CN109557928A - Automatic driving vehicle paths planning method based on map vector and grating map - Google Patents
Automatic driving vehicle paths planning method based on map vector and grating map Download PDFInfo
- Publication number
- CN109557928A CN109557928A CN201910045498.6A CN201910045498A CN109557928A CN 109557928 A CN109557928 A CN 109557928A CN 201910045498 A CN201910045498 A CN 201910045498A CN 109557928 A CN109557928 A CN 109557928A
- Authority
- CN
- China
- Prior art keywords
- map
- global
- automatic driving
- driving vehicle
- vector
- 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 61
- 230000033001 locomotion Effects 0.000 claims abstract description 82
- 230000007613 environmental effect Effects 0.000 claims abstract description 44
- 238000010586 diagram Methods 0.000 claims description 23
- 230000006870 function Effects 0.000 claims description 22
- 238000005457 optimization Methods 0.000 claims description 22
- 230000004888 barrier function Effects 0.000 claims description 21
- 230000004807 localization Effects 0.000 claims description 10
- 238000005070 sampling Methods 0.000 claims description 8
- 239000011159 matrix material Substances 0.000 claims description 7
- 230000000903 blocking effect Effects 0.000 claims description 4
- 238000005259 measurement Methods 0.000 claims description 4
- 238000013507 mapping Methods 0.000 claims description 3
- 230000008569 process Effects 0.000 description 7
- 230000008859 change Effects 0.000 description 4
- 238000010411 cooking Methods 0.000 description 3
- 241001269238 Data Species 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 230000001133 acceleration Effects 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000004033 diameter control Methods 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 230000003068 static 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
- G05D1/0268—Control of position or course in two dimensions specially adapted to land vehicles using internal positioning means
- G05D1/0274—Control of position or course in two dimensions specially adapted to land vehicles using internal positioning means using mapping information stored in a memory device
-
- 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
- G05D1/0217—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory in accordance with energy consumption, time reduction or distance reduction criteria
-
- 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
- G05D1/0238—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means using obstacle or wall sensors
- G05D1/024—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means using obstacle or wall sensors in combination with a laser
-
- 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
-
- 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
- G05D1/0268—Control of position or course in two dimensions specially adapted to land vehicles using internal positioning means
- G05D1/027—Control of position or course in two dimensions specially adapted to land vehicles using internal positioning means comprising intertial navigation means, e.g. azimuth detector
Landscapes
- Engineering & Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Physics & Mathematics (AREA)
- Aviation & Aerospace Engineering (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Optics & Photonics (AREA)
- Electromagnetism (AREA)
- Traffic Control Systems (AREA)
Abstract
The present invention provides a kind of automatic driving vehicle paths planning method based on map vector and grating map, comprising: the current location of automatic driving vehicle is cooked up to the global shortest path of target point by global vector map；Obtain the current local grid map of the current location of automatic driving vehicle；According to global shortest path, local motion path is calculated based on local grid map, in order to march to the target point according to local motion path clustering automatic driving vehicle.The present invention uses map vector as environmental model in global path planning layer, use grating map as environmental model in local motion path planning layer, use different maps as environmental model in different planning layers, cooperate simultaneously using different types of planning algorithm, it meets under actual scene to algorithm real-time and accuracy simultaneously, also, the algorithm that map vector and grating map combine greatly reduces the occupancy for system operations resource.
Description
Technical field
The present invention relates to automatic Pilot technical fields, are based on map vector and grating map more specifically to one kind
Automatic driving vehicle paths planning method.
Background technique
Automatic Pilot is the important development direction of current intelligent transportation, and Path Planning Technique is the core skill of automatic Pilot
One of art is the basis of intelligent vehicle navigation and control.
Automatic driving vehicle Path Planning Technique is divided into global path planning and local trajectory path planning, wherein global road
Diameter planning is responsible for cooking up the shortest path from origin-to-destination, and local motion path planning is responsible for cooking up that meet vehicle non-
Holonomic constriants, can in real time obstacle, the local motion path comprising time series control vehicle information.
In existing automatic Pilot paths planning method, using single use global path planning or local motion
Path planning, operand is big, occupies a large amount of system resources, also, using single local motion path planning to vehicle-mounted biography
The requirement of sensor is high, and path planning accuracy is poor.
Summary of the invention
In view of this, the present invention provides a kind of automatic driving vehicle path planning side based on map vector and grating map
Method, comprising:
By global vector map, the current location of automatic driving vehicle is cooked up to the global shortest path of target point；
Acquisition environmental information in real time, and point cloud data is converted by the environmental information, with being mapped as current local grid
Figure；
According to the global shortest path, it is based on the current local grid map, and combine local positioning information, utilized
Local motion path is calculated in sector planning algorithm, in order to the automatic Pilot vehicle according to the local motion path clustering
March to the target point.
Preferably, described " by global vector map, it is complete to target point to cook up the current location of automatic driving vehicle
Office shortest path " include:
By map sampling instrument, global vector map is obtained, and the global vector map is resolved into global path
Oriented cum rights node topology figure；Wherein, the global vector map includes the road point diagram and point cloud number that coordinate point set is constituted
According to the voice data figure of composition；
Current point cloud information is acquired by environment information acquisition device；According to Global localization algorithm, to the current point cloud
Information is matched with the point cloud data, and determines the automatic driving vehicle in the global vector according to matching result
World coordinates information converting in figure；
Receive the global object point that user is set based on the global vector map；
According to the oriented cum rights node topology figure, world coordinates information converting and global object point, calculate from
Most short global path of the current location of the automatic driving vehicle to the global object point.
Preferably, described " by map sampling instrument, to obtain global vector map, and the global vector is illustrated
Analysis is the oriented cum rights node topology figure of global path；Wherein, the global vector map includes the road that coordinate point set is constituted
The voice data figure that point diagram and point cloud data are constituted " includes:
Collect the global vector map；
Run global map resolver, in the global vector map path coordinate point set constitute road point diagram into
Row parsing, is resolved to road network node for the path coordinate point, has been stored as based on corresponding adjacent chained list or adjacency matrix form
To cum rights structure；And parse the road information comprising intersection, road width；
According to the road network node of oriented cum rights structure and the road information, the institute of global path is obtained
State oriented cum rights node topology figure.
Preferably, described " to acquire environmental information in real time, and convert point cloud data for the environmental information, be mapped as working as
Preceding local grid map " includes:
The current point cloud information collected to the environment information acquisition device is split and merges, and will segmentation
With the fused current point cloud information MAP to two-dimensional grid map, preliminary grating map is obtained；
Based on the current point cloud information, the current local grid map is obtained according to the preliminary grating map.
Preferably, described " to be based on the current point cloud information, the current part is obtained according to the preliminary grating map
Grating map " includes:
According to the range information of automatic driving vehicle and barrier described in the current point cloud acquisition of information；
Using grating map renovator, according to the range information, the preliminary grating map is updated based on expansion parameters,
Obtain the current local grid map.
Preferably, described " grating map renovator to be utilized, according to the range information, based on described in expansion parameters update
Preliminary grating map obtains the current local grid map " include:
Using grating map renovator, it is each grid point assignment in the preliminary grating map based on expansion parameters, obtains
To the corresponding cost value of each grid point；Wherein, there is the probability of barrier using the cost value as this grid point；Also,
Using the preliminary grating map of the updated probability with barrier comprising each grid point as the current part
Grating map.
Preferably, described " according to the global shortest path, to be based on the current local grid map, and combine part
Local motion path is calculated using sector planning algorithm in location information, in order to according to the local motion path clustering
The automatic driving vehicle marches to the target point " include:
Local positioning information and the current local grid according to the global shortest path, in conjunction with the current location
Map constructs multi-goal optimizing function；Wherein, the optimization item of the multi-goal optimizing function includes the environmental information；
The multi-goal optimizing function that item includes the environmental information will be optimized and be converted to figure optimization node, and according to institute
It states figure optimization node and the local motion path is calculated.
Preferably, described " according to the global shortest path, to be based on the current local grid map, and combine part
Local motion path is calculated using sector planning algorithm in location information " after, further includes:
According to the corresponding vehicle control instruction of the local motion coordinates measurement, and based on vehicle control instruction control
The automatic driving vehicle is mobile to global object point according to the global shortest path and the local motion path；
After the automatic driving vehicle is mobile, judge whether the automatic driving vehicle reaches the global object point；
If the automatic driving vehicle is not up to the global object point, judge whether that the local motion path is hindered
Gear；
If the local motion path is not blocked, " environmental information is acquired in real time, and the environment is believed described in return
Breath is converted into point cloud data, is mapped as current local grid map "；
If the local motion path is blocked, generates and stop path planning, and generate blocking prompt information.
In addition, to solve the above problems, the present invention also provides a kind of automatic Pilot based on map vector and grating map
Vehicle path planning device, comprising:
Global Algorithm module for parsing global road-net node topology by global vector map, and combines the overall situation fixed
Position algorithm, cooks up the current location of automatic driving vehicle to the global shortest path of target point；
Information-mapping module for acquiring environmental information in real time, and converts point cloud data for the environmental information, maps
For current local grid map；
Local algorithm module, for being based on the current local grid map, and combine according to the global shortest path
Local motion path is calculated using sector planning algorithm in local positioning information, in order to according to the local motion path
It controls the automatic driving vehicle and marches to the target point.
In addition, to solve the above problems, the computer equipment includes storage the present invention also provides a kind of computer equipment
Device and processor, the memory is for storing the automatic driving vehicle path planning journey based on map vector and grating map
Sequence, the processor run the automatic driving vehicle path planning program based on map vector and grating map so that described
Computer equipment executes the automatic driving vehicle paths planning method as described above based on map vector and grating map.
In addition, to solve the above problems, the present invention also provides a kind of computer readable storage medium, it is described computer-readable
The automatic driving vehicle path planning program based on map vector and grating map is stored on storage medium, it is described to be based on vector
The automatic driving vehicle path planning program of map and grating map is realized as described above based on vector when being executed by processor
The automatic driving vehicle paths planning method of map and grating map.
A kind of automatic driving vehicle paths planning method based on map vector and grating map provided by the invention.This hair
It is bright that the current location of automatic driving vehicle is cooked up to the global shortest path of target point by global vector map；Described in acquisition
The current local grid map of the current location of automatic driving vehicle；According to the global shortest path, based on the local grid
Lattice map calculation obtains local motion path, in order to the traveling of the automatic driving vehicle according to the local motion path clustering
To the target point.The present invention uses map vector as environmental model in global path planning layer, advises in local motion path
Drawing layer uses grating map as environmental model, i.e., uses different maps as environmental model in different planning layers, match simultaneously
It closes and uses different types of planning algorithm, while meeting under actual scene to algorithm real-time and accuracy, also, vector
The algorithm that figure and grating map combine greatly reduces the occupancy for system operations resource.
Detailed description of the invention
Fig. 1 is that the present invention is based on the automatic driving vehicle paths planning method example schemes of map vector and grating map
The structural schematic diagram for the hardware running environment being related to；
Fig. 2 is that the present invention is based on the automatic driving vehicle paths planning method first embodiments of map vector and grating map
Flow diagram；
Fig. 3 is that the present invention is based on the automatic driving vehicle paths planning method second embodiments of map vector and grating map
The flow diagram of middle step S100 refinement；
Fig. 4 is that the present invention is based on the automatic driving vehicle paths planning method second embodiments of map vector and grating map
The flow diagram of middle step S110 refinement；
Fig. 5 is that the present invention is based on the automatic driving vehicle paths planning method 3rd embodiments of map vector and grating map
The flow diagram of middle step S200 refinement；
Fig. 6 is that the present invention is based on the automatic driving vehicle paths planning method 3rd embodiments of map vector and grating map
The flow diagram of middle step S220 refinement；
Fig. 7 is that the present invention is based on the automatic driving vehicle paths planning method 3rd embodiments of map vector and grating map
The flow diagram of middle step S222 refinement；
Fig. 8 is that the present invention is based on the automatic driving vehicle paths planning method 3rd embodiments of map vector and grating map
The flow diagram of middle step S300 refinement；
Fig. 9 is that the present invention is based on the automatic driving vehicle paths planning method fourth embodiments of map vector and grating map
Flow diagram；
Figure 10 is that the present invention is based on the implementations of the automatic driving vehicle paths planning method the 5th of map vector and grating map
Flow diagram in example；
Figure 11 is that the present invention is based on the function moulds of map vector and the automatic driving vehicle path planning apparatus of grating map
Block connection schematic diagram；
Figure 12 is that the present invention is based on the automatic driving vehicle path planning apparatus another kind of map vector and grating map is real
Apply the functional module connection schematic diagram including integrated decision-making module in mode.
The embodiments will be further described with reference to the accompanying drawings for the realization, the function and the advantages of the object of the present invention.
Specific embodiment
The embodiment of the present invention is described below in detail, in which the same or similar labels are throughly indicated same or like
Element or element with the same or similar functions.
In addition, term " first ", " second " are used for descriptive purposes only and cannot be understood as indicating or suggesting relative importance
Or implicitly indicate the quantity of indicated technical characteristic.Define " first " as a result, the feature of " second " can be expressed or
Implicitly include one or more of the features.In the description of the present invention, the meaning of " plurality " is two or more,
Unless otherwise specifically defined.
It should be appreciated that the specific embodiments described herein are merely illustrative of the present invention, it is not intended to limit the present invention.
As shown in Figure 1, being the structural schematic diagram of the hardware running environment for the terminal that the embodiment of the present invention is related to.
The PC that computer equipment of the embodiment of the present invention can be is also possible to smart phone, tablet computer or with one
Determine the packaged types terminal device such as portable computer and mobile unit.As shown in Figure 1, the computer equipment may include: place
Manage device 1001, such as CPU, network interface 1004, user interface 1003, memory 1005, communication bus 1002.Wherein, it communicates
Bus 1002 is for realizing the connection communication between these components.User interface 1003 may include display screen, input unit ratio
Such as keyboard, remote controler, optional user interface 1003 can also include standard wireline interface and wireless interface.Network interface 1004
It may include optionally standard wireline interface and wireless interface (such as WI-FI interface).Memory 1005 can be high-speed RAM and deposit
Reservoir is also possible to stable memory, such as magnetic disk storage.Memory 1005 optionally can also be independently of aforementioned place
Manage the storage device of device 1001.Optionally, terminal can also include RF (Radio Frequency, radio frequency) circuit, audio-frequency electric
Road, WiFi module etc..In addition, computer equipment can also configure gyroscope, barometer, hygrometer, thermometer, infrared ray sensing
The other sensors such as device, details are not described herein.
It will be understood by those skilled in the art that computer equipment shown in Fig. 1 does not constitute the limit to computer equipment
It is fixed, it may include perhaps combining certain components or different component layouts than illustrating more or fewer components.Such as Fig. 1 institute
Show, as may include in a kind of memory 1005 of computer readable storage medium operating system, data-interface control program,
Network attachment procedure and automatic driving vehicle path planning program based on map vector and grating map.
A kind of automatic driving vehicle paths planning method based on map vector and grating map provided by the invention.Complete
Office's path planning layer uses map vector as environmental model, uses grating map as environment in local motion path planning layer
Model uses different maps as environmental model in different planning layers, while cooperating using different types of planning algorithm,
It is met under actual scene simultaneously to algorithm real-time and accuracy, also, the algorithm that map vector and grating map combine
Greatly reduce the occupancy for system operations resource.
