CN105184243B - A kind of environmental characteristic expression based on 3 d grid map and knowledge method for distinguishing - Google Patents
A kind of environmental characteristic expression based on 3 d grid map and knowledge method for distinguishing Download PDFInfo
- Publication number
- CN105184243B CN105184243B CN201510540211.9A CN201510540211A CN105184243B CN 105184243 B CN105184243 B CN 105184243B CN 201510540211 A CN201510540211 A CN 201510540211A CN 105184243 B CN105184243 B CN 105184243B
- Authority
- CN
- China
- Prior art keywords
- volume elements
- grid map
- transformation
- influence
- indicates
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/64—Three-dimensional objects
- G06V20/653—Three-dimensional objects by matching three-dimensional models, e.g. conformal mapping of Riemann surfaces
Landscapes
- Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Image Analysis (AREA)
Abstract
The present invention is that a kind of environmental characteristic based on 3 d grid map indicates and knows method for distinguishing, for the 3 d grid map built up, for the barrier and its boundary environment in 3 d grid map, carry out signature analysis, it refines out convenient for storage and the grid character representation method calculated, the basis identified as environmental characteristic.This method can be applied to the path planning and autokinetic movement of the Context awareness of robot, robot, and support is provided for robot game application in the actual environment, robot cleaner etc..
Description
Technical field
The discrete orthogonal transforms technologies such as the present invention relates to artificial intelligence, pattern-recognition and Fourier to convert, Walsh transformation,
Especially robot to the modeling of the three-dimensional environment of complex environment with know method for distinguishing, be applied to the Context awareness of robot with it is autonomous
In terms of movement.
Background technology
With industrial machine man-based development in recent years, the gradual turn up of service robot industry has been driven, while from 2014
The Intelligent hardware field that year starts also begins to protrusion, according to the statistics of international alliance of robot, service robot sale in 2015
Volume will be up to 8,500,000,000 dollars, and higher 20%~30% growth rate is kept to be studied according to Ai Rui in Intelligent hardware field, and 2014
Year, global Intelligent hardware installation amount reached 6,000,000,000, it is contemplated that 2017 will be more than 14,000,000,000.
The behind of high speed development in market, problem is equally apparent, and the potentiality in one side market are also excavated far away, another
Aspect, robot and Intelligent hardware enter service industry, and there is also the features of some technological difficulties, especially three-dimensional environment to build
Mould and identification technology, such as robot enter in actual home environment, carry out Context awareness and safely autonomous etc.,
All there are certain technological difficulties at present.
Goal of the invention
The main object of the present invention be exactly environmental characteristic after solving the environmental modeling based on 3 d grid map indicate with
Identification problem, it provides a kind of method so that the environmental characteristic based on 3 d grid map convenient for storage and calculates, to reach
To the purpose for facilitating identification, technical support is provided for other practical applications.It can be, but not limited to apply in the machine towards family
People plays and robot cleaner aspect.
Technical solution
The object of the present invention is achieved like this：By three-dimensional laser radar or binocular vision sensor, obtain
The 3 d grid cartographic information of actual environment indicates system by environmental characteristic, calculates and the feature of storage volume elements to three-dimensional grid
In lattice map, after the information for setting required target volume elements, by environmental characteristic identifying system, matched in 3 d grid map
Go out all required candidate volume elements.It includes the following steps：
(1) in environmental characteristic expression system, it is contemplated that the convenience of calculating, we set an influence distance delta, i.e. obstacle
For object member to the coverage of periphery volume elements, σ can be but not limited to Euclidean distance, Manhattan (Manhattan) distance etc..Together
When also for convenience of calculation, volume elements x on impacted all average discretes to eight yaw faces of volume elements x;δ0, δπ/4, δπ/2,
δ3π/4, δπ, δ5π/4, δ3π/2, δ7π/4], then each yaw face δiInterior influence component is all discrete to arrive yaw face δiInterior eight bow
[ on the elevation angle;η0, ηπ/12, ηπ/4, η5π/12, η7π/12, η3π/4, η11π/12, ηπ], the suffered influence matrix f (x) of volume elements x is formed, and count
The eigenmatrix and characteristic spectrum for calculating the suffered influence matrix f (x) of volume elements x, provide two kinds of eigenmatrixes and the meter of characteristic spectrum here
Calculation method,
(2) in environmental characteristic expression system, each element of the influence matrix of each idle volume elements is initialized as 0,
Influence of each barrier volume elements to all volume elements in σ distances is analyzed one by one, for example, during analysis, obstructing objects
