CN107063276A - One kind is without the high-precision unmanned vehicle on-vehicle navigation apparatus of delay and method - Google Patents

One kind is without the high-precision unmanned vehicle on-vehicle navigation apparatus of delay and method Download PDF

Info

Publication number
CN107063276A
CN107063276A CN201611138614.1A CN201611138614A CN107063276A CN 107063276 A CN107063276 A CN 107063276A CN 201611138614 A CN201611138614 A CN 201611138614A CN 107063276 A CN107063276 A CN 107063276A
Authority
CN
China
Prior art keywords
delay
unmanned vehicle
vehicle navigation
vehicle
laser radar
Prior art date
Application number
CN201611138614.1A
Other languages
Chinese (zh)
Inventor
向红先
Original Assignee
成都育芽科技有限公司
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 成都育芽科技有限公司 filed Critical 成都育芽科技有限公司
Priority to CN201611138614.1A priority Critical patent/CN107063276A/en
Publication of CN107063276A publication Critical patent/CN107063276A/en

Links

Classifications

    • GPHYSICS
    • G01MEASURING; TESTING
    • G01CMEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C21/00Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
    • G01C21/26Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
    • G01C21/34Route searching; Route guidance
    • GPHYSICS
    • G01MEASURING; TESTING
    • G01CMEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C21/00Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
    • G01C21/26Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
    • G01C21/34Route searching; Route guidance
    • G01C21/3446Details of route searching algorithms, e.g. Dijkstra, A*, arc-flags, using precalculated routes
    • GPHYSICS
    • G01MEASURING; TESTING
    • G01CMEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C21/00Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
    • G01C21/26Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
    • G01C21/34Route searching; Route guidance
    • G01C21/3453Special cost functions, i.e. other than distance or default speed limit of road segments
    • GPHYSICS
    • G01MEASURING; TESTING
    • G01SRADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
    • G01S19/00Satellite radio beacon positioning systems; Determining position, velocity or attitude using signals transmitted by such systems
    • G01S19/38Determining a navigation solution using signals transmitted by a satellite radio beacon positioning system
    • G01S19/39Determining a navigation solution using signals transmitted by a satellite radio beacon positioning system the satellite radio beacon positioning system transmitting time-stamped messages, e.g. GPS [Global Positioning System], GLONASS [Global Orbiting Navigation Satellite System] or GALILEO
    • G01S19/42Determining position
    • G01S19/45Determining position by combining measurements of signals from the satellite radio beacon positioning system with a supplementary measurement

Abstract

The invention discloses a kind of without the high-precision unmanned vehicle on-vehicle navigation apparatus of delay and method of GPS navigation field.The guider includes GPS receiver module, micro controller module, display screen, several sensors, laser radar and several high-speed cameras.Methods described, which includes starting, navigates;Feature extraction;Modeling, carries out pseudo-differential processing;Carry out vehicle dynamic detection tracking;Optimization path program results is obtained with algorithm.It is not in path planning failure that the present invention, which can be achieved in the case of gps signal is weak, improves navigation accuracy, and the function with drive recorder.

Description

One kind is without the high-precision unmanned vehicle on-vehicle navigation apparatus of delay and method

Technical field

The present invention relates to vehicle mounted guidance field, it is related specifically to a kind of without the high-precision unmanned vehicle on-vehicle navigation apparatus of delay And method.

Background technology

The walking-replacing tool that automobile is gone on a journey as modern, has higher requirement to the navigator fix of vehicle.As people receive The increase entered, the sales volume of automobile has also increased, and people are gone on a journey from the mode of self driving, needs to obtain in real time accordingly Position and planning driving path are managed, facilitates driver faster more accurately to arrive at.Into 21st century, technology of Internet of things it is general And, information is exchanged between realizing any article, to the track and localization of object, is convenient for people to handle emergency case in real time.With various countries Satellite navigation system obtained preferable development and application, GPS GPS have it is round-the-clock, high-precision, from The features such as dynamicization, high benefit, it is widely used in the fields such as road, aviation, agricultural.The system is designed based on GP S technologies can Continuous, accurate automobile navigation location information is provided for driver,

Existing unmanned vehicle vehicle mounted guidance handles the positioning letter received from GPS module by master controller of STM32F103 Information transmission to host computer, is realized remote monitoring, it is the next that the vehicle mounted guidance has the weak situation of signal by breath by GPRS network Put information updating not in time, easily cause guidance path delay, user is driven to the place of mistake.Therefore it provides a kind of No-delay vehicle-mounted, high-precision unmanned vehicle on-vehicle navigation apparatus is just necessary.

