CN109556611A - A kind of fusion and positioning method based on figure optimization and particle filter - Google Patents
A kind of fusion and positioning method based on figure optimization and particle filter Download PDFInfo
- Publication number
- CN109556611A CN109556611A CN201811459729.XA CN201811459729A CN109556611A CN 109556611 A CN109556611 A CN 109556611A CN 201811459729 A CN201811459729 A CN 201811459729A CN 109556611 A CN109556611 A CN 109556611A
- Authority
- CN
- China
- Prior art keywords
- particle
- optimization
- map
- robot
- pose
- 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.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/20—Instruments for performing navigational calculations
Landscapes
- Engineering & Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Automation & Control Theory (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
Abstract
The invention belongs to the synchronous positioning of mobile robot and building field map (SLAM), more particularly to a kind of fusion and positioning method based on figure optimization and particle filter, in this way, making robot that can fast and accurately complete to relocate in big map.Method based on figure optimization generates the sub- map with abundant local message, and is screened according to sub- map to the particle for sampling generation in global map, largely reduces the region of particle distribution, accelerates the convergence rate of particle in repositioning process；Secondly, being clustered to the particle after screening, and new particle is generated according to cluster result again stochastical sampling and ensure that particle collection can cover true pose well, to make robot that can fast and accurately complete to relocate in big map.
Description
Technical field
The invention belongs to the synchronous positioning of mobile robot and building field map (SLAM), and in particular to one kind is based on figure
The fusion and positioning method of optimization and particle filter.
Background technique
Omni-directional mobile robots are able to achieve the movement of any direction, can be widely applied to the neck such as military affairs, industry, home-care service
Domain.Positioning and map building (SLAM, SimultaneousLocalizationAndMapping) are while mobile robot
The hot research problem of robot field, it is the premise and basis of mobile robot self-service mission planning and path planning.Machine
The SLAM problem of device people is briefly exactly in a unknown environment, and mobile robot needs to establish environmental map, and
Itself is positioned while on map.This process is similar to people and goes in a completely strange environment, is not carrying any energy
In the case of the equipment for enough determining position and direction, ring can only be recognized according to the observation to ambient enviroment and to the estimation of displacement
Border and the position for determining oneself.SLAM is substantially that (including the current pose of robot and all maps are special for a system mode
Levy position etc.) estimation problem.From this angle, method for solving can be roughly divided into method based on Kalman filter, be based on
The method of particle filter, 3 class of method based on figure optimization.Based on the localization method of particle filter in currently existing scheme: passing through
Motion model carries out sampling to robot pose and generates a large amount of particles, and the weight of the observed result more new particle according to sensor is simultaneously
Resampling is carried out, continuous iteration restrains particle.The shortcomings that prior art: in big map, the reorientation based on particle filter
Convergence rate is slow, and if particle assembly does not cover true pose well, final particle will not converge to correct position
Appearance.
Summary of the invention
In order to solve technological deficiency existing in the prior art, the invention proposes one kind based on figure optimization and particle filter
Fusion and positioning method, by figure optimization and particle filter fusion position, enable reorientation of the robot in big map
Quickly converge to correct pose.
The invention is realized by the following technical scheme:
A kind of fusion and positioning method based on figure optimization and particle filter, includes the following steps:
S1: the method based on figure optimization generates sub- map；
S2: overall situation sampling generates particle collection, and all free spaces in map, which carry out stochastical sampling generation, indicates machine
The particle collection of people's pose；
S3: particle sizing；
S4: particle cluster；
S5: particle resampling；
S6: according to motion model more new particle collection；
S7: particle weights are updated；
S8: resampling is carried out to particle according to particle weights, and resets weight；
S9: jumping to S6 until particle is restrained, and seeking weighted average to convergent particle is final positioning result.
Further, the method based on figure optimization in the step S1 generates sub- map, further comprises,
1) robot rotates in place one week, records robot pose x in motion process according to robot motion model1:tWith
Observation z under the pose1:t, laser point cloud data is observation；
2) structure figures, using the pose of robot as vertex, that is, the variable for needing to optimize, with robot motion model and sight
The constraint of model is surveyed as side, then has objective function as follows:
X in formula0For initial pose, Ω0For initial pose covariance, g (ut,xt-1) it is robot motion model, utFor control
Amount processed, RtFor motion artifacts covariance, h (mt,xt) it is observation model, mtFor map feature, QtFor observation noise covariance；
3) optimization figure, optimizes by figure of the optimized variable to building of vertex, thus the robot position after being optimized
Appearance；
4) according to the robot pose and the sub- map of laser point cloud data generation after optimization.
Further, the optimization figure in the step 3) further comprises: adjusting each moment robot pose x1:t, make
Its constraint for meeting side as far as possible, even if also objective function J is minimized.
Further, the particle sizing in the step S3 further comprises, according to the pose of each particle, by S1
In sub- map maps into global map, retain the high particle of matching degree, the low particle of removal matching degree.
Further, the particle cluster in the step S4 further comprises hierarchical clustering algorithm being based on, in Step3
The particle of reservation is clustered, and cluster result is denoted as X={ X1,X2,…,Xn, wherein n is categorical measure.
Further, the particle resampling in the step S5 further comprises, by the particle after clustering in S4, difference
It averages to obtainExisted based on Gaussian ProfileMiddle pose nearby samples and generates new particle collection, is denoted as:
Wherein, particle weights are initialized as
Further, the more new particle collection in the step S6 further comprises updating particle shape according to motion model
State, i.e.,
In formula, utFor motion control amount, vtFor noise.
Further, the update grain weight in the step S7 further comprises, according to the pose of each particle, inciting somebody to action
Present laser point cloud data maps to global map, updates particle weights according to matching degree, i.e. the high particle of matching degree obtains
Big weight is obtained, the low particle of matching degree obtains small weight；Normalized weight has:
Further, resetting weight in the step S8 is
The invention also includes a kind of non-volatile memory mediums comprising one or more computer instruction, described one
Or a plurality of computer instruction realizes above-mentioned fusion and positioning method when being executed.
Compared with prior art, the present invention at least has the following beneficial effects or advantage: this programme passes through excellent based on scheming
Change the fusion and positioning method with particle filter, makes robot that can fast and accurately complete to relocate in big map.Firstly, base
The sub- map with abundant local message is generated in the method for figure optimization, and sampling in global map is generated according to sub- map
Particle is screened, and the region of particle distribution is largely reduced, and accelerates the convergence rate of particle in repositioning process；Its
It is secondary, the particle after screening is clustered, and new particle is generated according to cluster result again stochastical sampling and ensure that particle collection energy
It is enough to cover true pose well, to make robot that can fast and accurately complete to relocate in big map.
Specific embodiment
The following is a clear and complete description of the technical scheme in the embodiments of the invention, it is clear that described embodiment
It is a part of the embodiment of the present invention, instead of all the embodiments.Based on the embodiments of the present invention, ordinary skill people
Member's every other embodiment obtained without making creative work, shall fall within the protection scope of the present invention.
The present invention relates to the fusion and positioning methods based on figure optimization and particle filter, specifically comprise the following steps:
Step1: the method based on figure optimization generates sub- map.
Robot rotates in place one week, often receives a frame laser data, then the current pose and laser point of recorder people
Cloud data.Building is using the pose of robot as vertex, figure of the position orientation relation as side.Laser point cloud data under each pose
It is then observed quantity.It is optimized by figure of the optimized variable to building of vertex, thus the robot pose after being optimized, finally
Sub- map is generated according to robot pose and laser point cloud data.
Robot rotates in place one week, records robot pose x in motion process according to robot motion model1:tAnd this
Observation z under pose1:t.Laser point cloud data is observation.
Structure figures first, using the pose of robot as vertex, that is, the variable for needing to optimize, with robot motion model and
The constraint of observation model then has objective function as follows as side:
X in formula0For initial pose, Ω0For initial pose covariance, g (ut,xt-1) it is robot motion model, utFor control
Amount processed, RtFor motion artifacts covariance, h (mt,xt) it is observation model, mtFor map feature, QtFor observation noise covariance.
Then optimization figure, that is, adjust each moment robot pose x1:t, so that it is met the constraint on side as far as possible, even if also mesh
Scalar functions J is minimized.Finally with the robot pose and the sub- map of corresponding laser point cloud data generation after optimization.
Step2: overall situation sampling generates particle collection
All free spaces in map carry out stochastical sampling and generate the particle collection for indicating robot pose.
Step3: particle sizing
According to the pose of each particle, by the sub- map maps in Step1 into global map, retain matching degree
High particle, the low particle of removal matching degree
Step4: particle cluster
Based on hierarchical clustering algorithm, the particle retained in Step3 is clustered, cluster result is denoted as X={ X1,X2,…,
Xn, wherein n is categorical measure.
Step5: particle resampling
By the particle after clustering in Step4, average to obtain respectivelyExisted based on Gaussian Profile
Middle pose nearby samples and generates new particle collection, is denoted as
Wherein, particle weights are initialized as
Step6: more new particle collection:
Particle state is updated according to motion model, i.e.,
In formula, utFor motion control amount, vtFor noise.
Step7: particle weights are updated
According to the pose of each particle, present laser point cloud data is mapped into global map, more according to matching degree
The high particle of new particle weight, i.e. matching degree obtains big weight, and the low particle of matching degree obtains small weight.Then it normalizes
Weight has
Step8: resampling is carried out to particle according to particle weights, and resets weight and is
Step9: jumping to Step6 until particle is restrained, and seeking weighted average to convergent particle is final positioning result.
The present invention also provides a kind of non-volatile memory mediums comprising one or more computer instruction, described one
Item or a plurality of computer instruction realize above-mentioned fusion and positioning method when being executed.
Particular embodiments described above has carried out further in detail the purpose of the present invention, technical scheme and beneficial effects
Describe in detail it is bright, it should be understood that the above is only a specific embodiment of the present invention, the guarantor being not intended to limit the present invention
Protect range.Without departing from the spirit and scope of the invention, any modification, equivalent substitution, improvement and etc. done also belong to this
Within the protection scope of invention.
Claims (10)
1. a kind of fusion and positioning method based on figure optimization and particle filter, which comprises the steps of:
S1: the method based on figure optimization generates sub- map；
S2: overall situation sampling generates particle collection, and all free spaces in map, which carry out stochastical sampling generation, indicates robot position
The particle collection of appearance；
S3: particle sizing；
S4: particle cluster；
S5: particle resampling；
S6: according to motion model more new particle collection；
S7: particle weights are updated；
S8: resampling is carried out to particle according to particle weights, and resets weight；
S9: jumping to S6 until particle is restrained, and seeking weighted average to convergent particle is final positioning result.
2. the fusion and positioning method according to claim 1 based on figure optimization and particle filter, which is characterized in that the step
Method based on figure optimization in rapid S1 generates sub- map, further comprises,
1) robot rotates in place one week, records robot pose x in motion process according to robot motion model1:tWith the position
Observation z under appearance1:t, laser point cloud data is observation；
2) structure figures, using the pose of robot as vertex, that is, the variable for needing to optimize, with robot motion model and observation mould
The constraint of type then has objective function as follows as side:
X in formula0For initial pose, Ω0For initial pose covariance, g (ut,xt-1) it is robot motion model, utFor control amount,
RtFor motion artifacts covariance, h (mt,xt) it is observation model, mtFor map feature, QtFor observation noise covariance；
3) optimization figure, optimizes by figure of the optimized variable to building of vertex, thus the robot pose after being optimized；
4) according to the robot pose and the sub- map of laser point cloud data generation after optimization.
3. the fusion and positioning method according to claim 2 based on figure optimization and particle filter, which is characterized in that the step
It is rapid 3) in optimization figure further comprise: adjust each moment robot pose x1:t, so that it is met the constraint on side as far as possible, namely
Minimize objective function J.
4. the fusion and positioning method according to claim 3 based on figure optimization and particle filter, which is characterized in that the step
Particle sizing in rapid S3 further comprises, according to the pose of each particle, by the sub- map maps in S1 to global map
In.
5. the fusion and positioning method according to claim 4 based on figure optimization and particle filter, which is characterized in that the step
Particle cluster in rapid S4 further comprises being based on hierarchical clustering algorithm, clustering to the particle retained in Step3, clusters
As a result it is denoted as X={ X1,X2,...,Xn, wherein n is categorical measure.
6. the fusion and positioning method according to claim 5 based on figure optimization and particle filter, which is characterized in that the step
Particle resampling in rapid S5 further comprises, by the particle after clustering in S4, averaging to obtain respectivelyExisted based on Gaussian ProfileMiddle pose nearby samples and generates new particle collection, is denoted as:
Wherein, particle weights are initialized as
7. the fusion and positioning method according to claim 6 based on figure optimization and particle filter, which is characterized in that the step
More new particle collection in rapid S6 further comprises updating particle state according to motion model, i.e.,
In formula, utFor motion control amount, vtFor noise.
8. the fusion and positioning method according to claim 7 based on figure optimization and particle filter, which is characterized in that the step
Update grain weight in rapid S7, further comprises, according to the pose of each particle, present laser point cloud data being mapped to entirely
Local figure updates particle weights according to matching degree, i.e. the high particle of matching degree obtains big weight, the low particle of matching degree
Obtain small weight；Normalized weight has:
9. the fusion and positioning method according to claim 8 based on figure optimization and particle filter, which is characterized in that the step
Resetting weight in rapid S8 is
10. a kind of non-volatile memory medium, which is characterized in that including one or more computer instruction, described one or more
Computer instruction realizes the described in any item methods of the claims 1-9 when being executed.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811459729.XA CN109556611B (en) | 2018-11-30 | 2018-11-30 | Fusion positioning method based on graph optimization and particle filtering |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811459729.XA CN109556611B (en) | 2018-11-30 | 2018-11-30 | Fusion positioning method based on graph optimization and particle filtering |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109556611A true CN109556611A (en) | 2019-04-02 |
| CN109556611B CN109556611B (en) | 2020-11-10 |
Family
ID=65868342
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811459729.XA Active CN109556611B (en) | 2018-11-30 | 2018-11-30 | Fusion positioning method based on graph optimization and particle filtering |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109556611B (en) |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110260855A (en) * | 2019-06-24 | 2019-09-20 | 北京壹氢科技有限公司 | A kind of indoor pedestrian navigation localization method merging pedestrian's dead reckoning, Geomagnetism Information and indoor map information |
| CN110263905A (en) * | 2019-05-31 | 2019-09-20 | 上海电力学院 | Robot localization based on firefly optimized particle filter and build drawing method and device |
| CN110598804A (en) * | 2019-10-14 | 2019-12-20 | 安徽理工大学 | Improved FastSLAM algorithm based on clustering and membrane calculation |
| CN110645998A (en) * | 2019-09-10 | 2020-01-03 | 上海交通大学 | Dynamic object-free map segmentation establishing method based on laser point cloud |
| CN110749901A (en) * | 2019-10-12 | 2020-02-04 | 劢微机器人科技(深圳)有限公司 | Autonomous mobile robot, map splicing method and device thereof, and readable storage medium |
| CN110954113A (en) * | 2019-05-30 | 2020-04-03 | 北京初速度科技有限公司 | Vehicle pose correction method and device |
| CN111061287A (en) * | 2019-12-31 | 2020-04-24 | 芜湖哈特机器人产业技术研究院有限公司 | Mobile robot repositioning method based on particle self-convergence |
| CN111061276A (en) * | 2019-12-31 | 2020-04-24 | 芜湖哈特机器人产业技术研究院有限公司 | Mobile robot repositioning method based on dynamic area division |
| CN111369640A (en) * | 2020-02-28 | 2020-07-03 | 广州高新兴机器人有限公司 | Multi-robot graph establishing method and system, computer storage medium and electronic equipment |
| CN112070201A (en) * | 2020-08-26 | 2020-12-11 | 成都睿芯行科技有限公司 | Method for increasing mapping speed based on Gmapping |
| CN112097772A (en) * | 2020-08-20 | 2020-12-18 | 深圳市优必选科技股份有限公司 | Robot and map construction method and device thereof |
| WO2022068274A1 (en) * | 2020-09-30 | 2022-04-07 | 华为技术有限公司 | Positioning method, apparatus and system |
| CN114485607A (en) * | 2021-12-02 | 2022-05-13 | 陕西欧卡电子智能科技有限公司 | Method for determining motion track, operation equipment, device and storage medium |
| TWI822423B (en) * | 2022-07-22 | 2023-11-11 | 杜宇威 | Computing apparatus and model generation method |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103901895A (en) * | 2014-04-18 | 2014-07-02 | 江苏久祥汽车电器集团有限公司 | Target positioning method based on unscented FastSLAM algorithm and matching optimization and robot |
| CN107246873A (en) * | 2017-07-03 | 2017-10-13 | 哈尔滨工程大学 | A kind of method of the mobile robot simultaneous localization and mapping based on improved particle filter |
| CN107680133A (en) * | 2017-09-15 | 2018-02-09 | 重庆邮电大学 | A kind of mobile robot visual SLAM methods based on improvement closed loop detection algorithm |
| US20180077534A1 (en) * | 2016-09-13 | 2018-03-15 | Google Inc. | Systems and Methods for Graph-Based Localization and Mapping |
| CN108303710A (en) * | 2018-06-12 | 2018-07-20 | 江苏中科院智能科学技术应用研究院 | Drawing method is built in the more scene positioning of unmanned plane based on three-dimensional laser radar |
-
2018
- 2018-11-30 CN CN201811459729.XA patent/CN109556611B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103901895A (en) * | 2014-04-18 | 2014-07-02 | 江苏久祥汽车电器集团有限公司 | Target positioning method based on unscented FastSLAM algorithm and matching optimization and robot |
| US20180077534A1 (en) * | 2016-09-13 | 2018-03-15 | Google Inc. | Systems and Methods for Graph-Based Localization and Mapping |
| CN107246873A (en) * | 2017-07-03 | 2017-10-13 | 哈尔滨工程大学 | A kind of method of the mobile robot simultaneous localization and mapping based on improved particle filter |
| CN107680133A (en) * | 2017-09-15 | 2018-02-09 | 重庆邮电大学 | A kind of mobile robot visual SLAM methods based on improvement closed loop detection algorithm |
| CN108303710A (en) * | 2018-06-12 | 2018-07-20 | 江苏中科院智能科学技术应用研究院 | Drawing method is built in the more scene positioning of unmanned plane based on three-dimensional laser radar |
Non-Patent Citations (1)
| Title |
|---|
| 刘志: "基于多传感器的导盲机器人同时定位与地图构建", 《中国优秀硕士学位论文全文库》 * |
Cited By (23)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110954113A (en) * | 2019-05-30 | 2020-04-03 | 北京初速度科技有限公司 | Vehicle pose correction method and device |
| CN110954113B (en) * | 2019-05-30 | 2021-10-15 | 北京初速度科技有限公司 | Vehicle pose correction method and device |
| CN110263905A (en) * | 2019-05-31 | 2019-09-20 | 上海电力学院 | Robot localization based on firefly optimized particle filter and build drawing method and device |
| CN110260855A (en) * | 2019-06-24 | 2019-09-20 | 北京壹氢科技有限公司 | A kind of indoor pedestrian navigation localization method merging pedestrian's dead reckoning, Geomagnetism Information and indoor map information |
| CN110645998A (en) * | 2019-09-10 | 2020-01-03 | 上海交通大学 | Dynamic object-free map segmentation establishing method based on laser point cloud |
| CN110749901A (en) * | 2019-10-12 | 2020-02-04 | 劢微机器人科技(深圳)有限公司 | Autonomous mobile robot, map splicing method and device thereof, and readable storage medium |
| CN110749901B (en) * | 2019-10-12 | 2022-03-18 | 劢微机器人科技(深圳)有限公司 | Autonomous mobile robot, map splicing method and device thereof, and readable storage medium |
| CN110598804A (en) * | 2019-10-14 | 2019-12-20 | 安徽理工大学 | Improved FastSLAM algorithm based on clustering and membrane calculation |
| CN110598804B (en) * | 2019-10-14 | 2023-05-09 | 安徽理工大学 | Improved FastSLAM method based on clustering and membrane calculation |
| CN111061287A (en) * | 2019-12-31 | 2020-04-24 | 芜湖哈特机器人产业技术研究院有限公司 | Mobile robot repositioning method based on particle self-convergence |
| CN111061276A (en) * | 2019-12-31 | 2020-04-24 | 芜湖哈特机器人产业技术研究院有限公司 | Mobile robot repositioning method based on dynamic area division |
| CN111061287B (en) * | 2019-12-31 | 2022-05-27 | 芜湖哈特机器人产业技术研究院有限公司 | Mobile robot repositioning method based on particle self-convergence |
| CN111061276B (en) * | 2019-12-31 | 2022-07-26 | 芜湖哈特机器人产业技术研究院有限公司 | Mobile robot repositioning method based on dynamic area division |
| CN111369640B (en) * | 2020-02-28 | 2024-03-26 | 广州高新兴机器人有限公司 | Multi-robot mapping method, system, computer storage medium and electronic equipment |
| CN111369640A (en) * | 2020-02-28 | 2020-07-03 | 广州高新兴机器人有限公司 | Multi-robot graph establishing method and system, computer storage medium and electronic equipment |
| CN112097772A (en) * | 2020-08-20 | 2020-12-18 | 深圳市优必选科技股份有限公司 | Robot and map construction method and device thereof |
| CN112097772B (en) * | 2020-08-20 | 2022-06-28 | 深圳市优必选科技股份有限公司 | Robot and map construction method and device thereof |
| WO2022036981A1 (en) * | 2020-08-20 | 2022-02-24 | 深圳市优必选科技股份有限公司 | Robot, and map construction method and device thereof |
| CN112070201A (en) * | 2020-08-26 | 2020-12-11 | 成都睿芯行科技有限公司 | Method for increasing mapping speed based on Gmapping |
| WO2022068274A1 (en) * | 2020-09-30 | 2022-04-07 | 华为技术有限公司 | Positioning method, apparatus and system |
| CN114485607A (en) * | 2021-12-02 | 2022-05-13 | 陕西欧卡电子智能科技有限公司 | Method for determining motion track, operation equipment, device and storage medium |
| CN114485607B (en) * | 2021-12-02 | 2023-11-10 | 陕西欧卡电子智能科技有限公司 | Method, operation equipment, device and storage medium for determining motion trail |
| TWI822423B (en) * | 2022-07-22 | 2023-11-11 | 杜宇威 | Computing apparatus and model generation method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109556611B (en) | 2020-11-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109556611A (en) | A kind of fusion and positioning method based on figure optimization and particle filter | |
| CN110645974B (en) | Mobile robot indoor map construction method fusing multiple sensors | |
| US11830137B2 (en) | Automated three-dimensional building model estimation | |
| US11521022B2 (en) | Semantic state based sensor tracking and updating | |
| Zhao et al. | Learning-based bias correction for time difference of arrival ultra-wideband localization of resource-constrained mobile robots | |
| US10915673B2 (en) | Device, method, apparatus, and computer-readable medium for solar site assessment | |
| CN109798896A (en) | A kind of positioning of Indoor Robot with build drawing method and device | |
| CN108426582B (en) | Indoor three-dimensional map matching method for pedestrians | |
| Geng et al. | UAV surveillance mission planning with gimbaled sensors | |
| CN103533647A (en) | Radio frequency map self-adaption positioning method based on clustering mechanism and robust regression | |
| Schadler et al. | Multi-resolution surfel mapping and real-time pose tracking using a continuously rotating 2D laser scanner | |
| Sai et al. | A comprehensive survey on artificial intelligence for unmanned aerial vehicles | |
| Li et al. | A new RSS fingerprinting-based location discovery method under sparse reference point conditions | |
| CN111811502A (en) | Motion carrier multi-source information fusion navigation method and system | |
| CN111123953A (en) | Particle-based mobile robot group under artificial intelligence big data and control method thereof | |
| CN113050658A (en) | SLAM algorithm based on lion group algorithm optimization | |
| CN106950833B (en) | Based on the attitude of satellite dynamic programming method for improving PIO algorithm | |
| Sertthin et al. | On physical layer simulation model for 6-axis sensor assisted VLC based positioning system | |
| CN114415661B (en) | Planar laser SLAM and navigation method based on compressed three-dimensional space point cloud | |
| Yang | Research on key technologies of UAV navigation and positioning system | |
| CN113671511A (en) | Laser radar high-precision positioning method for regional scene | |
| Chen et al. | An optimized method for wireless sensor localization using heuristic-based adaptive particle swarm fusion | |
| CN118604865B (en) | Agricultural machinery positioning method based on field information constraint | |
| Palmer et al. | Detection of roof shading for PV based on LiDAR data using a multi-modal approach | |
| Zhang et al. | Research on formation control method of Multi-Automated Guided Vehicle 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 | ||
| PE01 | Entry into force of the registration of the contract for pledge of patent right |
Denomination of invention: A fusion localization method based on graph optimization and particle filter Effective date of registration: 20210615 Granted publication date: 20201110 Pledgee: Bank of China Limited by Share Ltd. Guangzhou Tianhe branch Pledgor: GUANGZHOU GOSUNCN ROBOT Co.,Ltd. Registration number: Y2021440000203 |
|
| PE01 | Entry into force of the registration of the contract for pledge of patent right |