Yaw angles of first ξ with respect to volume elements x is θ, pitch angle β, and distance is d, d≤σ, then influences of the barrier volume elements ξ to volume elements x
Function can be but not limited to f (xβ, θ, d)=1/d, if θ just on a certain yaw face of volume elements x, directly this partially
It is superimposed on movable surface, if θ, between certain two yaw face, such as θ ∈ (π/4, pi/2) are then decomposed according to vector, f
(xβ, θ, d) decompose project to yaw face δπ/4On vector faWith yaw face δπ/2On vector fb(two projection vector faWith fbSame Z
Axle clamp angle is equal, and with f (xβ, θ, d) coplanar), by same vector decomposition method again respectively vector faWith fbDecomposition projects to
On two neighboring pitching angular direction in each yaw face, after the completion of to all obstructing objects meta analysis, each volume elements
Influence matrix has calculated completion, and is stored in grid, is denoted as：
(3) in environmental characteristic expression system, it is contemplated that the convenience of calculating, we seek the eigenmatrix F (x) of f (x),
And it is stored in grid：
Method one seeks F (x) by two-dimensional fourier transform, enables transformation operatorAccording to fast two-dimensional
Fourier transformation calculations obtain,
Method two seeks F (x) by Walsh transformation, enables transformation operatorAccording to fast two-dimensional Walsh
Hadama changes convert,
8x8 matrixes in above-mentioned formula, are the Walsh Hadama transformation matrixs of 8 dimensions, and different dimensions is corresponding
Walsh Hadama transformation matrixs are different, wherein：
(4) in environmental characteristic expression system, it is contemplated that the convenience of calculating, we seek the characteristic spectrum of eigenmatrix F (x)
P (x), and be stored in grid：Method one converts eigenmatrix F (x), the Wo Menyou found out according to fast two-dimensional Fourier,
Pass through modulus operation, feature spectral element P (x);i][j]=|F(x)[i][j]=|FI+1, j+1|, i, j ∈ [0,7]
Method two converts eigenmatrix F (x), the Wo Menyou found out according to fast two-dimensional Walsh Hadama,
(5) in environmental characteristic identifying system, we are given threshold deg reethreshold, and construct target environment volume elements y
Influence matrixTwo dimension Walsh Hadama transform methods are used according to above step, are asked
Corresponding characteristic spectrum P (y) is taken, all volume elements x are searched on 3 d grid map, and compare corresponding characteristic spectrum, note vector P
(x) angle between vector P (y) is ∠ (P (x), P (y))≤deg reethreshold, calculateIf cos ∠ (P (x), P (y)) >=cos (deg reethreshold), with regard to table
Show that volume elements x with target volume elements y is similar in the actual environment, match volume elements of one of candidate,
(6) passing through environmental characteristic expression and identifying system, we can successfully find out all environment with object matching,
Support is provided for subsequent applications.
System composition used in the present invention is as follows：Environmental characteristic indicates system, environmental characteristic identifying system.This two are
System is the software systems according to function setting, and each subsystem concrete function is as follows：
* environmental characteristic indicates system：On existing 3 d grid map, relevant volume elements is analyzed, calculates simultaneously memory bank
The influence matrix of member, eigenmatrix, characteristic spectrum,
* environmental characteristic identifying system：The corresponding volume elements influence matrix of desired environment is provided, in have volume elements feature three
It ties up to search on grating map and search, match all volume elements similar with desired environment.
Description of the drawings：
Fig. 1 is the method for the present invention system for use in carrying composition figure
Fig. 2 (a) is 3 d grid map, is (b) the influence vector and decomposition method of volume elements, is (c) that the decomposition of yaw face is shown
It is intended to
Fig. 3 (a) is the yaw face of volume elements and the discretization of pitch angle, is (b) matrix after discretization
Fig. 4 is the schematic diagram of Yishanmen
Specific implementation mode
Below in conjunction with the accompanying drawings, illustrate embodiments of the present invention.
Overall system architecture used in the method for the present invention can refer to Fig. 1, it is made of two subsystems, specifically comprising as follows
Step：
The first step
First, environmental characteristic indicates that system, definition distance are Euclidean distance, and setting influences distance delta=4, i.e. obstructing objects
Member only influences the volume elements within peripheral distance 4, if Fig. 2 (a) is the 3 d grid map of environment, the shadow of Fig. 2 (b) barrier volume elements
Ring vector and decomposition method：
f(xβ, θ, d)=f1+f2
=f1+f3+f4(f3With f4It is f2Component on two adjacent yaw faces)
=f '3+f′4+f3+f4(f1By f3With f4The long ratio of mould resolve into f '3With f '4)
=(f '3+f3)+(f′4+f4)
=fa+fb(faWith fbIt is equal with Z axis angle)
By shown in Fig. 3 (a) discrete to eight of the influence of volume elements yaw faces on eight pitch angles, it is discrete after matrix such as
Shown in Fig. 3 (b).
