CN114719881B - Path-free navigation algorithm and system applying satellite positioning - Google Patents
Path-free navigation algorithm and system applying satellite positioning Download PDFInfo
- Publication number
- CN114719881B CN114719881B CN202210643295.9A CN202210643295A CN114719881B CN 114719881 B CN114719881 B CN 114719881B CN 202210643295 A CN202210643295 A CN 202210643295A CN 114719881 B CN114719881 B CN 114719881B
- Authority
- CN
- China
- Prior art keywords
- action
- path
- navigation
- mobile
- satellite
- 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
Links
Images
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
-
- 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
- G01C21/28—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network with correlation of data from several navigational instruments
-
- 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
- G01C21/3407—Route searching; Route guidance specially adapted for specific applications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO 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
- G01S19/00—Satellite radio beacon positioning systems; Determining position, velocity or attitude using signals transmitted by such systems
- G01S19/38—Determining a navigation solution using signals transmitted by a satellite radio beacon positioning system
- G01S19/39—Determining 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
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO 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
- G01S19/00—Satellite radio beacon positioning systems; Determining position, velocity or attitude using signals transmitted by such systems
- G01S19/38—Determining a navigation solution using signals transmitted by a satellite radio beacon positioning system
- G01S19/39—Determining 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
- G01S19/42—Determining position
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Landscapes
- Engineering & Computer Science (AREA)
- Remote Sensing (AREA)
- Radar, Positioning & Navigation (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Automation & Control Theory (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Computing Systems (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Health & Medical Sciences (AREA)
- Mathematical Physics (AREA)
- Computer Networks & Wireless Communication (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Navigation (AREA)
- Position Fixing By Use Of Radio Waves (AREA)
Abstract
The invention relates to a no-path navigation algorithm and a system applying satellite positioning; the system comprises a navigation system, a navigation system and a control system, wherein the navigation system acquires the action capability of a mobile body to ensure that an acquired navigation path is suitable for the action of the mobile body; secondly, a plurality of action intervals suitable for the mobile main body are determined by analyzing the ground characteristics based on the satellite remote sensing image through a satellite information processing module and matching with a ground information acquisition module arranged on the mobile main body to analyze the ground characteristics in real time on the ground in a short distance, and a plurality of optimized segment models are obtained from the action intervals in an iteration mode through a random sampling consistency algorithm, so that a plurality of sections of short-distance paths capable of being connected continuously are formed, and meanwhile, a suitable moving speed is calculated to guide the mobile main body to move to a target point. The navigation system realizes instant navigation calculation and temporary navigation path planning in an open environment without planning navigation paths, and considers a solution under the condition of no path navigation in a macroscopic view.
Description
Technical Field
The invention relates to the technical field of satellite navigation. And more particularly, to a path-less navigation algorithm and system using satellite positioning.
Background
As the development and utilization of earth by human beings is more frequent, the coverage has greatly increased in recent years, and the demand for mobile traffic planning on unknown earth has also greatly increased. However, path planning is impractical in most areas where roads are not constructed or where the road system is immature, and known paths rapidly fail as dirt roads continue to develop, thereby wasting a significant amount of time and labor cost in planning navigation paths. With the recent technological improvement of satellite positioning and the development of computer graphic operation technology, the navigation function using satellite positioning and unplanned path area becomes a solution for the traffic navigation of people in newly developed areas. If the temporary path demonstration and the temporary navigation scheme can be provided in real time by navigating the unplanned path area, the traffic movement capability of people in unknown fields can be greatly improved.
According to the related disclosed technical scheme, the technical scheme with the publication number of CN102944247B calculates weather prediction conditions of a plurality of areas in a passing section through satellite images, so that a movement path is planned to avoid a road section with bad weather, and the safety and the passing efficiency of a main body in the moving process are improved; the technical scheme of the publication number US9594380B2 discloses a path planning method and a recording method suitable for path-free autonomous movement of automation equipment such as a mower, and the operation interval and the non-involved interval are identified by a 360-degree panoramic shooting device arranged on the equipment, so that the operation path of the equipment is guided to completely cover a target area; the technical solution of publication No. JP2017003440A analyzes a desired course of action of a user by analyzing the user's taste, thereby optimizing the design of a path to improve the user's satisfaction. The above technical solutions all rely partially or totally on the existing ascertained path, and also lack navigation capability in the application scenario of completely no recorded path.
Disclosure of Invention
The invention aims to provide a path-free navigation algorithm and system applying satellite positioning; the navigation algorithm is suitable for mobile navigation in an unknown field environment without an existing path; the navigation system acquires the action capability of a mobile body to ensure that the acquired navigation path is suitable for the action of the mobile body; secondly, a plurality of action intervals suitable for the mobile main body are determined by analyzing the ground characteristics based on the satellite remote sensing image through a satellite information processing module and matching with a ground information acquisition module arranged on the mobile main body to analyze the ground characteristics in real time on the ground in a short distance, and a plurality of optimized segment models are obtained from the action intervals in an iteration mode through a random sampling consistency algorithm, so that a plurality of sections of short-distance paths capable of being connected continuously are formed, and meanwhile, a suitable moving speed is calculated to guide the mobile main body to move to a target point.