Embodiment 1:
Referring to Fig. 2, first embodiment of the invention provides a kind of automatic driving vehicle based on map vector and grating map
Paths planning method, comprising:
Step S100 cooks up the current location of automatic driving vehicle to the overall situation of target point by global vector map
Shortest path；
Automatic driving vehicle is also known as pilotless automobile, computer driving or wheeled mobile robot, is that one kind passes through
Computer system realizes unpiloted intelligent automobile.Have the history of many decades in 20th century, is showed at the beginning of 21 century close to real
With the trend of change.
Global vector map is a certain range of map vector, for example, the map vector in certain urban area, or
Map vector in certain parking lot.
It is the starting point and emphasis for needing to carry out path planning between the current location and target point of automatic driving vehicle.It is global
Shortest path, as in the case where not considering actual barrier and environment on global vector map, according in map vector
Route relevant information cook up come shortest path.For example, global shortest path is straight line by A point to B point, and in
Between during traveling, in fact it could happen that barrier C, then global shortest path does not take into account that the barrier, needs further office
Portion's trajectory path planning layer carries out planning avoidance.
In the present embodiment, including the algorithm based on global path planning level and the algorithm based on sector planning level.
Wherein, it in Global motion planning level, carries out that global shortest path is calculated using global vector map and its resolver, also,
It in sector planning level, is further calculated based on local grid map and its renovator, to obtain corresponding part fortune
Dynamic path.To which further planning path can be carried out by Comprehensive Decision Algorithm until target point.
Wherein, global vector map is a kind of priori map, is just adopted by map sampling instrument before path planning
What collection completed.The global vector map that the present embodiment uses includes the road point diagram and point cloud data being made of coordinate point set
Voice data figure two parts of composition are constituted.Wherein coordinate point diagram is used to describe the information of road, and phonogram is for describing environment
The environmental informations such as barrier, road instruction disk, traffic lights.Road sampling instrument is taken the photograph using laser radar, binocular in the present embodiment
Picture head, IMU are mounted in map collecting vehicle as map data collecting tool.The global map format that the present embodiment uses makes
Use OpenDrive.
Step S200 acquires environmental information in real time, and converts point cloud data for the environmental information, is mapped as current office
Portion's grating map；
Above-mentioned, current local grid map is the environmental information of local motion path planning level, is responsible for cooking up satisfaction
Vehicle nonholonomic constraint, can in real time obstacle, the local motion path comprising time series control vehicle information.
Wherein, grating image, also referred to as raster image refer on space and brightness all images of discretization.It can
A width grating image is thought of as a matrix, the either element in matrix corresponds to a point in image, and corresponding
Value corresponds to the gray level of the point, and the element in character matrix is called pixel.
It is above-mentioned, since current location is real-time transform in the traveling process of vehicle, so local grid map is real
When obtain, construct in real time, i.e., be acquired and update while carrying out path planning.By being converted to point cloud data, and
After being mapped, to obtain current local grid map.
Step S300 is based on the current local grid map, and combine local positioning according to the global shortest path
Local motion path is calculated using sector planning algorithm in information, in order to according to the local motion path clustering
Automatic driving vehicle marches to the target point.
It is above-mentioned, the planning and traveling for advance route are carried out according to local motion path, need to calculate by integrated decision-making
Method carries out control and operation, and Comprehensive Decision Algorithm is used for starting, stopping and the change of integrated dispatch Global motion planning and sector planning.
After system receives Global localization information and target point, decision making algorithm scheduling starts to carry out Global motion planning, complete in Global motion planning
Cheng Hou, carries out sector planning and the ECU unit for exporting control information to vehicle controls vehicle.It is completed after vehicle arrives at the destination
Planning process, while in planning process, according to the information of external environment, whether comprehensive descision is from new Global motion planning or parking
Braking etc..
It should be noted that Global motion planning algorithm uses in the oriented cum rights of road network that global vector map parses
Node topology cooks up the shortest path from origin-to-destination.This method is used as using A* (A-Star) algorithm from global road
Plan the algorithm of shortest path in net, A* is to solve the most effective direct search method of shortest path in a kind of static road network, is
A kind of heuritic approach.Cook up come global path along real road, with the shortest path of directional information.
A kind of automatic driving vehicle paths planning method based on map vector and grating map provided in this embodiment.?
Global path planning layer uses map vector as environmental model, uses grating map as ring in local motion path planning layer
Border model is used different maps as environmental model, while cooperating and being calculated using different types of planning in different planning layers
Method, while meeting under actual scene to algorithm real-time and accuracy, also, the calculation that map vector and grating map combine
Method greatly reduces the occupancy for system operations resource.
Embodiment 2:
Referring to Fig. 3-4, second embodiment of the invention provides a kind of automatic Pilot vehicle based on map vector and grating map
Paths planning method, is based on above-mentioned first embodiment shown in Fig. 2, and the step S100 " passes through global vector map, rule
The current location of automatic driving vehicle is marked to the global shortest path of target point " include:
Step S110 obtains global vector map by map sampling instrument, and the global vector map is resolved to
The oriented cum rights node topology figure of global path；Wherein, the global vector map includes the road point diagram that coordinate point set is constituted
The voice data figure constituted with point cloud data；
Further, the step S110 " obtains global vector map, and the global vector map has been resolved to
To cum rights node topology figure " include:
Step S111 collects the global vector map；
Step S112 runs global map resolver, constitutes to the path coordinate point set in the global vector map
Road point diagram is parsed, and the path coordinate point is resolved to road network node, is based on corresponding adjacent chained list or adjacency matrix shape
Formula is stored as oriented cum rights structure；And parse the road information comprising intersection, road width；
Step S113 obtains the overall situation according to the road network node of oriented cum rights structure and the road information
The oriented cum rights node topology figure in path.
Above-mentioned, global map resolver is used to parse the information that can be used for planning from global vector map.Road is sat
Punctuate resolves to road network node, and the oriented cum rights graph structure stored in the form of corresponding adjacent chained list or adjacency matrix, simultaneously
Parse the road informations such as intersection, road width.
Step S120 acquires current point cloud information by environment information acquisition device；According to Global localization algorithm, to described
Current point cloud information is matched with the point cloud data, and determines the automatic driving vehicle described complete according to matching result
World coordinates information converting in office's map vector；
Above-mentioned, environment information acquisition device is obtained or is adopted for real-time or timing for automatic driving vehicle is vehicle-mounted
The device for collecting the change information of ambient enviroment, can include but is not limited to vehicle-mounted multiple sensors, such as infrared sensor
Deng；Acousto-optic electric detection device or Image Acquisition and identification device, such as camera etc..
Step S130 receives the global object point that user is set based on the global vector map；
Step S140, according to the oriented cum rights node topology figure, world coordinates information converting and global object point,
Calculate the most short global path from the current location of the automatic driving vehicle to the global object point.
In the present embodiment, in Global motion planning level, it is based on Global motion planning algorithm, obtains global vector map, Jin Ergen
According to the matching result of current point cloud information and point cloud data, the overall situation of the automatic driving vehicle in the global vector map is determined
Coordinate transform information calculates the most short overall situation of the point from the current location of vehicle to global object after obtaining global object point
Path, realize in Global motion planning level by map vector, cook up global shortest path.
Embodiment 3:
Referring to Fig. 5-8, third embodiment of the invention provides a kind of automatic Pilot vehicle based on map vector and grating map
Paths planning method, is based on above-mentioned first embodiment shown in Fig. 2, the step S200, " environmental information is acquired in real time, and
Point cloud data is converted by the environmental information, is mapped as current local grid map " include:
Step S210, the current point cloud information collected to the environment information acquisition device are split and melt
It closes, and will divide with the fused current point cloud information MAP to two-dimensional grid map, obtain preliminary grating map；
Step S220 is based on the current point cloud information, obtains the current local grid according to the preliminary grating map
Lattice map.
Further, the step S220 " is based on the current point cloud information, is obtained according to the preliminary grating map
The current local grid map " includes:
Step S221, according to the range information of automatic driving vehicle and barrier described in the current point cloud acquisition of information；
Step S222 is updated described preliminary using grating map renovator according to the range information based on expansion parameters
Grating map obtains the current local grid map.
The step S222 " utilizes grating map renovator, according to the range information, updates institute based on expansion parameters
Preliminary grating map is stated, the current local grid map is obtained " include:
Step S222a is each grid in the preliminary grating map based on expansion parameters using grating map renovator
Point assignment, obtains the corresponding cost value of each grid point；Wherein, there is the general of barrier using the cost value as this grid point
Rate；Also, using the preliminary grating map of the updated probability with barrier comprising each grid point as described in
Current local grid map.
Local grid map constructs in real time, is acquired and updates while carrying out path planning.Vehicle-mounted sensing
Device includes laser radar, binocular camera, IMU.These sensors acquire extraneous environment in real time during vehicle movement
Data, and be converted into point cloud data, these data only include barrier through the methods of over-segmentation, fusion, for example, wall, fence,
Column etc., then these point cloud datas are mapped to two-dimensional grid map.Grating map is divided whole map with certain resolution ratio
For a certain number of small lattice, each lattice represents the probability with barrier with normalized 0 to 1, and real in vehicle movement
Shi Gengxin.
Generate local grid map, the as reality by preliminary grating map when moving in real time, environment changing
Shi Gengxin, to obtain local grid map.Further, it for the update of local grid map, is updated by grating map
Device is realized, specifically, grating map renovator updates each grid point of grating map using point cloud data and vehicle's current condition
Cost value, and layering and expansion function can be carried out.Probability of this grid point with barrier is represented as 0 with 0, is represented with 1
It is 1 that this grid point, which has the probability of barrier,.At no point in the update process, it is comprehensive combine point cloud data and vehicle distances grid point away from
Assignment is carried out from for each grid point.It is arranged by certain threshold value, can passes through or avoid passing point with guiding vehicle.
Further, the step S300, " according to the global shortest path, it is based on the current local grid map,
And local positioning information is combined, local motion path is calculated using sector planning algorithm, in order to transport according to the part
Automatic driving vehicle described in dynamic path clustering marches to the target point " include:
Step S310, according to the global shortest path, in conjunction with the current location local positioning information and described work as
Preceding local grid map constructs multi-goal optimizing function；Wherein, the optimization item of the multi-goal optimizing function includes the environment
Information；
Above-mentioned, the optimization item of the multi-goal optimizing function includes the environmental information, and the specific optimization item includes
Environmental information in can be but be not limited to obstacle distance, path length, run duration, with the spacing of global path etc..
Step S320 will optimize the multi-goal optimizing function that item includes the environmental information and be converted to figure optimization section
Point, and node is optimized according to the figure, the local motion path is calculated.
Sector planning algorithm combines the grating map acquired in real time and the global map planned, cooks up to have in real time and keep away
Barrier function meets the local path of vehicle nonholonomic constraint, output comprising vehicle control information.This method is based on multiple-objection optimization
Sector planning algorithm is decomposed into multi-objective optimization question, when optimization item includes obstacle distance, path length, movement by thought
Between, with the spacing of global path, optimization aim is that pursue run duration most short.It reuses figure optimum theory and says above-mentioned multiple target
Function is converted to node of graph, the local path optimized using g2o.In the present embodiment, sector planning can be set
Plan frequency cooperates grating map frequency acquisition and vehicle control algorithms frequency.
Wherein, the multiple target goes out majorized function are as follows:
Y=α f (v)+β f (a)+γ f (b)+δ f (r)+ε f (t)+η f (g)；
Wherein, f (r) is the constraint of vehicle minimum turning radius, f (v) speed is constraint of velocity, and f (a) is acceleration constraint, f
(b) be obstacles restriction, f (g) be global path tracking constraint, f (t) be to constrain the shortest time.Wherein α, β, γ, δ, ε ,+η are
Every weight.Then local paths planning is converted to the optimal solution asked with superior function, it may be assumed that min (y)；It is asked in combination with the optimization of the figures such as g2o
The value of solution tool calculating respective function.
It should be noted that sector planning algorithm combines the grating map acquired in real time and the global map planned, it is real
When cook up with barrier avoiding function, meet vehicle nonholonomic constraint, output include vehicle control information local motion path.This
Method is based on multiple-objection optimization thought, and sector planning algorithm is decomposed into multi-objective optimization question, optimization item include barrier away from
From, path length, run duration, with the spacing of global path, optimization aim is that pursue run duration most short.Reuse figure optimization
Theory says that above-mentioned multiple objective function is converted to node of graph, the local motion path optimized using g2o.This method can
The plan frequency of sector planning is arranged, cooperate grating map frequency acquisition and vehicle control algorithms frequency.
It should be noted that location algorithm includes Global localization and local positioning.Wherein Global localization is for determining vehicle
Coordinate of the Startup time in global map.Believed using the point cloud in the collected point cloud data of onboard sensor and global map
Breath carries out matching for determining global pose point.Can with the coordinate transform information to Map to Odometry.Local positioning passes through
Onboard sensor calculates vehicle rear axle center in real time and becomes to the coordinate transform of vehicle starting point and the coordinate of Odometry to base
It changes.Two kinds of location datas all will bring path planning algorithm into as input information.
Embodiment 4:
Referring to Fig. 9, third embodiment of the invention provides a kind of automatic driving vehicle based on map vector and grating map
Paths planning method, is based on above-mentioned first embodiment shown in Fig. 2, the step S300, " according to the global shortest path,
Based on the current local grid map, and local positioning information is combined, local motion is calculated using sector planning algorithm
After path ", further includes:
Step S400 is instructed according to the corresponding vehicle control of the local motion coordinates measurement, and is based on the vehicle control
System instruction controls the automatic driving vehicle according to the global shortest path and the local motion path to global object point
It is mobile；
Above-mentioned, global object point is to obtain in the target position of Global motion planning level, the i.e. emphasis of this path planning
To after vehicle control instruction, carried out in the global shortest path of global level and the local motion path of sector planning level
Planning, it is mobile to global object point.
Step S500 judges whether the automatic driving vehicle reaches described complete after the automatic driving vehicle is mobile
Office's target point；
Step S600 judges whether the part fortune if the automatic driving vehicle is not up to the global object point
Dynamic path is blocked；
If the local motion path is not blocked, " environmental information is acquired in real time, and the environment is believed described in return
Breath is converted into point cloud data, is mapped as current local grid map "；
The step S700 is generated if the local motion path is blocked and is stopped path planning, and generates blocking prompt
Information.
In addition, stopping path planning if the automatic driving vehicle has arrived the global object point.
It is above-mentioned, during automatic driving vehicle is advanced according to instruction, needs to hinder situation in front of real-time judge, that is, judge
Whether local motion path is blocked.If be blocked, stop path planning, need return step S200, carries out again real
When acquire environmental information, map current local grid map；At this point, instruction can be further generated, it is current according to what is be mapped to
Local grid map is planned again.And if having arrived at global object point, it can determine that reach home, stop path
Planning waits the instruction planned next time.
Comprehensive Decision Algorithm is used for starting, stopping and the change of integrated dispatch Global motion planning and sector planning.It is calculating
To after local motion path, path planning and decision on the spot further are carried out using Comprehensive Decision Algorithm.When system receives
After Global localization information and target point, decision making algorithm scheduling starts to carry out Global motion planning, after the completion of Global motion planning, carries out part
It plans and the ECU unit for exporting control information to vehicle controls vehicle.Planning process is completed after vehicle arrives at the destination, simultaneously
In planning process, according to the information of external environment, whether comprehensive descision is from new Global motion planning or stopping brake etc..This implementation
In example, by controlling using Comprehensive Decision Algorithm for the traveling of automatic driving vehicle, judge whether it reaches global mesh
Punctuate judges whether local motion path is blocked in sector planning level if do not reached, if stopped, stops advising
It draws.In the present embodiment, realizes and is further planned using map vector and the obtained local motion path of grating map,
The path planning and avoidance purpose combined both to realize in global level and local level, is automatic driving vehicle
The accurate avoidance advanced provides accurate guarantee.
Embodiment 5:
With reference to Fig. 9, to better illustrate method provided in the application, one kind is provided in the present embodiment based on vector
The automatic driving vehicle paths planning method of figure and grating map, includes the following steps:
S1, which is realized, acquires global map by map sampling instrument, includes road information and environmental information.
It is oriented cum rights node topology that S2, which runs global map resolver parsing global map, and loads global map.
S3 resolves Global localization, determines coordinate transform of the vehicle in global map.
Global motion planning target point is arranged in S4.
S5 starts global path planning.Planning algorithm input is the global road network topology of previous step load, Global localization
Coordinate transform and global object point are cooked up the most short global path from the current pose of vehicle to target point and are exported.
S6 starts to update local grid map.The point cloud data acquired from onboard sensor obtains preliminary grating map, then
Final grating map is updated in conjunction with the range information and expansion parameters of vehicle and barrier.
S7 starts local paths planning.According to the global path of global path planning arrived, in conjunction with local positioning information and
Local grid map constructs multi-goal optimizing function, is converted to figure optimization node, uses figure Optimization Solution optimal partial path.
Obtained local path is converted to the control signal such as steering wheel, brake, gear and is handed down to vehicle ECU control list by S8
Member.
S9, which is returned, repeats S6, S7, S8, and decision-making module monitors planning process in real time, judges whether that arrival target point, path are
It is no to there is situations such as stopping completely, and whether decision stops or planning path again.
In addition, with reference to Figure 11-12, the present invention also provides a kind of automatic driving vehicle based on map vector and grating map
Path planning apparatus, comprising:
Global Algorithm module 10 for parsing global road-net node topology by global vector map, and combines global
Location algorithm cooks up the current location of automatic driving vehicle to the global shortest path of target point；
Information-mapping module 20 for acquiring environmental information in real time, and converts point cloud data for the environmental information, reflects
It penetrates as current local grid map；
Local algorithm module 30, for being based on the current local grid map, and tie according to the global shortest path
Local positioning information is closed, local motion path is calculated using sector planning algorithm, in order to according to the local motion road
Diameter controls the automatic driving vehicle and marches to the target point.
In another embodiment, it is advised based on above-mentioned based on the automatic driving vehicle path of map vector and grating map
Draw device, further includes: integrated decision-making module 40,
The function of the integrated decision-making module 40 includes:
According to the corresponding vehicle control instruction of the local motion coordinates measurement, and based on vehicle control instruction control
The automatic driving vehicle is mobile to global object point according to the global shortest path and the local motion path；
After the automatic driving vehicle is mobile, judge whether the automatic driving vehicle reaches the global object point；
If the automatic driving vehicle is not up to the global object point, judge whether that the local motion path is hindered
Gear；
If the local motion path is not blocked, " environmental information is acquired in real time, and the environment is believed described in return
Breath is converted into point cloud data, is mapped as current local grid map "；
If the local motion path is blocked, generates and stop path planning, and generate blocking prompt information.
In addition, the computer equipment includes memory and processor, institute the present invention also provides a kind of computer equipment
Memory is stated for storing the automatic driving vehicle path planning program based on map vector and grating map, the processor fortune
The row automatic driving vehicle path planning program based on map vector and grating map is so that the computer equipment executes
Automatic driving vehicle paths planning method as described above based on map vector and grating map.
In addition, being stored on the computer readable storage medium the present invention also provides a kind of computer readable storage medium
There is the automatic driving vehicle path planning program based on map vector and grating map, it is described to be based on map vector and grating map
Automatic driving vehicle path planning program realize when being executed by processor it is as described above based on map vector and grating map
Automatic driving vehicle paths planning method.
The serial number of the above embodiments of the invention is only for description, does not represent the advantages or disadvantages of the embodiments.
Through the above description of the embodiments, those skilled in the art can be understood that above-described embodiment side
Method can be realized by means of software and necessary general hardware platform, naturally it is also possible to by hardware, but in many cases
The former is more preferably embodiment.Based on this understanding, technical solution of the present invention substantially in other words does the prior art
The part contributed out can be embodied in the form of software products, which is stored in one as described above
In storage medium (such as ROM/RAM, magnetic disk, CD), including some instructions are used so that terminal device (it can be mobile phone,
Computer, server or network equipment etc.) execute method described in each embodiment of the present invention.The above is only of the invention
Preferred embodiment is not intended to limit the scope of the invention, all using made by description of the invention and accompanying drawing content
Equivalent structure or equivalent flow shift is applied directly or indirectly in other relevant technical fields, and is similarly included in this hair
In bright scope of patent protection.
Claims (10)
1. a kind of automatic driving vehicle paths planning method based on map vector and grating map characterized by comprising
By global vector map, the current location of automatic driving vehicle is cooked up to the global shortest path of target point；
Acquisition environmental information in real time, and point cloud data is converted by the environmental information, it is mapped as current local grid map；
According to the global shortest path, it is based on the current local grid map, and combine local positioning information, utilizes part
Local motion path is calculated in planning algorithm, in order to the automatic driving vehicle row according to the local motion path clustering
Proceed to the target point.
2. the automatic driving vehicle paths planning method based on map vector and grating map as described in claim 1, feature
It is, it is described " by global vector map, to cook up the current location of automatic driving vehicle to the global shortest path of target point
Diameter " includes:
By map sampling instrument, global vector map is obtained, and the global vector map is resolved into having for global path
To cum rights node topology figure；Wherein, the global vector map includes the road point diagram and point cloud data structure that coordinate point set is constituted
At voice data figure；
Current point cloud information is acquired by environment information acquisition device；According to Global localization algorithm, to the current point cloud information
It is matched with the point cloud data, and determines the automatic driving vehicle in the global vector map according to matching result
World coordinates information converting；
Receive the global object point that user is set based on the global vector map；
According to the oriented cum rights node topology figure, world coordinates information converting and global object point, calculate from described
Most short global path of the current location of automatic driving vehicle to the global object point.
3. the automatic driving vehicle paths planning method based on map vector and grating map as claimed in claim 2, feature
It is, it is described " by map sampling instrument, to obtain global vector map, and the global vector map is resolved into global road
The oriented cum rights node topology figure of diameter；Wherein, the global vector map includes the road point diagram and point cloud that coordinate point set is constituted
Data constitute voice data figure " include:
Collect the global vector map；
Global map resolver is run, the road point diagram constituted to the path coordinate point set in the global vector map solves
Analysis, resolves to road network node for the path coordinate point, is stored as oriented band based on corresponding adjacent chained list or adjacency matrix form
Weigh structure；And parse the road information comprising intersection, road width；
According to the road network node of oriented cum rights structure and the road information, obtaining the described of global path has
To cum rights node topology figure.
4. the automatic driving vehicle paths planning method based on map vector and grating map as claimed in claim 3, feature
It is, it is described " to acquire environmental information in real time, and convert point cloud data for the environmental information, be mapped as current local grid
Map " includes:
The current point cloud information collected to the environment information acquisition device is split and merges, and will divide and melt
The current point cloud information MAP after conjunction obtains preliminary grating map to two-dimensional grid map；
Based on the current point cloud information, the current local grid map is obtained according to the preliminary grating map.
5. the automatic driving vehicle paths planning method based on map vector and grating map as claimed in claim 4, feature
It is, it is described " being based on the current point cloud information, the current local grid map is obtained according to the preliminary grating map "
Include:
According to the range information of automatic driving vehicle and barrier described in the current point cloud acquisition of information；
Using grating map renovator, according to the range information, the preliminary grating map is updated based on expansion parameters, is obtained
The current local grid map.
