CN105318888B - Automatic driving vehicle paths planning method based on unmanned plane perception - Google Patents

Automatic driving vehicle paths planning method based on unmanned plane perception Download PDF

Info

Publication number
CN105318888B
CN105318888B CN201510890380.5A CN201510890380A CN105318888B CN 105318888 B CN105318888 B CN 105318888B CN 201510890380 A CN201510890380 A CN 201510890380A CN 105318888 B CN105318888 B CN 105318888B
Authority
CN
China
Prior art keywords
vehicle
road
unmanned
image
unmanned vehicle
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN201510890380.5A
Other languages
Chinese (zh)
Other versions
CN105318888A (en
Inventor
王云鹏
余贵珍
李欣旭
陈鹏
徐永正
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beihang University
Original Assignee
Beihang University
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Beihang University filed Critical Beihang University
Priority to CN201510890380.5A priority Critical patent/CN105318888B/en
Publication of CN105318888A publication Critical patent/CN105318888A/en
Application granted granted Critical
Publication of CN105318888B publication Critical patent/CN105318888B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
    • G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
    • G01C21/34—Route searching; Route guidance
    • G01C21/3446—Details of route searching algorithms, e.g. Dijkstra, A*, arc-flags, using precalculated routes

Landscapes

  • Engineering & Computer Science (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Remote Sensing (AREA)
  • Automation & Control Theory (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
  • Traffic Control Systems (AREA)

Abstract

The present invention is a kind of automatic driving vehicle paths planning method perceived based on unmanned plane, realizes quickly planning vehicle running path.This method is sent to earth station based on unmanned vehicle sensory perceptual system using the road video image of unmanned vehicle photographic subjects vehicle periphery；Ground station reception video image is simultaneously handled, and vehicle and road information are obtained, and carries out path planning according to vehicle location, and route is passed to automatic driving vehicle；The computer module of earth station calculates flight control signal control unmanned vehicle following vehicle and advances, and corrects path in real time.The present invention is based on unmanned vehicle platforms, stable working state, vehicle periphery road environment is shot from high-altitude, wide coverage, observed Traffic Information clear and definite can quickly obtain target vehicle surrounding road distribution situation and traffic, can obtain rational path planning, route is more accurate, and road condition analyzing is more promptly and accurately.

Description

Automatic driving vehicle paths planning method based on unmanned plane perception
Technical field
The present invention relates to image processing fields, and in particular to a kind of automatic driving vehicle path rule based on unmanned plane perception The technology of drawing can perceive vehicle periphery road environment by unmanned vehicle, and quickly plan the vehicle running path.
Background technology
Intelligent vehicle rises with traffic technique, and automatic driving vehicle technology is developed as one of its key technology.Nobody Driving vehicle travel process needs multi-section point to cooperate, and ensures to monitor a large amount of internal data, the perception of outer vicinity obstacle And travel route anticipation and planning etc. can just be such that it exercises safely.
The travel route anticipation of existing automatic driving vehicle is learnt with planning technology part by road driving, partial dependency In GPS navigation.Road driving is learnt, after repeatedly carrying out travel route training, the achievement of automatic driving vehicle machine learning Significantly, but automatic driving vehicle can only cope with uniline later, be of limited application.GPS navigation technology maturation, using wide It is general, it is easy to use, it after being combined with intelligent transportation system, can navigate in conjunction with condition of road surface, formulate rational routes.But GPS positioning requires signal, and in urban environment, signal is interfered, and easy tos produce the inaccurate situation of positioning, influences to travel Safety.Meanwhile as various constructing items are implemented, electronic urban map update is slow, causes map and city actual conditions not Meet, the same safety for threatening automatic driving vehicle is exercised.In addition, the current application range of intelligent transportation system is smaller, reaction is handed over There is delay in logical situation, can not time update carry out path, cause vehicle to be stagnated, auxiliary programming effect is limited.
Invention content
The present invention is directed to the deficiency in existing vehicle path planning technology, provide it is a kind of perceived based on unmanned plane nobody Drive vehicle path planning method.This method is carried out according to the road obtained by unmanned vehicle High Altitude Platform and traffic information The planning of target vehicle driving path.
Automatic driving vehicle paths planning method provided by the invention based on unmanned plane perception, is based on unmanned vehicle sense Know system.
The unmanned vehicle sensory perceptual system includes unmanned vehicle and earth station.The unmanned vehicle, which passes through, is It stays rope to be powered by target vehicle, photographic device, the first wireless communication module and the first image transmitting mould is carried on unmanned vehicle Block；It is shot by photographic device road pavement, obtains the video image of road；By the first image transmission module by shooting Transmission of video images is to earth station；Flight control signal is received by the first wireless communication module.The earth station is placed on On target vehicle, and powered by target vehicle；Earth station is equipped with the second wireless communication module, the second image transmission module and calculating Machine module；Flight control signal is transmitted to unmanned vehicle by the second wireless communication module；Pass through the second image transmission module It receives unmanned vehicle and transmits video image；By computer module, the video image of reception is handled, obtains road letter It ceases and carries out path planning, and calculate flight control parameter to unmanned vehicle, while passing through data line and automatic driving vehicle Carry out information exchange.
The automatic driving vehicle paths planning method realizes that steps are as follows：
Step (1) starts unmanned vehicle sensory perceptual system, and unmanned vehicle takes off, and establishes and communicates with earth station after hovering, The road video image of photographic subjects vehicle periphery, is sent to earth station；
Step (2) ground station reception video image is simultaneously handled, and vehicle and road information are obtained, according to vehicle location into Row path planning, and route is passed into automatic driving vehicle.The vehicle and road information include target vehicle and road Position relationship, the distance between vehicle and road area.
Step (3) computer module controls unmanned vehicle following vehicle and advances, and corrects path in real time.
Further, the course of work of the step (2) includes：
When step 2.1, unmanned vehicle shooting, the camera lens for increasing steady cradle head control photographic device is shot perpendicular to the ground, Image is downward projection, and the actual range between object is obtained by transformation of scale.
Step 2.2, earth station computer module to video and graphic carry out image procossing, draw road area, retrieve vehicle , the ratio of the vehicle gross area and path area on each road is obtained, and path planning is carried out to target vehicle.
Further, in the step (3), computer module is using the picture center of video image as unmanned vehicle institute Locate position, the target vehicle of searching special color label roof in the regional extent of setting, after finding target vehicle position, Calculate actual shifts distance and the direction between unmanned vehicle and vehicle.Earth station is only to the pitching of unmanned flight's machine and yaw two A parameter is controlled, and flight control parameter is calculated using dual-mode parameter Self-tuning fuzzy PID, after obtaining flight control parameter It is sent to unmanned vehicle.In step (3), after unmanned vehicle loses target vehicle, is provided by mooring line and nobody is flown The guiding of row device.
Technical solution of the present invention has following innovative point and advantage：
(1) the present invention is based on unmanned vehicle platform, stable working state shoots vehicle periphery road environment from high-altitude, Wide coverage, under the position observed by Traffic Information clear and definite, by can quickly be obtained after image procossing Target vehicle surrounding road distribution situation and traffic, the information in real time, accurately, rational road can be obtained according to the data Diameter is planned.Route guidance is carried out compared to traditional GPS based on unmanned vehicle aware platform, route is more accurate, compared to The road traffic condition that intelligent traffic network provides, road condition analyzing are more timely.
(2) unmanned vehicle of the present invention follows automatic driving vehicle to move, and can in real time collect with vehicle Centered on around road distribution and traffic, realize in real time correct automatic driving vehicle driving path, it is ensured that can obtain Obtain best route.Since the speed of unmanned vehicle is limited, while for security consideration, automatic driving vehicle travel speed needs It controls in 40km/h or less.
(3) the unmanned vehicle system that the present invention uses is powered by car-mounted device.Earth station directly by charging interface with Information interactive interface is integrated, simplifies earth station's composed structure and is operated with system building, while maintaining the stable operation of earth station. The perception of road and traffic information then needs unmanned vehicle empty shooting stagnant for a long time, due to existing unmanned vehicle battery durable Limited time maintains its flight using mooring line power supply.In addition, mooring line has certain guidance capability, it can be to a certain degree Upper prevention unmanned vehicle scatters with vehicle.
(4) in the present invention, unmanned vehicle is for acquiring road information, and data processing work is taken by earth station.It reduces Unmanned vehicle treatment progress, so that unmanned vehicle is possessed more resources optimize flight control process with promoted flight precision with Flight safety.The computer module computing capability of earth station is higher, and stability is high, is responsible for receiving image, processing image, thus into Row path planning is calculated with unmanned aerial vehicle (UAV) control parameter, and completes information exchange.Two parts device cooperates with mutually, can quick, stream Freely realize the vehicle path planning of unmanned vehicle sensory perceptual system.
Description of the drawings
Fig. 1 is the unmanned vehicle sensory perceptual system composition schematic diagram that the present invention uses；
Fig. 2 is the flow diagram of the automatic driving vehicle paths planning method of the present invention；
Fig. 3 is the road and vehicle identification process schematic of the present invention；
Fig. 4 is the schematic diagram for carrying out Global motion planning in the embodiment of the present invention to path；
Fig. 5 is the schematic diagram for carrying out sector planning in the embodiment of the present invention to vehicle periphery driving path.
In attached drawing：1, the target vehicle of path planning is needed, 2, earth station, 3, mooring line, 4, unmanned vehicle.
Specific implementation mode
The invention will be further described below in conjunction with the accompanying drawings：
As shown in Figure 1, the unmanned vehicle sensory perceptual system that the present invention uses comprising：Need the target carriage of path planning 1, earth station 2, mooring line 3 and unmanned vehicle 4.The earth station 2 is placed on target vehicle 1, is supplied by vehicle 1 Electricity, unmanned vehicle 4 are powered by mooring line 3 by vehicle 1.
Unmanned vehicle of the embodiment of the present invention 4 is quadrotor unmanned vehicle.Equipped with (the whole world GPS on unmanned vehicle 4 Positioning system) module, AHRS (attitude heading reference system) modules and flight control assemblies, to ensure that stablizing for unmanned vehicle is safe Flight.The steady holder of increasing is carried on unmanned vehicle 4 and photographic device is obtained with realizing the steady shot of unmanned vehicle road pavement Obtain the video image of road and traffic.The first wireless communication module and the first image transmission module are carried on unmanned vehicle 4.It is logical It crosses the first wireless communication module and receives flight control signal.By the first image transmission module by the transmission of video images of shooting extremely Earth station 2.
Earth station 2 is equipped with the second wireless communication module, the second image transmission module and computer module.It is wireless by second Communication module transmission flight control signal is to unmanned vehicle 4.Unmanned vehicle 4 is received by the second image transmission module to transmit Video image.By computer module, the video image of reception is handled, obtain road information and carries out path planning, And information exchange is carried out by data line and automatic driving vehicle 1.Earth station 2 can be by charging interface and information interactive interface collection At to simplify ground station structure, while solving powerup issue.
As shown in Fig. 2, the present invention is based on the work flow diagram of the automatic driving vehicle paths planning method of unmanned plane perception, Its step are as follows：
Step (1) present invention is using the road video image around 4 photographic subjects vehicle 1 of unmanned vehicle, and by video Image is sent to earth station 2, to carry out the collection of 1 surrounding road of target vehicle distribution and road vehicle fleet size information.
When system brings into operation, unmanned vehicle 4, which takes off, to be risen 100-200 meters and hovers, while being established and being led to vehicle 1 Letter starts the video image of the road and traffic information around photographic subjects vehicle 1, is sent to earth station 2.
When 4 flying height of unmanned vehicle is 120-150 meters, angle lens are 60 ° -80 °.When positioned at the height, nothing The radius of view of people's aircraft 4 is at 70-125 meters, including a wide range of object including target vehicle 1, it is ensured that can obtain Enough road informations carry out path planning.
4 photographic device monocular camera lens mounted of unmanned vehicle is demarcated, to correct in its shooting process The radian that straight line generates, goes back original path and vehicle deformation, reduces interference and the false drop rate of environment sensing.
Step (2) earth station 2 receives video image and is handled, and vehicle and road information is obtained, according to vehicle location Path planning is carried out, then route is passed to automatic driving vehicle by earth station 2 by data line.Vehicle includes with road information The length and width of road, the distance between target vehicle and other vehicles etc..
The video that unmanned vehicle 4 is shot passes video image back earth station 2 by the first image transmission module.Ground The computer module at face station 2 will carry out image procossing immediately, to obtain vehicle, road information, and carry out path planning.Step (2) the course of work is as follows：
When step 2.1, shooting, the camera lens for increasing steady cradle head control photographic device is shot perpendicular to the ground, and image is to overlook Projection, wherein the range information of object can be directly calculated by ratio, avoid perspective operation and coordinate transform.
By inputting target vehicle length a, width b, according to ratio k：
S=kS
Wherein, A, B are be located at target vehicle 1 in image cornerwise 2 points, and coordinate is respectively (xA,yA)、(xB,yB)； S is the distance of two articles in image, and s is the distance in two articles reality.
Range information in image, including link length, width etc. can be obtained.
Step 2.2, earth station 2 computer module to collected road video image carry out image procossing, pass through figure As the methods of registration, color threshold segmentation, morphological operation and grader identification acquisition vehicle and road information, to carry out Path planning.Detailed process is as follows：
1., by image registration increase steady, the movement that the characteristic point in image obtains image background is tracked, to pass through Affine transformation method eliminates shake.
2., as shown in figure 3, by the image of shooting from RGB (red, green, blue) color space conversions to HSV (tone, saturation Degree, brightness) color space.Then region of the intensity value in 0%-5% in image is chosen its brightness adjustment is (black at 0 Color), the brightness in remaining region is set as 255 (whites), to obtain road bianry image.
Morphology opening and closing operation is carried out to bianry image, wherein use circle for structural element, vehicle on a diameter of road The 1/2 of width, to eliminate empty, smooth road boundary caused by vehicle on road.
Then edge detection is carried out, since the gray value of each pixel in bianry image is 0 or 255, wherein gray scale is prominent Then into road boundary at change.But the edge by being obtained after morphological operation may be irregular curve, need to pass through Hough Edge line is drawn in transformation, to obtain the road area of rule, establishes two-dimentional road model.
Hough transformation process：For the several points A on road edge line a1(x1,y1,),A2(x2,y2,),…,An(xn, yn), approximation meets straight line：Xcos θ+Ysin θ=r, wherein θ, r is parameter.With point A1(x1,y1) for, by x1、y1As ginseng Number, then in r- θ parameter planes, can obtain curve：R=Xcos θ+Ysin θ.It is put down thus, it is possible to which point set A is converted into r- θ If the stem curve on face, these curves cross same point (θ, r).After Hough transformation, the peak point in r- θ planes is counted, is obtained The point coordinates, the i.e. parameter θ of straight line, r are taken, to draw out straight line.
3., then, carry out vehicle detection by using based on Haar feature cascade classifiers, obtain in image in each vehicle The coordinate and vehicle length and width and size of heart point.When using detection of classifier, a certain oversize vehicle in figure, setting are found 1.2 times of a length of oversize vehicle length of search window, the width of search window is 1.2 times of the oversize vehicle width, and is protected It is constant to hold retrieval window size, to exclude to detect other non-vehicle objects, ensures accuracy of detection.After detection, calculate each The ratio of the vehicle gross area and path area on road, the ratio is by one of the foundation as path planning.
4., finally carry out path planning, it includes：Global motion planning and sector planning.
When Global motion planning, as shown in figure 4, computer module is according to the GPS information on unmanned vehicle 4, in current map Position centers area-of-interest, and the road model in the area obtaining above-mentioned steps carries out template matches, obtains mesh Mark position of the vehicle in electronic map.According to vehicle location and final position, in conjunction with C space arithmetics and dijkstra's algorithm, Carry out Global motion planning.Using C space arithmetics, in electronic map, by impassabitity regional expansion at polygon, by starting point, It is connected with straight line between terminal and all polygon vertexes, establishes routing information topological network.Then it is searched using dijkstra's algorithm Rope shortest path, the algorithm traverse all vertex successively, and with the weighted value w=k of vehicle fleet size in link length and road1d+ k2H is the weights on each vertex, carries out that optimal solution is calculated, and wherein d is two vertex spacing, and h is road vehicle area ratio, k1、k2Value is determined by place city, is preset empirical value.Global motion planning is on the hovering of unmanned vehicle 4 foundation and ground It stands after 2 communication, executes once, subsequently determine whether the driving trace of vehicle 1 whether on route, advised again if deviateing It draws.
When sector planning, when computer module image procossing, obtains the positional distance relationship of target vehicle 2 and other vehicles, It using Artificial Potential Field Method, limits range and is sailed on road (avoiding driving in the wrong direction) in present feasible, virtual front is field of force direction, other vehicles Be repulsion, establish gravitation field function carry out path finding.Other Velicle motion velocities are calculated as necessary by successive frame, and will It imports function and is calculated to carry out path finding.Sector planning provides a kind of driving trace reference, and practical decision is by vehicle 1 Electronic control unit combines each sensing data synthesis to provide.
Step (3) computer module control unmanned vehicle 4 follows target vehicle 1 to advance, for correcting path in real time.
Step (3) operation principle includes：
1, computer module obtains the position relationship of unmanned vehicle 4 and target vehicle 1 by image procossing, according to offset Distance and direction and PID control principle calculate the flight control parameter of unmanned vehicle 4 and are sent to unmanned vehicle 4, control 4 following vehicle of unmanned vehicle is advanced, for correcting path in real time.
2, for simplify control process, only to the pitching of the unmanned vehicle 4 in flight course and two parameters of yaw into Row control.Control calculates flight control parameter using dual-mode parameter Self-tuning fuzzy PID.
3, wherein, when the relationship of calculating position, using picture center as position residing for unmanned vehicle 4 in image processing process It sets, sets an area-of-interest range in picture immediate vicinity, searching marks the target vehicle of roof with special color.In root Distance in reality is calculated according to the position relationship of two articles in image.Then obtain actual shifts between unmanned vehicle and vehicle away from From with direction.
4, after unmanned vehicle loses target vehicle, mooring line can to a certain extent be provided to unmanned vehicle Guiding.

Claims (6)

1. a kind of automatic driving vehicle paths planning method based on unmanned plane perception, which is characterized in that this method is based on one kind Unmanned vehicle sensory perceptual system；The unmanned vehicle sensory perceptual system includes unmanned vehicle and earth station；
The unmanned vehicle is powered by mooring line by target vehicle, is carried on unmanned vehicle and is increased steady holder, camera shooting dress It sets, the first wireless communication module and the first image transmission module；It is shot by photographic device road pavement, obtains regarding for road Frequency image；By the first image transmission module by the transmission of video images of shooting to earth station；Pass through the first wireless communication module Receive flight control signal；
The earth station is placed on target vehicle, and is powered by target vehicle；Earth station equipped with the second wireless communication module, Second image transmission module and computer module；Flight control signal is transmitted to unmanned flight by the second wireless communication module Device；Unmanned vehicle, which is received, by the second image transmission module transmits video image；By computer module, to the video of reception Image is handled, and is obtained road information and is carried out path planning；
Steps are as follows for the realization of the automatic driving vehicle paths planning method：
Step 1, start unmanned vehicle sensory perceptual system, unmanned vehicle takes off, and establishes and communicates with earth station after hovering, shoots mesh The road video image for marking vehicle periphery, is sent to earth station；
Step 2, it ground station reception video image and is handled, obtains vehicle and road information, according to vehicle location into walking along the street Diameter is planned, and route is passed to automatic driving vehicle；The vehicle and the position that road information includes target vehicle and road Set the distance between relationship, vehicle and road area；
Step 2.1：When unmanned vehicle shoots video image, the camera lens for increasing steady cradle head control photographic device is clapped perpendicular to the ground It takes the photograph, obtained video image is downward projection, and the actual range between object is obtained by transformation of scale；
Step 2.2, earth station computer module to video and graphic carry out image procossing, draw road area, retrieve vehicle, obtain The ratio of the vehicle gross area and path area on to each road, and path planning is carried out to target vehicle；
Step 3, computer module control unmanned vehicle follows target vehicle to advance, and corrects path in real time.
2. the automatic driving vehicle paths planning method according to claim 1 based on unmanned plane perception, which is characterized in that In the step 1, unmanned vehicle takes off to hovering at 100-200 meters of vehicle up direction where earth station.
3. the automatic driving vehicle paths planning method according to claim 1 based on unmanned plane perception, which is characterized in that In the step 1, the monocular camera lens of the photographic device on unmanned vehicle is demarcated, to correct in its shooting process The radian that straight line generates.
4. the automatic driving vehicle paths planning method according to claim 1 based on unmanned plane perception, which is characterized in that In the step 2.2, graphics process is carried out, including：
1., by image registration increase steady, track the movement that the characteristic point in image obtains image background, pass through affine transformation Method eliminates shake；
2., the image of shooting is transformed into hsv color space from RGB color, then choose intensity value in image and exist By its brightness adjustment at 0, the brightness in remaining region is set as 255, obtains road bianry image in region in 0%-5%；
Morphology opening and closing operation is carried out to bianry image, wherein use circle for structural element, vehicle width on a diameter of road 1/2, eliminate cavity, smooth road boundary caused by vehicle on road；
Then edge detection and Hough transformation are carried out, edge line is drawn, the road area of rule is obtained, establishes road model；
3., using based on Haar feature cascade classifiers carry out vehicle detection, obtain image in each vehicle center point coordinate with And vehicle length and width and size；When using detection of classifier, a certain oversize vehicle in figure is found, the length of search window is set It it is 1.2 times of the oversize vehicle length, the width of search window is 1.2 times of the oversize vehicle width, and keeps retrieval window ruler It is very little constant；After vehicle detection, the ratio of the vehicle gross area and path area on each road is calculated；
4., carry out path planning, including：Global motion planning and sector planning；
When Global motion planning, according to the GPS information of unmanned vehicle, obtained road model is subjected to template matches, obtains mesh Position of the vehicle in electronic map is marked, according to vehicle location and final position, carries out Global motion planning；
When sector planning, according to the positional distance relationship of obtained target vehicle and other vehicles, using Artificial Potential Field Method, limit Determine range to sail on road in present feasible, virtual front is field of force direction, other vehicles are repulsion, establishes the progress of gravitation field function Path finding.
5. the automatic driving vehicle paths planning method according to claim 4 based on unmanned plane perception, which is characterized in that It is described 4. in when carrying out Global motion planning, in electronic map, by impassabitity regional expansion at polygon, by starting point, end It puts and is connected with straight line between all polygon vertexes, establish routing information topological network；Then dijkstra's algorithm is used to search for Weight w=the k on vertex is arranged in search in shortest path1d+k2H, wherein k1And k2For preset empirical value, d two Vertex spacing, h are road vehicle area ratio.
6. the automatic driving vehicle paths planning method according to claim 1 based on unmanned plane perception, which is characterized in that In the step 3, computer module is using the picture center of video image as unmanned vehicle present position, in the area of setting Searching marks the target vehicle of roof with special color within the scope of domain, after finding target vehicle position, calculate unmanned vehicle with Actual shifts distance between vehicle and direction；Only two parameters of the pitching of unmanned flight's machine and yaw are controlled, using double Mould parameter Self-tuning fuzzy PID calculates flight control parameter, and unmanned vehicle is sent to after obtaining flight control parameter；
After unmanned vehicle loses target vehicle, the guiding to unmanned vehicle is provided by mooring line.
CN201510890380.5A 2015-12-07 2015-12-07 Automatic driving vehicle paths planning method based on unmanned plane perception Active CN105318888B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201510890380.5A CN105318888B (en) 2015-12-07 2015-12-07 Automatic driving vehicle paths planning method based on unmanned plane perception

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201510890380.5A CN105318888B (en) 2015-12-07 2015-12-07 Automatic driving vehicle paths planning method based on unmanned plane perception

Publications (2)

Publication Number Publication Date
CN105318888A CN105318888A (en) 2016-02-10
CN105318888B true CN105318888B (en) 2018-08-14

Family

ID=55246786

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201510890380.5A Active CN105318888B (en) 2015-12-07 2015-12-07 Automatic driving vehicle paths planning method based on unmanned plane perception

Country Status (1)

Country Link
CN (1) CN105318888B (en)

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US11790664B2 (en) 2019-02-19 2023-10-17 Tesla, Inc. Estimating object properties using visual image data
US11797304B2 (en) 2018-02-01 2023-10-24 Tesla, Inc. Instruction set architecture for a vector computational unit
US11816585B2 (en) 2018-12-03 2023-11-14 Tesla, Inc. Machine learning models operating at different frequencies for autonomous vehicles
US11841434B2 (en) 2018-07-20 2023-12-12 Tesla, Inc. Annotation cross-labeling for autonomous control systems
US11893774B2 (en) 2018-10-11 2024-02-06 Tesla, Inc. Systems and methods for training machine models with augmented data
US11893393B2 (en) 2017-07-24 2024-02-06 Tesla, Inc. Computational array microprocessor system with hardware arbiter managing memory requests

Families Citing this family (82)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105702033A (en) * 2016-03-18 2016-06-22 哈尔滨理工大学 Air-land integrated car networking system and method for realizing navigation
JP7031581B2 (en) * 2016-06-02 2022-03-08 ソニーグループ株式会社 Information processing equipment and information processing method
CN106054922B (en) * 2016-06-22 2018-10-23 长安大学 A kind of unmanned plane-unmanned vehicle joint formation cooperative control method
CN105973230B (en) * 2016-06-30 2018-09-28 西安电子科技大学 A kind of double unmanned plane collaborative perceptions and planing method
CN106197464A (en) * 2016-07-04 2016-12-07 苏州光之翼智能科技有限公司 A kind of vehicle-mounted over the horizon navigation system based on unmanned plane and method
US11796673B2 (en) 2016-07-06 2023-10-24 Lawrence Livermore National Security, Llc Object sense and avoid system for autonomous vehicles
CN106020233B (en) * 2016-07-08 2023-11-28 聂浩然 Unmanned aerial vehicle plant protection operation system, unmanned aerial vehicle for plant protection operation and control method
CN106441333B (en) * 2016-09-30 2021-04-16 百度在线网络技术（北京）有限公司 Navigation method and device
CN106529466B (en) * 2016-11-03 2019-04-30 中国兵器工业计算机应用技术研究所 A kind of automatic driving vehicle paths planning method and system based on bionic eye
CN110132279B (en) * 2016-12-02 2021-07-27 百度在线网络技术（北京）有限公司 Testing method and device for local path planning
CN108225340A (en) * 2016-12-21 2018-06-29 致伸科技股份有限公司 Automatic DAS (Driver Assistant System) and its method
CN107871399B (en) * 2016-12-27 2020-11-24 珠海市杰理科技股份有限公司 Automatic vehicle driving system and method
CN106643664A (en) * 2016-12-28 2017-05-10 湖南省道通科技有限公司 Method and device for positioning unmanned aerial vehicle
CN110100152A (en) * 2016-12-28 2019-08-06 深圳市大疆创新科技有限公司 Flight path display methods, mobile platform, flight system, recording medium and program
CN106843279A (en) * 2017-01-17 2017-06-13 斑马信息科技有限公司 Unmanned plane Vehicular system and its management method
WO2018151712A1 (en) * 2017-02-15 2018-08-23 Ford Global Technologies, Llc Aerial vehicle-ground vehicle coordination
WO2018176000A1 (en) 2017-03-23 2018-09-27 DeepScale, Inc. Data synthesis for autonomous control systems
WO2018190834A1 (en) 2017-04-12 2018-10-18 Paglieroni David W Attract-repel path planner system for collision avoidance
US10317904B2 (en) * 2017-05-05 2019-06-11 Pinnacle Vista, LLC Underwater leading drone system
CN108931984A (en) * 2017-05-25 2018-12-04 深圳市天荧智能科技有限公司 Path planning method, control method, system, medium, control station and unmanned aerial vehicle
CN107368093A (en) * 2017-06-17 2017-11-21 广东容祺智能科技有限公司 One kind is tethered at unmanned plane synchronization system for tracking
CN107146447A (en) * 2017-07-16 2017-09-08 汤庆佳 A kind of Intelligentized vehicle management system and its method based on unmanned plane
CN107272739B (en) * 2017-07-24 2020-09-29 湘潭大学 Pesticide spraying system and method based on primary and secondary systems
US10671349B2 (en) 2017-07-24 2020-06-02 Tesla, Inc. Accelerated mathematical engine
US11409692B2 (en) 2017-07-24 2022-08-09 Tesla, Inc. Vector computational unit
US11157441B2 (en) 2017-07-24 2021-10-26 Tesla, Inc. Computational array microprocessor system using non-consecutive data formatting
WO2019023889A1 (en) * 2017-07-31 2019-02-07 深圳市大疆创新科技有限公司 Method and apparatus for planning path for movable object, and control device for movable object
CN107436610B (en) * 2017-07-31 2018-08-10 中南大学 A kind of vehicle and robot delivery navigation methods and systems of intelligence outdoor environment
CN107657623A (en) * 2017-08-28 2018-02-02 北京工业大学 A kind of river course line detecting system and method for unmanned plane
CN109426255A (en) * 2017-09-04 2019-03-05 中兴通讯股份有限公司 Automatic driving vehicle control method, device and storage medium based on unmanned plane
US10599138B2 (en) * 2017-09-08 2020-03-24 Aurora Flight Sciences Corporation Autonomous package delivery system
CN107839668A (en) * 2017-09-13 2018-03-27 潘金文 A kind of intelligent driving system for being used to prevent fatigue
CN109781124B (en) * 2017-11-14 2020-10-27 长城汽车股份有限公司 Unmanned aerial vehicle rescue method and device, unmanned aerial vehicle and vehicle
CN107908197A (en) * 2017-11-23 2018-04-13 深圳市智璟科技有限公司 The accurate landing system of unmanned plane and method based on infrared beacon and vision
CN108008738A (en) * 2017-12-27 2018-05-08 贵州大学 Target Tracking System under being cooperateed with based on unmanned plane with unmanned vehicle
US20190197890A1 (en) * 2017-12-27 2019-06-27 GM Global Technology Operations LLC Methods, systems, and drones for assisting communication between a road vehicle and other road users
CN108253957A (en) * 2017-12-29 2018-07-06 广州亿航智能技术有限公司 Route guidance method, unmanned plane, server and system based on unmanned plane
CN107957726A (en) * 2017-12-29 2018-04-24 南京工程学院 Unmanned vehicle navigation system
CN110388912B (en) * 2018-04-16 2021-06-08 杭州海康机器人技术有限公司 Method and device for planning flight path of flight equipment and storage medium
BR112020022476A2 (en) * 2018-05-10 2021-02-09 Beijing Xiaomi Mobile Software Co., Ltd. method for obtaining and sending automated air vehicle path information, device, device, and storage medium
CN110595495A (en) * 2018-06-13 2019-12-20 宝马股份公司 Method for automatically updating a vehicle route plan
US11215999B2 (en) 2018-06-20 2022-01-04 Tesla, Inc. Data pipeline and deep learning system for autonomous driving
US11636333B2 (en) 2018-07-26 2023-04-25 Tesla, Inc. Optimizing neural network structures for embedded systems
CN109213159A (en) * 2018-08-30 2019-01-15 上海海事大学 A method of marine Situation Awareness, which is carried out, with unmanned plane monitors ship path
CN109099925B (en) * 2018-08-31 2021-07-20 江苏大学 Unmanned agricultural machine navigation path planning and operation quality evaluation method and device
US11562231B2 (en) 2018-09-03 2023-01-24 Tesla, Inc. Neural networks for embedded devices
US11196678B2 (en) 2018-10-25 2021-12-07 Tesla, Inc. QOS manager for system on a chip communications
CN109540137B (en) * 2018-11-08 2020-12-25 中国科学技术大学 Aerial tether aircraft system and aircraft positioning method
US11537811B2 (en) 2018-12-04 2022-12-27 Tesla, Inc. Enhanced object detection for autonomous vehicles based on field view
CN109784526B (en) 2018-12-05 2023-02-28 阿波罗智能技术(北京)有限公司 Method, device and equipment for planning traffic path and readable storage medium
US10955853B2 (en) 2018-12-18 2021-03-23 Beijing Voyager Technology Co., Ltd. Systems and methods for autonomous driving
CN111338333B (en) * 2018-12-18 2021-08-31 北京航迹科技有限公司 System and method for autonomous driving
US11610117B2 (en) 2018-12-27 2023-03-21 Tesla, Inc. System and method for adapting a neural network model on a hardware platform
CN109782766B (en) 2019-01-25 2023-01-03 北京百度网讯科技有限公司 Method and device for controlling vehicle driving
CN109737983B (en) 2019-01-25 2022-02-22 北京百度网讯科技有限公司 Method and device for generating a travel route
CN111483592A (en) * 2019-01-29 2020-08-04 北京优位智停科技有限公司 Method and device for realizing automatic parking by using unmanned aerial vehicle
US11150664B2 (en) 2019-02-01 2021-10-19 Tesla, Inc. Predicting three-dimensional features for autonomous driving
US10997461B2 (en) 2019-02-01 2021-05-04 Tesla, Inc. Generating ground truth for machine learning from time series elements
US11567514B2 (en) 2019-02-11 2023-01-31 Tesla, Inc. Autonomous and user controlled vehicle summon to a target
CN111627256A (en) * 2019-02-28 2020-09-04 上海博泰悦臻电子设备制造有限公司 Unmanned aerial vehicle control method, vehicle-mounted terminal and computer-readable storage medium
CN110209126A (en) * 2019-03-21 2019-09-06 南京航空航天大学 The wheeled unmanned vehicle of modularization and rotor wing unmanned aerial vehicle fleet system
JP6956132B2 (en) * 2019-03-29 2021-10-27 本田技研工業株式会社 Shooting system, server, control method and program
CN113950612B (en) * 2019-06-14 2024-07-09 宝马股份公司 Road model manifold for 2D path planner
CN110347182A (en) * 2019-07-23 2019-10-18 广汽蔚来新能源汽车科技有限公司 Auxiliary driving device, system, unmanned plane and vehicle
CN110632925B (en) * 2019-09-18 2020-12-01 同济大学 Unmanned aerial vehicle assisted AGV self-guiding system and method thereof
CN110989505A (en) * 2019-10-28 2020-04-10 中国人民解放军96782部队 Unmanned command and dispatch system based on ground equipment machine vision
EP3859474B1 (en) * 2020-01-31 2024-04-17 Ningbo Geely Automobile Research & Development Co., Ltd. Unmanned aerial vehicle configured to be operated relative to a land vehicle
US11655028B2 (en) * 2020-02-19 2023-05-23 General Motors Llc Reinforcement learning based system for aerial imagery acquisition using drone following target vehicle
CN111309048B (en) * 2020-02-28 2023-05-26 重庆邮电大学 Method for detecting autonomous flight along road by combining multi-rotor unmanned aerial vehicle with road
CN111369819B (en) * 2020-03-02 2021-12-14 腾讯科技（深圳）有限公司 Method and device for selecting driving object
CN111459159A (en) * 2020-03-16 2020-07-28 江苏理工学院 Path following control system and control method
CN112364707B (en) * 2020-10-20 2023-09-26 华南理工大学 System and method for performing beyond-the-horizon perception on complex road conditions by intelligent vehicle
US11927972B2 (en) 2020-11-24 2024-03-12 Lawrence Livermore National Security, Llc Collision avoidance based on traffic management data
CN112817307B (en) * 2020-12-30 2022-08-02 广州大学 Vehicle auxiliary driving system and method based on unmanned aerial vehicle road perception
CN112776982A (en) * 2021-01-04 2021-05-11 高悦 Scenic spot accompanying equipment platform based on unmanned aerial vehicle
CN112964265A (en) * 2021-03-02 2021-06-15 恒大新能源汽车投资控股集团有限公司 Obstacle area marking method and device, electronic equipment and storage medium
CN113189989B (en) * 2021-04-21 2022-07-01 东风柳州汽车有限公司 Vehicle intention prediction method, device, equipment and storage medium
CN113359700B (en) * 2021-05-08 2022-12-20 安徽泗州拖拉机制造有限公司 Intelligent operation system of unmanned tractor based on 5G
CN113064451B (en) * 2021-06-02 2021-09-24 北京三快在线科技有限公司 Unmanned equipment control method and device, storage medium and electronic equipment
CN114020023B (en) * 2021-11-04 2022-07-26 中科晶锐(苏州)科技有限公司 Embedded AI camera analysis system and method based on unmanned aerial vehicle
CN114639088A (en) * 2022-03-23 2022-06-17 姜妹英 Big data automatic navigation method
CN116691790B (en) * 2023-08-04 2023-11-14 比亚迪股份有限公司 Rail vehicle control method, system, aircraft and target controller

Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP2515147A2 (en) * 2011-04-20 2012-10-24 Accenture Global Services Limited Capturing environmental information

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7765062B2 (en) * 2006-04-25 2010-07-27 Honeywell International Inc. Method and system for autonomous tracking of a mobile target by an unmanned aerial vehicle
ES2394540B1 (en) * 2012-07-26 2013-12-11 Geonumerics, S.L. PROCEDURE FOR THE ACQUISITION AND PROCESSING OF GEOGRAPHICAL INFORMATION OF A TRAJECT

Patent Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP2515147A2 (en) * 2011-04-20 2012-10-24 Accenture Global Services Limited Capturing environmental information

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US11893393B2 (en) 2017-07-24 2024-02-06 Tesla, Inc. Computational array microprocessor system with hardware arbiter managing memory requests
US11797304B2 (en) 2018-02-01 2023-10-24 Tesla, Inc. Instruction set architecture for a vector computational unit
US11841434B2 (en) 2018-07-20 2023-12-12 Tesla, Inc. Annotation cross-labeling for autonomous control systems
US11893774B2 (en) 2018-10-11 2024-02-06 Tesla, Inc. Systems and methods for training machine models with augmented data
US11816585B2 (en) 2018-12-03 2023-11-14 Tesla, Inc. Machine learning models operating at different frequencies for autonomous vehicles
US11790664B2 (en) 2019-02-19 2023-10-17 Tesla, Inc. Estimating object properties using visual image data

Also Published As

Publication number Publication date
CN105318888A (en) 2016-02-10

Similar Documents

Publication Publication Date Title
CN105318888B (en) Automatic driving vehicle paths planning method based on unmanned plane perception
CN105512628B (en) Vehicle environmental sensory perceptual system based on unmanned plane and method
US11693428B2 (en) Methods and system for autonomous landing
US11635775B2 (en) Systems and methods for UAV interactive instructions and control
CN108256413B (en) Passable area detection method and device, storage medium and electronic equipment
CN104049641B (en) A kind of automatic landing method, device and aircraft
CN109901580A (en) A kind of unmanned plane cooperates with unmanned ground robot follows diameter obstacle avoidance system and its method
CN106774386B (en) Unmanned plane vision guided navigation landing system based on multiple dimensioned marker
CN103411609B (en) A kind of aircraft return route planing method based on online composition
CN110222581A (en) A kind of quadrotor drone visual target tracking method based on binocular camera
JP5062498B2 (en) Reference data generation system and position positioning system for landscape matching
CN109885086B (en) Unmanned aerial vehicle vertical landing method based on composite polygonal mark guidance
CN103984355B (en) Routing inspection flying robot and overhead power line distance prediction and maintaining method
CN106407315A (en) Vehicle self-positioning method based on street view image database
CN108303103A (en) The determination method and apparatus in target track
CN106840148A (en) Wearable positioning and path guide method based on binocular camera under outdoor work environment
CN106054931A (en) Unmanned aerial vehicle fixed-point flight control system based on visual positioning
CN106651953A (en) Vehicle position and gesture estimation method based on traffic sign
CN112558608A (en) Vehicle-mounted machine cooperative control and path optimization method based on unmanned aerial vehicle assistance
KR101261409B1 (en) System for recognizing road markings of image
JP5182594B2 (en) Image processing system
KR101510745B1 (en) Autonomous vehicle system
CN109063532A (en) A kind of field lost contact personnel's method for searching based on unmanned plane
KR20200093271A (en) Apparatus and method for estimating location of landmark and computer recordable medium storing computer program thereof
CN107576329A (en) Fixed-wing unmanned plane based on machine vision drop guiding cooperation beacon design method

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant