CN106598055A - Intelligent vehicle local path planning method, device thereof, and vehicle - Google Patents
Intelligent vehicle local path planning method, device thereof, and vehicle Download PDFInfo
- Publication number
- CN106598055A CN106598055A CN201710044287.1A CN201710044287A CN106598055A CN 106598055 A CN106598055 A CN 106598055A CN 201710044287 A CN201710044287 A CN 201710044287A CN 106598055 A CN106598055 A CN 106598055A
- Authority
- CN
- China
- Prior art keywords
- key point
- path
- barrier
- point
- expected path
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 35
- 230000004888 barrier function Effects 0.000 claims description 156
- 230000006870 function Effects 0.000 claims description 15
- 238000000926 separation method Methods 0.000 claims description 9
- 230000008450 motivation Effects 0.000 claims description 6
- 238000001514 detection method Methods 0.000 claims description 4
- 238000000605 extraction Methods 0.000 claims description 3
- 239000000284 extract Substances 0.000 claims description 2
- 230000003044 adaptive effect Effects 0.000 abstract 1
- 238000010586 diagram Methods 0.000 description 7
- 230000033001 locomotion Effects 0.000 description 4
- 230000015572 biosynthetic process Effects 0.000 description 3
- 230000008859 change Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000011160 research Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 2
- 101000905241 Mus musculus Heart- and neural crest derivatives-expressed protein 1 Proteins 0.000 description 1
- 229910017435 S2 In Inorganic materials 0.000 description 1
- 230000006978 adaptation Effects 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000006073 displacement reaction Methods 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 230000004807 localization Effects 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
- 238000003909 pattern recognition Methods 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 238000012372 quality testing Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000003786 synthesis reaction Methods 0.000 description 1
- 230000001550 time effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0231—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means
- G05D1/0246—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means using a video camera in combination with image processing means
- G05D1/0253—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means using a video camera in combination with image processing means extracting relative motion information from a plurality of images taken successively, e.g. visual odometry, optical flow
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0212—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory
- G05D1/0214—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory in accordance with safety or protection criteria, e.g. avoiding hazardous areas
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0212—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory
- G05D1/0223—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory involving speed control of the vehicle
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0257—Control of position or course in two dimensions specially adapted to land vehicles using a radar
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Aviation & Aerospace Engineering (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Multimedia (AREA)
- Electromagnetism (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses an intelligent vehicle local path planning method, a device thereof, and a vehicle. The method comprises the steps of (S1) collecting vehicle actual driving information, expected path information and obstacle information; (S2) determining the current effective position of an obstacle according to the collected information of the step (S1); (S3) taking a current expected path as a final path in the condition that the obstacle does not stop the current expected path according to the current effective position of the obstacle and the expected path information, and searching the optimal key point of avoiding the obstacle in the condition that the obstacle stops the current expected path: going to the step (S4) if the opotimal key point exists, otherwise going to the step (S5); (S4) connecting each key point in a key point sequence and the front and back key points adjacent to the key point, forming an obstacle avoidance path, taking the path as an updated path, and returning to the step (S3); and (S5) generating a reversing path or a turn-around path. The curve generated by the method is in accordance with the law of vehicle kinematics, and the adaptive matching of different vehicles can be completed with only measuring vehicle body related parameters.
Description
Technical field
The present invention relates to the intelligent vehicles technology field, more particularly to a kind of intelligent vehicle local paths planning method and its dress
Put, vehicle.
Background technology
Intelligent driving technology is in traffic safety, environmental protection and alleviating the aspects such as traffic pressure has huge application to dive
Power, has become at present the emphasis of developed country, automobile vendor and scientific ＆ technical corporation research.Intelligent driving research be related to mechano-electronic,
Pattern-recognition, artificial intelligence, the control subjects knowledge such as science and soft project, wherein, intelligent vehicle local paths planning is
One of important content of research.
For intelligent vehicle local paths planning system, need according to current expected path and peripheral obstacle information, can
Generation can avoid the smoothed curve of all barriers, and curve needs to meet vehicle kinematics characteristic, so as to enable the vehicle to
Enough accurate trackings, it is ensured that vehicle driving safety.In addition it is also necessary to consider that various boundary constraints, path such as are blocked at the various limit
Condition.
Thus, it is desirable to have a kind of technical scheme come overcome or at least mitigate prior art drawbacks described above at least one
It is individual.
The content of the invention
It is an object of the invention to provide a kind of intelligent vehicle local paths planning method and its device are overcoming or at least subtract
At least one of drawbacks described above of light prior art.
For achieving the above object, the present invention provides a kind of intelligent vehicle local paths planning method, intelligent vehicle local road
Footpath planing method includes：S1, collection vehicle actual travel information, expected path information and obstacle information；S2, adopts according to S1
The each information for collecting, determines active position of the barrier at current time；S3, according to the calculated barriers of S2 when current
The expected path information collected in the active position and S1 at quarter, in the case of barrier does not stop current expected path, then
Current expected path is final path, and is sent to wagon control layer；In barrier obstruction in the case of current expected path,
The optimum key point of avoiding obstacles is capable of in searching：S4 is entered in the case of there is optimum key point, there is no optimum pass
S5 is entered in the case of key point；S4, the optimum key point searched out in S3 is added in existing crucial point sequence, key point sequence
The principle of ordering in front and back of each key point is apart from size sequential, key point sequence along expected path direction distance from car in row
First key point in row is currently located a little for vehicle, and last key point in crucial point sequence is the end of expected path
Point, is closed forward and backward two adjacent with the key point of each key point in crucial point sequence with bicircular arcs resultant curve
Key point connects, and forms avoidance path, and returns S3 as the expected path for updating；S5, generates reversing path or path of turning around.
Further, the obstacle information in S1 includes：Static-obstacle thing and dynamic barrier；Static-obstacle thing in S2
In the current location that the active position at current time is static-obstacle thing；Significance bit of the dynamic barrier in S2 at current time
Put determination method as follows：S21, judges whether dynamic barrier has and is cut transversely into the motivation of current expected path, if it has, then entering
Enter S22；Otherwise enter S23；S22, according to the cross stream component of the speed of dynamic barrier its currently active position is predicted；S23,
Using the actual lateral separation of dynamic barrier and current expected path as the currently active position.
Further, the obstacle information in S1 includes：Common barrier, effective barrier and virtual obstacles；In S3
The finding method of key point specifically include：S31, judges whether effective barrier blocks current expected path, if it is,
Into S32；Otherwise enter S33；S32, searches out the nearest path of effective barrier in S31 on current expected path
Point, crosses path point and does the tangent line of current expected path and the vertical line of the tangent line；S33, finds distance effectively near the tangent line of S32
Virtual obstacles around barrier；S34, centered on effective barrier, search is positioned at center left on the vertical line of S32
Left key point and the right key point on right side, each key point is apart from the border of effective barrier and virtual obstacles more than setting
Safe distance dsafe。
Further, in the case of S34 has searched out left key point and right key point, also include before S4：S6, in S3
Optimum key point is chosen in each key point for searching out, S6 is specifically included：S61, according to the left key point and You Guan that determine in S34
Key point, is calculated respectively when the cost function value of front left key point and right key point using following cost function formula：
Cleft=k1·dleftvehicle/dkeypoints+k2·dleft；Cright=k1·drightvehicle/dkeypoints+k2·
dright；
In formula：dleftvehicleFor a upper key point with the left avertence when front left key point away from drightvehicleFor upper one pass
Key point is with the right avertence when front right key point away from dkeypointsFor a upper key point with when front left key point/when front right key point
Front/rear offset distance, dleftIt is as front left key point and the distance of the nearest path point of effective barrier, drightIt is when front right key point
With the distance of the nearest path point of effective barrier, k1、k2For weight coefficient, CleftBe when the cost function value of front left key point,
CrightIt is when the cost function value of front right key point；
S62, chooses CleftAnd CrightIn a less key point as optimum key point.
Further, in S34, in the case of S34 has searched out left key point and right key point, also wrap before S5
Include：S7, when there is no key point as standard with the safe distance for setting, needs the safe distance d for being gradually reduced settingsafe,
Often reduce once safety apart from dsafe, according to S3 identicals method key point is found；As the safe distance d of settingsafeLess than minimum
Safe distance dsafeminWhen still there is no key point, then into S5；S5 is specifically included：Judge the whether whole quilts of road ahead
Block, if there is can traffic areas, then generate reversing path, otherwise generate and turn around path.
Further, the intelligent vehicle local paths planning method also includes：S8, according to the avoidance path entirely planned
Minimum profile curvature radius and barrier to path beeline, control vehicle travel speed.
Further, S4 also includes：Each avoidance path that history is planned is recorded and preserves, as historical map or atlas, vehicle
During traveling, an avoidance path is extracted only in historical map or atlas, and utilize keeping away for the sensor Detection and Extraction for being used for vehicle location
Barrier whether there is barrier obstruction on path, if without barrier obstruction, using the avoidance path as current expectation
Path is sent to wagon control layer, if barrier obstruction, then returns S1 and plans again.
The present invention also provides a kind of intelligent vehicle local paths planning device, the intelligent vehicle local paths planning device bag
Include：Information acquisition module, it is used for collection vehicle actual travel information, expected path information and obstacle information；Significance bit
Determining module is put, it is used for each information collected according to described information acquisition module, determines barrier having at current time
Effect position；Key point find module, its be used for according to the active position determining module determine barrier at current time
The expected path information that active position and described information acquisition module are collected, in barrier current expected path is not stopped
Under situation, then current expected path is final path, and is sent to wagon control layer；The current expected path in barrier obstruction
In the case of, the optimum key point of avoiding obstacles is capable of in searching；Obstacle-avoiding route planning module, it is used for the presence of optimum key
In the case of point, key point is found in the existing crucial point sequence of optimum key point addition that module is searched out, key point sequence
The principle of ordering in front and back of each key point is apart from size sequential, key point sequence along expected path direction distance from car in row
First key point in row is currently located a little for vehicle, and last key point in crucial point sequence is the end of expected path
Point, is closed forward and backward two adjacent with the key point of each key point in crucial point sequence with bicircular arcs resultant curve
Key point connects, and forms avoidance path, and as the expected path for updating, detects whether barrier stops currently expect road again
Footpath；Reversing path or the path planning module that turns around, in the case of it is used to there is no optimum key point, generates reversing path or fall
Parting footpath.
The present invention also provides a kind of vehicle, and the vehicle includes intelligent vehicle local paths planning device as above.
The present invention includes following advantage：
1st, because the present invention considers the multidate information from car and barrier, the following effectively position of barrier is extracted,
Make avoidance more reasonable.2nd, by finding key point, accurately avoid determining barrier and its neighbouring barrier.3rd, bicircular arcs are used
Resultant curve is sequentially connected each key point, meets vehicle kinematics characteristic.4th, can realize first falling according to barrier obstruction situation
Car readvances.5th, speed is controlled according to generation path and obstacle information.
Description of the drawings
Fig. 1 is local paths planning execution logic schematic diagram of the present invention；
Fig. 2 is the determination schematic diagram of the currently active position of barrier of the present invention；
Fig. 3 is the localization method schematic diagram of key point of the present invention；
Fig. 4 is the selection schematic diagram of key point of the present invention；
Fig. 5 is crucial point curve connection diagram before and after the present invention；
Fig. 6 is the generation schematic diagram of bicircular arcs resultant curve of the present invention；
Fig. 7 is that reversing path of the present invention generates schematic diagram.
Specific embodiment
In the accompanying drawings, same or similar element is represented or with same or like function using same or similar label
Element.Embodiments of the invention are described in detail below in conjunction with the accompanying drawings.
In describing the invention, term " " center ", " longitudinal direction ", " horizontal ", "front", "rear", "left", "right", " vertical ",
The orientation or position relationship of the instruction such as " level ", " top ", " bottom " " interior ", " outward " is to be closed based on orientation shown in the drawings or position
System, is for only for ease of the description present invention and simplifies description, rather than indicates or imply that the device or element of indication must have
Specific orientation, with specific azimuth configuration and operation, therefore it is not intended that limiting the scope of the invention.
As shown in figure 1, the intelligent vehicle local paths planning method that the present embodiment is provided includes：
S1, collection vehicle actual travel information, expected path information and obstacle information.Vehicle actual travel packet
The speed information of vehicle is included, speed information can be obtained using existing sensor.Expected path information is by multiple path point groups
There is corresponding coordinate value and course angle into, each path point, expected path information be by camera recognize lane line or
The expected path information that differential GPS devices are given.The coordinate value of each point referred in the present invention can be seen as in vehicle coordinate
The coordinate value of system, vehicle axis system can be determined using known method, be will not be described here.Obstacle information can be by existing
Some obstacle detecting apparatus are obtained, and these obstacle detecting apparatus can be using radar, GPS, video camera etc., by obstacle
Quality testing measurement equipment, can collect the relevant information of all multi-obstacle avoidances around expected path.Obstacle information is specifically included：Position
Coordinate points, width, Speed attribute are put, the barrier for having interference to the track of expected path is effective barrier etc..
S2, according to vehicle actual travel information, expected path information and obstacle information that S1 is collected, determines obstacle
Active position of the thing at current time.
S3, believes according to the expected path that the calculated barriers of S2 are collected in the active position and S1 at current time
Breath, in the case of barrier does not stop current expected path, then current expected path is final path, and is sent to vehicle control
Preparative layer；In barrier obstruction in the case of current expected path, the optimum key point of avoiding obstacles is capable of in searching；If deposited
In optimum key point, then into S4；Otherwise enter S5.
S4, the optimum key point searched out in S3 is added in existing crucial point sequence, each key in crucial point sequence
Point before and after principle of ordering be along expected path direction distance from car in size sequential, crucial point sequence first
Individual key point is currently located point (center of such as vehicle) for vehicle, and last key point in crucial point sequence is scheduled to last
Hope path terminal, with bicircular arcs resultant curve by each key point in crucial point sequence it is adjacent with the key point before,
Two key points connection afterwards, that is to say, that when last key point is connected to from first key point curve, then
Form an avoidance path.
S5, generates reversing path or path of turning around, and is sent to wagon control layer.
After the planning in avoidance path is completed, above-mentioned S4 can include：Return S1, that is to say, that detect that this is kept away again
Whether barrier path has barrier obstruction, if it has, then choosing optimum key point again according to S3 avoids effective barrier, and again
It is determined that optimum key point be added to existing crucial point sequence, avoidance path is generated again, until the avoidance path for generating does not have
Till barrier obstruction.By the step, avoidance curve can be in real time generated.
Above-mentioned S4 can also include：Each avoidance path that history is planned is recorded and preserves, as historical map or atlas.In car
Traveling when, it is only necessary to one is extracted in historical map or atlas using the sensor (such as inertial navigation or differential GPS etc.) of vehicle location
Whether there is barrier obstruction on avoidance path, and the avoidance path of Detection and Extraction, if without barrier obstruction, with this
Avoidance path is sent to wagon control layer as current expected path, can so cause in hgher efficiency, path more stable.Such as
Fruit has barrier obstruction, then return S1 and plan again.The present embodiment has bounce and loss due to the detection of barrier, so dynamic
In real time formation curve has certain saltus step, and updating original path can then overcome this shortcoming.
More new route is performed after the path of planning does not have barrier obstruction, is turned to global through vehicle relative coordinate
Change.When subsequent time does not have barrier obstruction, then the cartographic information at a upper moment was still extracted.Vehicle movement can cause the overall situation
Map is being converted from car relative coordinate system, and this needs is calculated according to differential GPS or inertial navigation information, so as to extract history ground
Figure is relative to the routing information from car current location.
In a preferred embodiment, as shown in Fig. 2 in S2, according to vehicle actual travel information, phase that S1 is collected
Routing information and obstacle information are hoped, determines that barrier is specifically included in the method for the active position at current time：
When vehicle is during current expected path is tracked, preceding object thing (referred to as effective barrier) stop is detected
Expected path, then energy will be found with the barrier of the corresponding expected path point of effective barrier and surrounding as foundation
The key point of enough avoiding obstacles.
Barrier can be classified from speed aspect, then can be divided into static-obstacle thing and dynamic barrier, wherein, speed
Spend for 0 barrier be static-obstacle thing, be otherwise dynamic barrier.Wherein：The current location of static-obstacle thing is it to be had
Effect position.Active position of the dynamic barrier at current time determines that method is as follows：
S21, judges whether dynamic barrier has the motivation for being cut transversely into current expected path, if it has, then entering S22；
Otherwise enter S23；
S22, according to the cross stream component of the speed of dynamic barrier its currently active position is predicted；
S23, by actual lateral separation d of dynamic barrier and current expected path1As the currently active position.
As shown in Fig. 2 the speed of the barrier 1 on the left of current expected path P is v1, it is dynamic barrier.Assume obstacle
The track of the current expected path P of thing 1 pair has an impact, and is not cut transversely into the motivation of current expected path.Grey filling
Barrier 1 is its current location, and the barrier 1 of dotted line is with speed v1Position after movement, former and later two positions with work as early stage
The lateral separation for hoping path P is all d1.So, with actual lateral separation d of barrier 1 and current expected path1As currently having
Effect position, and the range ability dis illustrated in Fig. 21It is the barrier 1 when reaching with 1 identical lengthwise position of barrier from car
Displacement be embodied in following formula：
dis1=dis01·v1/(v0-v1) (1)
In formula, dis01The fore-and-aft distance for being current time between car and barrier 1, v1It is barrier 1 relative to ground
Speed, v0It is the speed from car relative to ground.
It should be noted that " judging whether dynamic barrier has the motivation for being cut transversely into current expected path " is according to barrier
Hinder whether the relatively current expected path of thing has lateral shift to determine, barrier closer or far from this track, then can be considered this
Barrier relative to this track lateral velocity, i.e., with lateral shift." longitudinal direction " in the present invention is current expected path
Direction, " horizontal " is perpendicular to " longitudinal direction ".
S22 is specifically described with reference to Fig. 2.
The speed of the barrier 2 on the left of current expected path P is v2, it is dynamic barrier.Assume that 2 pairs, barrier works as early stage
Hope that path locus have an impact, and have the motivation for being cut transversely into current expected path.The barrier 2 of grey filling is its present bit
Put, the barrier 2 of dotted line is with speed v2Position after movement.So, by speed v of barrier 22It is decomposed into the longitudinal direction of speed
Component v21With the cross stream component v of speed22.Longitudinal component v21For determine barrier 2 apart from current expected path P longitudinal direction away from
From.Cross stream component v22For determining the currently active position of lateral separation of the barrier 2 apart from current expected path, i.e. barrier 2
Put, the expression of lateral separation is：Lateral separation is dis1=dis01/(v0-v1)。
In one embodiment, as shown in Figure 3 and Figure 4, it is assumed that barrier shown in figure is the active position of each barrier,
Consider the impact of speed, i.e. barrier further can also be classified from the aspect of its currently active position, then may be used
It is divided into common barrier, effective barrier and virtual obstacles, wherein, common barrier is temporarily do not have to current expected path P
Influential barrier.Effectively barrier is barrier (such as the A in Fig. 3) influential on current expected path P, its present bit
Put and be less than preset value with the lateral separation between current expected path P (preset value can be manually set, such as 0.5m).Virtually
Barrier is around effective barrier A and barrier influential on current expected path P.
The choosing method of virtual obstacles is：First, find what the pre-set radius circle centered on effective barrier A was surrounded
In the range of barrier, for example：B、C、D；Then, path closest with effective barrier A on current expected path P is found
Point A1；Furthermore, the tangent line T that path point A1 is current expected path P is crossed, it is the vertical line V of tangent line T after path point A1；Finally, exist
Subpoint B1, C1, D1 of B, C, D are on vertical line V, then subpoint B1, C1, D1 is virtual obstacles.
If the barrier A in figure blocks current expected path, then need to search out this effective barrier from working as
Nearest path point A1 of front expected path, then tangential direction T in this path point A1 find apart from this effective barrier A mono-
Other barriers in set a distance, such as project barrier, and these projection barriers will affect the selection of key point, so can be with
Avoid the situation for barrier nearby occur in key point.When key point is chosen, it is necessary to avoid these virtual barriers on line
Hinder thing and effective barrier.
In one embodiment, the finding method of the key point in S3 is specifically included：
S31, judges whether effective barrier blocks current expected path, if it is, into S32；Otherwise enter
S33.In the step, when the border of the current expected path of the frontier distance of barrier (is manually set, such as less than setpoint distance
When 0.5m), you can be considered effective barrier.
S32, searches out the nearest path point of effective barrier in S31 on current expected path, crosses path point
Do the tangent line of current expected path and the vertical line of the tangent line.
S33, finds the virtual obstacles around effective barrier near the tangent line of S32." effective barrier week
Enclose " pre-set radius that can be centered on effective barrier circle surround in the range of barrier, pre-set radius therein can be with
Be manually set, such as 3m to 6m, it is main according to the length and width from car, the size of cornering ability determining.
S34, centered on effective barrier, left key point L and the right side of the search positioned at center left on the vertical line of S32
Right key point R of side, left key point L and right key point R have to be larger than apart from the border of effective barrier and virtual obstacles and set
Fixed safe distance dsafe。
In the case of S34 is not found key point, then always according to the method described above to deep direction search for, directly
To left key point L and right key point R is found.
As shown in figure 4, in the case of S34 has searched out left key point L and right key point R, that is to say, that find in S3
In the case of key point, also include before S4：
S6, chooses an optimum key point, as the optimum key point that S4 is referred to, tool in each key point that S3 is searched out
Gymnastics is made as follows：
S61, according to the left key point and right key point that determine in S34, is calculated respectively using following cost function formula
When front left key point and the cost function value of right key point：Cleft=k1·dleftvehicle/dkeypoints+k2·dleft；Cright=
k1·drightvehicle/dkeypoints+k2·dright；
In formula：dleftvehicleFor a upper key point and as front left key point distance in the horizontal, drightvehicleFor upper
One key point with work as front right key point distance in the horizontal, dkeypointsFor a upper key point with when front left key point/when
Front right key point distance in the vertical, dleftBe when front left key point and effective barrier nearest path point in the horizontal
Distance, drightIt is the nearest path point distance in the horizontal when front right key point and effective barrier, k1、k2For weight system
Number, CleftIt is as the cost function value of front left key point, CrightIt is when the cost function value of front right key point.
S62, chooses CleftAnd CrightIn a less key point as optimum key point, cost function represents avoidance
The flatness in path and consider with the repeatability of former expected path, cost function value is less to illustrate this key point institute
The combination property in the path of planning is more preferable.
It should be noted that because the key point for searching out is a series of, be ranked up from the distance of car according to distance,
First key point is car's current position, and current key point is optimum key point (left key point or the right side determined in S34
Key point), then, the upper key point of current key point be distance from car closer to and one adjacent with current key point
Optimum key point.
In one embodiment, only expected path or avoidance path are represented with a curve in figure, in fact, path only table
Show the track that vehicle is travelled, and the road of vehicle traveling is all with transverse width, it is assumed that the width of road is 3.6m, then
Expected path or avoidance path refer to the center line of road, and the center line moves to left 1.8m for left margin along the width of road
Line, correspondingly, moves to right 1.8m for the right boundary line.In the case of S34 has searched out left key point L and right key point R, also,
The distance of one of key point and current expected path another key point and current expects road beyond the boundary line of road
When the distance in footpath is in lane boundary line, then, it is optimum with key point of the distance of current expected path in road boundary
Key point.The distance of current expected path " key point with " refers to the d in above-mentioned cost functionleftOr dright.In a reality
In applying example, in the case of S34 is not found left key point L and right key point R, that is to say, that current setting safety away from
From dsafeIt is interior, in the case of S3 is not found key point, also include before S5：
S7, when there is no key point as standard with the safe distance for setting, needs the safe distance for being gradually reduced setting
dsafe, often reduce once safety apart from dsafe, according to S3 identicals method key point is found；As the safe distance d of settingsafeIt is little
In minimum safe distance dsafeminWhen still there is no key point, then into S5.
" minimum safe distance dsafemin" according to the half of overall width and the Safety Redundancy distance allowed determining, if car
Wide half is 1m, and the Safety Redundancy distance allowed is 0.4m, then minimum safe distance is 1.4m.
As shown in fig. 7, correspondingly, S5 is specifically included：
Judge whether road ahead is all blocked, if there is can traffic areas, then generate reversing path, otherwise generate
Turn around path.That is, it is assumed that forward path exist can traffic areas, that is, need to plan reversing path, its generation is equally
According to from car rear expected path and obstacle information determining.When there is barrier obstruction from bus or train route footpath, need to find crucial
Point, and connected using bicircular arcs resultant curve, so as to generate smooth feasible reversing path.When from car along reversing path backward
During traveling, forward path is planned in real time, if front is still blocked, continue to move backward；If now can cook up to
Front path, then stop reversing, and plans that path forward moves forward then.
The present embodiment finds left key point and right key point again by reducing safe distance, and in the hope of finding barrier is avoided
Hinder the path of thing.But as reduction safe distance dsafeWhen can find feasible key point, then illustrate currently can traffic areas compare
It is narrow, need deceleration to pass through, this speed needs to be determined according to the distance apart from obstacles borders.
In a preferred embodiment, as shown in figure 5, right key point R chosen using in above-mentioned steps is used as optimum pass
Key point, illustrates the specific implementation of S4, specific as follows：
The optimum key point searched out in S3 is added in existing crucial point sequence, each key point in crucial point sequence
In front and back principle of ordering is first pass along expected path direction distance from car in size sequential, crucial point sequence
Key point is currently located point (center of such as vehicle) for vehicle, and last key point in crucial point sequence is expectation road
The terminal in footpath, with bicircular arcs resultant curve by forward and backward adjacent with the key point of each key point in crucial point sequence
Two key point connections, that is to say, that when last key point is connected to from first key point curve, then formed
One avoidance path.
In one embodiment, it is elected to and takes after key point junction curve, continues to detect whether the path of new planning is hindered
Gear, if be blocked, is further added by key point to avoid current effective barrier, until formation curve does not have barrier obstruction
Till.
The present embodiment uses the mode of bicircular arcs resultant curve and forms avoidance path, the bicircular arcs resultant curve of generation
Curvature varying it is dull continuous, radius of curvature will not beat on a large scale, be more conform with the actual motion path of vehicle.Root is presented herein below
According to beginning and end, the method for generating bicircular arcs resultant curve.
As shown in fig. 6, bicircular arcs resultant curve is that linear synthesis is carried out based on two intersecting circular arcs, two intersect
Point is all tangent with corresponding circular arc；Rise point circular arc be from the off, it is and tangent with the direction of starting point, with circular arc extension, arrive
Up to terminal till；And another circular arc is from the beginning of a terminal and tangent with the opposite direction of its tangent line, with circular arc extension, arrive
Up to starting point till.
Having assumed the parameter of point circular arc has radius of curvature R1, the center of circle (xc1,yc1), the corresponding central angle alpha of Origin And DestinationM1
And αP1, correspondingly, terminal circular arc has R2、xc2、yc2、αM2、αP2, the parametric equation of two circular arcs just can show：
Play point circular arc：
x1=xc1+R1cos(α1),y1=yc1+R1sin(α1),α1∈(αM1,αP1) (3)
Terminal circular arc：
x2=xc2+R2cos(α2),y2=yc2+R2sin(α2),α2∈(αM2,αP2) (4)
The independent variable for playing point circular arc and terminal an arc equation is respectively α1And α2, so needing to set a unified change certainly
Amount t, meets
α1=(1-t) αM1+t·αP1,α2=(1-t) αM2+t·αP2,0≤t≤1 (5)
Playing the composition rule of the resultant curve of point circular arc and terminal circular arc is：More toward the side of starting point, resultant curve is more leaned on
Point circular arc is closely played, more toward terminal side, the closer to terminal circular arc.Accordingly, it is determined that following linear resultant curve relational expression：
X=(1-t) x1+t·x2, y=(1-t) y1+t·y2 (6)
Simultaneous formula (3) to (6) formula, can obtain parametric equation of the resultant curve with regard to independent variable t.
The characteristics of above-mentioned gained resultant curve is towards tangent, in destination county with terminal towards phase in starting point with starting point
Cut, and continual curvature smooth change, so as to ensure that the flatness in path.
In one embodiment, the intelligent vehicle local paths planning method that the present embodiment is provided includes：
S8, according to the beeline of the minimum profile curvature radius and barrier in the avoidance path entirely planned to path,
The travel speed of control vehicle, it is specific as follows：
The avoidance path planned is compared with former expected path, it is understood that there may be the less place of radius of curvature, when vehicle edge
When avoidance route, need to be controlled speed.Bicircular arcs resultant curve can feed back the curvature at any point thereon
Radius, with the good all avoidance paths of inspection planning, the i.e. radius of curvature of bicircular arcs resultant curve, and can extract minimum curvature half
Footpath, then can limit speed, it is ensured that driving safety according to minimum profile curvature radius.The path planned is by a plurality of bicircular arcs
Resultant curve joins end to end a curve of composition, and the minimum profile curvature radius on this whole piece curve determine max. speed.
The present invention also provides a kind of intelligent vehicle local paths planning device, and the device includes：
Information acquisition module, it is used for collection vehicle actual travel information, expected path information and obstacle information；
Active position determining module, it is used for each information collected according to described information acquisition module, determines barrier
In the active position at current time；
Key point find module, its be used for according to the active position determining module determine barrier at current time
The expected path information that active position and described information acquisition module are collected, in barrier current expected path is not stopped
Under situation, then current expected path is final path, and is sent to wagon control layer；The current expected path in barrier obstruction
In the case of, the optimum key point of avoiding obstacles is capable of in searching；
Obstacle-avoiding route planning module, it is used in the case of there is optimum key point, key point is found into module and is found
To optimum key point add in existing crucial point sequence, in crucial point sequence each key point before and after principle of ordering be along the phase
Hope that first key point of the path direction distance from car in size sequential, crucial point sequence is currently located for vehicle
Point, last key point in crucial point sequence for expected path terminal, with bicircular arcs resultant curve by crucial point sequence
In the forward and backward two key point connection adjacent with the key point of each key point, form avoidance path, be sent to vehicle
Key-course；
Reversing path or the path planning module that turns around, in the case of it is used to there is no key point, generate reversing path or
Turn around path, to be sent to wagon control layer.
The present invention also provides a kind of vehicle, and the vehicle includes intelligent vehicle local paths planning device as above.
The present invention constructs suitable intelligent vehicle avoiding obstacles for the basic demand of above intelligent vehicle local paths planning
Local paths planning system, i.e., based on barrier and the design philosophy of smoothed curve, wherein, smoothed curve using bicircular arcs close
Into curve, meet vehicle kinematics, and the Curvature varying in whole piece path can be reflected, such that it is able to control the max speed really
Protect traffic safety.This method has extensive adaptability to the vehicle of various models, complete by only need to matching vehicle body parameter be
Adaptation of the system to vehicle.
It is last it is to be noted that：Above example only to illustrate technical scheme, rather than a limitation.This
The those of ordinary skill in field should be understood：Technical scheme described in foregoing embodiments can be modified, or it is right
Which part technical characteristic carries out equivalent；These modifications are replaced, and the essence for not making appropriate technical solution departs from this
Invent the spirit and scope of each embodiment technical scheme.
Claims (9)
1. a kind of intelligent vehicle local paths planning method, it is characterised in that include：
S1, collection vehicle actual travel information, expected path information and obstacle information；
S2, according to each information that S1 is collected, determines active position of the barrier at current time；
S3, according to the expected path information that the calculated barriers of S2 are collected in the active position and S1 at current time,
In the case of barrier does not stop current expected path, then current expected path is final path, and is sent to wagon control
Layer；In barrier obstruction in the case of current expected path, the optimum key point of avoiding obstacles is capable of in searching：Exist most
S4 is entered in the case of excellent key point, S5 is entered in the case of there is no optimum key point；
S4, the optimum key point searched out in S3 is added in existing crucial point sequence, each key point in crucial point sequence
In front and back principle of ordering is first pass along expected path direction distance from car in size sequential, crucial point sequence
Key point is currently located a little for vehicle, and last key point in crucial point sequence is the terminal of expected path, is closed with bicircular arcs
Into curve by the forward and backward two key point connection adjacent with the key point of each key point in crucial point sequence, formed
Avoidance path, and return S3 as the expected path for updating；
S5, generates reversing path or path of turning around, and is sent to wagon control layer.
2. intelligent vehicle local paths planning method as claimed in claim 1, it is characterised in that the obstacle information bag in S1
Include：Static-obstacle thing and dynamic barrier；
Active position of the static-obstacle thing in S2 at current time is the current location of static-obstacle thing；
Active position of the dynamic barrier in S2 at current time determines that method is as follows：
S21, judges whether dynamic barrier has the motivation for being cut transversely into current expected path, if it has, then entering S22；Otherwise
Into S23；
S22, according to the cross stream component of the speed of dynamic barrier its currently active position is predicted；
S23, using the actual lateral separation of dynamic barrier and current expected path as the currently active position.
3. intelligent vehicle local paths planning method as claimed in claim 1 or 2, it is characterised in that the obstacle information in S1
Including：Common barrier, effective barrier and virtual obstacles；
The finding method of the key point in S3 is specifically included：
S31, judges whether effective barrier blocks current expected path, if it is, into S32；Otherwise enter S33；
S32, searches out the nearest path point of effective barrier in S31 on current expected path, crosses path point and works as
The tangent line of front expected path and the vertical line of the tangent line；
S33, finds the virtual obstacles around effective barrier near the tangent line of S32；
S34, centered on effective barrier, left key point and right side of the search positioned at center left on the vertical line of S32
Right key point, each key point is apart from the border of effective barrier and virtual obstacles more than the safe distance d for settingsafe。
4. intelligent vehicle local paths planning method as claimed in claim 3, it is characterised in that searched out left key in S34
In the case of point and right key point, also include before S4：
S6, chooses optimum key point in each key point that S3 is searched out, and S6 is specifically included：
S61, according to the left key point and right key point that determine in S34, is calculated respectively currently using following cost function formula
The cost function value of left key point and right key point：
Cleft=k1·dleftvehicle/dkeypoints+k2·dleft；Cright=k1·drightvehicle/dkeypoints+k2·dright；
In formula：dleftvehicleFor a upper key point with the left avertence when front left key point away from drightvehicleFor a upper key point
With the right avertence when front right key point away from dkeypointsFor a upper key point with when front left key point/when before front right key point/
Retrodeviate away from dleftIt is as front left key point and the distance of the nearest path point of effective barrier, drightBe when front right key point with
The distance of the nearest path point of effective barrier, k1、k2For weight coefficient, CleftBe when the cost function value of front left key point,
CrightIt is when the cost function value of front right key point；
S62, chooses CleftAnd CrightIn a less key point as optimum key point.
5. intelligent vehicle local paths planning method as claimed in claim 4, it is characterised in that in S34, search out in S34
In the case of left key point and right key point, also include before S5：
S7, when there is no key point as standard with the safe distance for setting, needs the safe distance d for being gradually reduced settingsafe,
Often reduce once safety apart from dsafe, according to S3 identicals method key point is found；As the safe distance d of settingsafeLess than minimum
Safe distance dsafeminWhen still there is no key point, then into S5；
S5 is specifically included：
Judge whether road ahead is all blocked, if there is can traffic areas, then generate reversing path, otherwise generate turn around
Path.
6. intelligent vehicle local paths planning method as claimed in claim 5, it is characterised in that also include：
S8, according to the minimum profile curvature radius and barrier in the avoidance path entirely plan to the beeline in path, controls
The travel speed of vehicle.
7. intelligent vehicle local paths planning method as claimed in claim 1, it is characterised in that S4 also includes：Record and preserve
Each avoidance path that history is planned, as historical map or atlas, when vehicle is travelled, extracts an avoidance road only in historical map or atlas
Footpath, and utilize on the avoidance path for the sensor Detection and Extraction of vehicle location with the presence or absence of barrier obstruction, if do not had
Barrier obstruction, then be sent to wagon control layer using the avoidance path as current expected path, if barrier resistance
Gear, then return S1 and plan again.
8. a kind of intelligent vehicle local paths planning device, it is characterised in that include：
Information acquisition module, it is used for collection vehicle actual travel information, expected path information and obstacle information；
Active position determining module, it is used for each information collected according to described information acquisition module, determines that barrier is being worked as
The active position at front moment；
Key point finds module, and the barrier that it is used to be determined according to the active position determining module is effective at current time
The expected path information that position and described information acquisition module are collected, in barrier the situation of current expected path is not stopped
Under, then current expected path is exactly final path, and is sent to wagon control layer；The current expected path in barrier obstruction
Under situation, the optimum key point of avoiding obstacles is capable of in searching；
Obstacle-avoiding route planning module, it is used in the case of there is optimum key point, and key point is found into what module was searched out
Optimum key point is added in existing crucial point sequence, and the principle of ordering in front and back of each key point is along expectation road in crucial point sequence
First key point of the footpath direction distance from car in size sequential, crucial point sequence is currently located a little for vehicle,
Last key point in crucial point sequence is the terminal of expected path, with bicircular arcs resultant curve by crucial point sequence
The forward and backward two key point connection adjacent with the key point of each key point, forms avoidance path；
Reversing path or the path planning module that turns around, in the case of it is used to there is no optimum key point, generate reversing path or
Turn around path.
9. a kind of vehicle, it is characterised in that including intelligent vehicle local paths planning device as claimed in claim 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710044287.1A CN106598055B (en) | 2017-01-19 | 2017-01-19 | A kind of intelligent vehicle local paths planning method and its device, vehicle |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710044287.1A CN106598055B (en) | 2017-01-19 | 2017-01-19 | A kind of intelligent vehicle local paths planning method and its device, vehicle |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106598055A true CN106598055A (en) | 2017-04-26 |
| CN106598055B CN106598055B (en) | 2019-05-10 |
Family
ID=58585163
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710044287.1A Active CN106598055B (en) | 2017-01-19 | 2017-01-19 | A kind of intelligent vehicle local paths planning method and its device, vehicle |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106598055B (en) |
Cited By (51)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107065880A (en) * | 2017-05-16 | 2017-08-18 | 南京农业大学 | Remote operating agricultural vehicle man-computer cooperation paths planning method based on dynamic guiding point |
| CN107357168A (en) * | 2017-06-01 | 2017-11-17 | 同济大学 | A kind of unmanned vehicle barrier-avoiding method based on Chance-constrained Model PREDICTIVE CONTROL |
| CN107702716A (en) * | 2017-08-31 | 2018-02-16 | 广州小鹏汽车科技有限公司 | A kind of unmanned paths planning method, system and device |
| CN107992050A (en) * | 2017-12-20 | 2018-05-04 | 广州汽车集团股份有限公司 | Pilotless automobile local path motion planning method and device |
| CN108121347A (en) * | 2017-12-29 | 2018-06-05 | 北京三快在线科技有限公司 | For the method, apparatus and electronic equipment of control device movement |
| CN108196544A (en) * | 2018-01-02 | 2018-06-22 | 联想(北京)有限公司 | A kind of information processing method and information processing equipment |
| CN108614569A (en) * | 2018-06-22 | 2018-10-02 | 北京敏捷动力科技有限公司 | A method of being used for tracing control controlled motion object |
| CN108693878A (en) * | 2017-04-06 | 2018-10-23 | 丰田自动车株式会社 | Advance route setting device and advance route setting method |
| CN108762272A (en) * | 2018-06-05 | 2018-11-06 | 北京智行者科技有限公司 | A kind of obstacle recognition and preventing collision method |
| CN108776479A (en) * | 2018-06-05 | 2018-11-09 | 北京智行者科技有限公司 | A kind of collaboration cleaning work method |
| CN109062948A (en) * | 2018-06-22 | 2018-12-21 | 广州杰赛科技股份有限公司 | Target point is determining, destination path determines method and system |
| CN109062215A (en) * | 2018-08-24 | 2018-12-21 | 北京京东尚科信息技术有限公司 | Robot and barrier-avoiding method, system, equipment and medium are followed based on its target |
| CN109101022A (en) * | 2018-08-09 | 2018-12-28 | 北京智行者科技有限公司 | A kind of working path update method |
| CN109101017A (en) * | 2018-07-27 | 2018-12-28 | 江苏盛海智能科技有限公司 | A kind of unmanned vehicle tracks route planning method and terminal |
| CN109631899A (en) * | 2018-12-18 | 2019-04-16 | 仲恺农业工程学院 | A kind of method for optimizing route and system of the mobile robot for environment sensing |
| CN109624851A (en) * | 2018-11-23 | 2019-04-16 | 深圳市航盛电子股份有限公司 | Auxiliary driving method, system and readable storage medium storing program for executing based on augmented reality |
| CN109782807A (en) * | 2019-03-08 | 2019-05-21 | 哈尔滨工程大学 | A kind of AUV barrier-avoiding method under back-shaped obstacle environment |
| CN109814577A (en) * | 2019-02-25 | 2019-05-28 | 上海木木聚枞机器人科技有限公司 | A kind of motion control method and mobile device based on information sharing |
| CN109916422A (en) * | 2019-03-29 | 2019-06-21 | 北京经纬恒润科技有限公司 | A kind of global path planning method and device |
| CN109917794A (en) * | 2019-04-18 | 2019-06-21 | 北京智行者科技有限公司 | Global path planning method and device |
| CN110083158A (en) * | 2019-04-28 | 2019-08-02 | 深兰科技（上海）有限公司 | A kind of method and apparatus in determining sector planning path |
| WO2019149214A1 (en) * | 2018-02-05 | 2019-08-08 | 腾讯科技（深圳）有限公司 | Smart movement device and navigation method thereof, and storage medium |
| CN110169741A (en) * | 2018-06-25 | 2019-08-27 | 宁波洒哇地咔电器有限公司 | A kind of cleaning method and equipment |
| CN110239562A (en) * | 2018-03-10 | 2019-09-17 | 百度（美国）有限责任公司 | The real-time perception adjustment based on surrounding vehicles behavior of automatic driving vehicle is adjusted with driving |
| CN110262488A (en) * | 2019-06-18 | 2019-09-20 | 重庆长安汽车股份有限公司 | Local paths planning method, system and the computer readable storage medium of automatic Pilot |
| CN110383192A (en) * | 2018-03-16 | 2019-10-25 | 深圳市大疆创新科技有限公司 | Moveable platform and its control method |
| CN110703758A (en) * | 2019-10-25 | 2020-01-17 | 北京京东乾石科技有限公司 | Path planning method and device |
| CN110766220A (en) * | 2019-10-21 | 2020-02-07 | 湖南大学 | Local path planning method for structured road |
| CN110879560A (en) * | 2019-12-23 | 2020-03-13 | 北京百度网讯科技有限公司 | Method, apparatus, device and storage medium for controlling vehicle |
| CN111142520A (en) * | 2019-12-24 | 2020-05-12 | 中国科学院合肥物质科学研究院 | Planning and control method of crawler-type unmanned vehicle on cliff obstacle road |
| CN111183067A (en) * | 2017-10-05 | 2020-05-19 | 日产自动车株式会社 | Parking control method and parking control device |
| CN111368639A (en) * | 2020-02-10 | 2020-07-03 | 浙江大华技术股份有限公司 | Vehicle lane crossing determination method, vehicle lane crossing determination device, computer device, and storage medium |
| CN111381594A (en) * | 2020-03-09 | 2020-07-07 | 兰剑智能科技股份有限公司 | AGV space obstacle avoidance method and system based on 3D vision |
| CN111439257A (en) * | 2019-06-26 | 2020-07-24 | 纵目科技（上海）股份有限公司 | Memory parking system, method, terminal and cloud server |
| CN111506070A (en) * | 2020-04-26 | 2020-08-07 | 北京踏歌智行科技有限公司 | Local path planning method based on path point deviation |
| CN111504340A (en) * | 2020-05-22 | 2020-08-07 | 北京汽车研究总院有限公司 | Vehicle path planning method and device and vehicle |
| CN111653113A (en) * | 2020-04-20 | 2020-09-11 | 浙江吉利汽车研究院有限公司 | Method, device, terminal and storage medium for determining local path of vehicle |
| CN111703421A (en) * | 2020-05-13 | 2020-09-25 | 重庆长安汽车股份有限公司 | Trajectory planning system, method and storage medium for automatic driving and getting rid of difficulty of vehicle |
| CN111739342A (en) * | 2020-03-26 | 2020-10-02 | 腾讯科技（深圳）有限公司 | Method, device, medium, and vehicle for avoiding vehicle ahead of side |
| CN112034848A (en) * | 2020-08-13 | 2020-12-04 | 驭势科技（北京）有限公司 | Obstacle avoiding method and device, electronic equipment and storage medium |
| TWI715221B (en) * | 2019-09-27 | 2021-01-01 | 財團法人車輛研究測試中心 | Adaptive trajectory generation method and system |
| CN112172807A (en) * | 2020-10-23 | 2021-01-05 | 上海伯镭智能科技有限公司 | Obstacle avoidance judging method of unmanned automobile obstacle avoidance system |
| CN112504288A (en) * | 2020-07-22 | 2021-03-16 | 北京智行者科技有限公司 | Local path planning method based on dynamic planning |
| CN113063423A (en) * | 2021-03-23 | 2021-07-02 | 广东工业大学 | Global path planning and cutting method and system based on Lanelet frame |
| CN113267199A (en) * | 2021-06-24 | 2021-08-17 | 上海欧菲智能车联科技有限公司 | Driving track planning method and device |
| CN113396122A (en) * | 2019-02-14 | 2021-09-14 | 株式会社多田野 | Crane and route generation system |
| CN113568400A (en) * | 2020-04-28 | 2021-10-29 | 北京猎户星空科技有限公司 | Robot control method and device, electronic equipment and storage medium |
| CN113790725A (en) * | 2020-09-22 | 2021-12-14 | 北京京东乾石科技有限公司 | Path planning method, path planning device, storage medium and mobile equipment |
| CN113885525A (en) * | 2021-10-30 | 2022-01-04 | 重庆长安汽车股份有限公司 | Path planning method and system for automatically driving vehicle to get rid of trouble, vehicle and storage medium |
| CN114995398A (en) * | 2022-05-16 | 2022-09-02 | 中国第一汽车股份有限公司 | Path generation method, path generation device, storage medium, processor and electronic device |
| WO2023273731A1 (en) * | 2021-06-30 | 2023-01-05 | 北京旷视科技有限公司 | Obstacle avoidance method and apparatus, and automatic navigation apparatus |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1987357A (en) * | 2006-12-26 | 2007-06-27 | 浙江工业大学 | Intelligent parking auxiliary device based on omnibearing computer sight |
| CN101075352A (en) * | 2007-06-29 | 2007-11-21 | 中国科学院计算技术研究所 | Laminated barrier-avoiding method for dynamic body |
| US8589013B2 (en) * | 2011-10-25 | 2013-11-19 | Jaybridge Robotics, Inc. | Method and system for dynamically positioning a vehicle relative to another vehicle in motion |
| CN104765371A (en) * | 2015-04-22 | 2015-07-08 | 福州大学 | Route planning method based on rolling window deep searching and fuzzy control fusion |
| CN106023244A (en) * | 2016-04-13 | 2016-10-12 | 南京邮电大学 | Pedestrian tracking method based on least square locus prediction and intelligent obstacle avoidance model |
| CN106275066A (en) * | 2016-08-30 | 2017-01-04 | 北京智行者科技有限公司 | The rotating direction control method of a kind of intelligent vehicle and device |
-
2017
- 2017-01-19 CN CN201710044287.1A patent/CN106598055B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1987357A (en) * | 2006-12-26 | 2007-06-27 | 浙江工业大学 | Intelligent parking auxiliary device based on omnibearing computer sight |
| CN101075352A (en) * | 2007-06-29 | 2007-11-21 | 中国科学院计算技术研究所 | Laminated barrier-avoiding method for dynamic body |
| US8589013B2 (en) * | 2011-10-25 | 2013-11-19 | Jaybridge Robotics, Inc. | Method and system for dynamically positioning a vehicle relative to another vehicle in motion |
| CN104765371A (en) * | 2015-04-22 | 2015-07-08 | 福州大学 | Route planning method based on rolling window deep searching and fuzzy control fusion |
| CN106023244A (en) * | 2016-04-13 | 2016-10-12 | 南京邮电大学 | Pedestrian tracking method based on least square locus prediction and intelligent obstacle avoidance model |
| CN106275066A (en) * | 2016-08-30 | 2017-01-04 | 北京智行者科技有限公司 | The rotating direction control method of a kind of intelligent vehicle and device |
Non-Patent Citations (2)
| Title |
|---|
| 庄慧忠，等: "动态不确定环境下移动机器人的在线实时路径规划", 《计算机应用与软件》 * |
| 柳在鑫，等: "双圆弧优化算法的足球机器人路径规划", 《华侨大学学报（自然科学版）》 * |
Cited By (80)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108693878A (en) * | 2017-04-06 | 2018-10-23 | 丰田自动车株式会社 | Advance route setting device and advance route setting method |
| CN108693878B (en) * | 2017-04-06 | 2021-06-29 | 丰田自动车株式会社 | Course setting device and course setting method |
| CN107065880A (en) * | 2017-05-16 | 2017-08-18 | 南京农业大学 | Remote operating agricultural vehicle man-computer cooperation paths planning method based on dynamic guiding point |
| CN107357168A (en) * | 2017-06-01 | 2017-11-17 | 同济大学 | A kind of unmanned vehicle barrier-avoiding method based on Chance-constrained Model PREDICTIVE CONTROL |
| CN107357168B (en) * | 2017-06-01 | 2019-12-31 | 同济大学 | Unmanned vehicle obstacle avoidance method based on opportunity constraint model predictive control |
| WO2019042295A1 (en) * | 2017-08-31 | 2019-03-07 | 广州小鹏汽车科技有限公司 | Path planning method, system, and device for autonomous driving |
| CN107702716A (en) * | 2017-08-31 | 2018-02-16 | 广州小鹏汽车科技有限公司 | A kind of unmanned paths planning method, system and device |
| CN107702716B (en) * | 2017-08-31 | 2021-04-13 | 广州小鹏汽车科技有限公司 | Unmanned driving path planning method, system and device |
| US11460311B2 (en) | 2017-08-31 | 2022-10-04 | Guangzhou Xiaopeng Motors Technology Co., Ltd. | Path planning method, system and device for autonomous driving |
| CN111183067A (en) * | 2017-10-05 | 2020-05-19 | 日产自动车株式会社 | Parking control method and parking control device |
| CN111183067B (en) * | 2017-10-05 | 2022-09-27 | 日产自动车株式会社 | Parking control method and parking control device |
| CN107992050B (en) * | 2017-12-20 | 2021-05-11 | 广州汽车集团股份有限公司 | Method and device for planning local path motion of unmanned vehicle |
| CN107992050A (en) * | 2017-12-20 | 2018-05-04 | 广州汽车集团股份有限公司 | Pilotless automobile local path motion planning method and device |
| CN108121347A (en) * | 2017-12-29 | 2018-06-05 | 北京三快在线科技有限公司 | For the method, apparatus and electronic equipment of control device movement |
| CN108196544A (en) * | 2018-01-02 | 2018-06-22 | 联想(北京)有限公司 | A kind of information processing method and information processing equipment |
| WO2019149214A1 (en) * | 2018-02-05 | 2019-08-08 | 腾讯科技（深圳）有限公司 | Smart movement device and navigation method thereof, and storage medium |
| US11247701B2 (en) | 2018-02-05 | 2022-02-15 | Tencent Technology (Shenzhen) Company Ltd | Smart moving device, navigation method thereof, and storage medium |
| CN110239562B (en) * | 2018-03-10 | 2022-10-28 | 百度（美国）有限责任公司 | Real-time perceptual adjustment and driving adaptation of autonomous vehicles based on surrounding vehicle behavior |
| CN110239562A (en) * | 2018-03-10 | 2019-09-17 | 百度（美国）有限责任公司 | The real-time perception adjustment based on surrounding vehicles behavior of automatic driving vehicle is adjusted with driving |
| CN110383192A (en) * | 2018-03-16 | 2019-10-25 | 深圳市大疆创新科技有限公司 | Moveable platform and its control method |
| CN108762272A (en) * | 2018-06-05 | 2018-11-06 | 北京智行者科技有限公司 | A kind of obstacle recognition and preventing collision method |
| CN108762272B (en) * | 2018-06-05 | 2021-01-22 | 北京智行者科技有限公司 | Obstacle identification and avoidance method |
| CN108776479B (en) * | 2018-06-05 | 2021-05-07 | 北京智行者科技有限公司 | Collaborative sweeping operation method |
| CN108776479A (en) * | 2018-06-05 | 2018-11-09 | 北京智行者科技有限公司 | A kind of collaboration cleaning work method |
| CN108614569B (en) * | 2018-06-22 | 2021-01-15 | 北京敏捷动力科技有限公司 | Method for tracking and controlling controlled moving object |
| CN109062948B (en) * | 2018-06-22 | 2020-11-13 | 广州杰赛科技股份有限公司 | Target point determination method, target path determination method and system |
| CN108614569A (en) * | 2018-06-22 | 2018-10-02 | 北京敏捷动力科技有限公司 | A method of being used for tracing control controlled motion object |
| CN109062948A (en) * | 2018-06-22 | 2018-12-21 | 广州杰赛科技股份有限公司 | Target point is determining, destination path determines method and system |
| CN110169741A (en) * | 2018-06-25 | 2019-08-27 | 宁波洒哇地咔电器有限公司 | A kind of cleaning method and equipment |
| CN109101017A (en) * | 2018-07-27 | 2018-12-28 | 江苏盛海智能科技有限公司 | A kind of unmanned vehicle tracks route planning method and terminal |
| CN109101022A (en) * | 2018-08-09 | 2018-12-28 | 北京智行者科技有限公司 | A kind of working path update method |
| CN109062215A (en) * | 2018-08-24 | 2018-12-21 | 北京京东尚科信息技术有限公司 | Robot and barrier-avoiding method, system, equipment and medium are followed based on its target |
| CN109624851B (en) * | 2018-11-23 | 2022-04-19 | 深圳市航盛电子股份有限公司 | Augmented reality-based driving assistance method and system and readable storage medium |
| CN109624851A (en) * | 2018-11-23 | 2019-04-16 | 深圳市航盛电子股份有限公司 | Auxiliary driving method, system and readable storage medium storing program for executing based on augmented reality |
| CN109631899B (en) * | 2018-12-18 | 2022-05-06 | 仲恺农业工程学院 | Path optimization method and system for mobile robot for environment perception |
| CN109631899A (en) * | 2018-12-18 | 2019-04-16 | 仲恺农业工程学院 | A kind of method for optimizing route and system of the mobile robot for environment sensing |
| CN113396122A (en) * | 2019-02-14 | 2021-09-14 | 株式会社多田野 | Crane and route generation system |
| CN113396122B (en) * | 2019-02-14 | 2023-10-10 | 株式会社多田野 | Crane and path generation system |
| US11981548B2 (en) | 2019-02-14 | 2024-05-14 | Tadano Ltd. | Crane and path generation system |
| CN109814577A (en) * | 2019-02-25 | 2019-05-28 | 上海木木聚枞机器人科技有限公司 | A kind of motion control method and mobile device based on information sharing |
| CN109782807B (en) * | 2019-03-08 | 2021-10-01 | 哈尔滨工程大学 | AUV obstacle avoidance method under environment of square-shaped obstacle |
| CN109782807A (en) * | 2019-03-08 | 2019-05-21 | 哈尔滨工程大学 | A kind of AUV barrier-avoiding method under back-shaped obstacle environment |
| CN109916422A (en) * | 2019-03-29 | 2019-06-21 | 北京经纬恒润科技有限公司 | A kind of global path planning method and device |
| CN109917794B (en) * | 2019-04-18 | 2022-02-18 | 北京智行者科技有限公司 | Global path planning method and device |
| CN109917794A (en) * | 2019-04-18 | 2019-06-21 | 北京智行者科技有限公司 | Global path planning method and device |
| CN110083158A (en) * | 2019-04-28 | 2019-08-02 | 深兰科技（上海）有限公司 | A kind of method and apparatus in determining sector planning path |
| CN110262488A (en) * | 2019-06-18 | 2019-09-20 | 重庆长安汽车股份有限公司 | Local paths planning method, system and the computer readable storage medium of automatic Pilot |
| CN110262488B (en) * | 2019-06-18 | 2021-11-30 | 重庆长安汽车股份有限公司 | Automatic driving local path planning method, system and computer readable storage medium |
| CN111439257A (en) * | 2019-06-26 | 2020-07-24 | 纵目科技（上海）股份有限公司 | Memory parking system, method, terminal and cloud server |
| TWI715221B (en) * | 2019-09-27 | 2021-01-01 | 財團法人車輛研究測試中心 | Adaptive trajectory generation method and system |
| CN110766220A (en) * | 2019-10-21 | 2020-02-07 | 湖南大学 | Local path planning method for structured road |
| CN110703758A (en) * | 2019-10-25 | 2020-01-17 | 北京京东乾石科技有限公司 | Path planning method and device |
| CN110879560B (en) * | 2019-12-23 | 2022-02-25 | 北京百度网讯科技有限公司 | Method, apparatus, device and storage medium for controlling vehicle |
| CN110879560A (en) * | 2019-12-23 | 2020-03-13 | 北京百度网讯科技有限公司 | Method, apparatus, device and storage medium for controlling vehicle |
| CN111142520A (en) * | 2019-12-24 | 2020-05-12 | 中国科学院合肥物质科学研究院 | Planning and control method of crawler-type unmanned vehicle on cliff obstacle road |
| CN111142520B (en) * | 2019-12-24 | 2022-03-11 | 中国科学院合肥物质科学研究院 | Planning and control method of crawler-type unmanned vehicle on cliff obstacle road |
| CN111368639A (en) * | 2020-02-10 | 2020-07-03 | 浙江大华技术股份有限公司 | Vehicle lane crossing determination method, vehicle lane crossing determination device, computer device, and storage medium |
| CN111381594A (en) * | 2020-03-09 | 2020-07-07 | 兰剑智能科技股份有限公司 | AGV space obstacle avoidance method and system based on 3D vision |
| CN111739342A (en) * | 2020-03-26 | 2020-10-02 | 腾讯科技（深圳）有限公司 | Method, device, medium, and vehicle for avoiding vehicle ahead of side |
| CN111739342B (en) * | 2020-03-26 | 2022-03-01 | 腾讯科技（深圳）有限公司 | Method, device, medium, and vehicle for avoiding vehicle ahead of side |
| CN111653113A (en) * | 2020-04-20 | 2020-09-11 | 浙江吉利汽车研究院有限公司 | Method, device, terminal and storage medium for determining local path of vehicle |
| CN111653113B (en) * | 2020-04-20 | 2022-09-27 | 浙江吉利汽车研究院有限公司 | Method, device, terminal and storage medium for determining local path of vehicle |
| CN111506070B (en) * | 2020-04-26 | 2023-09-08 | 北京踏歌智行科技有限公司 | Local path planning method based on path point offset |
| CN111506070A (en) * | 2020-04-26 | 2020-08-07 | 北京踏歌智行科技有限公司 | Local path planning method based on path point deviation |
| CN113568400A (en) * | 2020-04-28 | 2021-10-29 | 北京猎户星空科技有限公司 | Robot control method and device, electronic equipment and storage medium |
| CN111703421A (en) * | 2020-05-13 | 2020-09-25 | 重庆长安汽车股份有限公司 | Trajectory planning system, method and storage medium for automatic driving and getting rid of difficulty of vehicle |
| CN111504340A (en) * | 2020-05-22 | 2020-08-07 | 北京汽车研究总院有限公司 | Vehicle path planning method and device and vehicle |
| CN112504288B (en) * | 2020-07-22 | 2022-06-28 | 北京智行者科技有限公司 | Local path planning method based on dynamic planning |
| CN112504288A (en) * | 2020-07-22 | 2021-03-16 | 北京智行者科技有限公司 | Local path planning method based on dynamic planning |
| CN112034848A (en) * | 2020-08-13 | 2020-12-04 | 驭势科技（北京）有限公司 | Obstacle avoiding method and device, electronic equipment and storage medium |
| CN113790725B (en) * | 2020-09-22 | 2024-03-01 | 北京京东乾石科技有限公司 | Path planning method, path planning device, storage medium and mobile device |
| CN113790725A (en) * | 2020-09-22 | 2021-12-14 | 北京京东乾石科技有限公司 | Path planning method, path planning device, storage medium and mobile equipment |
| CN112172807A (en) * | 2020-10-23 | 2021-01-05 | 上海伯镭智能科技有限公司 | Obstacle avoidance judging method of unmanned automobile obstacle avoidance system |
| CN112172807B (en) * | 2020-10-23 | 2022-07-19 | 上海伯镭智能科技有限公司 | Obstacle avoidance judgment method of unmanned automobile obstacle avoidance system |
| CN113063423A (en) * | 2021-03-23 | 2021-07-02 | 广东工业大学 | Global path planning and cutting method and system based on Lanelet frame |
| CN113063423B (en) * | 2021-03-23 | 2023-01-10 | 广东工业大学 | Global path planning and cutting method and system based on Lanelet frame |
| CN113267199A (en) * | 2021-06-24 | 2021-08-17 | 上海欧菲智能车联科技有限公司 | Driving track planning method and device |
| WO2023273731A1 (en) * | 2021-06-30 | 2023-01-05 | 北京旷视科技有限公司 | Obstacle avoidance method and apparatus, and automatic navigation apparatus |
| CN113885525A (en) * | 2021-10-30 | 2022-01-04 | 重庆长安汽车股份有限公司 | Path planning method and system for automatically driving vehicle to get rid of trouble, vehicle and storage medium |
| CN114995398A (en) * | 2022-05-16 | 2022-09-02 | 中国第一汽车股份有限公司 | Path generation method, path generation device, storage medium, processor and electronic device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106598055B (en) | 2019-05-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106598055B (en) | A kind of intelligent vehicle local paths planning method and its device, vehicle | |
| US11933627B2 (en) | High-definition map building method and apparatus | |
| CN112068545B (en) | Method and system for planning running track of unmanned vehicle at crossroad and storage medium | |
| WO2022193584A1 (en) | Multi-scenario-oriented autonomous driving planning method and system | |
| KR20200101855A (en) | Travelling track prediction method and device for vehicle | |
| CN110111566A (en) | Trajectory predictions method, apparatus and storage medium | |
| CN107121980A (en) | A kind of automatic driving vehicle paths planning method based on virtual constraint | |
| WO2019042295A1 (en) | Path planning method, system, and device for autonomous driving | |
| CN104897168B (en) | The intelligent vehicle method for searching path and system assessed based on road hazard | |
| CN108088456A (en) | A kind of automatic driving vehicle local paths planning method with time consistency | |
| CN105936276A (en) | Travel control device | |
| CN104819724A (en) | Unmanned ground vehicle self-driving assisting system based on GIS | |
| CN109084798A (en) | Network issues the paths planning method at the control point with road attribute | |
| WO2018142527A1 (en) | Travel history storage method, method for producing travel path model, method for estimating local position, and travel history storage device | |
| US20230296382A1 (en) | Determination of free space around a vehicle | |
| CN107664504A (en) | A kind of path planning apparatus | |
| CN110146087B (en) | Ship path planning method based on dynamic planning idea | |
| US20220351526A1 (en) | Multi-frame image segmentation | |
| US20230195122A1 (en) | Systems and methods for map-based real-world modeling | |
| WO2021262976A1 (en) | Systems and methods for detecting an open door | |
| CN111896004A (en) | Narrow passage vehicle track planning method and system | |
| CN107289938A (en) | A kind of unmanned ground vehicle local paths planning method | |
| US20230202473A1 (en) | Calculating vehicle speed for a road curve | |
| CN104699791B (en) | A kind of path restoring method for being used to damage floating wheel paths | |
| CN113009912A (en) | Low-speed commercial unmanned vehicle path planning calculation method based on mixed A star |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CP03 | Change of name, title or address |
Address after: Building C-3, Northern Territory, Zhongguancun Dongsheng Science Park, 66 Xixiaokou Road, Haidian District, Beijing, 100176 Patentee after: Beijing Idriverplus Technology Co.,Ltd. Address before: B4-006, maker Plaza, 338 East Street, Huilongguan town, Changping District, Beijing 102208 Patentee before: Beijing Idriverplus Technology Co.,Ltd. |
|
| CP03 | Change of name, title or address |