The invention adopts the following technical scheme:
a path-less navigation algorithm using satellite positioning, said navigation algorithm comprising the steps of:
s1: determining coordinates of a departure point and a target point of the mobile body through a satellite positioning system, and determining the action capacity of the mobile body;
s2: planning the action range which can be covered;
s3: gridding and dividing the action range, and recording the vertex longitude and latitude coordinates of each divided grid;
s4: determining earth surface features in the action range through the satellite remote sensing images, and determining a plurality of grids suitable for the mobile body in the action range based on the earth surface features of the grids;
s5: tracking the real-time position of the mobile main body through a satellite positioning system, performing short-distance planning on a temporary path inside a grid of the real-time position, finally obtaining an optimal path for navigation, and indicating the current orientation and the current target orientation of the mobile main body according to the optimal path;
s6: with the movement of the moving body, the navigation system guides the moving direction and the moving speed of the moving body in real time, and calculates the moving distance of the moving body so as to calibrate a satellite positioning coordinate, and further enables the moving body to pass through a plurality of grids to reach a target coordinate;
wherein step S5 includes the following substeps for planning a temporary path within the grid:
s501: selecting a plurality of action sections suitable for the mobile body from the grid based on the action capacity of the mobile body;
s502: randomly sampling from any two action intervals by using a random sampling consistency algorithm, and respectively selecting a coordinate point subset to establish a line segment model;
s503: calculating the number of pixel points falling into any action interval in a line segment model, thereby checking the correctness of the line segment model;
s504: iteration of the line segment model is carried out by repeating the sampling calculation of the step S502 and the step S503 for multiple times, and the optimal line segment model in any two action intervals is obtained to be used as a temporary path, so that a plurality of temporary paths connecting any two action intervals are obtained;
s505: based on a priority condition, finally selecting one temporary path from a plurality of temporary paths connecting any two action intervals as an optimal path;
optionally, the action capability information of the mobile subject includes one or more of the following information: the wheel track, the rated moving speed, the rated load, the current load, the cross-country moving grade, the wading moving grade, the highest endurance mileage and the current remaining endurance mileage of the left side and the right side of the moving main body;
optionally, the surface features of the grid include stiffness features and friction features within the region and are estimated by one or more of the following geographical features: the degree of immersion, the vegetation proportion of shrubs, the sandy soil proportion and the elevation variance;
further, in step S5, short-distance planning for the temporary path includes determining the boundary position of the temporary path from the current mesh and the next mesh to be entered;
optionally, the priority condition includes calculating a temporary path meeting one of the three conditions as an optimal path based on a shortest route condition, a shortest time condition and a lowest risk condition;
optionally, a navigation system applying said navigation algorithm is included; the navigation system includes:
the storage module is used for storing the action capability data, the satellite positioning data and the temporary path planning data of the mobile body, and further comprises the steps of storing the control method and data processing required by the navigation algorithm;
the mobile capability acquisition module is configured for acquiring preset action capability and real-time action capability data of the mobile body;
the satellite information processing module is configured to acquire a satellite remote sensing image of the action range and determine the earth surface characteristics of the action range by analyzing the satellite remote sensing image;
the ground information acquisition module is configured to acquire the surrounding environment of the mobile main body so as to determine the accurate measurement of the earth surface characteristics analyzed by the satellite remote sensing image, and feed the accurate measurement back to the satellite information processing module so as to correct the earth surface characteristics in the action range;
a path operation module configured to acquire a temporary path of a target area based on the analysis data of the satellite information processing module and the ground information acquisition module and based on the mobility of the mobile body;
optionally, the ground information acquisition module scans ground information in the front and two sides of the mobile body by using a laser radar arranged above the mobile body, and generates ground environment point cloud information; the path operation module analyzes the earth surface characteristics of the current surrounding ground environment of the mobile main body according to the ground environment point cloud information.
The beneficial effects obtained by the invention are as follows:
1. the navigation algorithm can plan a proper moving path based on the moving capability of the moving body, for example, when an off-road vehicle or a domestic vehicle is adopted for field area crossing, so that accidents caused by insufficient crossing capability of the moving body are avoided, and a more efficient path scheme is provided for the moving body with strong action capability;
2. the navigation algorithm of the invention finishes the analysis of the satellite remote sensing image and the ground imaging equipment, realizes the large-scale consideration of the macroscopic level based on the satellite remote sensing image, and then specifically judges the earth surface characteristics by combining the ground data, thereby optimizing the earth surface characteristic algorithm of the satellite information processing module in real time and carrying out rapid iterative update on the short-distance path in real time;
3. the navigation system is suitable for various manually controlled mobile instruments and is also suitable for automatically controlled mobile devices, such as unmanned vehicles or mobile robots;
4. according to the navigation algorithm and the early warning system, the hardware module and the device are in modular design and matched, and flexible optimization and change can be performed through software and hardware in the later period, so that a large amount of later maintenance and upgrading cost is saved.
Drawings
The invention will be further understood from the following description in conjunction with the accompanying drawings. The components in the figures are not necessarily to scale, emphasis instead being placed upon illustrating the principles of the embodiments. Like reference numerals designate corresponding parts throughout the different views.
FIG. 1 is a schematic representation of the steps of the navigation algorithm of the present invention;
FIG. 2 is a schematic diagram of planning action ranges and meshing by determining departure and target points according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of segment model planning performed in an embodiment of the present invention;
FIG. 4 is a schematic diagram illustrating temporary path planning according to an embodiment of the present invention;
fig. 5 is a schematic diagram of scanning the surrounding environment by using a lidar scanning apparatus in an embodiment of the present invention.
The reference numbers in the figures indicate: 10-starting point; 20-target point; 30-temporary navigation start point; 30 a-first line segment model; 30 b-a second line segment model; 30 c-third line segment model; 31-temporary navigation target points; 301-soft earth plots; 302-rock face parcel; 310-a first grid; 311-a second grid; 312-a third grid; 321-a first movement interval; 322-second action interval; 323-third movement interval; 40 a-a first temporary path; 40 c-third temporary path.
Detailed Description
In order to make the technical solution and advantages of the present invention more apparent, the present invention is further described in detail below with reference to the embodiments thereof; it should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention. Other systems, methods, and/or features of the present embodiments will become apparent to those skilled in the art upon review of the following detailed description. It is intended that all such additional systems, methods, features and advantages be included within this description, be within the scope of the invention, and be protected by the accompanying claims. Additional features of the disclosed embodiments are described in, and will be apparent from, the detailed description that follows.
The same or similar reference numerals in the drawings of the embodiments of the present invention correspond to the same or similar components; in the description of the present invention, it should be understood that if there is an orientation or positional relationship indicated by the terms "upper", "lower", "left", "right", etc. based on the orientation or positional relationship shown in the drawings, it is only for convenience of describing the present invention and simplifying the description, but it is not indicated or implied that the device or component referred to must have a specific orientation or be constructed and operated in a specific orientation, and thus, the terms describing the positional relationship in the drawings are only used for illustrative purposes and are not to be construed as limitations of the present patent, and specific meanings of the terms may be understood by those skilled in the art according to specific situations.
The first embodiment is as follows:
as shown in fig. 1, a path-less navigation algorithm using satellite positioning, the navigation algorithm comprises the following steps:
s1: determining coordinates of a departure point and a target point of the mobile body through a satellite positioning system, and determining the action capacity of the mobile body;
s2: planning the action range which can be covered;
s3: gridding and dividing the action range, and recording the vertex longitude and latitude coordinates of each divided grid;
s4: determining earth surface features in the action range through the satellite remote sensing images, and determining a plurality of grids suitable for the mobile body in the action range based on the earth surface features of the grids;
s5: tracking the real-time position of the mobile main body through a satellite positioning system, performing short-distance planning on a temporary path inside a grid of the real-time position, finally obtaining an optimal path for navigation, and indicating the current orientation and the current target orientation of the mobile main body according to the optimal path;
s6: with the movement of the moving body, the navigation system guides the moving direction and the moving speed of the moving body in real time, and calculates the moving distance of the moving body so as to calibrate a satellite positioning coordinate, and further enables the moving body to pass through a plurality of grids to reach a target coordinate;
wherein step S5 includes the following substeps for planning a temporary path within the grid:
s501: selecting a plurality of action sections suitable for the mobile subject from the grid based on the action capacity of the mobile subject;
s502: randomly sampling from any two action intervals by using a random sampling consistency algorithm, and respectively selecting a coordinate point subset to establish a line segment model;
s503: calculating the number of pixel points falling into any one action interval in a line segment model so as to check the correctness of the line segment model;
s504: iteration of the line segment model is carried out by repeating the sampling calculation of the step S502 and the step S503 for multiple times, and the optimal line segment model in any two action intervals is obtained to be used as a temporary path, so that a plurality of temporary paths connecting any two action intervals are obtained;
s505: based on a priority condition, one temporary path which connects any two action intervals is finally selected as an optimal path;
optionally, the action capability information of the mobile subject includes one or more of the following information: the wheel track, the rated moving speed, the rated load, the current load, the cross-country moving grade, the wading moving grade, the highest endurance mileage and the current remaining endurance mileage of the left side and the right side of the moving main body;
optionally, the surface features of the grid include stiffness features and friction features within the region and are estimated by one or more of the following geographical features: the degree of immersion, the vegetation proportion of shrubs, the sandy soil proportion and the elevation variance;
further, in step S5, the short-distance planning of the temporary path includes determining the boundary position of the temporary path from the current mesh to the next mesh to be entered;
optionally, the priority condition includes calculating a temporary path meeting one of the three conditions as an optimal path based on a shortest route condition, a shortest time condition and a lowest risk condition;
optionally, a navigation system applying said navigation algorithm is included; the navigation system includes:
the storage module is used for storing the action capability data, the satellite positioning data and the temporary path planning data of the mobile body, and further comprises the steps of storing the control method and data processing required by the navigation algorithm;
the mobile capability acquisition module is configured to acquire preset action capability and real-time action capability data of the mobile main body;
the satellite information processing module is configured to acquire a satellite remote sensing image of the action range and determine the earth surface characteristics of the action range by analyzing the satellite remote sensing image;