Secondly, environmental characteristic identifying system, setting deg reethreshold=5 °.
Second step
Environmental characteristic indicates system, initializes the element f of the influence matrix of each volume elementsij=0, i, j ∈ [1,8], one by one
Each volume elements in 3 d grid map is scanned, to each influence of the barrier volume elements total calculation to periphery volume elements.
For example, as shown in figure 4, barrier volume elements (1,1,1) is to the influence f (x of volume elements (2,1,1)Pi/2, π, 1)=1, to this
It influences in discretization to the yaw face of volume elements (2,1,1) and pitch angle, is apparent from f (xPi/2, π, 1) just in yaw face δπOn, and bowing
Elevation angle η5π/12With η7π/12Between, so in such a way that vector decomposes, it only need to be f (xPi/2, π, 1) project to pitch angle η5π/12With
η7π/12It is upper, f (x are known by Fig. 2 and Fig. 3Pi/2, π, 1) decompose later obtain：
Similarly, influence of the barrier volume elements (1,2,1) to volume elements (2,1,1)It is discrete to arrive yaw face
δ3π/4On pitch angle η5π/12With η7π/12On, after decomposition：
Influence of the barrier volume elements (1,3,1) to volume elements (2,1,1)It is discrete to arrive yaw face
δ3π/4With yaw face δπ/2It is respectively after upper：
Again faWith fbPitch angle η on yaw face belonging to projecting to5π/12With η7π/12On, it decomposes
Afterwards：
Influence of the barrier volume elements (1,1,2) to volume elements (2,1,1)It is discrete to arrive yaw face δπOn bow
Elevation angle ηπ/4On, after decomposition：
Influence of the barrier volume elements (1,2,2) to volume elements (2,1,1)It is discrete to arrive yaw face δ3π/4
On pitch angle ηπ/4With η5π/12On, after decomposition：
Influence of the barrier volume elements (1,3,2) to volume elements (2,1,1)It is discrete to arrive yaw face
δ3π/4With yaw face δπ/2It is respectively after upper (coordinate representation in each yaw face, do not consider directionality)：
Again faWith fbPitch angle η on yaw face belonging to projecting to5π/12With ηπ/4On, it is as follows：
After decomposition：
Influence of the barrier volume elements (1,1,3) to volume elements (2,1,1)It is discrete to arrive yaw face δπOn
Pitch angle η5π/12With ηπ/4After upper：
Influence of the barrier volume elements (1,2,3) to volume elements (2,1,1)It is discrete to arrive yaw face δ3π/4
On pitch angle ηπ/4With ηπ/12On, after decomposition：
Influence of the barrier volume elements (1,3,3) to volume elements (2,1,1)It is discrete to arrive yaw face
δ3π/4With yaw face δπ/2It is respectively after upper：
Again faWith fbPitch angle η on yaw face belonging to projecting to5π/12With ηπ/4On, it is as follows：
After decomposition：
To sum up, the influence matrix suffered by volume elements (2,1,1)
Third walks
The eigenmatrix F of the influence matrix f (2,1,1) of volume elements (2,1,1) is found out according to Fast W alsh Hadama transformation
(2,1,1), Wo Menyou：
4th step
The characteristic spectrum P (2,1,1) that volume elements (2,1,1) is found out according to Fast W alsh Hadama transformation, by the spy of previous step
Levying matrix F (2,1,1), we have：
P (2,1,1)=[0.0051,0.0001,0.0057,0.0325]
5th step
In environmental characteristic identifying system, such as we are interested in Yishanmen, we want to look on 3 d grid map
Place near to door constructs the influence matrix of this fitting of door environment first, as follows：
Similarly we have：
P (door)=s [0.0045,0.0003,0.0064,0.0336]
6th step
By environmental characteristic identifying system, entire 3 d grid map is searched for, searches and all matches with P (door)
Volume elements, such as we compare P (2,1,1) and P (door)
Cos ∠ (P (2,1,1), P (door))=0.999625 >=cos (deg reethreshold)=0.996195
Similarly, we are interested in another Yishanmen, we want to find the place near door, ring on 3 d grid map
The influence matrix in border is as follows：
Equally we have：
P ' (door)=s [0.0045,0.0003,0.0064,0.0336]
To sum up, it may be seen that characteristic spectrum P (door) and the P ' (door) of f (door) and f ' (door) is identical,
It is in the actual environment and similar, it is indicated by our environmental characteristics and identifying system, it can be these whole of " door " environment
It allots, this has just absolutely proved our system, has rotational invariance for similar environment, in the mistake of environmental characteristic identification
Cheng Zhong is considerably reduced exhaustive comparison number, and the efficiency of entire method is high, the time complexity and grid of entire method
The size of lattice map is linear.