6. the automatic driving vehicle paths planning method based on map vector and grating map as claimed in claim 5, feature
It is, it is described " to utilize grating map renovator, according to the range information, with updating the preliminary grid based on expansion parameters
Figure, obtains the current local grid map " include:
It is each grid point assignment in the preliminary grating map based on expansion parameters using grating map renovator, obtains every
The corresponding cost value of a grid point；Wherein, there is the probability of barrier using the cost value as this grid point；Also, it will more
The preliminary grating map of the probability with barrier comprising each grid point after new is as the current local grid
Map.
7. the automatic driving vehicle paths planning method based on map vector and grating map as described in claim 1, feature
It is, it is described " according to the global shortest path, to be based on the current local grid map, and combine local positioning information, benefit
Local motion path is calculated with sector planning algorithm, in order to the automatic Pilot according to the local motion path clustering
Vehicle marches to the target point " include:
According to the global shortest path, in conjunction with the local positioning information of the current location and the current local grid
Figure constructs multi-goal optimizing function；Wherein, the optimization item of the multi-goal optimizing function includes the environmental information；
The multi-goal optimizing function that item includes the environmental information will be optimized and be converted to figure optimization node, and according to the figure
The local motion path is calculated in optimization node.
8. the automatic driving vehicle paths planning method based on map vector and grating map as described in claim 1, feature
It is, it is described " according to the global shortest path, to be based on the current local grid map, and combine local positioning information, benefit
Local motion path is calculated with sector planning algorithm " after, further includes:
According to the corresponding vehicle control instruction of the local motion coordinates measurement, and based on described in vehicle control instruction control
Automatic driving vehicle is mobile to global object point according to the global shortest path and the local motion path；
After the automatic driving vehicle is mobile, judge whether the automatic driving vehicle reaches the global object point；
If the automatic driving vehicle is not up to the global object point, judge whether that the local motion path is blocked；
If the local motion path is not blocked, " environmental information is acquired in real time, and the environmental information is turned described in return
Point cloud data is turned to, current local grid map is mapped as "；
If the local motion path is blocked, generates and stop path planning, and generate blocking prompt information.
9. a kind of automatic driving vehicle path planning apparatus based on map vector and grating map characterized by comprising
Global Algorithm module for parsing global road-net node topology by global vector map, and combines Global localization to calculate
Method cooks up the current location of automatic driving vehicle to the global shortest path of target point；
Information-mapping module for acquiring environmental information in real time, and converts point cloud data for the environmental information, is mapped as working as
Preceding local grid map；
Local algorithm module, for being based on the current local grid map, and combine part according to the global shortest path
Local motion path is calculated using sector planning algorithm in location information, in order to according to the local motion path clustering
The automatic driving vehicle marches to the target point.
10. a kind of computer equipment, which is characterized in that the computer equipment includes memory and processor, the storage
Device is for store the automatic driving vehicle path planning program based on map vector and grating map, described in the processor is run
Automatic driving vehicle path planning program based on map vector and grating map is so that the computer equipment executes such as right
It is required that the automatic driving vehicle paths planning method described in any one of 1-8 based on map vector and grating map.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910045498.6A CN109557928A (en) | 2019-01-17 | 2019-01-17 | Automatic driving vehicle paths planning method based on map vector and grating map |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910045498.6A CN109557928A (en) | 2019-01-17 | 2019-01-17 | Automatic driving vehicle paths planning method based on map vector and grating map |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109557928A true CN109557928A (en) | 2019-04-02 |
Family
ID=65873098
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910045498.6A Pending CN109557928A (en) | 2019-01-17 | 2019-01-17 | Automatic driving vehicle paths planning method based on map vector and grating map |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109557928A (en) |
Cited By (36)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110244734A (en) * | 2019-06-20 | 2019-09-17 | 中山大学 | A kind of automatic driving vehicle paths planning method based on depth convolutional neural networks |
| CN110262495A (en) * | 2019-06-26 | 2019-09-20 | 山东大学 | Mobile robot autonomous navigation and pinpoint control system and method can be achieved |
| CN110262518A (en) * | 2019-07-22 | 2019-09-20 | 上海交通大学 | Automobile navigation method, system and medium based on track topological map and avoidance |
| CN110333714A (en) * | 2019-04-09 | 2019-10-15 | 武汉理工大学 | A kind of pilotless automobile paths planning method and device |
| CN110361013A (en) * | 2019-07-22 | 2019-10-22 | 上海应用技术大学 | A kind of path planning system and method for auto model |
| CN110377029A (en) * | 2019-06-27 | 2019-10-25 | 北京汽车集团有限公司 | The control method and device of Vehicular automatic driving |
| CN110471422A (en) * | 2019-08-29 | 2019-11-19 | 南京理工大学 | The detection of obstacles and automatic obstacle avoiding method of intelligent wheel chair |
| CN110502004A (en) * | 2019-07-01 | 2019-11-26 | 江苏大学 | A kind of running region importance weight distribution modeling method towards the processing of intelligent vehicle laser radar data |
| CN110532846A (en) * | 2019-05-21 | 2019-12-03 | 华为技术有限公司 | Automatic lane-change method, apparatus and storage medium |
| CN111238519A (en) * | 2020-01-06 | 2020-06-05 | 华侨大学 | Multi-unmanned vehicle road finding method based on topological map and conflict elimination strategy |
| CN111338361A (en) * | 2020-05-22 | 2020-06-26 | 浙江远传信息技术股份有限公司 | Obstacle avoidance method, device, equipment and medium for low-speed unmanned vehicle |
| CN111367275A (en) * | 2020-02-18 | 2020-07-03 | 吉利汽车研究院（宁波）有限公司 | Intelligent driving control method, device and system and storage medium |
| CN111474935A (en) * | 2020-04-27 | 2020-07-31 | 华中科技大学无锡研究院 | Mobile robot path planning and positioning method, device and system |
| CN111566583A (en) * | 2019-10-04 | 2020-08-21 | 香港应用科技研究院有限公司 | System and method for adaptive path planning |
| CN112393719A (en) * | 2019-08-12 | 2021-02-23 | 科沃斯商用机器人有限公司 | Grid semantic map generation method and device and storage equipment |
| CN112406859A (en) * | 2019-08-23 | 2021-02-26 | 斯堪尼亚商用车有限公司 | Method and control device for vehicle motion planning and control algorithm |
| CN112444263A (en) * | 2020-09-22 | 2021-03-05 | 重庆智行者信息科技有限公司 | Global path planning method and device |