the ground information acquisition module is configured to acquire the surrounding environment of the mobile main body so as to determine the accurate measurement of the earth surface characteristics analyzed by the satellite remote sensing image, and feed the accurate measurement back to the satellite information processing module so as to correct the earth surface characteristics in the action range;
a path operation module configured to acquire a temporary path of a target area based on the analysis data of the satellite information processing module and the ground information acquisition module and based on the mobility of the mobile body;
optionally, the ground information acquisition module scans ground information in the front and two sides of the mobile main body by using a laser radar arranged above the mobile main body, and generates ground environment point cloud information; the path operation module analyzes the earth surface characteristics of the current surrounding ground environment of the mobile main body according to the ground environment point cloud information;
in one embodiment, the method comprises the steps of obtaining absolute coordinate positioning of a mobile body on the earth based on a satellite positioning system, such as a GPS-based global positioning system, a Beidou satellite positioning system, a Galileo satellite positioning system, a Glonass satellite positioning system and the like;
preferably, a satellite signal receiver is installed on the mobile body, and the main function of the satellite signal receiver is to capture the satellites to be tested selected according to a certain satellite cut-off angle and track the operation of the satellites; after a receiver captures a tracked satellite signal, the change rate of the pseudo distance and the distance from a receiving antenna to a satellite can be measured, and data such as satellite orbit parameters can be demodulated; according to the data, the microprocessor computer in the receiver can perform positioning calculation according to a positioning calculation method, and calculate the information of longitude and latitude, height, speed, time and the like of the geographic position of the user; the receiver hardware and software within the receiver and the post-processing software package for the positioning system data form a complete user satellite positioning device. The structure of the satellite signal receiver is divided into an antenna unit and a receiving unit; the receiver generally adopts two DC power supplies, namely an internal DC power supply and an external DC power supply; the purpose of setting the built-in power supply is to continuously observe when an external power supply is replaced; the battery is automatically charged when the external power supply is used; after the computer is shut down, the built-in battery supplies power to the random access memory to prevent data loss; further, the positioning data of the receiver is stored in the storage module and can be called and read by modules of other navigation systems;
as shown in fig. 2, the satellite information processing module performs positioning of the mobile body through a satellite positioning system to obtain a current coordinate of the mobile body, which may be a longitude and latitude coordinate, or a coordinate of another positioning calibration system; taking the positioning of the current mobile main body as a starting point 10; on the other hand, by the control user of the mobile body, by inputting the target point 20 into the navigation system; therefore, a possibly covered action range can be defined according to the coordinates of the departure point and the coordinates of the target point;
in one embodiment, the departure point and the target point are connected by a line segment, the connected line segment is used as a diagonal line of a rectangle, and the rectangle is proportionally expanded, so that a rectangular action range is obtained;
in one embodiment, the midpoint of the connecting line segment is taken as the geometric center of the rectangle, and a regular quadrangle is drawn as the action range;
further, the satellite information processing module acquires the satellite remote sensing image of the action range, and divides the action range into a plurality of grids in a gridding manner, as shown in fig. 2;
further, the movement capability acquisition module needs to acquire a movement capability parameter of the mobile subject, and the navigation algorithm needs to consider the movement capability of the mobile subject so as to make a suitable navigation guidance plan;
for example, in some cases, the moving body is a normal type vehicle, the tire size of which is 17 inches or 18 inches, the exhaust pipe is located behind the vehicle, and the maximum wading depth is not more than 38 cm; the tire is a common anti-skid tire and can be suitable for common wading areas and sandy lands; the highest speed per hour is 150 kilometers per hour, and the rated load is 2000 kg;
also in some cases, the mobile body may be an off-road truck, with 8 large tires and may reach wading depths above 1 meter, rated load of 5 tons, and currently already fully loaded;
in addition, in some cases, the mobile body may be a four-legged or six-legged mobile robot having a water depth of 80cm or more and capable of passing through a swamp area, but having a moving speed of 5 km/h;
based on each type of mobile body, the mobile capability of which has advantages and disadvantages, the mobile capability obtaining module quantifies the mobile capability of the mobile body and obtains a value E = [ E1, E2 … … En ] of the mobile capability, wherein E1 and E2 … … En are a plurality of items representing the mobile capability, such as speed, loading rate, wading depth and the like, and are selected and divided according to actual conditions; preferentially, a plurality of numerical values with the same dimension and numerical value range are obtained by carrying out data normalization processing on the items of each moving capability;
on the other hand, the satellite information processing module carries out further earth surface characteristic analysis according to the satellite remote sensing image in the action range; the classification of the surface features is to use a computer to analyze the spectral information and the spatial information of various ground features in the remote sensing image and select the features, divide each pixel in the image into different categories according to a certain rule or algorithm, and then obtain the corresponding information of the actual ground features in the remote sensing image, thereby realizing the classification of the images; the computer classification of the remote sensing image is based on the similarity of the pixels of the remote sensing image; distance and correlation coefficient are often used to measure similarity; preferably, the classification method comprises: supervised classification, unsupervised classification;
firstly, determining a discrimination model and a corresponding discrimination criterion according to empirical knowledge of categories by using a supervision classification method; determining undetermined parameters in a discrimination function by using observed values of a certain number of samples (namely training samples) of known classes, establishing a ground surface feature discrimination model, substituting the observed values of the samples of unknown classes into the discrimination model, and judging the class of the samples according to a discrimination criterion;
