CN114559961A - Method and device for avoiding obstacles on road surface of automatic driving vehicle and readable storage medium - Google Patents
Method and device for avoiding obstacles on road surface of automatic driving vehicle and readable storage medium Download PDFInfo
- Publication number
- CN114559961A CN114559961A CN202210343173.8A CN202210343173A CN114559961A CN 114559961 A CN114559961 A CN 114559961A CN 202210343173 A CN202210343173 A CN 202210343173A CN 114559961 A CN114559961 A CN 114559961A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- obstacle
- lane
- driving
- width
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 55
- 238000003860 storage Methods 0.000 title claims abstract description 15
- 238000004590 computer program Methods 0.000 claims description 16
- 238000005516 engineering process Methods 0.000 claims description 10
- 230000008859 change Effects 0.000 claims description 9
- 238000012360 testing method Methods 0.000 claims description 9
- 238000004364 calculation method Methods 0.000 claims description 5
- 238000001514 detection method Methods 0.000 claims description 5
- 230000001133 acceleration Effects 0.000 description 12
- 230000004888 barrier function Effects 0.000 description 12
- 230000008447 perception Effects 0.000 description 9
- 230000008569 process Effects 0.000 description 9
- 238000010586 diagram Methods 0.000 description 7
- 230000006870 function Effects 0.000 description 4
- 239000000725 suspension Substances 0.000 description 3
- 238000013473 artificial intelligence Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000004927 fusion Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 206010039203 Road traffic accident Diseases 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000005314 correlation function Methods 0.000 description 1
- 238000013016 damping Methods 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012806 monitoring device Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000003825 pressing Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000013519 translation Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
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
- B60W60/00—Drive control systems specially adapted for autonomous road vehicles
- B60W60/001—Planning or execution of driving tasks
- B60W60/0011—Planning or execution of driving tasks involving control alternatives for a single driving scenario, e.g. planning several paths to avoid obstacles
-
- 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
- B60W50/00—Details 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
- B60W50/0097—Predicting future conditions
-
- 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
- B60W50/00—Details 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
- B60W50/0098—Details of control systems ensuring comfort, safety or stability not otherwise provided for
-
- 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
- B60W2552/00—Input parameters relating to infrastructure
- B60W2552/50—Barriers
Landscapes
- Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Human Computer Interaction (AREA)
- Transportation (AREA)
- Mechanical Engineering (AREA)
- Traffic Control Systems (AREA)
- Control Of Driving Devices And Active Controlling Of Vehicle (AREA)
Abstract
The application relates to a method and a device for avoiding obstacles on a road surface of an automatic driving vehicle and a readable storage medium, relating to the technical field of automatic driving vehicles, and comprising the steps of obtaining a predicted driving track of the vehicle and obtaining road surface color information corresponding to the predicted driving track; detecting whether an obstacle exists in front of the vehicle or not based on the road surface color information; if yes, point cloud information corresponding to the obstacle is obtained; calculating basic information of the obstacle according to the point cloud information, wherein the basic information comprises contour data, size data, concave-convex shape data and position data of the obstacle; determining an obstacle avoidance strategy of the vehicle according to the basic information, the vehicle body information and the lane information of the vehicle, wherein the obstacle avoidance strategy is normal driving, deceleration driving, obstacle avoidance driving in a lane, obstacle crossing driving in the lane or cooperative merging lane changing driving; and controlling the vehicle according to the obstacle avoidance strategy. The method and the device can effectively identify the hollow ground or small-size road surface obstacles and realize active avoidance of the hollow ground or small-size road surface obstacles.
Description
Technical Field
The application relates to the technical field of automatic driving vehicles, in particular to a road obstacle avoidance method and device for an automatic driving vehicle and a readable storage medium.
Background
With the well-blowout development of intelligent interconnection, artificial intelligence technology and new energy technology, a new era of automobile intelligence different from science fiction movies has been in the way. For example, due to the wide application of the internet of vehicles in the large scale of the automobile manufacturing industry, not only the intelligent transportation is realized, but also the automatic driving is possible. The autonomous vehicle may rely on the cooperative use of artificial intelligence, visual computing, radar, monitoring devices, and global positioning systems, such that the computer may operate the vehicle automatically and safely without any active operation by anyone.
In the related technology, environmental perception is the key of information interaction between an automatic driving vehicle and the external environment, and the core of the method is that the automatic driving vehicle better simulates and finally surpasses the perception capability of a driver, and accurately perceives and understands the motion situation of the vehicle and the surrounding environment. The obstacle perception function of the automatic driving vehicle is mainly realized through a machine vision technology and a radar, and the vision perception is prior to the radar perception, namely the vision perception is used as a main part, and the radar perception is used as an auxiliary part.
However, the obstacle sensing function of the current automatic driving vehicle is still not mature enough, for example, it only relates to an obstacle with a road height greater than 30cm, and therefore it is unable to actively avoid pothole ground or small road obstacles, so that when the vehicle speed is fast, emergency braking will also be unable to avoid collision or prevent the vehicle from falling into the pothole, and further causing traffic accidents.
Disclosure of Invention
The application provides a method and a device for avoiding obstacles on a road surface of an automatic driving vehicle and a readable storage medium, which aim to solve the problem that the automatic driving vehicle in the related technology can not realize the active avoidance of pothole ground or small-size road surface obstacles.
In a first aspect, a method for avoiding obstacles on a road surface of an automatic driving vehicle is provided, which comprises the following steps:
acquiring a predicted running track of a vehicle, and acquiring road surface color information corresponding to the predicted running track;
detecting whether an obstacle exists in front of the vehicle or not based on the road surface color information;
if yes, point cloud information corresponding to the obstacle is obtained;
calculating basic information of the obstacle according to the point cloud information, wherein the basic information comprises contour data, size data, concave-convex shape data and position data of the obstacle;
determining an obstacle avoidance strategy of the vehicle according to the basic information, the vehicle body information and the lane information of the vehicle, wherein the obstacle avoidance strategy is normal driving or deceleration driving, in-lane obstacle avoidance driving, in-lane obstacle crossing driving or in-lane line crossing and lane changing driving;
and controlling the vehicle according to the obstacle avoidance strategy.
In some embodiments, when the obstacle is a convex obstacle, the determining an obstacle avoidance policy of the host vehicle according to the basic information, the vehicle body information, and the lane information includes:
when the highest height of the obstacle is smaller than the height threshold value, determining that the obstacle avoidance strategy of the vehicle is normal running;
when the highest height of the obstacle is detected to be larger than or equal to the height threshold value, judging whether the transverse size of the obstacle is larger than or equal to the sum of the widths of all co-directional driving lanes;
and if so, determining that the obstacle avoidance strategy of the vehicle is deceleration driving.
In some embodiments, after the step of determining whether the transverse dimension of the obstacle is greater than or equal to the sum of the widths of all co-running lanes, the method further comprises:
if the transverse size of the obstacle is smaller than the sum of the widths of all co-directional driving lanes, detecting whether a first part with the height smaller than the height threshold value exists in the obstacle;
if the vehicle exists, calculating the sum of the distance between the outer side surface of the first part and the lane line, close to the first part, of the lane where the vehicle is located, and the width of the first part to obtain a first width;
when the difference value between the first width and the vehicle body width of the vehicle is larger than or equal to the difference threshold value, determining that the obstacle avoidance strategy of the vehicle is in-lane crossing obstacle driving, and the in-lane crossing obstacle driving is guiding the vehicle to drive on a road corresponding to the first width.
In some embodiments, after the step of detecting whether the obstacle has a first portion with a height less than the height threshold, the method further comprises:
if the obstacle does not have a first part with the height smaller than the height threshold, respectively calculating the distance between two side faces of the obstacle and the lane line on the same side of the lane where the vehicle is located;
when the difference value between the distance between one side face of the obstacle and the corresponding lane line on the same side and the width of the vehicle body of the vehicle is larger than or equal to the difference threshold value, determining that the obstacle avoidance strategy of the vehicle is to drive the vehicle to avoid the obstacle in the road, and the drive to avoid the obstacle in the road is to guide the vehicle to drive away from the obstacle.
In some embodiments, after the step of calculating the distances between the two side faces of the obstacle and the lanes on the same side of the lane where the host vehicle is located, the method further includes:
and when the difference between the distance between the two side faces of the obstacle and the corresponding lane lines on the same side and the width of the vehicle body of the vehicle is smaller than the difference threshold value, determining that the obstacle avoidance strategy of the vehicle is collaborative parallel lane changing driving.
In some embodiments, after the step of calculating a sum of a distance between an outer side surface of the first portion and a lane line, close to the first portion, of a lane where the host vehicle is located, and a width of the first portion to obtain the first width, the method further includes:
when the difference value between the first width and the vehicle body width of the vehicle is smaller than a difference threshold value, judging whether the width of a second part of an obstacle is smaller than the width threshold value, whether the highest height of the obstacle is smaller than the minimum ground clearance of the vehicle, and whether the distance between the outer side surface of the first part and a lane line, close to the first part, of a lane where the vehicle is located, of the first part is not smaller than a distance threshold value, wherein the second part of the obstacle is a part with the height larger than or equal to the height threshold value, the width threshold value is determined based on the wheel distance, and the distance threshold value is determined based on the tire width and the vehicle speed;
if the width of the second part of the obstacle is smaller than the width threshold value, the highest height of the obstacle is smaller than the minimum ground clearance of the vehicle, and the distance between the outer side surface of the first part and the lane line, close to the first part, of the lane where the vehicle is located, of the first part is not smaller than the distance threshold value, the obstacle avoidance strategy of the vehicle is determined to be in-lane crossing obstacle running, and the in-lane crossing obstacle running is to guide the vehicle to run on the lane corresponding to the first width.
In some embodiments, after the step of determining whether the width of the second portion of the obstacle is smaller than the width threshold, whether the highest height of the obstacle is smaller than the minimum height of the host vehicle from the ground, and whether the distance between the outer side surface of the first portion and the lane line of the corresponding lane where the host vehicle is located and which is close to the first portion is not smaller than the distance threshold, the method further includes:
and if the width of the second part of the obstacle is greater than the width threshold value, or the highest height of the obstacle is greater than the minimum ground clearance of the vehicle, or the distance between the outer side surface of the first part and the corresponding lane of the lane where the vehicle is located and close to the first part is smaller than the distance threshold value, determining that the obstacle avoidance strategy of the vehicle is collaborative parallel lane changing driving.
In some embodiments, the controlling a host vehicle according to the obstacle avoidance policy includes:
acquiring working condition information of other vehicles based on a V2X technology, and acquiring road condition information from a road test device;
determining a lane capable of being paralleled according to the working condition information and the road condition information;
and controlling the vehicle to change lanes to the lane capable of being paralleled for running.
In a second aspect, an obstacle avoidance device for a road surface of an autonomous vehicle is provided, comprising:
a first acquisition unit configured to acquire a predicted travel trajectory of a host vehicle and acquire road surface color information corresponding to the predicted travel trajectory;
a detection unit for detecting whether an obstacle exists in front of the host vehicle based on the road surface color information;
a second obtaining unit, configured to obtain point cloud information corresponding to the obstacle if the obstacle exists;
a calculation unit for calculating basic information of the obstacle from the point cloud information, the basic information including contour data, size data, concave-convex shape data, and position data of the obstacle;
the strategy determination unit is used for determining an obstacle avoidance strategy of the vehicle according to the basic information, the vehicle body information and the lane information, wherein the obstacle avoidance strategy is normal driving or deceleration driving, in-lane obstacle avoidance driving, in-lane obstacle crossing driving or cooperative parallel lane changing driving;
and the control unit is used for controlling the vehicle according to the obstacle avoidance strategy.
In a third aspect, a computer-readable storage medium is provided, which stores a computer program, which when executed by a processor, implements the aforementioned method for road obstacle avoidance for an autonomous vehicle.
The beneficial effect that technical scheme that this application provided brought includes: the method can effectively identify the hollow ground or small-size road surface obstacles and realize active avoidance of the hollow ground or small-size road surface obstacles.
The application provides a method, a device and a readable storage medium for avoiding obstacles on a road surface of an automatic driving vehicle, which comprises the steps of obtaining a predicted driving track of the vehicle and obtaining road surface color information corresponding to the predicted driving track; detecting whether an obstacle exists in front of the vehicle or not based on the road surface color information; if yes, point cloud information corresponding to the obstacle is obtained; calculating basic information of the obstacle according to the point cloud information, wherein the basic information comprises contour data, size data, concave-convex shape data and position data of the obstacle; determining an obstacle avoidance strategy of the vehicle according to the basic information, the vehicle body information and the lane information of the vehicle, wherein the obstacle avoidance strategy is normal driving or deceleration driving, in-lane obstacle avoidance driving, in-lane obstacle crossing driving or in-lane line crossing and lane changing driving; and controlling the vehicle according to the obstacle avoidance strategy. Through the method and the device, the profile, the concave-convex shape, the size and other relevant information of the barrier can be effectively identified, the convex barrier and the concave barrier on the road are added to adjust local avoidance planning, and then the active avoidance of the barrier on the hollow ground or the small-size road surface is realized, so that the driving safety, the driving comfort and the vehicle suspension protection of the vehicle are facilitated.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
Fig. 1 is a schematic flow chart of a method for avoiding obstacles on a road surface of an autonomous vehicle according to an embodiment of the present disclosure;
fig. 2 is a schematic view of a positional relationship between a convex obstacle and a host vehicle according to an embodiment of the present disclosure;
FIG. 3 is a schematic view illustrating another position relationship between a convex obstacle and a host vehicle according to an embodiment of the present disclosure;
FIG. 4 is a diagram illustrating a numerical relationship between a maximum height above ground of an obstacle and a speed of the host vehicle crossing the obstacle according to an embodiment of the present disclosure;
fig. 5 is a schematic view illustrating a positional relationship between a concave obstacle and a host vehicle according to an embodiment of the present disclosure;
FIG. 6 is a schematic view illustrating another positional relationship between a concave obstacle and a host vehicle according to an embodiment of the present disclosure;
fig. 7 is a schematic view of a positional relationship between a host vehicle and another vehicle according to an embodiment of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are some embodiments of the present application, but not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
The embodiment of the application provides a method and a device for avoiding obstacles on a road surface of an automatic driving vehicle and a readable storage medium, which can solve the problem that the automatic driving vehicle in the related technology can not realize the active avoidance of pothole ground or small-size road surface obstacles.
Fig. 1 is a road obstacle avoidance method for an automatic driving vehicle, which is provided by the embodiment of the application and comprises the following steps:
step S10: acquiring a predicted running track of a vehicle, and acquiring road surface color information corresponding to the predicted running track;
step S20: detecting whether an obstacle exists in front of the vehicle or not based on the road surface color information;
step S30: if yes, point cloud information corresponding to the obstacle is obtained;
step S40: calculating basic information of the obstacle according to the point cloud information, wherein the basic information comprises contour data, size data, concave-convex shape data and position data of the obstacle;
step S50: determining an obstacle avoidance strategy of the vehicle according to the basic information, the vehicle body information and the lane information of the vehicle, wherein the obstacle avoidance strategy is normal driving or deceleration driving, in-lane obstacle avoidance driving, in-lane obstacle crossing driving or in-lane line crossing and lane changing driving;
step S60: and controlling the vehicle according to the obstacle avoidance strategy.
Exemplarily, in the embodiment of the present application, the active obstacle avoidance may be performed based On a Vehicle equipped with a network-connected automatic driving kit, such as a camera, a laser radar, a millimeter wave radar, a GPS (Global Positioning System), an IMU (Inertial Measurement Unit), a wheel speed meter, and an OBU (On board Unit) of V2X (Vehicle to outside information exchange).
The camera can be used for recognizing and classifying obstacles, recognizing traffic signal lamps, recognizing road test signboards and the like; measuring related parameters such as the outline, depth information, distance information, speed information and the like of the obstacle through a laser radar; measuring the distance of an obstacle and the like by a millimeter wave radar; all sensors and information such as V2X, GPS, CAN (Controller Area Network) signals of the whole vehicle and the like are processed through a vehicle main Controller, and decision and control are carried out through a fusion sensing and planning decision module and a control instruction is sent out; vehicle positioning is carried out through a GPS, an IMU, a wheel speed meter and the like, and the IMU and the wheel speed meter are mainly used for auxiliary positioning after the GPS is lost; receiving a Road test message of RSU (Road Side Unit) and V2X equipment or an operation message of a vehicle through an Internet of vehicles cloud platform, and performing overall monitoring and scheduling, storing necessary information, sharing calculation capacity, issuing a control command if necessary and the like; broadcasting Information such as MAP (MAP) Information, space (traffic light phase and timing Information), RSM (Road Safety Message), RSI (Road Side Information), BSM (Basic Safety Message) and the like through the RSU; and displaying a user-friendly Interface through a user HMI (Human Machine Interface), providing some adjustable configuration items for a user to configure on the Interface, and synchronizing the background to take effect in real time.
The present embodiment performs obstacle detection based on color information, that is, divides an image by using a difference in color information between an obstacle and a background area to extract an obstacle area. Specifically, in the process of driving of the automatic driving vehicle, the driving track of the vehicle can be predicted to obtain a predicted driving track, a corresponding road lane line on the predicted driving track and road color change information in the process of predicting the driving track are obtained through a camera, and the change condition of a road color block is detected through the camera; when the fact that the road surface color information is inconsistent with the road surface color information of the road surface background area is detected, and the fact that an obstacle exists in front of the vehicle is indicated, a detection application signal and target position information of the obstacle are sent, laser radar real-time point cloud signals are collected based on the signals, position matching and point cloud information extraction are conducted on the target position information, therefore basic information such as outline information of the obstacle and the position relation between the obstacle and a lane line are extracted, namely 'concave-convex attribute', shape, size, position information and the like of the obstacle can be specifically extracted, then the concave ground or small-size road surface obstacle can be accurately identified, and a label of the convex obstacle or the concave obstacle is added to the obstacle.
Meanwhile, vehicle body information such as a vehicle body load, a minimum ground clearance, a width that can be safely spanned, a speed, acceleration information, a braking distance, and lane information including a lane number, a lane width W, and the like of the host vehicle are acquired. The driving safety distance of the automatic driving vehicle can be determined based on the braking distance, taking a passenger vehicle as an example, the braking distance of the passenger vehicle with the speed of 50KM/h is about 20m, the braking distance of the passenger vehicle with the speed of 30KM/h is 10m, and the braking distance of the passenger vehicle with the speed of 100KM/h is 50m, so that the driving safety distance of the passenger vehicle within the speed of 100KM/h can be set to be half of the speed value.
Then, specifically judging an obstacle avoidance strategy of the vehicle based on basic information, vehicle body information and lane information of the obstacle, for example, considering cooperative merging if the vehicle body cannot safely cross; if the obstacle can be decelerated or crossed at a constant speed in the current lane, obstacle crossing guidance is given; and the vehicle is controlled according to a given obstacle avoidance strategy so as to realize the active avoidance of the obstacles on the hollow ground or the small-size road surface.
For the internet-connected vehicle which is not provided with the sensing equipment, the obstacle avoidance guide or the parallel line guide can be carried out by receiving obstacle positions pushed by the road test equipment or the internet-of-things cloud platform and information such as a GPS, an IMU, a wheel speed meter and the like in the driving process.
Therefore, the method and the device can effectively identify the profile, the concave-convex shape, the size and other relevant information of the barrier, and increase the convex barrier and the concave barrier on the road to adjust the local avoidance plan, so as to realize the active avoidance of the barrier on the hollow ground or the small-size road, and further be beneficial to the driving safety, the driving comfort and the vehicle suspension protection of the vehicle.
Further, when the obstacle is a convex obstacle, determining an obstacle avoidance strategy of the vehicle according to the basic information, the vehicle body information and the lane information of the vehicle includes:
when the highest height of the obstacle is smaller than the height threshold value, determining that the obstacle avoidance strategy of the vehicle is normal running;
when the highest height of the obstacle is detected to be larger than or equal to the height threshold value, judging whether the transverse size of the obstacle is larger than or equal to the sum of the widths of all co-directional driving lanes;
and if so, determining that the obstacle avoidance strategy of the vehicle is deceleration driving.
Exemplarily, in the embodiment of the present application, the information (such as the minimum ground clearance H of the vehicle body) is determined according to the vehicle bodyminCurrent gross vehicle weight GtotalSpring travel l of damping systemkAnd coefficient of elasticity k, vehicle front tread LfAnd rear track LbMin (L) of mediumf,Lb) Etc.) and combines the obstacle information and the lane information to judge whether the vehicle should cross the obstacle or change the lane to avoid. For example, whether the vehicle should cross an obstacle or change the lane to avoid can be judged based on the height of the obstacle or the depth of the recess.
Referring to fig. 2 and fig. 3, because the obstacle avoidance principle of the convex obstacle and the concave obstacle is similar, for the simplicity of description, the following embodiments in the present application are explained by taking the obstacle as the convex obstacle as an example: detecting whether the highest height H of the obstacle from the ground is less than a height threshold (the height threshold is based on the minimum ground-to-ground distance H of the vehicle body)minIf yes, the obstacle does not obstruct the normal running of the vehicle, namely, the vehicle can normally cross the obstacle, so that the obstacle avoidance strategy of the vehicle is determined to be normal running; if not, it is determined that the obstacle may hinder the normal driving of the vehicle, and therefore, it is further determined whether the transverse dimension of the obstacle is greater than the sum of the widths of the lanes in the same direction (the lanes in the same direction refer to lanes in the same direction as the driving direction of the vehicle, for example, if the driving direction of the vehicle is the east direction, the lanes in the east direction are the lanes in the same direction); if the cross of the obstacleWhen the size is larger than or equal to the sum of the widths of the lanes running in the same direction, the obstacle covers all the lanes running in the same direction, namely, no other lanes are available for the vehicles to change lanes for avoiding, at the moment, the vehicles can only adopt a strategy of passing through in a decelerating way, and the vehicles can safely cross the obstacle, so that the obstacle avoiding strategy of the vehicle can be judged to be in the decelerating way.
The speed of the vehicle crossing the obstacle can be further determined according to the highest height h from the ground of the obstacle, specifically, as shown in fig. 4, the highest height h from the ground of the obstacle and the speed v of the vehicle crossing the obstacleallowThe numerical relationship between them is: when H is presentmin≥h≥hsetor-Hmin≤h≤hsetThen, thenWhen-hset<h<hsetWhen it is, thenWherein h issetIndicating a height threshold or a depth threshold, i.e. hsetIs a positive value representing a height threshold for a convex obstacle, hsetA negative value represents a threshold depth value for a concave obstacle, the default value of which may be based on the minimum body clearance HminSet to 10cm, vlimitIs the highest speed limit of the current road section, vsetTo pass through a height threshold of hsetOr a depth threshold of-hsetThe vehicle speed of the obstacle may be set to 30Km/h as a default value. For example, if the height h of the obstacle from the ground exceeds 10cm, the speed of the vehicle crossing the obstacle needs to be reduced to within 30 Km.
Further, after the step of determining whether the transverse dimension of the obstacle is greater than or equal to the sum of the widths of all co-running lanes, the method further includes:
if the transverse size of the obstacle is smaller than the sum of the widths of all co-directional driving lanes, detecting whether a first part with the height smaller than the height threshold value exists in the obstacle;
if the vehicle exists, calculating the sum of the distance between the outer side surface of the first part and the lane line, close to the first part, of the lane where the vehicle is located, and the width of the first part to obtain a first width;
when the difference value between the first width and the vehicle body width of the vehicle is larger than or equal to the difference threshold value, determining that the obstacle avoidance strategy of the vehicle is in-lane crossing obstacle driving, and the in-lane crossing obstacle driving is guiding the vehicle to drive on a road corresponding to the first width.
For example, in the embodiment of the present application, if it is detected that the lateral size of the obstacle is smaller than the sum of the widths of the lanes traveling in the same direction, it is indicated that the obstacle does not cover all the lanes traveling in the same direction, and even the lane where the vehicle is located may not be completely covered by the obstacle, and the vehicle may avoid the obstacle or cross the obstacle in the lane traveling in the vehicle, so it is necessary to further determine whether there is a first portion of the obstacle whose height is smaller than the height threshold.
Referring to fig. 2, where L represents a wheel track, if a first portion with an obstacle height smaller than a height threshold is detected, which indicates that there is a distance between the top of the first portion and the bottom of the host vehicle (where the tire of the host vehicle is located on the ground), the sum of the distance N1 between the outer side surface of the first portion of the obstacle and the lane on the same side of the lane where the host vehicle is located, and the width N2 of the first portion is further calculated, so as to obtain a first width N3; when it is further detected that the difference between the first width N3 and the vehicle body width of the host vehicle is greater than or equal to the difference threshold, which indicates that the first width N3 is sufficient for the host vehicle to easily cross the obstacle at this time, it is determined that the obstacle avoidance strategy of the host vehicle is in-lane crossing obstacle driving, and the host vehicle is guided to drive on the road corresponding to the first width N3.
In addition, if the obstacle is a concave obstacle, as shown in fig. 5, when the lateral dimension of the obstacle is smaller than the wheel track L of the vehicle, it is determined that the obstacle avoidance strategy of the vehicle is in-lane crossing obstacle driving; and if the transverse size of the obstacle is smaller than the sum of the widths of the equidirectional driving lanes, detecting that the depth of the depression of the obstacle is larger than the depth threshold value and the transverse length l of the obstacle is larger than the depth threshold valueWherein r is the radius of the wheels of the vehicle, h is the deepest recess depth of the obstacle, and the obstacle avoidance strategy of the vehicle is determined to be in-lane crossing obstacle driving; referring to fig. 6, if the distance between the portion of the obstacle with the depression depth lower than the depth threshold value and the lane line on the other side is greater than 10cm of the vehicle body width, it may also be determined that the obstacle avoidance strategy of the vehicle is in-lane crossing obstacle driving; otherwise, the obstacle avoidance condition in the lane is deemed not to be satisfied, and at the moment, the vehicle needs to be considered to be controlled to carry out the collaborative parallel lane changing driving.
Further, after the step of detecting whether the obstacle has a first portion with a height smaller than the height threshold, the method further includes:
if the obstacle does not have a first part with the height smaller than the height threshold, respectively calculating the distance between two side faces of the obstacle and the lane line on the same side of the lane where the vehicle is located;
when the difference value between the distance between one side face of the obstacle and the corresponding lane line on the same side and the width of the vehicle body of the vehicle is larger than or equal to the difference threshold value, determining that the obstacle avoidance strategy of the vehicle is to drive the vehicle to avoid the obstacle in the road, and the drive to avoid the obstacle in the road is to guide the vehicle to drive away from the obstacle.
Further, after the step of calculating the distance between the two side surfaces of the obstacle and the lane on the same side of the lane where the host vehicle is located, the method further includes:
and when the difference between the distance between the two side faces of the obstacle and the corresponding lane lines on the same side and the width of the vehicle body of the vehicle is smaller than the difference threshold value, determining that the obstacle avoidance strategy of the vehicle is collaborative parallel lane changing driving.
For example, in the embodiment of the present application, if it is detected that there is no first portion with a height smaller than the height threshold, it is indicated that the heights of the shortest portions of the obstacles are all greater than the height threshold, and at this time, if the host vehicle is forced to cross the obstacle, a safety accident may occur, so that this embodiment further determines whether a difference between an interval between two sides of the obstacle and a width of the host vehicle is greater than or equal to the difference threshold (the difference threshold may be set to other specific values such as 0, 1cm, or 2cm, and may be determined according to actual requirements). If it is detected that the difference between the distance between one side (for example, the left side) of the obstacle and the corresponding lane line on the same side (for example, the lane line on the left side) and the width of the vehicle body of the vehicle is greater than or equal to the difference threshold, it is indicated that the distance between the side (for example, the left side) of the obstacle and the corresponding lane line on the same side (for example, the lane line on the left side) is enough for the vehicle to perform obstacle avoidance driving in the lane after avoiding the obstacle, that is, the vehicle is guided to travel away from the obstacle in the lane.
However, if it is detected that the difference between the distance between any one side of the obstacle and the corresponding lane on the same side and the width of the vehicle body of the vehicle is smaller than the difference threshold, it is indicated that the distance between any one side of the obstacle and the corresponding lane on the same side is not enough for the vehicle to perform obstacle avoidance driving in the lane after avoiding the obstacle, and at this time, the vehicle needs to be considered to perform cooperative lane merging and lane changing driving instead of emergency braking.
Further, after the step of calculating the sum of the distance between the outer side surface of the first portion and the lane line, close to the first portion, of the lane where the host vehicle is located and the corresponding outer side surface of the first portion, and the width of the first portion to obtain the first width, the method further includes:
when the difference value between the first width and the vehicle body width of the vehicle is smaller than a difference threshold value, judging whether the width of a second part of an obstacle is smaller than the width threshold value, whether the highest height of the obstacle is smaller than the minimum ground clearance of the vehicle, and whether the distance between the outer side surface of the first part and a lane line, close to the first part, of a lane where the vehicle is located, of the first part is not smaller than a distance threshold value, wherein the second part of the obstacle is a part with the height larger than or equal to the height threshold value, the width threshold value is determined based on the wheel distance, and the distance threshold value is determined based on the tire width and the vehicle speed;
if the width of the second part of the obstacle is smaller than the width threshold value, the highest height of the obstacle is smaller than the minimum ground clearance of the vehicle, and the distance between the outer side surface of the first part and the lane line, close to the first part, of the lane where the vehicle is located, of the first part is not smaller than the distance threshold value, the obstacle avoidance strategy of the vehicle is determined to be in-lane crossing obstacle running, and the in-lane crossing obstacle running is to guide the vehicle to run on the lane corresponding to the first width.
For example, in the embodiment of the present application, if it is detected that the difference between the first width N3 and the vehicle body width of the host vehicle is smaller than the difference threshold, which indicates that the first width N3 may not be sufficient for the host vehicle to easily cross the obstacle (i.e. when the tire of the host vehicle is on the ground, there is no gap between the top of the obstacle and the bottom of the host vehicle), it needs to be further determined whether the width of the second portion of the obstacle is smaller than the width threshold (the width threshold is determined based on the wheel distance L, for example, the width threshold may be preset to L-20cm), whether the highest height of the obstacle is smaller than the minimum ground clearance of the host vehicle (if the vehicle has a chassis lifting function, the vehicle is controlled to lift the chassis, the height of the raised chassis is counted in the minimum ground clearance), and whether the distance between the outer side surface of the first portion and the lane of the host vehicle corresponding to the first portion close to the first portion is not smaller than the distance threshold (the distance threshold is determined based on the tire width and the vehicle speed, for example, the distance threshold may be preset to 30 cm).
When it is detected that the width of the second part of the obstacle is smaller than the width threshold value, the highest height of the obstacle is smaller than the minimum ground clearance of the vehicle, and the distance between the outer side surface of the first part and the lane line, close to the first part, of the lane where the vehicle is located is not smaller than the distance threshold value, it is indicated that the vehicle can drive across the obstacle in the lane by pressing the obstacle by one side of the tire, so that the vehicle can be guided to drive on the road corresponding to the first width.
Further, after the step of determining whether the width of the second portion of the obstacle is smaller than the width threshold, whether the highest height of the obstacle is smaller than the minimum ground clearance of the vehicle, and whether the distance between the outer side surface of the first portion and the lane line of the corresponding lane where the vehicle is located and which is close to the first portion is not smaller than the distance threshold, the method further includes:
and if the width of the second part of the obstacle is greater than the width threshold value, or the highest height of the obstacle is greater than the minimum ground clearance of the vehicle, or the distance between the outer side surface of the first part and the corresponding lane of the lane where the vehicle is located and close to the first part is smaller than the distance threshold value, determining that the obstacle avoidance strategy of the vehicle is collaborative parallel lane changing driving.
Exemplarily, in the embodiment of the present application, when it is detected that the width of the second portion of the obstacle is greater than the width threshold, or the highest height of the obstacle is greater than the minimum ground clearance of the host vehicle, or the distance between the outer side surface of the first portion and the lane line of the corresponding lane where the host vehicle is located, which is close to the first portion, is less than the distance threshold, it is indicated that the host vehicle cannot perform obstacle crossing driving in the lane, and at this time, it is necessary to consider that the host vehicle performs cooperative lane merging and lane changing driving instead of emergency braking.
Further, the controlling the vehicle according to the obstacle avoidance strategy includes:
acquiring working condition information of other vehicles based on a V2X technology, and acquiring road condition information from a road test device;
determining a lane capable of being paralleled according to the working condition information and the road condition information;
and controlling the vehicle to change lanes to the lane capable of being paralleled for running.
Exemplarily, in the embodiment of the present application, if it is not feasible to avoid the obstacle or perform crossing guidance in the lane, the intelligent network connection type parallel guidance is entered. According to the lane merging judgment method, the merging possibility of adjacent lanes is judged by preferentially using the fusion perception data of the perception sensors such as the camera, the laser radar, the blind-filling radar and the millimeter wave radar, and if lanes which can be merged exist, the lanes which are adjacent to the obstacles and have smaller distance are preferentially merged. Referring to FIG. 7, the lane-to-lane decision is made such that the distance between the front and rear of the translation position of the vehicle in the adjacent lane is equal(wherein, LDis≥2Lcar0,Lcar0The length of the vehicle) and the range between the 1, 3 or 2, 4 position blocks around the vehicle are not provided with vehicles or static obstacles, the lanes can be considered to be directly merged. If no lane capable of being directly merged is available on both sides of the vehicle, the cooperation merging through the communication of V2X, GPS, high-precision map, inertial navigation and the like is considered, and the cooperation merging comprises prompting that the adjacent vehicle to be merged into the lane accelerates or decelerates to pass.
The embodiment is carried out according to the preferential selection of the lane far away from the obstacleThe thread principle is used for doubling and guiding. Specifically, the weighted value of the lane close to the obstacle is preset to 1, if there is a vehicle in the position 1, the position 2, the position 3 and the position 4 in fig. 7, the weighted value of each position is preset to 4, and if there is an obstacle to be crossed or to be avoided in a certain lane, the weighted value of the lane is preset to 4; the weighted value of the speed of the adjacent vehicle at No. 1, No. 2, No. 3 and No. 4 is lambda f (v)o,aoV, a, TTC), where λ is the adjustment coefficient, f is the correlation function used to calculate the vehicle speed weighting value, voIs the speed of the vehicle, aoThe vehicle acceleration is the vehicle acceleration, v is the adjacent vehicle speed, a is the acceleration, TTC is the collision time, the weighted value of the adjacent vehicle speed can be determined according to the actual situation, when the adjacent vehicle speeds of the No. 1 position and the No. 2 position are faster, the weighted value is lower, even can be a negative number, and when the adjacent vehicle speeds of the No. 3 position and the No. 4 position are slower, the weighted value is lower, even can be a negative number; the weighted values of the attributes are added, and the smaller the obtained value is, the more suitable the lane is as a lane capable of being lined up.
Wherein, the calculation to the weighted value of No. 1 position, No. 2 position, No. 3 position and No. 4 position can be degenerated into the instantaneous space that calculates the vehicle current place, the area size of No. 1 position, No. 2 position, No. 3 position and No. 4 position block, and further, can also degenerated into the length size of calculating No. 1 position, No. 2 position, No. 3 position and No. 4 position block.
This embodiment will be further explained with reference to fig. 7.
The first vehicle in position 1, position 2, position 3 and position 4 is denoted as C1, C2, C3, C4, respectively. For example, the weight M of the distance from the front end of the vehicle C3 in the No. 3 position to the front side line of the No. 3 position in the figure3Is composed ofWherein λ is an adjustment coefficient, voIs the speed of the vehicle, aoIs the acceleration of the vehicle, v3The vehicle speed of the vehicle C3, a3Is the acceleration of the vehicle C3,
respectively calculating the vehicle speed weighted values of the vehicles on the No. 1 position, the No. 2 position, the No. 3 position and the No. 4 position:
(1) when the obstacle is in front of the vehicle LDisWithin the distance or No. 3 position, No. 4 positions all do not have other vehicles to encroach on, then only consider the target location and carry out the guidance of drawing a parallel line for No. 3 position and No. 4 position, specific:
when no vehicle exists in the No. 1 position, the weighted value of the vehicle speed of the No. 3 vehicle C3 is as follows:
when the vehicle exists in the No. 1 position, the vehicle speed weighted value of the vehicle C3 in the No. 3 position is as follows:
wherein λ issingle,λmult,β,γ,Are all corrected values, determined according to the actual conditions, as shown in FIG. 7, alphaLIs an included angle alpha between the connecting line of the point at the outermost right front side of the vehicle and the point at the outermost left rear side of the obstacle and the direction vertical to the lane lineL0Is the angle between the speed direction of the vehicle and the tangent line of the adjacent lane line on the left side, WL0The vertical distance between the outermost point at the left front of the vehicle and the adjacent lane line, v1The vehicle speed of the vehicle C1, a1Is the acceleration of the vehicle C1.
When no vehicle exists in the No. 2 position, the vehicle speed weighted value of the No. 4 vehicle C4 is as follows:
when the vehicle exists in the No. 2 position, the vehicle speed weighted value of the vehicle C4 in the No. 4 position is as follows:
wherein λ issingle,λmult,β,γ,Are all corrected values, determined according to the actual conditions, as shown in FIG. 7, alphaRIs an included angle alpha between the connecting line of the outermost point at the left front side of the vehicle and the outermost point at the right rear side of the obstacle and the direction vertical to the lane lineR0Is the angle between the speed direction of the vehicle and the tangent line of the right lane line, WR0Is the vertical distance between the outermost point on the right front side of the vehicle and the adjacent lane line, v2The vehicle speed of the vehicle C2, a2Is the acceleration of the vehicle C2.
(2) When the obstacle is in front of the vehicle LDisOutside the distance, the target position is considered to be the No. 1 position, the No. 2 position, the No. 3 position and the No. 4 position for the doubling guide, however, because of the existence of the obstacle, the deceleration doubling is preferentially considered, namely whether the image block positions of the No. 3 position and the No. 4 position meet the conditions or not is preferentially calculated, specifically:
when no vehicle encroachment in No. 3 position and No. 4 position, then the weight in No. 3 position and No. 4 position is respectively:
guiding the vehicle to be merged to a position with a smaller weight, and broadcasting a guiding operation; however, if there is a vehicle encroaching at one of the positions 3 and 4, the host vehicle is directly guided to merge to a position block where there is no vehicle encroachment.
When No. 3 position and No. 4 position all have the vehicle to encroach on, then:
if the No. 1 position is not in the vehicle, the weighted value of the vehicle speed of the No. 3 vehicle C3 is as follows:
if the No. 1 vehicle exists, the weighted value of the vehicle speed of the No. 3 vehicle C3 is as follows:
if the No. 2 vehicle is not in the vehicle, the weighted value of the vehicle speed of the No. 4 vehicle C4 is as follows:
if the vehicle is in the No. 2 position, the weighted value of the vehicle speed of the No. 4 vehicle C4 is as follows:
and finally, comparing the M1, the M2, the M3 and the M4, and selecting the lane corresponding to the lowest weighted value as a joinable lane. However, if there are vehicles in the 1 st and 3 rd positions and there are vehicles in the 2 nd and 4 th positions and it is necessary to receive the vehicle for merging, the weight comparison is not performed in principle, but the acceleration of the vehicle C1 in the 1 st position or the vehicle C2 in the 2 nd position is directly guided, and the deceleration of the vehicle C3 in the 3 rd position or the vehicle C4 in the 4 th position is simultaneously guided, so as to achieve the cooperative merging.
After selecting the lane with smaller weighted value, if the vehicle speed on the No. 1 position, the No. 2 position, the No. 3 position and the No. 4 position is not ideal, the available position is less than LDisThen the vehicle in the target lane is informed through V2X: the vehicles are about to merge, and the vehicles at No. 1 or No. 2 are requested to accelerate and keep in the current lane or to merge to the non-vehicle lane for driving away, and the vehicles at No. 3 or No. 4 are requested to decelerate or to merge to the non-vehicle lane for driving away.
The vehicles on the No. 1 position, the No. 2 position, the No. 3 position and the No. 4 position respectively and simultaneously calculate the weighted values of self acceleration, deceleration and doubling and reply to the vehicle; after receiving the reply, the vehicle accelerates or decelerates or merges the vehicles with the lowest notification weighted value, and simultaneously sends the conclusion to the vehicles participating in the cooperative merging; after the vehicle is confirmed, the vehicle with the lowest weighted value performs operation in a mode of lowest weighted value, and other vehicles can perform behavior adjustment according to the operation of the vehicle with the lowest weighted value and real-time parameters such as vehicle speed and acceleration of the vehicle, so that the vehicle can be safely merged into a target lane. And when the vehicle is merged into the lane where the vehicle with the lowest weighted value is located, the merging is completed.
The embodiment of the present application still provides an obstacle avoidance device for a road surface of an automatic driving vehicle, including:
a first acquisition unit configured to acquire a predicted travel trajectory of a host vehicle and acquire road surface color information corresponding to the predicted travel trajectory;
a detection unit for detecting whether an obstacle exists in front of the host vehicle based on the road surface color information;
a second obtaining unit, configured to obtain point cloud information corresponding to the obstacle if the obstacle exists;
a calculation unit for calculating basic information of the obstacle from the point cloud information, the basic information including contour data, size data, concave-convex shape data, and position data of the obstacle;
the strategy determining unit is used for determining an obstacle avoidance strategy of the vehicle according to the basic information, the vehicle body information and the lane information of the vehicle, wherein the obstacle avoidance strategy is normal driving or deceleration driving, obstacle avoidance driving in a lane, obstacle crossing driving in the lane or cooperative parallel lane changing driving;
and the control unit is used for controlling the vehicle according to the obstacle avoidance strategy.
Through the method and the device, the profile, the concave-convex shape, the size and other relevant information of the barrier can be effectively identified, the convex barrier and the concave barrier on the road are added to adjust local avoidance planning, and then the active avoidance of the barrier on the hollow ground or the small-size road surface is realized, so that the driving safety, the driving comfort and the vehicle suspension protection of the vehicle are facilitated.
Further, when the obstacle is a convex obstacle, the policy determination unit is specifically configured to:
when the highest height of the obstacle is smaller than the height threshold value, determining that the obstacle avoidance strategy of the vehicle is normal running;
when the highest height of the obstacle is detected to be larger than or equal to the height threshold value, judging whether the transverse size of the obstacle is larger than or equal to the sum of the widths of all co-directional driving lanes;
and if so, determining that the obstacle avoidance strategy of the vehicle is deceleration driving.
Further, the policy determining unit is further configured to:
if the transverse size of the obstacle is smaller than the sum of the widths of all co-directional driving lanes, detecting whether a first part with the height smaller than the height threshold value exists in the obstacle;
if the vehicle exists, calculating the sum of the distance between the outer side surface of the first part and the lane line, close to the first part, of the lane where the vehicle is located, and the width of the first part to obtain a first width;
when the difference value between the first width and the vehicle body width of the vehicle is larger than or equal to the difference threshold value, determining that the obstacle avoidance strategy of the vehicle is in-lane crossing obstacle driving, and the in-lane crossing obstacle driving is guiding the vehicle to drive on a road corresponding to the first width.
Further, the policy determination unit is further configured to:
if the obstacle does not have a first part with the height smaller than the height threshold, respectively calculating the distance between two side faces of the obstacle and the lane line on the same side of the lane where the vehicle is located;
when the difference value between the distance between one side face of the obstacle and the corresponding lane line on the same side and the width of the vehicle body of the vehicle is larger than or equal to the difference threshold value, determining that the obstacle avoidance strategy of the vehicle is to drive the vehicle to avoid the obstacle in the road, and the drive to avoid the obstacle in the road is to guide the vehicle to drive away from the obstacle.
Further, the policy determination unit is further configured to:
and when the difference between the distance between the two side faces of the obstacle and the corresponding lane lines on the same side and the width of the vehicle body of the vehicle is smaller than the difference threshold value, determining that the obstacle avoidance strategy of the vehicle is collaborative parallel lane changing driving.
Further, the policy determination unit is further configured to:
when the difference value between the first width and the vehicle body width of the vehicle is smaller than a difference threshold value, judging whether the width of a second part of an obstacle is smaller than the width threshold value, whether the highest height of the obstacle is smaller than the minimum ground clearance of the vehicle, and whether the distance between the outer side surface of the first part and a lane line, close to the first part, of a lane where the vehicle is located, of the first part is not smaller than a distance threshold value, wherein the second part of the obstacle is a part with the height larger than or equal to the height threshold value, the width threshold value is determined based on the wheel distance, and the distance threshold value is determined based on the tire width and the vehicle speed;
if the width of the second part of the obstacle is smaller than the width threshold value, the highest height of the obstacle is smaller than the minimum ground clearance of the vehicle, and the distance between the outer side surface of the first part and the lane line, close to the first part, of the lane where the vehicle is located, of the first part is not smaller than the distance threshold value, the obstacle avoidance strategy of the vehicle is determined to be in-lane crossing obstacle running, and the in-lane crossing obstacle running is to guide the vehicle to run on the lane corresponding to the first width.
Further, the policy determining unit is further configured to:
and if the width of the second part of the obstacle is greater than the width threshold value, or the highest height of the obstacle is greater than the minimum ground clearance of the vehicle, or the distance between the outer side surface of the first part and the corresponding lane of the lane where the vehicle is located and close to the first part is smaller than the distance threshold value, determining that the obstacle avoidance strategy of the vehicle is collaborative parallel lane changing driving.
Further, the control unit is specifically configured to:
acquiring working condition information of other vehicles based on a V2X technology, and acquiring road condition information from a road test device;
determining a lane capable of being paralleled according to the working condition information and the road condition information;
and controlling the vehicle to change lanes to the lane capable of being paralleled for running.
Therefore, the embodiment of the application provides a road surface obstacle avoidance automatic driving device based on vehicle end, road test and cloud collaborative sensing, and the device can be used for solving the main problems that the existing automatic driving vehicle cannot actively avoid pothole ground, small and short road surface obstacles and the like during local planning. If the vehicle speed is high, the emergency braking can not avoid collision or can not avoid accidents caused by the fact that the vehicle falls into a pit, the emergency braking can be replaced by coordinating and combining the vehicle according to the surrounding vehicle states (such as the vehicle speed, the position, the acceleration and the like); meanwhile, the size information and specific coordinates of the convex or concave road surface are informed to other vehicles, road testing equipment and a cloud end through the V2X so as to be referred by other vehicles and road surface maintenance systems, and the obstacle avoidance parameters can be configured through a user HMI (human machine interface), so that the universality of the system to different vehicle types and vehicle conditions and the regulation and control performance of passengers on the driving comfort level are enhanced.
It should be noted that, as will be clearly understood by those skilled in the art, for convenience and brevity of description, the specific working processes of the above-described apparatus and each unit may refer to the corresponding processes in the foregoing embodiments of the method for avoiding obstacles on a road surface of an automatically-driven vehicle, and are not described herein again.
The embodiment of the application also provides a computer readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, all steps or part of steps of the above-mentioned road obstacle avoidance method for the automatically-driven vehicle are realized.
The embodiments of the present application may implement all or part of the foregoing processes, or may be implemented by a computer program to instruct related hardware, where the computer program may be stored in a computer-readable storage medium, and when the computer program is executed by a processor, the computer program may implement the steps of the foregoing methods. Wherein the computer program comprises computer program code, which may be in the form of source code, object code, an executable file or some intermediate form, etc. The computer readable medium may include: any entity or device capable of carrying computer program code, recording medium, U.S. disk, removable hard disk, magnetic diskette, optical disk, computer memory, Read-Only memory (ROM), Random Access Memory (RAM), electrical carrier signal, telecommunications signal, software distribution medium, etc. It should be noted that the computer readable medium may contain other components which may be suitably increased or decreased as required by legislation and patent practice in jurisdictions, for example, in some jurisdictions, in accordance with legislation and patent practice, the computer readable medium does not include electrical carrier signals and telecommunications signals.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, server, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, optical storage, and the like) having computer-usable program code embodied therein.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or system. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in the process, method, article, or system in which the element is included.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The above description is merely exemplary of the present application and is presented to enable those skilled in the art to understand and practice the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the application. Thus, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (10)
1. A road obstacle avoidance method for an automatic driving vehicle is characterized by comprising the following steps:
acquiring a predicted running track of a vehicle, and acquiring road surface color information corresponding to the predicted running track;
detecting whether an obstacle exists in front of the vehicle or not based on the road surface color information;
if yes, point cloud information corresponding to the obstacle is obtained;
calculating basic information of the obstacle according to the point cloud information, wherein the basic information comprises contour data, size data, concave-convex shape data and position data of the obstacle;
determining an obstacle avoidance strategy of the vehicle according to the basic information, the vehicle body information and the lane information of the vehicle, wherein the obstacle avoidance strategy is normal driving or deceleration driving, in-lane obstacle avoidance driving, in-lane obstacle crossing driving or in-lane line crossing and lane changing driving;
and controlling the vehicle according to the obstacle avoidance strategy.
2. The method for avoiding obstacles on road surface of automatic vehicle as claimed in claim 1, wherein when the obstacle is a convex obstacle, the determining the obstacle avoidance strategy of the vehicle according to the basic information, the vehicle body information and the lane information comprises:
when the highest height of the obstacle is smaller than the height threshold value, determining that the obstacle avoidance strategy of the vehicle is normal running;
when the highest height of the obstacle is detected to be larger than or equal to the height threshold value, judging whether the transverse size of the obstacle is larger than or equal to the sum of the widths of all co-directional driving lanes;
if so, determining that the obstacle avoidance strategy of the vehicle is deceleration driving.
3. The method of claim 2, wherein after the step of determining whether the lateral dimension of the obstacle is greater than or equal to the sum of the widths of all co-directional driving lanes, the method further comprises:
if the transverse size of the obstacle is smaller than the sum of the widths of all co-directional driving lanes, detecting whether a first part with the height smaller than the height threshold value exists in the obstacle;
if the vehicle exists, calculating the sum of the distance between the outer side surface of the first part and the lane line, close to the first part, of the lane where the vehicle is located, and the width of the first part to obtain a first width;
when the difference value between the first width and the vehicle body width of the vehicle is larger than or equal to the difference threshold value, determining that the obstacle avoidance strategy of the vehicle is in-lane crossing obstacle driving, and the in-lane crossing obstacle driving is guiding the vehicle to drive on a road corresponding to the first width.
4. A method of obstacle avoidance for an autonomous vehicle as claimed in claim 3, wherein after said step of detecting whether said obstacle has a first portion with a height less than said height threshold, further comprising:
if the obstacle does not have a first part with the height smaller than the height threshold, respectively calculating the distance between two side faces of the obstacle and the lane line on the same side of the lane where the vehicle is located;
when the difference value between the distance between one side face of the obstacle and the corresponding lane line on the same side and the width of the vehicle body of the vehicle is larger than or equal to the difference threshold value, determining that the obstacle avoidance strategy of the vehicle is to drive the vehicle to avoid the obstacle in the road, and the drive to avoid the obstacle in the road is to guide the vehicle to drive away from the obstacle.
5. The method for avoiding obstacles on road surface of automatic vehicle as claimed in claim 4, wherein after the step of calculating the distance between two side surfaces of the obstacle and the lane on the same side of the corresponding lane, further comprising:
and when the difference between the distance between the two side faces of the obstacle and the corresponding lane lines on the same side and the width of the vehicle body of the vehicle is smaller than the difference threshold value, determining that the obstacle avoidance strategy of the vehicle is collaborative parallel lane changing driving.
6. The method as claimed in claim 3, further comprising, after the step of calculating a sum of a distance between an outer side of the first portion and a lane line of the corresponding lane where the host vehicle is located and close to the first portion and a width of the first portion to obtain the first width:
when the difference value between the first width and the vehicle body width of the vehicle is smaller than a difference threshold value, judging whether the width of a second part of an obstacle is smaller than the width threshold value, whether the highest height of the obstacle is smaller than the minimum ground clearance of the vehicle, and whether the distance between the outer side surface of the first part and a lane line, close to the first part, of a lane where the vehicle is located, of the first part is not smaller than a distance threshold value, wherein the second part of the obstacle is a part with the height larger than or equal to the height threshold value, the width threshold value is determined based on the wheel distance, and the distance threshold value is determined based on the tire width and the vehicle speed;
if the width of the second part of the obstacle is smaller than the width threshold value, the highest height of the obstacle is smaller than the minimum ground clearance of the vehicle, and the distance between the outer side surface of the first part and the lane line, close to the first part, of the lane where the vehicle is located, of the first part is not smaller than the distance threshold value, the obstacle avoidance strategy of the vehicle is determined to be in-lane crossing obstacle running, and the in-lane crossing obstacle running is to guide the vehicle to run on the lane corresponding to the first width.
7. The method as claimed in claim 6, further comprising, after the step of determining whether the width of the second portion of the obstacle is smaller than the width threshold, the maximum height of the obstacle is smaller than the minimum height of the vehicle, and the distance between the outer side surface of the first portion and the corresponding lane line of the lane where the vehicle is located and close to the first portion is not smaller than the distance threshold:
and if the width of the second part of the obstacle is greater than the width threshold value, or the highest height of the obstacle is greater than the minimum ground clearance of the vehicle, or the distance between the outer side surface of the first part and the corresponding lane of the lane where the vehicle is located and close to the first part is smaller than the distance threshold value, determining that the obstacle avoidance strategy of the vehicle is collaborative parallel lane changing driving.
8. The method for avoiding obstacles on road surface by using automatic driving vehicle as claimed in claim 5 or 7, wherein the controlling the vehicle according to the obstacle avoiding strategy comprises:
acquiring working condition information of other vehicles based on a V2X technology, and acquiring road condition information from a road test device;
determining a lane capable of being paralleled according to the working condition information and the road condition information;
and controlling the vehicle to change lanes to the lane capable of being paralleled for running.
9. The utility model provides an obstacle-avoiding device for automatic driving vehicle road surface, which is characterized in that includes:
a first acquisition unit configured to acquire a predicted travel trajectory of a host vehicle and acquire road surface color information corresponding to the predicted travel trajectory;
a detection unit for detecting whether an obstacle exists in front of the host vehicle based on the road surface color information;
a second obtaining unit, configured to obtain point cloud information corresponding to the obstacle if the obstacle exists;
a calculation unit for calculating basic information of the obstacle from the point cloud information, the basic information including contour data, size data, concave-convex shape data, and position data of the obstacle;
the strategy determining unit is used for determining an obstacle avoidance strategy of the vehicle according to the basic information, the vehicle body information and the lane information of the vehicle, wherein the obstacle avoidance strategy is normal driving or deceleration driving, obstacle avoidance driving in a lane, obstacle crossing driving in the lane or cooperative parallel lane changing driving;
and the control unit is used for controlling the vehicle according to the obstacle avoidance strategy.
10. A computer-readable storage medium characterized by: the computer storage medium stores a computer program which, when executed by a processor, implements the method of road obstacle avoidance for an autonomous vehicle of any of claims 1 to 8.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210343173.8A CN114559961A (en) | 2022-03-31 | 2022-03-31 | Method and device for avoiding obstacles on road surface of automatic driving vehicle and readable storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210343173.8A CN114559961A (en) | 2022-03-31 | 2022-03-31 | Method and device for avoiding obstacles on road surface of automatic driving vehicle and readable storage medium |
Publications (1)
Publication Number | Publication Date |
---|---|
CN114559961A true CN114559961A (en) | 2022-05-31 |
Family
ID=81719462
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210343173.8A Pending CN114559961A (en) | 2022-03-31 | 2022-03-31 | Method and device for avoiding obstacles on road surface of automatic driving vehicle and readable storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114559961A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114708567A (en) * | 2022-06-06 | 2022-07-05 | 济南融瓴科技发展有限公司 | Road surface depression detection and avoidance method and system based on binocular camera |
WO2023241672A1 (en) * | 2022-06-18 | 2023-12-21 | Huimin Li | Bipolar coordinate multi-line laser beam structured light method, apparatus and application thereof |
-
2022
- 2022-03-31 CN CN202210343173.8A patent/CN114559961A/en active Pending
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114708567A (en) * | 2022-06-06 | 2022-07-05 | 济南融瓴科技发展有限公司 | Road surface depression detection and avoidance method and system based on binocular camera |
WO2023241672A1 (en) * | 2022-06-18 | 2023-12-21 | Huimin Li | Bipolar coordinate multi-line laser beam structured light method, apparatus and application thereof |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110488802B (en) | Decision-making method for dynamic behaviors of automatic driving vehicle in internet environment | |
JP6804596B2 (en) | Processing equipment | |
US20210188356A1 (en) | Vehicle control device | |
US20210188262A1 (en) | Vehicle control device | |
US20210188258A1 (en) | Vehicle control device | |
CN103158705B (en) | Method and system for controlling a host vehicle | |
US20210009115A1 (en) | Vehicle control device | |
CN114559961A (en) | Method and device for avoiding obstacles on road surface of automatic driving vehicle and readable storage medium | |
US20130197736A1 (en) | Vehicle control based on perception uncertainty | |
WO2017126250A1 (en) | Driving assistance method and device | |
EP3715204A1 (en) | Vehicle control device | |
CN107848537A (en) | Automatic Pilot servicing unit, automatic Pilot householder method and automatic Pilot auxiliary program | |
CN105848981A (en) | Method and system for driver assistance for a vehicle | |
US20200180614A1 (en) | Vehicle control device | |
CN104340152A (en) | Dynamic safety shields for situation assessment and decision making in collision avoidance tasks | |
WO2004110809A1 (en) | Curve rollover warning system for trucks | |
US20200073405A1 (en) | Vehicle navigation and control | |
CN111806433B (en) | Obstacle avoidance method, device and equipment for automatically driven vehicle | |
JP7289760B2 (en) | electronic controller | |
CN110182210A (en) | Controller of vehicle and control method for vehicle | |
KR20190138312A (en) | Driving assistance device and driving assistance method | |
EP3738849A1 (en) | Vehicle control device | |
CN111645682B (en) | Cruise control method and system and vehicle | |
EP4368465A1 (en) | Vehicle decision-making planning method and apparatus, and device and medium | |
CN111683853A (en) | Method and control unit for recognizing lane boundaries |
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 |