Claims (6)
1. a kind of environmental characteristic based on 3 d grid map indicates and knows method for distinguishing, the 3 d grid map in this method is such as
Give a definition：Environment space is abstracted as three-dimensional cartesian coordinate system O：Grid space under xyz, the complete or collected works in space are Ω, in Ω
Each element is known as volume elements, uses cX, y, zIt indicates, (x, y, z) is the three-dimensional coordinate of the volume elements, and each volume elements is that a length of side is λ
Square, each edge of square is all parallel with solid axes, and according to actual environment, whether there is or not objects to occupy, to determine or generally
Determine that the duty ratio value of corresponding volume elements, the map based on this formation are known as 3 d grid map in rate meaning, λ is with being known as 3 d grid
The resolution ratio of figure；It is to be indicated by establishing the 3 d grid map of actual environment, for barrier volume elements to periphery free time volume elements
Impact analysis, the feature of volume elements is extracted, as the expression of actual environment feature, by aspect ratio to reaching the identification of environment
Purpose comprising following steps：
(1) by three-dimensional laser radar or binocular vision sensor, 3 d grid map corresponding with actual environment is established,
(2) influence of each barrier volume elements to periphery free time volume elements is analyzed one by one on grating map, as follows：
Influence of the barrier volume elements to volume elements x is denoted as f (xβ, θ, d), β ∈ [0, π ]Indicate the pitching of barrier volume elements opposite bank member x
Angle, the Z-direction of 3 d grid map is as 0 degree of prime direction of pitch angle, θ ∈ [0,2 π) indicate barrier volume elements opposite bank member
The yaw angle of x, for the X-direction of 3 d grid map as 0 degree of prime direction of yaw angle, d indicates barrier volume elements opposite bank member x
Distance, according to β, the incremental order of θ, volume elements x institutes are affected to be denoted as：
(3) discretization of f (x),
First, discrete to volume elements x institute angularly θ affected to arrive in limited yaw face;δ1, δ2..., δs], s ∈ N, each
Yaw face δ indicates one using the Z-direction where volume elements x as the half-plane on boundary, secondly, in each yaw face δ, angularly
β is discrete to [ on limited pitch angle;η1, η2..., ηn], n ∈ N, such as：
Certain influence of barrier volume elements to volume elements xWork as δi≤θk≤δi+1, i ∈ [1, s-1], k ∈ [1, s], thenYaw face δ is projected to by vector decompositioniWith yaw face δi+1On, then again respectively yaw face δiWith yaw face δi+1
Interior component projects to η by vector decomposition respectivelyjWith ηj+1On two pitch angles, after discretization,
(4) according to the impacted f (x) of institute of volume elements x, its eigenmatrix F (x) is extracted,
It is a kind of transformation, is two-dimensional fourier transform or two-dimensional walsh transform,
(5) according to the eigenmatrix F (x) of volume elements x, its characteristic spectrum P (x) with rotational invariance is calculated,
What rotational invariance here was defined as：
Matrix f (x) is n × s ranks, f (x) [i][j], i ∈ [1, n], j ∈ [1, s]Indicate the i-th row jth row in vector f (x)
Element,
Each element cycle of matrix f (x) moves down r ∈ N steps, and recycling moves to right l ∈ N steps, is denoted as frl(x),
If f (x) [i][j]=frl(x)[(i+r) %n][(j+l) %s],
Then matrix f (x) and matrix frl(x) corresponding characteristic spectrum is identical, as rotational invariance；
(6) characteristic spectrum compares,
The corresponding characteristic spectrums of influence matrix f (x) of volume elements x are P (x), and the corresponding characteristic spectrums of influence matrix f (y) of volume elements y are P
(y), a threshold angle deg ree are definedthresholdIf angle ∠ (P (x), P (y)) between vector P (x) and vector P (y)≤
deg reethresholdOr cos ∠ (P (x), P (y)) >=cos (deg reethreshold), representing matrix f (x) and f (y) is phase
As, that is, volume elements x and volume elements y is similar in the actual environment, using vector operation rule, is calculated：
With cos (deg reethreshold) relatively after, can both obtain similitude；
(7) it is compared by characteristic spectrum, finds out volume elements x similar with target volume elements y, achieve the purpose that Context awareness.