the theoretical basis of unsupervised classification is that the same ground objects on the remote sensing images have the same or similar spectral characteristics under the conditions of the same surface structure characteristics, vegetation coverage, illumination and the like, so that certain internal similarity is shown and the ground objects belong to the same spectral space region; different ground objects have different spectral information characteristics and belong to different spectral space regions;
the earth surface characteristics of each grid in the action range are obtained through the earth surface characteristic analysis of the action range, and therefore the next navigation path is planned;
as further shown in fig. 3, the temporary navigation target point 31 is needed to be reached by the temporary navigation start point 30 where the mobile body is currently located; the action range comprises 4 grids, the grids are analyzed from the satellite remote sensing image, the action range comprises a soft soil plot 301 and a rock surface plot 302, and the rest earth surfaces are grasslands or dry and hard lands;
based on the mobile body's mobility determination, in one implementation, the mobile body is not suitable for traversing the soft soil mass 301, and therefore, the soft soil mass 301 is excluded from the sampled range, and a portion of the soft soil mass 301 is excluded from the first grid 310, and the remaining sections are used as mobility sections, including a first mobility section 321, a second mobility section 322, and a third mobility section 323;
further, a random sampling consistency method is used, in three action intervals, a coordinate subset is selected respectively, at least one point included in each coordinate subset is selected to be connected with the temporary navigation starting point 30, and at least three line segment models 30a, 30b and 30c are obtained; calculating the correctness of the segment model by calculating the number of pixel points included in the motion interval of the segment model;
for example, as can be seen from fig. 3, since the second line segment model 30b passes through the soft soil region 301, the number of pixels included in the action zone of the second line segment model 30b is small, and the first line segment model 30a and the third line segment model 30c are mostly included in the action zone;
taking fig. 3 as an example, only an exemplary calculation principle example is listed; in a real implementation mode, the division mode of the action section is to perform more detailed implementation operation based on the movement capacity of the moving body and the earth surface feature analysis precision of the satellite remote sensing image;
furthermore, the passability of the transverse width of the body-moving body needs to be considered, so that a temporary path is defined as a central line into two line segment models on the left side and the right side of the temporary path respectively, and the two line segment models are used as the left boundary and the right boundary of the temporary path to allow the body-moving body to move from the space in the left boundary and the right boundary; as shown in fig. 4, a first temporary path 40a is planned by the first line segment model 30a, and a third temporary path 40c is planned by the third line segment model 30 c; wherein the first temporary path 40a is more inclined to enter the third trellis 312, and the third temporary path 40c is more inclined to enter the second trellis 311;
further, based on the priority condition, such as the shortest path condition, one of the first temporary path 40a and the third temporary path 40c is finally selected as the optimal path to start moving;
furthermore, taking the terminal point of the optimal path as the next starting point, and considering the connection and planning of the subsequent temporary path.
Example two:
this embodiment should be understood to include at least all of the features of any of the foregoing embodiments and further modifications thereon;
furthermore, the satellite remote sensing image has certain defects, such as insufficient resolution, general classification accuracy of earth surface features through spectral characteristics and the like; therefore, in the embodiment, the method comprises the steps of further collecting and analyzing the surface characteristic data through a ground information acquisition module arranged on the mobile main body;
in one embodiment, the ground information acquisition module comprises a scanning device configured with a laser radar, and further judges and analyzes the environment around the mobile body, including the combined analysis of the data of the ground information acquisition module and the satellite information acquisition module;
as shown in fig. 5, a laser radar scanning device is used to scan the earth surface features in the direction right in front of the moving body to obtain point cloud image data; the point cloud data transmits laser signals to the ground through a laser radar, and collects and records the laser signals reflected by the ground; then, the ground information acquisition module can calculate accurate spatial information of the point clouds through joint calculation and deviation correction; each point cloud has space coordinate information, so that each point cloud has space description capability; two points form a line, three points form a plane, four points form a body, coordinate information of objects or earth surface shapes on earth surface space can be clearly known through point cloud information, and information such as length, area, volume, angle and the like among the objects or the earth surface shapes can be calculated;
in some embodiments, the method comprises the steps of further analyzing whether the area judged as the bush in the satellite remote sensing image comprises the arbor through the obtained ground point cloud image, so as to correct the leak marking the bush as the action section;
in some embodiments, the method comprises the steps of knowing whether a large number of concave-convex rock grounds or a large number of hollow zones exist on the ground surface through a ground point cloud image, so that a moving body cannot pass through the navigation system at the current moving capacity, and feeding back the moving body to the navigation system to re-plan a temporary path;
in some embodiments, the method comprises the steps of judging whether the road surface is flat or has obvious obstacles through a ground point cloud image so as to guide whether a moving body can increase the moving speed or carry out slow advancing;
in some embodiments, the method comprises the steps of judging the elevation variance of the environment right in front of the mobile main body, and determining whether the mobile main body continuously advances to meet a steep slope or a sudden falling risk;
in some embodiments, the method comprises the step of providing more reference data to the satellite information processing module by the ground information acquisition module through the analysis of the earth surface characteristics of the current region, so as to adjust and optimize the calculation parameters or calculation models for analyzing the earth surface characteristics, thereby realizing more accurate analysis results of the satellite remote sensing images.
Example three:
this embodiment is to be understood as embracing at least all the features of any one of the preceding embodiments and further modifications thereto;
in order to further obtain more accurate earth surface characteristics for analysis, the earth surface information acquisition module adopts an RGB image sensor to acquire current earth surface information, and establishes an earth surface characteristic analysis model in a deep learning mode, so that the earth surface characteristic analysis model can be combined with satellite telegraph image data, thereby realizing more accurate earth surface characteristic classification;
the preliminary classification of the surface features can be divided into seven categories, including: grasslands, terraces, rocky lands, ice surfaces, shallow water, tarmac, large obstacles, and including mixed types of seven categories;
further, it includes further sub-dividing the above seven types of land, such as green grass, dry grass, loose sand, land puddle, dirty ice surface, smooth rock, etc;
further, a neural network for classifying the land types is established, and training of the neural network is carried out for enhancing the semantic segmentation function for classifying the land types;
the neural network includes sampling the acquired image, that is, reducing the image with a large amount of characteristic data, for example, performing pooling, convolution and other operations; wherein the input original resolution image is subjected to convolution of n =63, f =3, p =1, s =2, maximal pooling of f =2, p =0, s =2, and average pooling of f =2, p =0, s =2 simultaneously; wherein, the parameters in the convolution operation are iterated in the process of multiple times of model learning so as to realize learning optimization, and the parameters are used for extracting certain low-level features of the image; average pooling can extract average features in the image that belong to a window portion of a pooling kernel; the maximum pooling can be used for extracting the maximum pixel value of a window part belonging to a pooling kernel in the image, namely directly selecting the most representative pixel in the window; through the three operations, the information features of the original resolution image can be extracted from different implementation depths respectively;
further, geometric texture recognition is carried out on the surface features in the image, and the geometric texture recognition is used for distinguishing the texture features of the surface;
furthermore, the method comprises the steps of carrying out sensing research on context information in the image, namely identifying a certain type of surrounding environment in the image, including coexistence, spatial position relation and the like of the type and other types on the same image, so that the neural network can consider the environment where the earth surface to be classified is located, and the analysis capability of scene characteristics is improved; wherein the context information includes daylight illumination conditions, time conditions, weather conditions, etc.; the partial context information comprises the information which can be obtained from a satellite information obtaining module and more information channels;
further, the mechanical characteristics of the surface of the earth can be further identified, including performing convolution operation on the surface part on the image by using a Sobel operator, so as to obtain the change degree of pixels in the surface image, and further estimating the roughness of the surface;
further, the method comprises the steps of identifying optical characteristics of the surface of the earth, including information such as color, glossiness and transparency presented by the surface image, so as to assist in judging the type of the earth;
by establishing the earth surface characteristic analysis model, the navigation system can obtain more accurate action interval information, so that more efficient and safe navigation path planning is further realized.
In the above embodiments, the descriptions of the respective embodiments have respective emphasis, and reference may be made to the related descriptions of other embodiments for parts that are not described or illustrated in a certain embodiment.
Although the invention has been described above with reference to various embodiments, it should be understood that many changes and modifications may be made without departing from the scope of the invention. That is, the methods, systems, and devices discussed above are examples. Various configurations may omit, substitute, or add various procedures or components as appropriate. For example, in alternative configurations, the methods may be performed in an order different than described, and/or various components may be added, omitted, and/or combined. Moreover, features described with respect to certain configurations may be combined in various other configurations, as different aspects and elements of the configurations may be combined in a similar manner. Further, elements therein may be updated as technology evolves, i.e., many elements are examples and do not limit the scope of the disclosure or claims.
Specific details are given in the description to provide a thorough understanding of the exemplary configurations including implementations. However, configurations may be practiced without these specific details, for example, well-known circuits, processes, algorithms, structures, and techniques have been shown without unnecessary detail in order to avoid obscuring the configurations. This description provides example configurations only, and does not limit the scope, applicability, or configuration of the claims. Rather, the foregoing description of the configurations will provide those skilled in the art with an enabling description for implementing the described techniques. Various changes may be made in the function and arrangement of elements without departing from the spirit or scope of the disclosure.
In conclusion, it is intended that the foregoing detailed description be regarded as illustrative rather than limiting, and that it be understood that it is illustrative only and is not intended to limit the scope of the invention. After reading the description of the invention, the skilled person can make various changes or modifications to the invention, and these equivalent changes and modifications also fall into the scope of the invention defined by the claims.
Claims (7)
1. A path-free navigation algorithm using satellite positioning, said navigation algorithm comprising the steps of:
s1: determining coordinates of a departure point and a target point of the mobile body through a satellite positioning system, and determining the action capacity of the mobile body;
s2: planning the action range covered;
s3: gridding and dividing the action range, and recording the vertex longitude and latitude coordinates of each divided grid;
s4: determining earth surface features in the action range through the satellite remote sensing images, and determining a plurality of grids suitable for the mobile body in the action range based on the earth surface features of the grids;
s5: tracking the real-time position of the mobile main body through a satellite positioning system, performing short-distance planning on a temporary path inside a grid of the real-time position, finally obtaining an optimal path for navigation, and indicating the current orientation and the current target orientation of the mobile main body according to the optimal path;
s6: with the movement of the mobile body, the navigation system guides the moving direction and the moving speed of the mobile body in real time, and calculates the moving distance of the mobile body so as to calibrate a satellite positioning coordinate, and finally the mobile body passes through a plurality of grids to reach a target point coordinate;
wherein step S5 includes the following substeps for planning a temporary path within the grid:
s501: selecting a plurality of action sections suitable for the mobile subject from the grid based on the action capacity of the mobile subject;
s502: randomly sampling from any two action intervals by using a random sampling consistency algorithm, and respectively selecting a coordinate point subset to establish a line segment model;
s503: calculating the number of pixel points falling into any action interval in a line segment model, thereby checking the correctness of the line segment model;
s504: iteration of the segment model is carried out by repeating the sampling calculation of the step S502 and the step S503 for multiple times, and an optimal segment model in any two action intervals is obtained to be used as a temporary path, so that a plurality of temporary paths connecting any two action intervals are obtained;
s505: and finally selecting one temporary path from a plurality of temporary paths connecting any two action intervals as an optimal path based on the priority condition.
2. The algorithm of claim 1, wherein the mobility capability of the mobile object comprises one or more of the following information: the wheel track, the rated moving speed, the rated load, the current load, the cross-country moving grade, the wading moving grade, the highest endurance mileage and the current remaining endurance mileage of the left side and the right side of the moving body.
3. The algorithm of claim 2, wherein the earth surface features of the grid comprise stiffness features and friction features within the region, and are estimated by one or more of the following geographical features: the degree of soaking, the vegetation proportion of shrubs, the sandy soil proportion and the elevation variance.
4. The algorithm of claim 3, wherein the step S5 of planning the temporary path comprises determining the intersection position of the temporary path from the current cell to the next cell to be entered.
5. The algorithm according to claim 4, wherein the priority condition comprises calculating a temporary path meeting one of the three conditions as the optimal path based on the shortest route condition, the shortest time condition and the lowest risk condition.
6. A pathless navigation system using satellite positioning, the navigation system comprising:
a storage module for storing the performance data, satellite positioning data and temporary path planning data of the mobile body, comprising the steps of storing the control method and data processing required by the navigation algorithm according to any one of claims 1-5;
the mobile capability acquisition module is configured for acquiring preset action capability and real-time action capability data of the mobile body;
the satellite information processing module is configured to acquire a satellite remote sensing image of the action range and determine the earth surface characteristics of the action range by analyzing the satellite remote sensing image;
the ground information acquisition module is configured to acquire the surrounding environment of the mobile body so as to determine the accurate measurement of the earth surface characteristics analyzed by the satellite remote sensing image, and feed the accurate measurement back to the satellite information processing module so as to correct the earth surface characteristics of the action range;
and the path operation module is configured to acquire a temporary path of a target area based on the analysis data of the satellite information processing module and the ground information acquisition module and based on the action capability of the mobile body.
7. The system of claim 6, wherein the ground information acquisition module comprises a laser radar disposed above the mobile body for scanning the ground information right in front of and on both sides of the mobile body and generating the ground environment point cloud information; the path operation module analyzes the earth surface characteristics of the current surrounding ground environment of the mobile main body according to the ground environment point cloud information.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210643295.9A CN114719881B (en) | 2022-06-09 | 2022-06-09 | Path-free navigation algorithm and system applying satellite positioning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210643295.9A CN114719881B (en) | 2022-06-09 | 2022-06-09 | Path-free navigation algorithm and system applying satellite positioning |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114719881A CN114719881A (en) | 2022-07-08 |
| CN114719881B true CN114719881B (en) | 2022-08-23 |
Family
ID=82232347
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210643295.9A Active CN114719881B (en) | 2022-06-09 | 2022-06-09 | Path-free navigation algorithm and system applying satellite positioning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114719881B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117740022B (en) * | 2024-02-21 | 2024-05-14 | 航天宏图信息技术股份有限公司 | Road network-free navigation data production method and device, electronic equipment and storage medium |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2009019932A (en) * | 2007-07-10 | 2009-01-29 | Toyota Motor Corp | Route search system, route search method, and autonomous moving body |
| CN106092103A (en) * | 2016-08-18 | 2016-11-09 | 广东省交通规划设计研究院股份有限公司 | The air navigation aid of the field investigation of a kind of mountain area, prospecting and search and device |
| CN107228668A (en) * | 2017-05-17 | 2017-10-03 | 桂林电子科技大学 | A kind of path planning new method of rule-based grid dem data |
| CN110967032A (en) * | 2019-12-03 | 2020-04-07 | 清华大学 | Real-time planning method for local driving route of unmanned vehicle in field environment |
| CN111667101A (en) * | 2020-05-22 | 2020-09-15 | 武汉大学 | Personalized electric power field operation path planning method and system integrating high-resolution remote sensing image and terrain |
| WO2021076099A1 (en) * | 2019-10-15 | 2021-04-22 | Google Llc | Weather and road surface type-based navigation directions |
| CN113126618A (en) * | 2021-03-17 | 2021-07-16 | 中国科学院合肥物质科学研究院 | Unmanned global path planning and re-planning method in cross-country environment |
| CN114326754A (en) * | 2022-03-09 | 2022-04-12 | 中国科学院空天信息创新研究院 | Complex terrain path planning method and device, electronic equipment and storage medium |
-
2022
- 2022-06-09 CN CN202210643295.9A patent/CN114719881B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2009019932A (en) * | 2007-07-10 | 2009-01-29 | Toyota Motor Corp | Route search system, route search method, and autonomous moving body |
| CN106092103A (en) * | 2016-08-18 | 2016-11-09 | 广东省交通规划设计研究院股份有限公司 | The air navigation aid of the field investigation of a kind of mountain area, prospecting and search and device |
| CN107228668A (en) * | 2017-05-17 | 2017-10-03 | 桂林电子科技大学 | A kind of path planning new method of rule-based grid dem data |
| WO2021076099A1 (en) * | 2019-10-15 | 2021-04-22 | Google Llc | Weather and road surface type-based navigation directions |
| CN110967032A (en) * | 2019-12-03 | 2020-04-07 | 清华大学 | Real-time planning method for local driving route of unmanned vehicle in field environment |
| CN111667101A (en) * | 2020-05-22 | 2020-09-15 | 武汉大学 | Personalized electric power field operation path planning method and system integrating high-resolution remote sensing image and terrain |
| CN113126618A (en) * | 2021-03-17 | 2021-07-16 | 中国科学院合肥物质科学研究院 | Unmanned global path planning and re-planning method in cross-country environment |
| CN114326754A (en) * | 2022-03-09 | 2022-04-12 | 中国科学院空天信息创新研究院 | Complex terrain path planning method and device, electronic equipment and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| "基于通行性分析的分层越野路径规划方法";闫星宇等;《火力与指挥控制》;20220515;第47卷(第5期);第153-158页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114719881A (en) | 2022-07-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP4318397A2 (en) | Method of computer vision based localisation and navigation and system for performing the same | |
| CN108369420B (en) | Apparatus and method for autonomous positioning | |
| Biçici et al. | An approach for the automated extraction of road surface distress from a UAV-derived point cloud | |
| Jaakkola et al. | A low-cost multi-sensoral mobile mapping system and its feasibility for tree measurements | |
| Wang et al. | Intelligent vehicle self-localization based on double-layer features and multilayer LIDAR | |
| US6728608B2 (en) | System and method for the creation of a terrain density model | |
| CN109813335B (en) | Calibration method, device and system of data acquisition system and storage medium | |
| Hodgson et al. | Accuracy of airborne lidar-derived elevation | |
| Goulette et al. | An integrated on-board laser range sensing system for on-the-way city and road modelling | |
| JP2007322391A (en) | Own vehicle position estimation device | |
| CN114719881B (en) | Path-free navigation algorithm and system applying satellite positioning | |
| CN113239864A (en) | Route planning method of unmanned aerial vehicle suitable for agricultural investigation | |
| Vandapel et al. | Experimental results in using aerial ladar data for mobile robot navigation | |
| Jozkow et al. | Performance evaluation of sUAS equipped with Velodyne HDL-32E LiDAR sensor | |
| CN111556157A (en) | Crop distribution monitoring method, equipment, storage medium and device | |
| KR20230101241A (en) | Method for 3d position recognition in underground mine | |
| Rebelo et al. | Building 3D city models: Testing and comparing Laser scanning and low-cost UAV data using FOSS technologies | |
| Dehbi et al. | Improving gps trajectories using 3d city models and kinematic point clouds | |
| Mayr et al. | 3D point errors and change detection accuracy of unmanned aerial vehicle laser scanning data | |
| Bouziani et al. | Comparison assessment of digital 3D models obtained by drone-based lidar and drone imagery | |
| US20230029573A1 (en) | Mapping Objects Using Unmanned Aerial Vehicle Data in GPS-Denied Environments | |
| Kokamägi et al. | UAV photogrammetry for volume calculations | |
| Rekleitis et al. | Terrain modelling for planetary exploration | |
| Leedekerken et al. | Mapping complex marine environments with autonomous surface craft | |
| JP2005056186A (en) | Traffic condition observation system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |