the vehicle is a preset second target speed;
the preset second target speed value is smaller than the preset first target speed value;
and if the current meeting state belongs to the parking type, the target speed of the vehicle is zero.
Preferably, in step S3, the method further includes the following steps:
controlling the self-vehicle to perform uniform deceleration movement, and calculating the deceleration distance from the self-vehicle to the meeting position, wherein the specific formula is as follows:
Figure BDA0002677180770000041
wherein v isegoRepresenting the current speed of the vehicle;
vgoalrepresenting a target speed of the own vehicle;
vobjindicating a current vehicle speed of the oncoming vehicle;
y represents the distance from the current position of the host vehicle to the oncoming vehicle.
In addition, the invention also provides an automatic driving meeting scene processing device, which comprises the following modules:
the vehicle crossing state judging module is used for judging whether the vehicle is in a vehicle crossing state or not, and when the vehicle is in the vehicle crossing state, sending a triggering signal to the vehicle crossing judging module to trigger the running vehicle crossing type judging module;
and the meeting type judging and processing module is connected with the meeting state judging module and used for classifying the current meeting state after being triggered by the meeting state judging module to operate, judging the corresponding meeting type and executing the corresponding meeting processing operation according to the preset corresponding relation between a plurality of different meeting types and a plurality of different meeting processing operations.
Preferably, the following modules are also included:
the device comprises a transverse rightward offset distance and target speed determining module, a meeting vehicle type judging and processing module and a meeting vehicle speed judging and processing module, wherein the transverse rightward offset distance and target speed determining module is connected with the meeting vehicle type judging and processing module and is used for determining the transverse rightward offset distance and the target speed of the own vehicle according to the meeting vehicle type to which the current meeting state determined by the meeting vehicle type judging and processing module belongs;
the planned target end point determining module is connected with the transverse rightward offset distance and target speed determining module and used for obtaining a planned target end point of the self-vehicle according to the transverse rightward offset distance and the target speed of the self-vehicle determined by the transverse rightward offset distance and target speed determining module, wherein the planned target end point of the self-vehicle is the end point of a reference path of the self-vehicle;
and the driving planning module is connected with the planning target end point determining module and used for generating a driving track from the current position to the planning target end point of the vehicle according to the current position of the vehicle and the position of the planning target end point of the vehicle determined by the planning target end point determining module.
In addition, the invention also provides a vehicle which comprises the automatic driving meeting scene processing device.
Compared with the prior art, the technical scheme provided by the invention has the advantages that the method, the device and the vehicle for processing the automatic driving meeting scene are scientific in design, the speed and the transverse position of the vehicle can be actively adjusted when meeting the meeting scene, so that the vehicle speed at the meeting moment is reduced, the transverse spacing distance between the vehicle and the opposite vehicle is increased, the driving safety is further improved, the driving habit of people is met, and the method and the device have great practical significance.
Drawings
Fig. 1 is a schematic basic flow chart of an automatic driving meeting scene processing method provided by the present invention;
fig. 2 is a schematic flowchart of an embodiment of a method for processing an automatic driving meeting scene according to the present invention;
FIG. 3 is a schematic view of a speed-limited type meeting scenario faced by the present invention;
FIG. 4 is a schematic view of an avoidance type meeting scenario faced by the present invention;
fig. 5 is a schematic view of a parking type meeting scenario faced by the present invention.
Detailed Description
In order to make the technical means for realizing the invention easier to understand, the following detailed description of the present application is made in conjunction with the accompanying drawings and embodiments. It is to be understood that the specific embodiments described herein are merely illustrative of the relevant application and are not limiting of the application. It should be noted that, for convenience of description, only the portions related to the present application are shown in the drawings.
It should be noted that the embodiments and features of the embodiments in the present application may be combined with each other without conflict. The present application will be described in detail below with reference to the embodiments with reference to the attached drawings.
It should be noted that in the description of the present application, the terms of direction or positional relationship indicated by the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc. are based on the directions or positional relationships shown in the drawings, which are merely for convenience of description, and do not indicate or imply that the device or element must have a specific orientation, be constructed and operated in a specific orientation, and thus, should not be construed as limiting the present application.
Referring to fig. 1 to 5, the present invention provides an automatic driving meeting scene processing method, including the following steps:
step S1, vehicle meeting state judgment: judging whether the vehicle is in a vehicle meeting state, and when the vehicle is in the vehicle meeting state, continuing to execute the step S2;
in a specific implementation of the present invention, the meeting state determining operation in step S1 specifically includes the following sub-steps:
step S11, firstly, judging whether the vehicle meets the preset meeting condition, if so, executing step S12, otherwise, judging that the vehicle is not in the meeting state and not processing;
the preset meeting conditions are as follows: the vehicle is positioned on the leftmost lane, and no physical barrier (namely an obstacle such as a guardrail and the like) exists on the left side of the vehicle; both of these conditions need to be satisfied simultaneously.
In step S11, the autonomous vehicle relies on an existing high-precision map in the autonomous state, and the high-precision map stores information such as a lane type, a lane topology, a lane line, and a geographical position in advance.
According to the output of a positioning module installed on the self-vehicle, the absolute position of the self-vehicle can be obtained, then the lane where the self-vehicle is located is obtained based on a high-precision map, then whether the lane of the self-vehicle has the left parallel lane in the same direction or not is searched through the high-precision map, and if not, the fact that the self-vehicle is located in the leftmost lane is shown.
The vehicle-meeting method is characterized in that the condition that the vehicle belongs to the leftmost lane is a precondition for vehicle-meeting, and if the left side of the vehicle has a parallel lane and the driving direction of the vehicle on the left side is the same as that of the vehicle, a vehicle-meeting scene is not formed.
That is to say, it is the existing mature technology to determine whether the own vehicle is located in the leftmost lane, and the detailed description is omitted here.
In addition, the left and right boundary types, solid lines, broken lines, physical occlusion, and the like of the lane are recorded in advance in the conventional high-precision map, and if the left boundary type of the own vehicle lane is not a physical occlusion, it indicates that there is no physical occlusion on the left side of the own vehicle.
The fact that a physical shielding object does not exist on the left side of the automobile is a precondition for automobile meeting, if a guardrail lamp is physically shielded on the left side, the left side of the automobile cannot have a vehicle opposite to the moving direction of the automobile, and an automobile meeting scene is not formed.
Similarly, whether there is a physical shelter on the left side of the bicycle is determined, which is a mature technology and is not described herein again.
Step S12, screening all opposite vehicles (namely opposite traveling vehicles) in front of the vehicle, if the opposite vehicles are traveling in the adjacent opposite lanes, judging that the vehicle is in a vehicle meeting state at the moment, and continuing to execute step S2, otherwise, judging that the vehicle is not in the vehicle meeting state and not processing;
in step S12, it should be noted that, based on the output of the existing sensing module (e.g., laser radar, camera, etc.) provided on the host vehicle, the relative positions of the obstacles around the host vehicle (including the oncoming vehicle) can be obtained, so as to screen information such as the speed and category of all oncoming vehicles ahead of the host vehicle (i.e., oncoming vehicles). Wherein, the vehicle which is positioned in front of the vehicle and has the speed direction opposite to the vehicle belongs to the opposite vehicle.
In the present invention, an oncoming vehicle ahead of the host vehicle is a necessary condition for being a target vehicle in a meeting scene.
In the present invention, the specific way to determine whether there is a case where the oncoming vehicle is traveling in an oncoming lane adjacent to the own vehicle is: the absolute position of obstacles (including opposite vehicles) around the self-vehicle can be obtained through the existing sensing module, then the corresponding lane can be obtained according to the absolute position of the obstacles around the self-vehicle through the high-precision map, and all lanes with topological relation in each lane are provided (the high-precision map stores information such as lane types, lane topology, lane lines and geographic positions in advance). If the adjacent opposite lane of the lane where the opposite vehicle (as the obstacle around the vehicle) is located contains the vehicle lane, it is explained that the opposite vehicle runs in the adjacent opposite lane of the vehicle. The technical means are well-established in the art and are not described herein in detail.
Among them, an oncoming vehicle traveling in an oncoming lane adjacent to the own vehicle is a necessary condition as a target vehicle in the meeting scene.
Step S2, meeting type determination processing: classifying the current meeting state, judging the corresponding meeting type, and executing the corresponding meeting processing operation according to the preset corresponding relation between a plurality of different meeting types and a plurality of different meeting processing operations;
in a specific implementation of the present invention, step S2 specifically includes the following sub-steps:
step S21, first, determining whether there is a collision risk between the predicted trajectory of the oncoming vehicle and the reference path of the own vehicle, and if there is no collision risk, determining that the current meeting state belongs to the speed-limiting type, and performing the meeting processing operation correspondingly as follows: reducing the speed of the vehicle, if the collision risk exists, judging that the current meeting state does not belong to the speed-limiting type, and continuing to execute the step S22;
it should be noted that when the current meeting state belongs to the speed limit type, the safety of the driver can be improved only by reducing the speed, as shown in fig. 3.
In step S21, the predicted trajectory of the oncoming vehicle may be calculated according to the distribution of obstacles around the oncoming vehicle in combination with the motion state, and is typically obtained by using a kinematic trajectory estimation or a machine learning algorithm.
In addition, with respect to the predicted trajectory of the oncoming vehicle, the prediction module in the conventional autonomous driving system mounted on the host vehicle can estimate the position information of the obstacle around the host vehicle such as the oncoming vehicle in a future period of time, that is, can obtain the predicted trajectory of the obstacle around the host vehicle such as the oncoming vehicle, based on the information such as the historical position and speed of the obstacle around the host vehicle such as the oncoming vehicle. Currently, a predicted trajectory of an obstacle around a host vehicle such as an oncoming vehicle can be obtained by an algorithm such as kalman filtering or deep learning. This is the well-established technology and will not be described herein.
The predicted trajectory of the oncoming vehicle may be, for example, position information of the oncoming vehicle corresponding to 8 seconds in the future at an interval of 0.1 second. The predicted track is an important basis for judging the type of the meeting scene.
It should be noted that, regarding the reference path of the own vehicle, the existing automatic driving planning module arranged on the own vehicle can output the position points that the own vehicle needs to pass through in a future period of time in real time according to the environmental information around the own vehicle, and the combination of the position points is the reference path. At present, the reference path of the vehicle can be obtained through the existing algorithms such as mixed A and quintic polynomial optimization. This is the well-established technology and will not be described herein.
The reference path of the self-vehicle can be the position and speed information of the self-vehicle corresponding to 8 seconds in the future every 0.1 second.
It should be further noted that the reference path of the own vehicle is an important basis for judging the type and the state of the vehicle-meeting scene, and the position of the vehicle can be controlled through reference path planning, so that the vehicle-meeting function is realized.
In step S21, to determine whether there is a risk of collision between the predicted trajectory of the oncoming vehicle and the reference path of the own vehicle, the following specific operations are performed:
and calculating the distance between every two position points in the predicted track of the opposite vehicle and the reference path of the self vehicle (between any two position points, namely between any one position point of the predicted track of the opposite vehicle and any one position point in the reference path of the self vehicle), and if the distance value is smaller than a preset safe distance (for example, 5m), indicating that the collision risk exists, otherwise, not existing.
In the invention, whether the predicted track and the reference path have collision or not is an important basis for judging the type of the meeting scene.
Step S22, determining whether a collision region (i.e. a region that does not allow two vehicles to pass through simultaneously) exists between the host vehicle and the opposite vehicle, and if no collision region exists, determining that the current meeting state belongs to the avoidance type, where the meeting processing operation executed correspondingly is: the collision is avoided by controlling the self-vehicle to do lateral rightward deviation movement, if a collision area exists, the current meeting state is judged to belong to the parking type, and the corresponding meeting processing operation is as follows: and controlling the self vehicle to stop before the conflict area and waiting for the opposite vehicle to pass.
In the present invention, in step S22, the method for determining whether there is a collision area between the host vehicle and the oncoming vehicle specifically includes the following operations:
referring to fig. 5, when the left static obstacle (i.e., the static obstacle exists on the opposite lane) occupies a larger passable area, and the width of the left space on the right side of the static obstacle on the opposite lane is smaller than the sum of the width of the host vehicle, the width of the opposite vehicle, and a preset safety distance (e.g., 0.5m, which is the reserved safety distance between the right side of the opposite vehicle and the left side of the host vehicle), it is determined that a collision area exists between the host vehicle and the opposite vehicle, and the left space on the right side of the static obstacle (horizontal right direction space) on the opposite lane belongs to the collision area.
In particular, the determining whether a conflict area exists between the host vehicle and the oncoming vehicle may specifically include the following substeps:
the first step is to detect the distance between the vehicle and the opposite vehicle at regular intervals (1m), and to obtain the distance between the left road boundary point and the right road boundary point corresponding to the detected distance from the existing high-precision map.
And secondly, screening all static obstacles covering the detection distance, namely the obstacles with the shortest distance to the self vehicle being greater than the detection distance and the longest distance to the self vehicle being less than the detection distance, wherein the left boundary point and the right boundary point are the left point and the right point of the obstacles positioned at the detection distance.
And thirdly, sequencing all the obstacles in order from left to right, and calculating the passable distance between the adjacent obstacles, namely the distance between the right boundary point of the left obstacle and the left boundary point of the right obstacle, as the alternative passable distance. The distance between the left road boundary point and the left boundary point of the leftmost obstacle and the distance between the right boundary point of the rightmost obstacle and the right road boundary point are also used as the candidate passable distances.
And fourthly, calculating the width of the opposite vehicle, taking the sum of the width of the own vehicle and the left and right safety distances as the minimum simultaneous passing distance, and if the minimum simultaneous passing distance is larger than the maximum alternative passable distance, indicating that the conflict exists. If any detection distance has conflict, the conflict area exists between the own vehicle and the opposite vehicle.
In the invention, the judgment of whether a collision area exists between the own vehicle and the opposite vehicle is an important basis for judging the type of the meeting scene.
In the present invention, the collision position is calculated as the end point of the decelerated stop of the own vehicle, and it is possible to ensure that the own vehicle does not obstruct the passage of the oncoming vehicle.
It should be noted that if there is no collision region between the host vehicle and the opposite vehicle, that is, there is no region that does not allow two vehicles to pass through simultaneously, it is indicated that the host vehicle can avoid collision through lateral offset motion, and the current meeting state is of an avoidance type, as shown in fig. 4. Otherwise, the current meeting state belongs to the parking type, and the vehicle needs to be parked in front of the conflict area to wait for the opposite vehicle to pass through, as shown in fig. 5.
In the present invention, after step S2, the following steps may be further included:
step S3, determining the lateral rightward offset distance and the target speed of the vehicle according to the vehicle meeting type of the current vehicle meeting state judged in the step S2;
step S4, according to the lateral rightward shift distance of the own vehicle and the target speed determined at step S3,
obtaining a planned target end point of the self-vehicle (namely the end point of the reference path of the self-vehicle);
in the present invention, it should be noted that, regarding step S4, the reference path of the vehicle and the end point of the reference path may be obtained by an existing algorithm, such as a mixed a and quintic polynomial optimization. This is the well-established technology and will not be described herein.
In step S5, a driving path from the current position to the planned target end point of the vehicle (i.e. the end point of the reference path of the vehicle) is generated according to the current position of the vehicle and the position of the planned target end point of the vehicle (i.e. the end point of the reference path of the vehicle) determined in step S4 (for example, by using an existing search algorithm or other existing algorithms capable of generating driving paths).
It should be noted that the driving trajectory is a safe trajectory that satisfies the vehicle dynamics constraints.
In the present invention, it should be noted that, in step S5, a driving path from the current position to the planned target end point of the vehicle (i.e., the end point of the reference path of the vehicle) may be generated according to the current position of the vehicle and the position of the planned target end point of the vehicle (i.e., the end point of the reference path of the vehicle) determined in step S4 by using an existing algorithm, such as a mixed a-order polynomial optimization. This is the well-established technology and will not be described herein.