The content of the invention

The technical problem to be solved in the present invention is to provide a kind of no-delay vehicle-mounted, high-precision on-vehicle navigation apparatus.Its Can be in the case of no gps signal, by detecting itself dynamic position progress position estimation to environment, so as to enter walking along the street Footpath is planned, is reached and is eliminated delay, the purpose of high accuracy navigation.

The technical solution adopted for the present invention to solve the technical problems is to include:GPS receiver module, micro controller module, Display screen, several sensors, laser radar and several high-speed cameras;The GPS module is used to receive gps satellite Data are sent to micro controller module;Several described sensors are used to collection vehicle peripheral location information and environmental information;Institute State dynamic change parameter of the multi-layer laser radar to recognize itself and environment;The ARM microcontroller is used to computing determine The orientation and path planning of vehicle;The display screen is to the program results that shows paths.

For optimization design, further, the laser radar is 4 layers of laser radar.

Further, the micro-control module is ARM micro-control modules.

Further, the sensor includes acceleration sensor, direction sensor and range sensor.

Further, aspect sensor quantity >=4.

The present invention also provides a kind of a kind of without the high-precision unmanned vehicle vehicle mounted guidance of delay according to claim 1-5 Method,

Methods described is comprised the steps of:

(1) start and navigate, the unlatching GPS receiver module, micro controller module, display screen LCD, several sensors, Laser radar and several high-speed cameras;

(2) feature extraction:Extract the echo impulse width of gps data, sensing data and laser radar;

(3) extract feature according to the step (1) to be modeled, carry out pseudo-differential processing;

(4) the echo impulse width characteristics extracted according to step (2), carry out vehicle dynamic detection tracking;

(5) optimization path program results is obtained with algorithm.

Further, feature extraction includes in the step (2), extract laser radar data in each put angle, away from From and reflected impulse width information, then use the method based on distance that laser spots are carried out into cluster segmentation.

Further, corresponding kinematics model is set up including the use of frame model and expression barrier in the step (3)

M=(w, l, x, y)

Wherein w and l represent the wide of barrier and long respectively, and (x, y) represents the position of barrier.With the obstacle detected Thing edge features and corner features determination are represented with frame model.

Further, the tracking of vehicle dynamic detection is wide according to step (2) described echo impulse in the step (4) Degree is in the range of 0~500, and 50~150 concentrate scope for the echo impulse width of lane line, and 220~405 be back echo arteries and veins Rush width and concentrate scope, select the echo impulse width in the range of this as virtual value, it is then that the echo impulse of barrier is wide Degree average is used as one of matching characteristic;The corresponding pulse width values of different barriers have very big difference, can be used for of surrounding With association, itself track computing is carried out, itself dynamic detection result is obtained;It is special according to the figure of high-speed camera to testing result Levy and checking is compared.

Further, the step (5) uses best-first search algorithm, generates the optimal path of an arrival target point, protects Card is minimum to be expended;The evaluation function of the best-first search algorithm is:

F (n)=G (n)+H (n)

Wherein F (n) is node n evaluation function, and G (n) is state space from start node to the actual cost of n nodes, H (n) it is estimate cost from n to destination node optimal path.

The present invention gathers the mode that ambient parameters are combined by using gps signal and sensor, is aided with multilayer radar The echo impulse width of progress gathers detects itself dynamic position to estimate, carries out making up without gps signal, can obtain following Technique effect:

Effect one, raising positioning precision;

Effect two, raising path planning correctness;

Effect three, elimination gps signal are weak or without the influence to path planning and positioning precision;

Effect four, high-speed camera can be used as drive recorder.

Brief description of the drawings

The present invention is further described with reference to the accompanying drawings and examples.

Fig. 1 is structured flowchart of the present invention.

Embodiment

In order to make the purpose , technical scheme and advantage of the present invention be clearer, with reference to embodiments, to the present invention It is further elaborated.It should be appreciated that the specific embodiments described herein are merely illustrative of the present invention, it is not used to Limit the present invention.

Embodiment 1

The present embodiment provides a kind of without the high-precision unmanned vehicle on-vehicle navigation apparatus of delay, including:GPS receiver module, it is micro- Controller module, display screen, several sensors, laser radar and several high-speed cameras;

The data that the GPS module is used to receive gps satellite are sent to micro controller module;Several described sensors are used With collection vehicle peripheral location information and environmental information;Dynamic change of the multi-layer laser radar to recognize itself and environment Parameter;The ARM microcontroller is used to computing determine the orientation and path planning of vehicle;The display screen is to show paths Program results.

The laser radar is 4 layers of laser radar.The micro-control module is ARM micro-control modules, with outside serial ports. The sensor includes acceleration sensor, direction sensor and range sensor;Aspect sensor is 4, respectively positioned at car 4 orientation all around.

One kind is comprised the steps of without high-precision unmanned vehicle navigation method is postponed:

(1) start and navigate, the unlatching GPS receiver module, micro controller module, display screen LCD, several sensors, Laser radar and several high-speed cameras;

(2) feature extraction:Extract the echo impulse width of gps data, sensing data and laser radar;Extract laser Angle, distance and the reflected impulse width information each put in radar data, then use the method based on distance by laser Point carries out cluster segmentation.

(3) extract feature according to the step (1) to be modeled, carry out pseudo-differential processing;Including the use of frame model and Barrier is represented, corresponding kinematics model is set up, and pseudo-differential processing is carried out to kinematics model;

M=(w, l, x, y)

Wherein w and l represent the wide of barrier and long respectively, and (x, y) represents the position of barrier.With the obstacle detected Thing edge features and corner features determination are represented with frame model.

(4) the echo impulse width characteristics extracted according to step (2), carry out vehicle dynamic detection tracking;The step Suddenly in (4) vehicle dynamic detection tracking be according to step (2) the echo impulse width in the range of 0~500,50~ 150 concentrate scope for the echo impulse width of lane line, and 220~405 be that back echo pulse width concentrates scope, selects this In the range of echo impulse width as virtual value, then using the echo impulse width average of barrier as matching characteristic it One;The corresponding pulse width values of different barriers have very big difference, can be used for the matching association of surrounding, carry out itself track fortune Calculate, obtain itself dynamic detection result;Checking is compared to testing result contrast high-speed camera Graph Extraction feature.

(5) optimization path program results is obtained with algorithm;The step (5) uses best-first search algorithm, generation one Bar reaches the optimal path of target point, it is ensured that minimum expends;The evaluation function of the best-first search algorithm is:

F (n)=G (n)+H (n)

Wherein F (n) is node n evaluation function, and G (n) is state space from start node to the actual cost of n nodes, H (n) it is estimate cost from n to destination node optimal path.

Although illustrative embodiment of the invention is described above, in order to the technology of the art Personnel are it will be appreciated that the present invention, but the present invention is not limited only to the scope of embodiment, to the common skill of the art For art personnel, as long as long as various change is in the spirit and scope of the invention that appended claim is limited and is determined, one The innovation and creation using present inventive concept are cut in the row of protection.

Claims (10)

1. it is a kind of without the high-precision unmanned vehicle on-vehicle navigation apparatus of delay, it is characterised in that:The on-vehicle navigation apparatus includes: GPS receiver module, micro controller module, display screen, several sensors, laser radar and several high-speed cameras;
The data that the GPS module is used to receive gps satellite are sent to micro controller module;Several described sensors are to adopt Collect vehicle periphery positional information and environmental information;The multi-layer laser radar is to recognize that the dynamic change of itself and environment is joined Number;The ARM microcontroller is used to computing determine the orientation and path planning of vehicle;The display screen is to the rule that show paths Check off fruit.
2. it is according to claim 1 a kind of without the high-precision unmanned vehicle on-vehicle navigation apparatus of delay, it is characterised in that:It is described Laser radar is 4 layers of laser radar.
3. it is according to claim 1 a kind of without the high-precision unmanned vehicle on-vehicle navigation apparatus of delay, it is characterised in that:It is described Micro-control module is ARM micro-control modules.
4. it is according to claim 1 a kind of without the high-precision unmanned vehicle on-vehicle navigation apparatus of delay, it is characterised in that:It is described Sensor includes acceleration sensor, direction sensor and range sensor.
5. it is according to claim 1 a kind of without the high-precision unmanned vehicle on-vehicle navigation apparatus of delay, it is characterised in that:It is described Aspect sensor quantity >=4.
6. it is a kind of without the high-precision unmanned vehicle navigation method of delay according to claim 1-5, it is characterised in that:Institute The method of stating is comprised the steps of:
(1) start navigation, open the GPS receiver module, micro controller module, display screen, several sensors, laser radar And several high-speed cameras;
(2) feature extraction:The echo impulse of extraction gps data, sensing data, high-speed camera figure and laser radar is wide Degree;
(3) extract feature according to the step (2) to be modeled, carry out pseudo-differential processing;
(4) the echo impulse width and high-speed camera graphic feature extracted according to step (2), carries out vehicle and dynamically examines Survey tracking;
(5) optimization path program results is obtained with algorithm.
7. it is according to claim 6 a kind of without the high-precision unmanned vehicle navigation method of delay, it is characterised in that:It is described Method is comprised the steps of:Feature extraction includes in the step (2), extract laser radar data in each put angle, away from From and reflected impulse width information, then use the method based on distance that laser spots are carried out into cluster segmentation.
8. it is according to claim 6 a kind of without the high-precision unmanned vehicle navigation method of delay, it is characterised in that:It is described Method is comprised the steps of:Including the use of frame model and expression barrier in the step (3), corresponding kinematics model is set up
M=(w, l, x, y)
Wherein w and l represent the wide of barrier and long respectively, and (x, y) represents the position of barrier.With the barrier side detected Represented along feature and corner features determination with frame model.
9. it is according to claim 6 a kind of without the high-precision unmanned vehicle navigation method of delay, it is characterised in that:It is described Method is comprised the steps of:The tracking of vehicle dynamic detection is wide according to step (2) described echo impulse in the step (4) Degree is in the range of 0~500, and 50~150 concentrate scope for the echo impulse width of lane line, and 220~405 be back echo arteries and veins Rush width and concentrate scope, select the echo impulse width in the range of this as virtual value, it is then that the echo impulse of barrier is wide Degree average is used as one of matching characteristic;The corresponding pulse width values of different barriers have very big difference, can be used for of surrounding With association, itself track computing is carried out, itself dynamic detection result is obtained.
10. it is according to claim 6 a kind of without the high-precision unmanned vehicle navigation method of delay, it is characterised in that:Institute The method of stating is comprised the steps of:The step (5) uses best-first search algorithm, generates the optimal path of an arrival target point, Ensure minimum expend;The evaluation function of the best-first search algorithm is:
F (n)=G (n)+H (n)
Wherein F (n) is node n evaluation function, and G (n) is state space from start node to the actual cost of n nodes, H (n) It is the estimate cost from n to destination node optimal path.
CN201611138614.1A 2016-12-12 2016-12-12 One kind is without the high-precision unmanned vehicle on-vehicle navigation apparatus of delay and method CN107063276A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201611138614.1A CN107063276A (en) 2016-12-12 2016-12-12 One kind is without the high-precision unmanned vehicle on-vehicle navigation apparatus of delay and method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201611138614.1A CN107063276A (en) 2016-12-12 2016-12-12 One kind is without the high-precision unmanned vehicle on-vehicle navigation apparatus of delay and method

Publications (1)

Publication Number Publication Date
CN107063276A true CN107063276A (en) 2017-08-18

Family

ID=59618806

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201611138614.1A CN107063276A (en) 2016-12-12 2016-12-12 One kind is without the high-precision unmanned vehicle on-vehicle navigation apparatus of delay and method

Country Status (1)

Country Link
CN (1) CN107063276A (en)

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102158684A (en) * 2010-02-12 2011-08-17 王炳立 Self-adapting scene image auxiliary system with image enhancement function
CN104932493A (en) * 2015-04-01 2015-09-23 上海物景智能科技有限公司 Autonomous navigation mobile robot and autonomous navigation method thereof
CN105318884A (en) * 2014-07-28 2016-02-10 现代自动车株式会社 Apparatus and method for generating global path for autonomous vehicle
US9395727B1 (en) * 2013-03-22 2016-07-19 Google Inc. Single layer shared aperture beam forming network
CN105938365A (en) * 2015-03-02 2016-09-14 丰田自动车株式会社 Vehicle control device

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102158684A (en) * 2010-02-12 2011-08-17 王炳立 Self-adapting scene image auxiliary system with image enhancement function
US9395727B1 (en) * 2013-03-22 2016-07-19 Google Inc. Single layer shared aperture beam forming network
CN105318884A (en) * 2014-07-28 2016-02-10 现代自动车株式会社 Apparatus and method for generating global path for autonomous vehicle
CN105938365A (en) * 2015-03-02 2016-09-14 丰田自动车株式会社 Vehicle control device
CN104932493A (en) * 2015-04-01 2015-09-23 上海物景智能科技有限公司 Autonomous navigation mobile robot and autonomous navigation method thereof

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
HOANG HUU VIET, ETC.: "BA*: an online complete coverage algorithm for cleaning robots", 《APPLIED INTELLIGENCE》 *

Similar Documents

Publication Publication Date Title
US10197404B2 (en) Path curve confidence factors
Hata et al. Feature detection for vehicle localization in urban environments using a multilayer LIDAR
US10670404B2 (en) Extended kalman filter for 3D localization and vision-aided inertial navigation
US10366289B2 (en) Systems and methods for providing vehicle cognition
Hashemi et al. A critical review of real-time map-matching algorithms: Current issues and future directions
US10558222B2 (en) Navigating a vehicle using a crowdsourced sparse map
CN104793202B (en) The object emerging system of more radar imagery sensors
US9255989B2 (en) Tracking on-road vehicles with sensors of different modalities
CN103954275B (en) Lane line detection and GIS map information development-based vision navigation method
US10248124B2 (en) Localizing vehicle navigation using lane measurements
DE102016120507A1 (en) Predicting vehicle movements on the basis of driver body language
US9495602B2 (en) Image and map-based detection of vehicles at intersections
US20170069206A1 (en) Negative Image for Sign Placement Detection
Garcia et al. Sensor fusion methodology for vehicle detection
Alonso et al. Accurate global localization using visual odometry and digital maps on urban environments
Bétaille et al. Creating enhanced maps for lane-level vehicle navigation
JP2017535873A (en) Continuous occlusion model for street scene recognition
Suhr et al. Sensor fusion-based low-cost vehicle localization system for complex urban environments
US8775063B2 (en) System and method of lane path estimation using sensor fusion
WO2018125939A1 (en) Visual odometry and pairwise alignment for high definition map creation
JP2015506310A (en) Vehicle control based on cognitive uncertainty
US9062979B1 (en) Pose estimation using long range features
CN106441319A (en) System and method for generating lane-level navigation map of unmanned vehicle
Wang et al. Simultaneous localization, mapping and moving object tracking
Goldbeck et al. Lane following combining vision and DGPS

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
WD01 Invention patent application deemed withdrawn after publication

Application publication date: 20170818

WD01 Invention patent application deemed withdrawn after publication