| CN112487016A (en) * | 2020-11-30 | 2021-03-12 | 上海汽车集团股份有限公司 | Method and device for planning local path of unmanned vehicle |
| WO2021062891A1 (en) * | 2019-10-04 | 2021-04-08 | Hong Kong Applied Science and Technology Research Institute Company Limited | Systems and methods for adaptive path planning |
| CN112783144A (en) * | 2019-10-22 | 2021-05-11 | 舜宇光学（浙江）研究院有限公司 | Path generation method, path planning method, system and equipment |
| CN112799404A (en) * | 2021-01-05 | 2021-05-14 | 佛山科学技术学院 | Global path planning method and device for AGV and computer readable storage medium |
| CN113177427A (en) * | 2020-01-23 | 2021-07-27 | 宝马股份公司 | Road prediction method, autonomous driving method, vehicle and equipment |
| CN113607171A (en) * | 2021-08-04 | 2021-11-05 | 清华大学建筑设计研究院有限公司 | Evacuation path planning method, evacuation path planning device, evacuation path planning equipment and storage medium |
| CN113759938A (en) * | 2021-11-10 | 2021-12-07 | 北京理工大学 | Unmanned vehicle path planning quality evaluation method and system |
| CN113962639A (en) * | 2021-12-23 | 2022-01-21 | 湖北普罗格科技股份有限公司 | Distribution path planning method and system based on global map |
| CN114035576A (en) * | 2021-11-09 | 2022-02-11 | 北京赛目科技有限公司 | Method and device for determining driving path |
| CN114115283A (en) * | 2021-12-02 | 2022-03-01 | 深圳市证通电子股份有限公司 | Robot path planning method and system based on improved opposite direction parallel algorithm |
| CN114326744A (en) * | 2021-12-31 | 2022-04-12 | 安徽海博智能科技有限责任公司 | Mine truck path planning method based on global map updating |
| CN114460939A (en) * | 2022-01-22 | 2022-05-10 | 贺晓转 | Intelligent walking robot autonomous navigation improvement method under complex environment |
| CN114838723A (en) * | 2020-03-02 | 2022-08-02 | 阿波罗智能技术(北京)有限公司 | Method, apparatus, device and medium for detecting environmental changes |
| CN114911244A (en) * | 2021-06-17 | 2022-08-16 | 北京博创联动科技有限公司 | Ridge obstacle avoidance control method and device and agricultural automatic driving equipment |
| CN115973197A (en) * | 2023-03-21 | 2023-04-18 | 宁波均胜智能汽车技术研究院有限公司 | Lane planning method and device, electronic equipment and readable storage medium |
| CN116337103A (en) * | 2023-05-17 | 2023-06-27 | 中国地质大学（武汉） | Hierarchical ubiquitous navigation method and device based on region classification and computer equipment |
| CN117407552A (en) * | 2023-12-15 | 2024-01-16 | 南京气象科技创新研究院 | Information expression method of grid information accurate assignment vector line |
| CN117889866A (en) * | 2024-03-18 | 2024-04-16 | 深圳竹芒科技有限公司 | Navigation path planning method, device and storage medium |
| CN114911244B (en) * | 2021-06-17 | 2024-07-09 | 北京博创联动科技有限公司 | Ridge obstacle avoidance control method and device and agricultural automatic driving equipment |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101620803A (en) * | 2009-08-11 | 2010-01-06 | 北京四维图新科技股份有限公司 | Method and device for recording traffic restricted information on electronic map |
| CN103278170A (en) * | 2013-05-16 | 2013-09-04 | 东南大学 | Mobile robot cascading map building method based on remarkable scenic spot detection |
| US20170219353A1 (en) * | 2014-09-30 | 2017-08-03 | Nec Europe Ltd. | Method and system for determining a path of an object for moving from a starting state to an end state set avoiding one or more obstacles |
| CN107544501A (en) * | 2017-09-22 | 2018-01-05 | 广东科学技术职业学院 | A kind of intelligent robot wisdom traveling control system and its method |
| CN107703945A (en) * | 2017-10-30 | 2018-02-16 | 洛阳中科龙网创新科技有限公司 | A kind of intelligent farm machinery paths planning method of multiple targets fusion |
| CN108036794A (en) * | 2017-11-24 | 2018-05-15 | 华域汽车系统股份有限公司 | A kind of high accuracy map generation system and generation method |
-
2019
- 2019-01-17 CN CN201910045498.6A patent/CN109557928A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101620803A (en) * | 2009-08-11 | 2010-01-06 | 北京四维图新科技股份有限公司 | Method and device for recording traffic restricted information on electronic map |
| CN103278170A (en) * | 2013-05-16 | 2013-09-04 | 东南大学 | Mobile robot cascading map building method based on remarkable scenic spot detection |
| US20170219353A1 (en) * | 2014-09-30 | 2017-08-03 | Nec Europe Ltd. | Method and system for determining a path of an object for moving from a starting state to an end state set avoiding one or more obstacles |
| CN107544501A (en) * | 2017-09-22 | 2018-01-05 | 广东科学技术职业学院 | A kind of intelligent robot wisdom traveling control system and its method |
| CN107703945A (en) * | 2017-10-30 | 2018-02-16 | 洛阳中科龙网创新科技有限公司 | A kind of intelligent farm machinery paths planning method of multiple targets fusion |
| CN108036794A (en) * | 2017-11-24 | 2018-05-15 | 华域汽车系统股份有限公司 | A kind of high accuracy map generation system and generation method |
Non-Patent Citations (1)
| Title |
|---|
| 郑宏 等: ""基于地图的移动机器人自定位与导航系统"", 《机器人》 * |
Cited By (51)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110333714B (en) * | 2019-04-09 | 2022-06-10 | 武汉理工大学 | Unmanned vehicle path planning method and device |
| CN110333714A (en) * | 2019-04-09 | 2019-10-15 | 武汉理工大学 | A kind of pilotless automobile paths planning method and device |
| CN110532846B (en) * | 2019-05-21 | 2022-09-16 | 华为技术有限公司 | Automatic channel changing method, device and storage medium |
| CN110532846A (en) * | 2019-05-21 | 2019-12-03 | 华为技术有限公司 | Automatic lane-change method, apparatus and storage medium |
| CN110244734A (en) * | 2019-06-20 | 2019-09-17 | 中山大学 | A kind of automatic driving vehicle paths planning method based on depth convolutional neural networks |
| CN110262495A (en) * | 2019-06-26 | 2019-09-20 | 山东大学 | Mobile robot autonomous navigation and pinpoint control system and method can be achieved |
| CN110377029A (en) * | 2019-06-27 | 2019-10-25 | 北京汽车集团有限公司 | The control method and device of Vehicular automatic driving |
| CN110502004A (en) * | 2019-07-01 | 2019-11-26 | 江苏大学 | A kind of running region importance weight distribution modeling method towards the processing of intelligent vehicle laser radar data |
| CN110361013A (en) * | 2019-07-22 | 2019-10-22 | 上海应用技术大学 | A kind of path planning system and method for auto model |
| CN110262518A (en) * | 2019-07-22 | 2019-09-20 | 上海交通大学 | Automobile navigation method, system and medium based on track topological map and avoidance |
| CN110361013B (en) * | 2019-07-22 | 2023-05-26 | 上海应用技术大学 | Path planning system and method for vehicle model |
| CN112393719A (en) * | 2019-08-12 | 2021-02-23 | 科沃斯商用机器人有限公司 | Grid semantic map generation method and device and storage equipment |
| CN112406859A (en) * | 2019-08-23 | 2021-02-26 | 斯堪尼亚商用车有限公司 | Method and control device for vehicle motion planning and control algorithm |
| CN110471422A (en) * | 2019-08-29 | 2019-11-19 | 南京理工大学 | The detection of obstacles and automatic obstacle avoiding method of intelligent wheel chair |
| WO2021062891A1 (en) * | 2019-10-04 | 2021-04-08 | Hong Kong Applied Science and Technology Research Institute Company Limited | Systems and methods for adaptive path planning |
| CN111566583A (en) * | 2019-10-04 | 2020-08-21 | 香港应用科技研究院有限公司 | System and method for adaptive path planning |
| CN112783144B (en) * | 2019-10-22 | 2023-09-29 | 舜宇光学（浙江）研究院有限公司 | Path generation method, path planning method, system and equipment thereof |
| CN112783144A (en) * | 2019-10-22 | 2021-05-11 | 舜宇光学（浙江）研究院有限公司 | Path generation method, path planning method, system and equipment |
| CN111238519B (en) * | 2020-01-06 | 2022-05-03 | 华侨大学 | Multi-unmanned vehicle road finding method based on topological map and conflict elimination strategy |
| CN111238519A (en) * | 2020-01-06 | 2020-06-05 | 华侨大学 | Multi-unmanned vehicle road finding method based on topological map and conflict elimination strategy |
| CN113177427A (en) * | 2020-01-23 | 2021-07-27 | 宝马股份公司 | Road prediction method, autonomous driving method, vehicle and equipment |
| CN111367275A (en) * | 2020-02-18 | 2020-07-03 | 吉利汽车研究院（宁波）有限公司 | Intelligent driving control method, device and system and storage medium |
| CN114838723A (en) * | 2020-03-02 | 2022-08-02 | 阿波罗智能技术(北京)有限公司 | Method, apparatus, device and medium for detecting environmental changes |
| CN111474935A (en) * | 2020-04-27 | 2020-07-31 | 华中科技大学无锡研究院 | Mobile robot path planning and positioning method, device and system |
| CN111338361A (en) * | 2020-05-22 | 2020-06-26 | 浙江远传信息技术股份有限公司 | Obstacle avoidance method, device, equipment and medium for low-speed unmanned vehicle |
| CN112444263B (en) * | 2020-09-22 | 2023-05-23 | 北京智行者科技股份有限公司 | Global path planning method and device |
| CN112444263A (en) * | 2020-09-22 | 2021-03-05 | 重庆智行者信息科技有限公司 | Global path planning method and device |
| CN112487016B (en) * | 2020-11-30 | 2023-10-03 | 上海汽车集团股份有限公司 | Unmanned vehicle local path planning method and device |
| CN112487016A (en) * | 2020-11-30 | 2021-03-12 | 上海汽车集团股份有限公司 | Method and device for planning local path of unmanned vehicle |
| CN112799404A (en) * | 2021-01-05 | 2021-05-14 | 佛山科学技术学院 | Global path planning method and device for AGV and computer readable storage medium |
| CN112799404B (en) * | 2021-01-05 | 2024-01-16 | 佛山科学技术学院 | Global path planning method and device of AGV and computer readable storage medium |
| CN114911244A (en) * | 2021-06-17 | 2022-08-16 | 北京博创联动科技有限公司 | Ridge obstacle avoidance control method and device and agricultural automatic driving equipment |
| CN114911244B (en) * | 2021-06-17 | 2024-07-09 | 北京博创联动科技有限公司 | Ridge obstacle avoidance control method and device and agricultural automatic driving equipment |
| CN113607171A (en) * | 2021-08-04 | 2021-11-05 | 清华大学建筑设计研究院有限公司 | Evacuation path planning method, evacuation path planning device, evacuation path planning equipment and storage medium |
| CN113607171B (en) * | 2021-08-04 | 2023-05-26 | 清华大学建筑设计研究院有限公司 | Evacuation path planning method, device, equipment and storage medium |
| CN114035576B (en) * | 2021-11-09 | 2023-09-08 | 北京赛目科技股份有限公司 | Driving path determining method and device |
| CN114035576A (en) * | 2021-11-09 | 2022-02-11 | 北京赛目科技有限公司 | Method and device for determining driving path |
| CN113759938A (en) * | 2021-11-10 | 2021-12-07 | 北京理工大学 | Unmanned vehicle path planning quality evaluation method and system |
| CN114115283A (en) * | 2021-12-02 | 2022-03-01 | 深圳市证通电子股份有限公司 | Robot path planning method and system based on improved opposite direction parallel algorithm |
| CN114115283B (en) * | 2021-12-02 | 2023-09-19 | 深圳市证通电子股份有限公司 | Robot path planning method and system based on improved opposite parallel algorithm |
| CN113962639A (en) * | 2021-12-23 | 2022-01-21 | 湖北普罗格科技股份有限公司 | Distribution path planning method and system based on global map |
| CN114326744A (en) * | 2021-12-31 | 2022-04-12 | 安徽海博智能科技有限责任公司 | Mine truck path planning method based on global map updating |
| CN114460939A (en) * | 2022-01-22 | 2022-05-10 | 贺晓转 | Intelligent walking robot autonomous navigation improvement method under complex environment |
| CN115973197B (en) * | 2023-03-21 | 2023-08-11 | 宁波均胜智能汽车技术研究院有限公司 | Lane planning method and device, electronic equipment and readable storage medium |
| CN115973197A (en) * | 2023-03-21 | 2023-04-18 | 宁波均胜智能汽车技术研究院有限公司 | Lane planning method and device, electronic equipment and readable storage medium |
| CN116337103B (en) * | 2023-05-17 | 2023-08-29 | 中国地质大学（武汉） | Hierarchical ubiquitous navigation method and device based on region classification and computer equipment |
| CN116337103A (en) * | 2023-05-17 | 2023-06-27 | 中国地质大学（武汉） | Hierarchical ubiquitous navigation method and device based on region classification and computer equipment |
| CN117407552A (en) * | 2023-12-15 | 2024-01-16 | 南京气象科技创新研究院 | Information expression method of grid information accurate assignment vector line |
| CN117407552B (en) * | 2023-12-15 | 2024-02-09 | 南京气象科技创新研究院 | Information expression method of grid information accurate assignment vector line |
| CN117889866A (en) * | 2024-03-18 | 2024-04-16 | 深圳竹芒科技有限公司 | Navigation path planning method, device and storage medium |
| CN117889866B (en) * | 2024-03-18 | 2024-06-11 | 深圳竹芒科技有限公司 | Navigation path planning method, device and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109557928A (en) | Automatic driving vehicle paths planning method based on map vector and grating map | |
| US11644319B2 (en) | Destination changes in autonomous vehicles | |
| CN111656295B (en) | Object interaction prediction system and method for autonomous vehicle | |
| CN113748314B (en) | Interactive three-dimensional point cloud matching | |
| CN109425359A (en) | For generating the method and system of real-time map information | |
| US11269334B2 (en) | Systems and methods for automated testing of autonomous vehicles | |
| US20210080955A1 (en) | Systems and Methods for Vehicle Motion Planning Based on Uncertainty | |
| US20210278539A1 (en) | Systems and Methods for Object Detection and Motion Prediction by Fusing Multiple Sensor Sweeps into a Range View Representation | |
| CN109283924A (en) | Classification method and system | |
| US11694557B2 (en) | Integrating air and ground data collection for improved drone operation | |
| US11507090B2 (en) | Systems and methods for vehicle motion control with interactive object annotation | |
| US10915112B2 (en) | Autonomous vehicle system for blending sensor data | |
| US20210278523A1 (en) | Systems and Methods for Integrating Radar Data for Improved Object Detection in Autonomous Vehicles | |
| CN110470311A (en) | A kind of ground drawing generating method, device and computer storage medium | |
| US11643105B2 (en) | Systems and methods for generating simulation scenario definitions for an autonomous vehicle system | |
| CN113479195A (en) | Method for automatic valet parking and system for carrying out said method | |
| US11981338B2 (en) | Systems and methods for generation and utilization of vehicle testing knowledge structures for autonomous vehicle simulation | |
| US20220032961A1 (en) | Systems and Methods for Autonomous Vehicle Motion Control and Motion Path Adjustments | |
| EP4160146A1 (en) | Quadtree based data structure for storing information relating to an environment of an autonomous vehicle and methods of use thereof | |
| CN114577233B (en) | Vehicle navigation method and device, computer equipment and storage medium | |
| CN116420096A (en) | Method and system for marking LIDAR point cloud data | |
| CN116724214A (en) | Method and system for generating a lane-level map of a region of interest for navigation of an autonomous vehicle | |
| CN115655288A (en) | Intelligent laser positioning method and device, electronic equipment and storage medium | |
| CN114693727A (en) | Information processing method and device, and information processing system | |
| WO2022264962A1 (en) | Behavior prediction system, behavior prediction device, behavior prediction method, and behavior prediction program |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20220328 Address after: 430090 No. b1336, chuanggu startup area, taizihu cultural Digital Creative Industry Park, No. 18, Shenlong Avenue, Wuhan Economic and Technological Development Zone, Hubei Province Applicant after: Yikatong (Hubei) Technology Co.,Ltd. Address before: 430000 no.c101, chuanggu start up area, taizihu cultural Digital Industrial Park, No.18 Shenlong Avenue, Wuhan Economic and Technological Development Zone, Hubei Province Applicant before: HUBEI ECARX TECHNOLOGY Co.,Ltd. |
|
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190402 |