It should be noted that, regarding step S3, in order to ensure that there is a sufficient safety distance during the meeting process, the corresponding lateral offset distance needs to be calculated according to the type of the meeting. If the current vehicle belongs to the speed limit type, the current reference path can be kept by the vehicle without shifting to the right. If the current vehicle belongs to an avoidance type, the current vehicle needs to keep a certain safety distance from the rightmost side of the barrier.
In step S3, the method for determining the lateral rightward offset distance of the host vehicle according to the meeting type of the current meeting state determined in step S2 specifically includes the following steps:
if the current meeting state belongs to the speed-limiting type, the self-vehicle does not need to transversely shift rightwards, namely the transverse rightward shift distance of the self-vehicle is zero.
In step S3, the method for determining the lateral rightward offset distance of the host vehicle according to the meeting type of the current meeting state determined in step S2 specifically includes the following steps:
if the current meeting state belongs to the avoidance type, calculating the transverse rightward offset distance of the obtained vehicle according to the following calculation formula, wherein the specific formula is as follows:
s＝l+0.5w+d；
where l represents a straight-line distance (considering an obstacle area) between a point on the rightmost side of the predicted trajectory of the oncoming vehicle (which belongs to a dynamic obstacle) and the reference path of the own vehicle, and the right side is positive;
where w represents the width of the vehicle and d represents a preset safety distance (i.e., a lateral vertical distance maintained between a line on the left side of the vehicle and a line on the rightmost side of the oncoming vehicle), d is typically about 0.5m, e.g., 0.5m, in view of sensing and control errors.
The lateral rightward shift distance of the host vehicle refers to a distance in which a waypoint of the host vehicle reference path shifts rightward in the road direction.
In a specific implementation, l represents a straight-line distance (considering an obstacle area) between a point on the rightmost side of a predicted trajectory of an oncoming vehicle (which belongs to a dynamic obstacle) and a reference path of the own vehicle, and specifically may not be: the minimum value is taken by calculating the vertical distance between four corner points (namely four corner position points of the vehicle) on the opposite vehicle corresponding to each point in the predicted track of the opposite vehicle and the reference path of the own vehicle, and the minimum value is taken as l.
Here, it should be noted that if the current meeting state is of an avoidance type, the host vehicle needs to keep a certain safety distance d from the rightmost side of the oncoming vehicle (which is a dynamic obstacle).
In step S3, the method for determining the lateral rightward offset distance of the host vehicle according to the meeting type of the current meeting state determined in step S2 specifically includes the following steps:
if the current meeting state belongs to the parking type, calculating the lateral rightward offset distance obtained from the vehicle according to the following calculation formula, wherein the specific formula is as follows:
s＝x-d；
wherein x represents the distance from the center of the vehicle to the rightmost boundary line of the road in front of the collision area;
d represents a preset safety distance (i.e. a certain transverse vertical distance is kept between a straight line on the left side of the self-vehicle and a straight line on the rightmost side of the opposite vehicle), and the distance d is generally about 0.5m, for example 0.5m, in consideration of sensing and control errors.
In concrete implementation, according to the existing high-precision map, the right side boundary of the road where the self-vehicle is located can be obtained, the vertical distance between the self-vehicle position and the right side boundary line of the road is calculated, and the vertical distance is as follows: and the distance x from the center of the vehicle to the rightmost boundary line of the road in front of the collision area.
Here, it should be noted that, if the current meeting state belongs to the parking type, the host vehicle needs to travel to the rightmost side of the road to provide sufficient space for the oncoming vehicle.
In step S3, the method for determining the target speed of the vehicle according to the meeting type to which the current meeting state belongs specifically includes the following steps:
if the current meeting state belongs to the speed limit type, the target speed of the vehicle is a preset first target speed (for example, about 20 km/h).
If the current meeting state belongs to an avoidance type, the target speed of the vehicle is a preset second target speed (for example, about 10 km/h);
the preset second target speed value is smaller than the preset first target speed value;
and if the current meeting state belongs to the parking type, the target speed of the vehicle is zero.
In a specific implementation of the present invention, in step S3, the method further includes the following steps:
controlling the self-vehicle to perform uniform deceleration movement, and calculating the deceleration distance from the self-vehicle to the meeting position, wherein the specific formula is as follows:
Figure BDA0002677180770000121
wherein v isegoRepresenting the current speed of the vehicle;
vgoalrepresents a target speed of the own vehicle (i.e., a target vehicle speed);
vobjindicating a current vehicle speed of the oncoming vehicle;
y represents a distance from the current position of the host vehicle to the oncoming vehicle (specifically, a vertical distance from the head-foremost position of the host vehicle to the head-foremost position of the oncoming vehicle).
It should be noted that the meeting positions are: and the position of the vehicle when the longitudinal distance between the opposite vehicle and the vehicle is zero.
It should be noted that the current vehicle speed v of the host vehicleegoProvided by a positioning module mounted on the bicycle. Speed v of the oncoming vehicleobjAnd a relative distance y provided by an existing sensing module installed on the host vehicle, the target speed of the host vehicle being derived from the logic (e.g., about 20km/h, or about 10 km/h).
In the present invention, the deceleration distance obtained from the arrival of the vehicle at the meeting location can be calculated by the above formula, where it is not necessary to obtain a specific location of the meeting location.
It should be noted that, with the present invention, in order to reduce the vehicle speed of the vehicle at the meeting instant, it is necessary to estimate the location of the meeting instant (i.e., the meeting location), and determine the target vehicle speed of the meeting location according to the type of the meeting. If the current vehicle belongs to the speed limit type, the target speed of the vehicle can be about 20km/h, and if the current vehicle belongs to the avoidance type, the target speed of the vehicle can be about 10 km/h.
It should be noted that, with the present invention, if the current meeting type belongs to a parking type, the vehicle needs to park in front of the conflict area and wait for the oncoming vehicle to pass, so the deceleration distance is the vertical distance between the position of the vehicle (specifically, the head-side position) and the conflict area, and the target vehicle speed is 0 km/h.
The collision area position is described above, the position of the vehicle is obtained by the existing positioning module, and the vertical distance between the vehicle and the collision area is the above described detection distance where the collision exists.
Based on the technical scheme, compared with the prior art, the invention provides the judgment method and the classification standard of the meeting scene, and the meeting scene can be planned into the target terminal point and selected and converted into the transverse offset distance and the target speed for calculation. Meanwhile, a corresponding planning target end point calculation method and a key parameter design principle for different meeting types are provided.
In the present invention, the planned target end point of the own vehicle (i.e., the end point of the reference path of the own vehicle) is determined by the lateral deviation distance and the target speed limit value (i.e., the target speed), and as described in step S4, the reference path of the own vehicle and the end point of the reference path may be obtained by the existing algorithms such as hybrid a × and quintic polynomial optimization. This is the well-established technology and will not be described herein.
The calculation method and the key parameters of the lateral offset distance and the target speed limit (i.e., the target speed) depend on the type of the vehicle meeting, as described above.
In addition, based on the above method for processing the automatic driving meeting scene, in order to execute the method for processing the automatic driving meeting scene, the invention further provides a device for processing the automatic driving meeting scene, which comprises the following modules:
the vehicle crossing state judging module is used for judging whether the vehicle is in a vehicle crossing state or not, and when the vehicle is in the vehicle crossing state, sending a triggering signal to the vehicle crossing judging module to trigger the running vehicle crossing type judging module;
the meeting type judging and processing module is connected with the meeting state judging module and used for classifying the current meeting state after being triggered to operate by the meeting state judging module, judging the corresponding meeting type and executing the corresponding meeting processing operation according to the preset corresponding relation between a plurality of different meeting types and a plurality of different meeting processing operations;
in the present invention, based on the above method for processing an auto-driving meeting scene provided by the present invention, the auto-driving meeting scene processing apparatus provided by the present invention further includes the following modules:
the system comprises a transverse right offset distance and target speed determining module, a meeting type judging and processing module and a meeting type judging and processing module, wherein the transverse right offset distance and target speed determining module is connected with the meeting type judging and processing module and is used for determining the transverse right offset distance and the target speed of the own vehicle according to the meeting type to which the current meeting state determined by the meeting type judging and processing module belongs;
the planned target end point determining module is connected with the transverse rightward offset distance and target speed determining module and used for obtaining a planned target end point of the self-vehicle according to the transverse rightward offset distance and the target speed of the self-vehicle determined by the transverse rightward offset distance and target speed determining module, wherein the planned target end point of the self-vehicle is the end point of a reference path of the self-vehicle;
and the driving planning module is connected with the planning target end point determining module and used for generating a driving track (for example, by using an existing search algorithm or other existing algorithms capable of generating a driving path) from the current position to the planning target end point of the vehicle according to the current position of the vehicle and the position of the planning target end point of the vehicle determined by the planning target end point determining module.
It should be noted that the driving trajectory is a safe trajectory that satisfies the vehicle dynamics constraints.
It should be noted that the driving trajectory planning, which is an existing driving path planning method, can be determined by using an existing known method, and is not described herein again.
In addition, the invention also provides a vehicle which comprises the automatic driving meeting scene processing device.
In the present invention, in particular, in the implementation, the target speed in the present invention may be estimated during the deceleration process of the vehicle, or may be based on a kinematic model such as trapezoidal acceleration and minimum jerk.
In the invention, in particular implementation, after the planned target end point is obtained by calculation, sampling can be performed around the planned target end point to generate a plurality of planned end points for generating a motion track.
Compared with the prior art, the automatic driving meeting scene processing method, the automatic driving meeting scene processing device and the automatic driving meeting vehicle have the following beneficial technical effects:
1. the meeting scene processing method designed by the invention can ensure that the automatic driving vehicle keeps reasonable speed in the meeting process, and enough space exists for the self vehicle and the opposite vehicle to pass through, thereby improving the driving safety, conforming to the driving habit of human, and improving the riding experience of passengers.
2. The planning end point selection method fully combines the characteristics of the driving environment of the vehicle and the current meeting scene type, converts the characteristics into the calculation of the transverse rightward offset distance and the target speed, and has a concise and clear implementation process.
In summary, compared with the prior art, the method, the device and the vehicle for processing the automatic driving meeting scene provided by the invention have scientific design, can actively adjust the speed and the transverse position of the vehicle when meeting the meeting scene, thereby reducing the vehicle speed at the meeting moment, simultaneously increasing the transverse spacing distance between the vehicle and the opposite vehicle, being beneficial to further improving the driving safety, meeting the driving habits of people, and having great practical significance.
The foregoing is only a preferred embodiment of the present invention, and it should be noted that, for those skilled in the art, various modifications and decorations can be made without departing from the principle of the present invention, and these modifications and decorations should also be regarded as the protection scope of the present invention.

Claims (8)

1. An automatic driving meeting scene processing method is characterized by comprising the following steps:
step S1, vehicle meeting state judgment: judging whether the vehicle is in a vehicle meeting state, and when the vehicle is in the vehicle meeting state, continuing to execute the step S2;
step S2, meeting type determination processing: classifying the current meeting state, judging the corresponding meeting type, and executing the corresponding meeting processing operation according to the preset corresponding relation between a plurality of different meeting types and a plurality of different meeting processing operations;
step S2 specifically includes the following substeps:
step S21, first, determining whether there is a collision risk between the predicted trajectory of the oncoming vehicle and the reference path of the own vehicle, and if there is no collision risk, determining that the current meeting state belongs to the speed-limiting type, and performing the meeting processing operation correspondingly as follows: reducing the speed of the vehicle, if the collision risk exists, judging that the current meeting state does not belong to the speed-limiting type, and continuing to execute the step S22;
step S22, determining whether a collision area exists between the host vehicle and the oncoming vehicle, and if no collision area exists, determining that the current vehicle-meeting state belongs to an avoidance type, wherein the vehicle-meeting processing operation executed correspondingly is: the collision is avoided by controlling the self-vehicle to do lateral rightward deviation movement, if a collision area exists, the current meeting state is judged to belong to the parking type, and the corresponding meeting processing operation is as follows: controlling the self vehicle to stop before the conflict area and waiting for the opposite vehicle to pass;
in step S21, to determine whether there is a risk of collision between the predicted trajectory of the oncoming vehicle and the reference path of the own vehicle, the following specific operations are performed:
calculating the distance between any position point of the predicted track of the opposite vehicle and any position point in the reference path of the self vehicle, and if the distance value is smaller than the preset safety distance, indicating that the collision risk exists, otherwise, not existing;
in step S22, the method for determining whether there is a collision area between the host vehicle and the oncoming vehicle specifically includes the following operations:
and when the static obstacle exists on the opposite lane and the width of the left space on the right side of the static obstacle on the opposite lane is smaller than the sum of the width of the vehicle, the width of the opposite vehicle and the preset safety distance, judging that a conflict area exists between the vehicle and the opposite vehicle.
2. The automatic driving meeting scenario processing method of claim 1, further comprising, after step S2, the steps of:
step S3, determining the lateral rightward offset distance and the target speed of the vehicle according to the vehicle meeting type of the current vehicle meeting state judged in the step S2;
step S4, obtaining a planned target end point of the self-vehicle according to the transverse rightward offset distance and the target speed of the self-vehicle determined in the step S3, wherein the planned target end point of the self-vehicle is the end point of the reference path of the self-vehicle;
and step S5, generating a driving track from the current position to the planned target end point according to the current position of the vehicle and the position of the planned target end point of the vehicle determined in the step S4.
3. The method according to claim 1, wherein step S11 is performed by first determining whether the vehicle meets a predetermined meeting condition, and if so, performing step S12, otherwise, determining that the vehicle is not in a meeting state and not performing the processing;
the preset meeting conditions are as follows: the self-vehicle is positioned on the leftmost lane, and no physical shelter exists on the left side of the self-vehicle;
and step S12, screening all opposite vehicles in front of the own vehicle, if the opposite vehicles run in the opposite lane adjacent to the own vehicle, judging that the own vehicle is in a vehicle meeting state at the moment, and continuing to execute step S2, otherwise, judging that the own vehicle is not in the vehicle meeting state and not processing.
4. The method of claim 2, wherein in step S3, the step of determining the lateral-to-right offset distance of the host vehicle according to the meeting type to which the current meeting state belongs, which is determined in step S2, comprises the following steps:
if the current meeting state belongs to the speed-limiting type, the transverse rightward offset distance of the self vehicle is zero;
if the current meeting state belongs to the avoidance type, calculating the transverse right offset distance obtained from the vehicle according to the following calculation formula, wherein the specific formula is as follows:
s＝l+0.5w+d；
wherein l represents a straight-line distance between a point on the rightmost side of the predicted trajectory of the oncoming vehicle and the reference path of the own vehicle;
wherein w represents the width of the vehicle; d represents a preset safety distance, namely a transverse vertical distance kept between a straight line on the left side of the self vehicle and a straight line on the rightmost side of the opposite vehicle;
if the current meeting state belongs to the parking type, calculating the lateral rightward offset distance obtained from the vehicle according to the following calculation formula, wherein the specific formula is as follows:
s＝x-d；
wherein x represents the distance from the center of the vehicle to the rightmost boundary line of the road in front of the collision area;
d represents a preset safety distance, namely a certain transverse vertical distance is kept between a straight line on the left side of the self vehicle and a straight line on the rightmost side of the opposite vehicle;
in step S3, determining a target speed of the vehicle according to the meeting type to which the current meeting state belongs, specifically including the following steps:
if the current meeting state belongs to the speed limit type, the target speed of the vehicle is a preset first target speed;
if the current meeting state belongs to the avoidance type, the target speed of the vehicle is a preset second target speed;
the preset second target speed value is smaller than the preset first target speed value;
and if the current meeting state belongs to the parking type, the target speed of the vehicle is zero.
5. The automatic meeting scene processing method of claim 2, further comprising, in step S3, the steps of:
controlling the self-vehicle to perform uniform deceleration movement, and calculating the deceleration distance from the self-vehicle to the meeting position, wherein the specific formula is as follows:
Figure FDA0003445101280000031
wherein v isegoRepresenting the current speed of the vehicle;
vgoalrepresenting a target speed of the own vehicle;
vobjindicating a current vehicle speed of the oncoming vehicle;
y represents the distance from the current position of the host vehicle to the oncoming vehicle.
6. An automatic driving meeting scene processing device is characterized by comprising the following modules:
the vehicle crossing state judging module is used for judging whether the vehicle is in a vehicle crossing state or not, and when the vehicle is in the vehicle crossing state, sending a triggering signal to the vehicle crossing judging module to trigger the running vehicle crossing type judging module;
the meeting type judging and processing module is connected with the meeting state judging module and used for classifying the current meeting state after being triggered to operate by the meeting state judging module, judging the corresponding meeting type and executing the corresponding meeting processing operation according to the preset corresponding relation between a plurality of different meeting types and a plurality of different meeting processing operations;
the meeting type judging and processing module specifically executes the following operations:
firstly, judging whether a predicted track of an opposite vehicle and a reference path of a self vehicle have collision risks, if not, judging that the current meeting state belongs to a speed-limiting type, and correspondingly executing meeting processing operations of: reducing the speed of the vehicle, if collision risk exists, judging that the current meeting state does not belong to the speed-limiting type, and continuing to execute the second step;
and secondly, judging whether a collision area exists between the own vehicle and the opposite vehicle, if not, judging that the current meeting state belongs to an avoidance type, and correspondingly executing meeting processing operations as follows: the collision is avoided by controlling the self-vehicle to do lateral rightward deviation movement, if a collision area exists, the current meeting state is judged to belong to the parking type, and the corresponding meeting processing operation is as follows: controlling the self vehicle to stop before the conflict area and waiting for the opposite vehicle to pass;
in the first step, in order to determine whether there is a collision risk between the predicted trajectory of the oncoming vehicle and the reference path of the own vehicle, the meeting type determination processing module specifically operates as follows:
calculating the distance between any position point of the predicted track of the opposite vehicle and any position point in the reference path of the self vehicle, and if the distance value is smaller than the preset safety distance, indicating that the collision risk exists, otherwise, not existing;
in the second step, the meeting type judgment processing module specifically comprises the following operations of judging whether a conflict area exists between the vehicle and the opposite vehicle:
and when the static obstacle exists on the opposite lane and the width of the left space on the right side of the static obstacle on the opposite lane is smaller than the sum of the width of the vehicle, the width of the opposite vehicle and the preset safety distance, judging that a conflict area exists between the vehicle and the opposite vehicle.
7. The automated meeting scenario processing device of claim 6, further comprising the following modules:
the system comprises a transverse right offset distance and target speed determining module, a meeting type judging and processing module and a meeting type judging and processing module, wherein the transverse right offset distance and target speed determining module is connected with the meeting type judging and processing module and is used for determining the transverse right offset distance and the target speed of the own vehicle according to the meeting type to which the current meeting state belongs, which is determined by the meeting type judging module;
the planned target end point determining module is connected with the transverse rightward offset distance and target speed determining module and used for obtaining a planned target end point of the self-vehicle according to the transverse rightward offset distance and the target speed of the self-vehicle determined by the transverse rightward offset distance and target speed determining module, wherein the planned target end point of the self-vehicle is the end point of a reference path of the self-vehicle;
and the driving planning module is connected with the planning target end point determining module and used for generating a driving track from the current position to the planning target end point of the vehicle according to the current position of the vehicle and the position of the planning target end point of the vehicle determined by the planning target end point determining module.
8. A vehicle characterized by comprising the automatic vehicle-meeting scene processing device of claim 6 or 7.
CN202010951662.2A 2020-09-11 2020-09-11 Automatic driving meeting scene processing method and device and vehicle Active CN112265542B (en)

Priority Applications (2)

Application Number Priority Date Filing Date Title
CN202010951662.2A CN112265542B (en) 2020-09-11 2020-09-11 Automatic driving meeting scene processing method and device and vehicle
PCT/CN2021/117764 WO2022053026A1 (en) 2020-09-11 2021-09-10 Automatic driving meeting scene processing method and apparatus, vehicle, and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010951662.2A CN112265542B (en) 2020-09-11 2020-09-11 Automatic driving meeting scene processing method and device and vehicle

Publications (2)

Publication Number Publication Date
CN112265542A CN112265542A (en) 2021-01-26
CN112265542B true CN112265542B (en) 2022-05-27

Family

ID=74348986

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010951662.2A Active CN112265542B (en) 2020-09-11 2020-09-11 Automatic driving meeting scene processing method and device and vehicle

Country Status (2)

Country Link
CN (1) CN112265542B (en)
WO (1) WO2022053026A1 (en)

Families Citing this family (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112265542B (en) * 2020-09-11 2022-05-27 武汉智行者科技有限公司 Automatic driving meeting scene processing method and device and vehicle
CN113095601B (en) * 2021-05-18 2023-12-12 郑州大学 Artificial intelligence-based safe meeting method and system for poor-vision intersection
CN114674334A (en) * 2022-03-24 2022-06-28 江铃汽车股份有限公司 Off-road route planning method and system, storage medium and vehicle
CN115497322B (en) * 2022-09-28 2023-07-14 广州文远知行科技有限公司 Narrow road vehicle meeting method, device, equipment and storage medium
CN115638804B (en) * 2022-10-24 2024-04-30 西北工业大学 Deadlock-free unmanned vehicle online path planning method
CN117405124B (en) * 2023-12-13 2024-02-27 融科联创(天津)信息技术有限公司 Path planning method and system based on big data

Family Cites Families (15)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DE102012215093A1 (en) * 2012-08-24 2014-02-27 Robert Bosch Gmbh Driver assistance system and method for operating the driver assistance system
CN106080371B (en) * 2015-08-31 2018-05-29 陈觉明 Automatic driving of motor vehicle auxiliary control appliance and its signal control display device
CN106740834B (en) * 2015-11-24 2020-07-28 中国移动通信集团公司 Method and device for assisting vehicle meeting
US10081357B2 (en) * 2016-06-23 2018-09-25 Honda Motor Co., Ltd. Vehicular communications network and methods of use and manufacture thereof
JP6662284B2 (en) * 2016-12-22 2020-03-11 株式会社オートネットワーク技術研究所 Driving support system and driving support device
WO2018122586A1 (en) * 2016-12-30 2018-07-05 同济大学 Method of controlling automated driving speed based on comfort level
JP6630375B2 (en) * 2018-01-17 2020-01-15 本田技研工業株式会社 Travel control device and travel control method
JP7243034B2 (en) * 2018-04-17 2023-03-22 株式会社デンソー Collision determination device and method
CN108875998A (en) * 2018-04-20 2018-11-23 北京智行者科技有限公司 A kind of automatic driving vehicle method and system for planning
CN112262065A (en) * 2018-06-13 2021-01-22 日立汽车系统株式会社 Vehicle control device
CN110789450B (en) * 2018-08-02 2021-10-26 长城汽车股份有限公司 Vehicle meeting danger alarm prompting method and system and vehicle
CN110221605A (en) * 2019-05-16 2019-09-10 厦门理工学院 Meeting method, apparatus, equipment and the storage medium of pilotless automobile
CN111238520B (en) * 2020-02-06 2022-10-14 阿波罗智能技术(北京)有限公司 Automatic driving lane change path planning method and device and electronic equipment
CN111552284A (en) * 2020-04-20 2020-08-18 宁波吉利汽车研究开发有限公司 Method, device, equipment and medium for planning local path of unmanned vehicle
CN112265542B (en) * 2020-09-11 2022-05-27 武汉智行者科技有限公司 Automatic driving meeting scene processing method and device and vehicle

Also Published As

Publication number Publication date
CN112265542A (en) 2021-01-26
WO2022053026A1 (en) 2022-03-17

Similar Documents

Publication Publication Date Title
CN112265542B (en) Automatic driving meeting scene processing method and device and vehicle
US20230115658A1 (en) Autonomous driving system
CN112498365B (en) Delay decisions for autonomous vehicles responsive to obstacles based on confidence level and distance
JP6308233B2 (en) Vehicle control apparatus and vehicle control method
EP3407329B1 (en) Driving assistance method and device
EP3048023B1 (en) Method for assisting a driver in driving an ego vehicle and corresponding driver assistance system
WO2018132607A2 (en) Navigation based on vehicle activity
CN110356394A (en) A kind of vehicle actively avoids the method, apparatus and automobile of barrier
JP7331939B2 (en) In-vehicle device and driving support method
JP7156394B2 (en) Other Vehicle Motion Prediction Method and Other Vehicle Motion Prediction Device
WO2019073525A1 (en) Driving control method and driving control apparatus
US20230123418A1 (en) Method for planning a target trajectory
WO2019073526A1 (en) Driving control method and driving control apparatus
US20190035278A1 (en) Driving Assistance Method and Device
US20210387617A1 (en) Method and Control Unit for Detecting a Vehicle Moving In or Out
CN111731294B (en) Travel control device, travel control method, and storage medium storing program
CN113795801B (en) Obstacle avoidance trajectory planning for autonomous vehicles
CN110673595B (en) Method and system for avoiding obstacle during automatic driving of vehicle and vehicle
JP2019160031A (en) Vehicle control device, vehicle control method, and program
CN115056787A (en) Automatic driving speed decision planning system and method and automatic driving vehicle
JP7356892B2 (en) Vehicle driving environment estimation method and driving environment estimation system
WO2016170683A1 (en) Travel control device and data structure
JP7291015B2 (en) Surrounding object recognition method and surrounding object recognition device
US11447130B2 (en) Behavior prediction method, behavior prediction apparatus and vehicle control apparatus
JPWO2021197729A5 (en)

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
TA01 Transfer of patent application right

Effective date of registration: 20210809

Address after: 430056 106-6, 1st floor, xiaojunshan community commercial building, Junshan street, Wuhan Economic and Technological Development Zone, Hubei Province

Applicant after: Wuhan Zhixing Technology Co.,Ltd.

Address before: 401122 No.1, 1st floor, building 3, No.21 Yunzhu Road, Yubei District, Chongqing

Applicant before: Chongqing Zhixing Information Technology Co., Ltd

TA01 Transfer of patent application right
GR01 Patent grant
GR01 Patent grant