2. a kind of environmental characteristic based on 3 d grid map as described in claim 1 indicates and knows method for distinguishing, feature
It is, the influence barrier volume elements to periphery free time volume elements quantifies, the variable of this quantization function is angle or apart from structure
The expression formula made.
3. a kind of environmental characteristic based on 3 d grid map as described in claim 1 indicates and knows method for distinguishing, feature
It is, discretization or non-discretization can be considered in application, the element number after discretization, which can be limited, can also be
It is unlimited, can uniformly or non-uniform discrete, the element within discrete segment can be added to by vector decomposition both sides from
It dissipates on direction.
4. a kind of environmental characteristic based on 3 d grid map as described in claim 1 indicates and knows method for distinguishing, feature
It is, in order to which the influence matrix of volume elements is sought eigenmatrix by convenience of calculation by transformation, naturally it is also possible to not do any transformation
Operation directly is participated in influence matrix, transformation here is Fourier transformation or Walsh transformation.
5. a kind of environmental characteristic based on 3 d grid map as described in claim 1 indicates and knows method for distinguishing, feature
It is, in order to which convenience of calculation seeks the eigenmatrix of volume elements by transformation the characteristic spectrum of rotational invariance, naturally it is also possible to no
It does any transformation and directly participates in operation with eigenmatrix, transformation here is that the spectral magnitude of Fourier transformation or Walsh are converted
Power spectrum.
6. a kind of environmental characteristic based on 3 d grid map as described in claim 1 indicates and knows method for distinguishing, feature
It is, is compared by the characteristic spectrum of volume elements to find similar volume elements, comparison method is the direction cosines of vector.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510540211.9A CN105184243B (en) | 2015-08-24 | 2015-08-24 | A kind of environmental characteristic expression based on 3 d grid map and knowledge method for distinguishing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510540211.9A CN105184243B (en) | 2015-08-24 | 2015-08-24 | A kind of environmental characteristic expression based on 3 d grid map and knowledge method for distinguishing |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105184243A CN105184243A (en) | 2015-12-23 |
| CN105184243B true CN105184243B (en) | 2018-10-23 |
Family
ID=54906312
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510540211.9A Active CN105184243B (en) | 2015-08-24 | 2015-08-24 | A kind of environmental characteristic expression based on 3 d grid map and knowledge method for distinguishing |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105184243B (en) |
Families Citing this family (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106097431A (en) * | 2016-05-09 | 2016-11-09 | 王红军 | A kind of object global recognition method based on 3 d grid map |
| CN106338736B (en) * | 2016-08-31 | 2019-01-25 | 东南大学 | A kind of full 3D based on laser radar occupies volume elements terrain modeling method |
| CN107145610B (en) * | 2017-06-15 | 2021-11-26 | 北京吉瑞祥航空科技有限公司 | Digital representation and retrieval method of environment or object based on visual perception |
| CN110141164B (en) * | 2019-06-13 | 2021-08-10 | 深圳市银星智能科技股份有限公司 | Door area identification method, door area identification system and cleaning robot |
| CN110269550B (en) * | 2019-06-13 | 2021-06-08 | 深圳市银星智能科技股份有限公司 | Door position identification method and mobile robot |
| CN110763223B (en) * | 2019-10-31 | 2022-03-18 | 苏州大学 | Sliding window based indoor three-dimensional grid map feature point extraction method |
| CN110974091B (en) * | 2020-02-27 | 2020-07-17 | 深圳飞科机器人有限公司 | Cleaning robot, control method thereof, and storage medium |
| CN111368760B (en) * | 2020-03-09 | 2023-09-01 | 阿波罗智能技术(北京)有限公司 | Obstacle detection method and device, electronic equipment and storage medium |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101920498A (en) * | 2009-06-16 | 2010-12-22 | 泰怡凯电器(苏州)有限公司 | Device for realizing simultaneous positioning and map building of indoor service robot and robot |
| CN101944240A (en) * | 2010-08-20 | 2011-01-12 | 浙江大学 | Fusion method of multi-robot three-dimensional geometrical map |
| CN102402225A (en) * | 2011-11-23 | 2012-04-04 | 中国科学院自动化研究所 | Method for realizing localization and map building of mobile robot at the same time |
-
2015
- 2015-08-24 CN CN201510540211.9A patent/CN105184243B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101920498A (en) * | 2009-06-16 | 2010-12-22 | 泰怡凯电器(苏州)有限公司 | Device for realizing simultaneous positioning and map building of indoor service robot and robot |
| CN101944240A (en) * | 2010-08-20 | 2011-01-12 | 浙江大学 | Fusion method of multi-robot three-dimensional geometrical map |
| CN102402225A (en) * | 2011-11-23 | 2012-04-04 | 中国科学院自动化研究所 | Method for realizing localization and map building of mobile robot at the same time |
Non-Patent Citations (3)
| Title |
|---|
| 《基于图像配准的栅格地图拼接方法》;祝继华等;《自动化学报》;20150228;第41卷(第2期);正文第284-294页 * |
| 《基于拓扑高程模型的室外三维环境建模与路径规划》;闫飞等;《自动化学报》;20101130;第36卷(第11期);正文第1493-1501页 * |
| 《基于栅格地图的遗传算法路径规划》;徐美清等;《SCIENCE & TECHNOLOGY INFORMATION》;20111231(第31期);正文第76-77页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105184243A (en) | 2015-12-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105184243B (en) | A kind of environmental characteristic expression based on 3 d grid map and knowledge method for distinguishing | |
| Tobin et al. | Domain randomization for transferring deep neural networks from simulation to the real world | |
| Cai et al. | Autoplace: Robust place recognition with single-chip automotive radar | |
| CN106097431A (en) | A kind of object global recognition method based on 3 d grid map | |
| CN105205859B (en) | A kind of method for measuring similarity of the environmental characteristic based on 3 d grid map | |
| Rizzini | Place recognition of 3D landmarks based on geometric relations | |
| Xingteng et al. | Image matching method based on improved SURF algorithm | |
| CN105096733B (en) | A kind of environmental characteristic based on grating map is represented with knowing method for distinguishing | |
| Song et al. | Robot autonomous sorting system for intelligent logistics | |
| Harada et al. | Experiments on learning-based industrial bin-picking with iterative visual recognition | |
| Wang et al. | Robust and real-time outdoor localization only with a single 2-D LiDAR | |
| Wang et al. | LiDAR-SLAM loop closure detection based on multi-scale point cloud feature transformer | |
| Hofstetter et al. | On ambiguities in feature-based vehicle localization and their a priori detection in maps | |
| Li et al. | Exterior orientation revisited: A robust method based on lq-norm | |
| An et al. | Research on binocular vision absolute localization method for indoor robots based on natural landmarks | |
| CN105160122B (en) | A kind of method for measuring similarity of the environmental characteristic based on grating map | |
| CN113483661B (en) | Point cloud data acquisition method, device, equipment and storage medium | |
| Kuang et al. | An improved Robot’s localization and mapping method based on ORB-SLAM | |
| Hofstetter et al. | Reliable data association for feature-based vehicle localization using geometric hashing methods | |
| Mei et al. | A new spin-image based 3D Map registration algorithm using low-dimensional feature space | |
| Rambhatla et al. | TensorMap: LiDAR-based topological mapping and localization via tensor decompositions | |
| Ma et al. | Global localization in 3d maps for structured environment | |
| Horváth et al. | Object localization utilizing 3D point cloud clustering approach | |
| Sobel et al. | 3D LADAR ATR based on recognition by parts | |
| Qiang et al. | IM2DP: An intensity-based approach to loop closure detection and optimization for LiDAR mapping |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| CB02 | Change of applicant information |
Address after: 518129, Shenzhen District, Guangdong City, Bantian Longgang Vanke street, seven seasons, rue R502 room Applicant after: Wang Hongjun Address before: 518129, Shenzhen District, Guangdong City, Bantian Longgang Vanke street, seven seasons, rue N302 room Applicant before: Wang Hongjun |
|
| COR | Change of bibliographic data | ||
| CB02 | Change of applicant information | ||
| CB02 | Change of applicant information |
Address after: 518129, Guangdong City, Longgang province Shenzhen District Bantian Street Vanke City two period, autumn Tong residence A502 room Applicant after: Wang Hongjun Address before: 518129, Shenzhen District, Guangdong City, Bantian Longgang Vanke street, seven seasons, rue R502 room Applicant before: Wang Hongjun |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |