CN107091643A - A kind of indoor navigation method based on many 3D structure lights camera splicings - Google Patents
A kind of indoor navigation method based on many 3D structure lights camera splicings Download PDFInfo
- Publication number
- CN107091643A CN107091643A CN201710423104.7A CN201710423104A CN107091643A CN 107091643 A CN107091643 A CN 107091643A CN 201710423104 A CN201710423104 A CN 201710423104A CN 107091643 A CN107091643 A CN 107091643A
- Authority
- CN
- China
- Prior art keywords
- map
- robot
- pose
- many
- premeasuring
- 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.)
- Pending
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
- G01C21/206—Instruments for performing navigational calculations specially adapted for indoor navigation
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course or altitude of land, water, air, or space vehicles, e.g. automatic pilot
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0231—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means
- G05D1/0246—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means using a video camera in combination with image processing means
- G05D1/0251—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means using a video camera in combination with image processing means extracting 3D information from a plurality of images taken from different locations, e.g. stereo vision
Abstract
The invention discloses a kind of indoor navigation method based on many 3D structure lights camera splicings, comprise the following steps：Map is expressed by the way of grating map, initial map is set to sky, if the initial pose of robot is the origin of global coordinate system, during structure map, mileage is counted by robot motion model's calculating robot's pose premeasuring, observed quantity is extracted from sensing data is constantly updated using Feature Extraction Technology simultaneously, by the observation model of design, observation premeasuring is calculated by robot pose premeasuring and visual global map and obtained.The present invention carries out pose estimation using many 3D structure lights camera splicing simulated laser radar methods, and a variety of filtering algorithms based on Probability, realizes robot localization and navigation.The influence of environment is not readily susceptible to by 3D structure light camera gathered datas, and data error is small, and with the advantage of low cost, the shortcoming of laser radar can be filled up.
Description
Technical field
The present invention relates to a kind of air navigation aid, specifically a kind of indoor navigation side based on many 3D structure lights camera splicings
Method.
Background technology
Positioning and airmanship are just constantly causing the attention in industry as the first step of robot automtion in real time, in real time
Positioning and navigation refer to robot under the conditions of self-position is uncertain, map are created in totally unknown environment, simultaneously
A kind of technology of autonomous positioning and navigation is carried out using map, in the process, robot typically passes through pose estimation and ranging
Unit determines the positional information of oneself.Common range cells include laser ranging, ultrasonic sensor and image ranging
Deng.
Common range cells include laser ranging, ultrasonic sensor and image ranging etc..Laser ranging is to utilize
Laser carries out Accurate Determining to the distance of target；Ultrasonic sensor use ultrasonic echo range measurement principle, with it is accurate when
The distance between difference measurements technology, detection sensor and object.
Precision of laser ranging is relatively low and cost is high；The applicable frequency range of ultrasonic sensor ranging and sensitivity all mistakes
It is small.
The content of the invention
It is an object of the invention to provide a kind of indoor navigation method based on many 3D structure lights camera splicings, to solve
The problem of being proposed in above-mentioned background technology.
To achieve the above object, the present invention provides following technical scheme：
A kind of indoor navigation method based on many 3D structure lights camera splicings, comprises the following steps：（1）Using grating map
Mode expresses map, and initial map is set to sky, if the initial pose of robot is the origin of global coordinate system, builds map
During, mileage is counted by robot motion model's calculating robot's pose premeasuring, while using feature extraction skill
Art extracts observed quantity from sensing data is constantly updated, and by the observation model of design, observation premeasuring is by robot pose
Premeasuring and visual global map, which are calculated, to be obtained, after observed quantity and observation premeasuring is obtained, using feature association algorithm come real
Information between existing characteristic matching, matching characteristic, does not realize that pose updates and feature updates by particle filter more new formula, not
The new feature matched somebody with somebody adds global map by feature increase technology, realizes the structure of incremental map；（2）Use one group of discrete band
The Posterior distrbutionp of particle simulation robot location is weighed, and repeats status predication, update the completion of the step such as weight and resampling
Filtering, realizes the positioning of robot；（3）Optimal design is carried out to path using path planning unit, path planning unit includes
Global path planning module and local path planning module, global path planning unit are based on static map and use A* algorithm search
One optimal path or approximate optimal path from initial state to dbjective state；Local paths planning unit, based on local barrier
Hinder thing map to find the optimal trajectory in a period of time using dynamic window method, choose the speed corresponding to optimal trajectory to drive
Robot motion；（4）It is combined and spliced by ad-hoc location by many 3D structure lights cameras, to be more than in front of robot 90 degree and
Less than the obstacle detection of 6 meters of scopes, the operation of simulated laser radar is realized, the coordinate of object in investigative range is obtained, is ground
Figure, which is built, provides coordinate data, and realizes motion control while carrying out avoidance operation.
It is used as further scheme of the invention：The 3D structure lights camera is more than 2.
Compared with prior art, the beneficial effects of the invention are as follows：The present invention is using many 3D structure lights camera splicing simulations
Laser radar method, and a variety of filtering algorithms based on Probability carry out pose estimation, realize robot localization and navigation.
The influence of environment is not readily susceptible to by 3D structure light camera gathered datas, and data error is small, and with the advantage of low cost,
The shortcoming of laser radar can be filled up.
Brief description of the drawings
Fig. 1 is many camera connecting methods in the indoor navigation method based on many 3D structure lights camera splicings.
Fig. 2 is camera parallel surface naive model in the indoor navigation method based on many 3D structure lights camera splicings.
Fig. 3 is camera vertical plane naive model in the indoor navigation method based on many 3D structure lights camera splicings.
Fig. 4 is the flow chart of the indoor navigation method based on many 3D structure lights camera splicings.
Embodiment
Below in conjunction with the accompanying drawing in the embodiment of the present invention, the technical scheme in the embodiment of the present invention is carried out clear, complete
Site preparation is described, it is clear that described embodiment is only a part of embodiment of the invention, rather than whole embodiments.It is based on
Embodiment in the present invention, it is every other that those of ordinary skill in the art are obtained under the premise of creative work is not made
Embodiment, belongs to the scope of protection of the invention.
Refer in Fig. 1~4, the embodiment of the present invention, a kind of indoor navigation side based on many 3D structure lights camera splicings
Method, comprises the following steps：（1）Map is expressed by the way of grating map, initial map is set to sky, if robot is first
Beginning pose is the origin of global coordinate system, is built during map, mileage is counted by robot motion model's computer
Device people's pose premeasuring, while extracting observed quantity from sensing data is constantly updated using Feature Extraction Technology, passes through design
Observation model, observation premeasuring calculates by robot pose premeasuring and visual global map and obtained, obtain observed quantity and
Observe after premeasuring, the information between characteristic matching, matching characteristic is realized using feature association algorithm, by particle filter more
New formula realizes that pose updates and feature updates, and the new feature not matched adds global map by feature increase technology, realizes
The structure of incremental map；（2）Using the Posterior distrbutionp of one group of discrete cum rights particle simulation robot location, and repeat shape
State prediction, renewal weight and resampling etc. step complete filtering, realize the positioning of robot；（3）Using path planning unit pair
Path carries out optimal design, and path planning unit includes global path planning module and local path planning module, global path
Planning unit based on static map using optimal path of the A* algorithm search one from initial state to dbjective state or it is approximate most
Shortest path；Local paths planning unit, finds optimal in a period of time based on partial barriers map using dynamic window method
Track, chooses the speed corresponding to optimal trajectory to drive robot motion；（4）Certain bits are pressed by many 3D structure lights cameras
That puts is combined and spliced, to the obstacle detection in front of robot more than 90 degree and less than 6 meters of scopes, realizes simulated laser radar
Operation, obtains the coordinate of object in investigative range, provides coordinate data for map structuring, and realize motion control while being kept away
Barrier operation.
The 3D structure lights camera is more than 2.
, can be to more than 90 degree and small in front of robot by many 3D structure lights cameras by the combined and spliced of ad-hoc location
In the obstacle detection of 6 meters of scopes, the operation of simulated laser radar is realized.It is as shown in Figure 1 many 3D structure lights camera splicings
Mode, four 3D structure lights cameras are fixed on mechanical fastening system according to certain angle, are obtained by gridiron pattern scaling method
Rotational component R and translational component T of each camera based on central point are obtained, the depth data of many cameras is mapped to using R and T
Splice in the same coordinate system, remove two camera laps, finally give a bigger laser radar data of investigative range.Such as
Shown in Fig. 1, separate unit depth data level detection scope is 58.4 °, removes remaining adjacent cameras lap, its real level
Investigative range is 45 °.
The 3D structure lights camera horizontal direction distance measuring method, its horizontal direction angular field of view is to (different 3D structures
Light camera is different, and 3D structure lights camera here is 29.2 °).To the depth image naive model of 3D structure light cameras
Description, as shown in Fig. 2 model plane is plane parallel to the ground, the origin of coordinates is 3D structure light image centers, its correspondence picture
The width of plain plane, the barrier that camera is got from imaging plane depth value, by obtaining barrier after conversion from photocentre
The laser range value of distance.Conversion regime is as follows：For the certain point depth value of the row of row in depth image, 3D structure light phases
Machine horizontal direction scanning range, the calculation formula of its angle step is, therefore the pixel corresponds to camera coordinates system x-axis direction
Angle, thus be converted into laser point data can be to be obtained according to formula.
The 3D structure lights camera vertical direction ranging, is described to the depth image of 3D structure light cameras with naive model,
As shown in figure 3, model plane is plane perpendicular to the ground, the origin of coordinates is 3D structure light image centers, and its vertical direction is regarded
Angular region is to (different 3D structure light cameras are different, and 3D structure lights camera here is 22.5 °).Respective pixel is put down
The height in face, can set different vertical scan direction scopes, for example according to application to the height difference of vertical scan direction
It is set to -22.5 ° to 5 °.
Scanning 3D structure light camera a line all pixels carry out horizontal direction ranging calculating as described above, you can set up and work as
Preceding local environment, two laser radar functions of simulated implementation.Some rows of 3D structure light cameras can also be taken simultaneously according to actual needs
Minimum depth value is asked it to be calculated as the depth value of laser point data, you can to reach the two dimension of approximate three-dimensional radar effect
Laser radar data.
Indoor navigation method flow based on many 3D structure lights camera splicings is as follows：
1. start machine people's location navigation function.
2. system sets up initial map, and sets origin of the robot current location as global coordinate system.
3. many 3D structure lights cameras are combined and spliced by ad-hoc location, obtain and be more than 90 degree in front of robot and less than 6
The coordinate of the object of rice scope, coordinate data is provided for map structuring.
4. using A* algorithms based on static map, an optimal path or near from initial state to dbjective state is calculated
Like optimal path.
5. system by obtain odometer information to robot carry out pose estimation, and extract surrounding environment characteristic information with
Priori map carries out characteristic matching, and robot is positioned in real time using MLC localization methods.
6. in local motion, splice simulated laser radar method to robot probe's model using many 3D structure lights cameras
The barrier enclosed is identified.System carries out local paths planning, and the optimal rail in a period of time is found using dynamic window method
Mark, chooses the speed corresponding to optimal trajectory to realize motion planning and robot control while carrying out avoidance operation.
It is obvious to a person skilled in the art that the invention is not restricted to the details of above-mentioned one exemplary embodiment, Er Qie
In the case of without departing substantially from spirit or essential attributes of the invention, the present invention can be realized in other specific forms.Therefore, no matter
From the point of view of which point, embodiment all should be regarded as exemplary, and be nonrestrictive, the scope of the present invention is by appended power
Profit is required rather than described above is limited, it is intended that all in the implication and scope of the equivalency of claim by falling
Change is included in the present invention.Any reference in claim should not be considered as to the claim involved by limitation.
Moreover, it will be appreciated that although the present specification is described in terms of embodiments, not each embodiment is only wrapped
Containing an independent technical scheme, this narrating mode of specification is only that for clarity, those skilled in the art should
Using specification as an entirety, the technical solutions in the various embodiments may also be suitably combined, forms those skilled in the art
It may be appreciated other embodiment.
Claims (2)
1. a kind of indoor navigation method based on many 3D structure lights camera splicings, it is characterised in that comprise the following steps：（1）
Map structuring：Map is expressed by the way of grating map, initial map is set to sky, if the initial pose of robot is complete
The origin of office's coordinate system, builds during map, mileage is counted by pre- to robot motion model's calculating robot's pose
Measurement, while observed quantity is extracted from sensing data is constantly updated using Feature Extraction Technology, by the observation model of design,
Observation premeasuring is calculated by robot pose premeasuring and visual global map and obtained, and is obtaining observed quantity and observation premeasuring
Afterwards, the information between characteristic matching, matching characteristic is realized using feature association algorithm, is realized by particle filter more new formula
Pose updates and feature updates, and the new feature not matched adds global map by feature increase technology, realizes incremental map
Build；（2）Positioning：Using the Posterior distrbutionp of one group of discrete cum rights particle simulation robot location, and it is pre- to repeat state
Survey, update the completion filtering of the step such as weight and resampling, realize the positioning of robot；（3）Path planning：Using path planning list
Member carries out optimal design to path, and path planning unit includes global path planning module and local path planning module, global
Optimal path or near of the path planning unit based on static map using A* algorithm search one from initial state to dbjective state
Like optimal path；Local paths planning unit, is found in a period of time based on partial barriers map using dynamic window method
Optimal trajectory, chooses the speed corresponding to optimal trajectory to drive robot motion；（4）Avoidance：Pass through many 3D structure light phases
Machine is combined and spliced by ad-hoc location, to the obstacle detection in front of robot more than 90 degree and less than 6 meters of scopes, realizes simulation
The operation of laser radar, obtains the coordinate of object in investigative range, provides coordinate data for map structuring, and realize motion control
Avoidance operation is carried out simultaneously.
2. the indoor navigation method according to claim 1 based on many 3D structure lights camera splicings, it is characterised in that institute
3D structure lights camera is stated more than 2.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710423104.7A CN107091643A (en) | 2017-06-07 | 2017-06-07 | A kind of indoor navigation method based on many 3D structure lights camera splicings |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710423104.7A CN107091643A (en) | 2017-06-07 | 2017-06-07 | A kind of indoor navigation method based on many 3D structure lights camera splicings |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107091643A true CN107091643A (en) | 2017-08-25 |
Family
ID=59639202
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710423104.7A Pending CN107091643A (en) | 2017-06-07 | 2017-06-07 | A kind of indoor navigation method based on many 3D structure lights camera splicings |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107091643A (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107239076A (en) * | 2017-06-28 | 2017-10-10 | 仲训昱 | The AGV laser SLAM methods matched based on virtual scan with ranging |
| CN107911409A (en) * | 2017-10-13 | 2018-04-13 | 纳恩博（北京）科技有限公司 | The control method of loading equipment, loading equipment, server, computer-readable storage medium |
| CN108303089A (en) * | 2017-12-08 | 2018-07-20 | 浙江国自机器人技术有限公司 | Based on three-dimensional laser around barrier method |
| CN108762264A (en) * | 2018-05-22 | 2018-11-06 | 重庆邮电大学 | The dynamic obstacle avoidance method of robot based on Artificial Potential Field and rolling window |
| CN109118940A (en) * | 2018-09-14 | 2019-01-01 | 杭州国辰机器人科技有限公司 | A kind of mobile robot composition based on map splicing |
| CN109144056A (en) * | 2018-08-02 | 2019-01-04 | 上海思岚科技有限公司 | The global method for self-locating and equipment of mobile robot |
| CN111801635A (en) * | 2017-11-22 | 2020-10-20 | 轨迹机器人公司 | Robot charger docking control |
| CN111932675A (en) * | 2020-10-16 | 2020-11-13 | 北京猎户星空科技有限公司 | Map building method and device, self-moving equipment and storage medium |
| CN113506344A (en) * | 2021-07-07 | 2021-10-15 | 西南科技大学 | High-precision three-dimensional positioning device and method for nuclear radiation environment robot |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101694521A (en) * | 2009-10-12 | 2010-04-14 | 茂名学院 | Target predicting and tracking method based on probability graph model |
| 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 |
| CN102175222A (en) * | 2011-03-04 | 2011-09-07 | 南开大学 | Crane obstacle-avoidance system based on stereoscopic vision |
| CN103400392A (en) * | 2013-08-19 | 2013-11-20 | 山东鲁能智能技术有限公司 | Binocular vision navigation system and method based on inspection robot in transformer substation |
| CN103413313A (en) * | 2013-08-19 | 2013-11-27 | 国家电网公司 | Binocular vision navigation system and method based on power robot |
| CN103679707A (en) * | 2013-11-26 | 2014-03-26 | 西安交通大学 | Binocular camera disparity map based road obstacle detection system and method |
| CN104134188A (en) * | 2014-07-29 | 2014-11-05 | 湖南大学 | Three-dimensional visual information acquisition method based on two-dimensional and three-dimensional video camera fusion |
| CN105045263A (en) * | 2015-07-06 | 2015-11-11 | 杭州南江机器人股份有限公司 | Kinect-based robot self-positioning method |
| CN105955273A (en) * | 2016-05-25 | 2016-09-21 | 速感科技（北京）有限公司 | Indoor robot navigation system and method |
| CN106681353A (en) * | 2016-11-29 | 2017-05-17 | 南京航空航天大学 | Unmanned aerial vehicle (UAV) obstacle avoidance method and system based on binocular vision and optical flow fusion |
| CN106708084A (en) * | 2016-11-24 | 2017-05-24 | 中国科学院自动化研究所 | Method for automatically detecting and avoiding obstacles for unmanned aerial vehicle under complicated environments |
| CN106780618A (en) * | 2016-11-24 | 2017-05-31 | 周超艳 | 3 D information obtaining method and its device based on isomery depth camera |
-
2017
- 2017-06-07 CN CN201710423104.7A patent/CN107091643A/en active Pending
Patent Citations (12)
| 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 |
| CN101694521A (en) * | 2009-10-12 | 2010-04-14 | 茂名学院 | Target predicting and tracking method based on probability graph model |
| CN102175222A (en) * | 2011-03-04 | 2011-09-07 | 南开大学 | Crane obstacle-avoidance system based on stereoscopic vision |
| CN103400392A (en) * | 2013-08-19 | 2013-11-20 | 山东鲁能智能技术有限公司 | Binocular vision navigation system and method based on inspection robot in transformer substation |
| CN103413313A (en) * | 2013-08-19 | 2013-11-27 | 国家电网公司 | Binocular vision navigation system and method based on power robot |
| CN103679707A (en) * | 2013-11-26 | 2014-03-26 | 西安交通大学 | Binocular camera disparity map based road obstacle detection system and method |
| CN104134188A (en) * | 2014-07-29 | 2014-11-05 | 湖南大学 | Three-dimensional visual information acquisition method based on two-dimensional and three-dimensional video camera fusion |
| CN105045263A (en) * | 2015-07-06 | 2015-11-11 | 杭州南江机器人股份有限公司 | Kinect-based robot self-positioning method |
| CN105955273A (en) * | 2016-05-25 | 2016-09-21 | 速感科技（北京）有限公司 | Indoor robot navigation system and method |
| CN106708084A (en) * | 2016-11-24 | 2017-05-24 | 中国科学院自动化研究所 | Method for automatically detecting and avoiding obstacles for unmanned aerial vehicle under complicated environments |
| CN106780618A (en) * | 2016-11-24 | 2017-05-31 | 周超艳 | 3 D information obtaining method and its device based on isomery depth camera |
| CN106681353A (en) * | 2016-11-29 | 2017-05-17 | 南京航空航天大学 | Unmanned aerial vehicle (UAV) obstacle avoidance method and system based on binocular vision and optical flow fusion |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107239076B (en) * | 2017-06-28 | 2020-06-23 | 仲训昱 | AGV laser SLAM method based on virtual scanning and distance measurement matching |
| CN107239076A (en) * | 2017-06-28 | 2017-10-10 | 仲训昱 | The AGV laser SLAM methods matched based on virtual scan with ranging |
| CN107911409A (en) * | 2017-10-13 | 2018-04-13 | 纳恩博（北京）科技有限公司 | The control method of loading equipment, loading equipment, server, computer-readable storage medium |
| CN111801635B (en) * | 2017-11-22 | 2023-10-13 | 轨迹机器人公司 | Robot charger docking control |
| CN111801635A (en) * | 2017-11-22 | 2020-10-20 | 轨迹机器人公司 | Robot charger docking control |
| CN108303089A (en) * | 2017-12-08 | 2018-07-20 | 浙江国自机器人技术有限公司 | Based on three-dimensional laser around barrier method |
| CN108762264A (en) * | 2018-05-22 | 2018-11-06 | 重庆邮电大学 | The dynamic obstacle avoidance method of robot based on Artificial Potential Field and rolling window |
| CN108762264B (en) * | 2018-05-22 | 2021-05-04 | 重庆邮电大学 | Dynamic obstacle avoidance method of robot based on artificial potential field and rolling window |
| CN109144056A (en) * | 2018-08-02 | 2019-01-04 | 上海思岚科技有限公司 | The global method for self-locating and equipment of mobile robot |
| CN109144056B (en) * | 2018-08-02 | 2021-07-06 | 上海思岚科技有限公司 | Global self-positioning method and device for mobile robot |
| CN109118940A (en) * | 2018-09-14 | 2019-01-01 | 杭州国辰机器人科技有限公司 | A kind of mobile robot composition based on map splicing |
| CN111932675A (en) * | 2020-10-16 | 2020-11-13 | 北京猎户星空科技有限公司 | Map building method and device, self-moving equipment and storage medium |
| CN111932675B (en) * | 2020-10-16 | 2020-12-29 | 北京猎户星空科技有限公司 | Map building method and device, self-moving equipment and storage medium |
| CN113506344A (en) * | 2021-07-07 | 2021-10-15 | 西南科技大学 | High-precision three-dimensional positioning device and method for nuclear radiation environment robot |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107091643A (en) | A kind of indoor navigation method based on many 3D structure lights camera splicings | |
| CN111108342B (en) | Visual range method and pair alignment for high definition map creation | |
| CN106066645B (en) | The method of scaling terrain information and the control system of bull-dozer are generated when operating bull-dozer | |
| CN111492403A (en) | Lidar to camera calibration for generating high definition maps | |
| US9330504B2 (en) | 3D building model construction tools | |
| Montemerlo et al. | Large-scale robotic 3-d mapping of urban structures | |
| CN113906414A (en) | Distributed processing for generating pose maps for high definition maps for navigating autonomous vehicles | |
| CN107656545A (en) | A kind of automatic obstacle avoiding searched and rescued towards unmanned plane field and air navigation aid | |
| CN107167139A (en) | A kind of Intelligent Mobile Robot vision positioning air navigation aid and system | |
| Abuhadrous et al. | Digitizing and 3D modeling of urban environments and roads using vehicle-borne laser scanner system | |
| Levinson | Automatic laser calibration, mapping, and localization for autonomous vehicles | |
| Gruen et al. | Joint processing of UAV imagery and terrestrial mobile mapping system data for very high resolution city modeling | |
| CN112833892B (en) | Semantic mapping method based on track alignment | |
| Karam et al. | Integrating a low-cost mems imu into a laser-based slam for indoor mobile mapping | |
| Soheilian et al. | Generation of an integrated 3D city model with visual landmarks for autonomous navigation in dense urban areas | |
| RU2562368C1 (en) | Three-dimensional (3d) mapping method | |
| Wysocki et al. | Unlocking point cloud potential: Fusing MLS point clouds with semantic 3D building models while considering uncertainty | |
| CN112146627B (en) | Aircraft imaging system using projection patterns on featureless surfaces | |
| CN116380039A (en) | Mobile robot navigation system based on solid-state laser radar and point cloud map | |
| Huang et al. | Integration of mobile laser scanning data with UAV imagery for very high resolution 3D city modeling | |
| Wei | Multi-sources fusion based vehicle localization in urban environments under a loosely coupled probabilistic framework | |
| Wu et al. | An Assessment of Errors Using Unconventional Photogrammetric Measurement Technology-with UAV Photographic Images as an Example | |
| Uno et al. | Deep Inertial Underwater Odometry System. | |
| Ernst et al. | Large-scale 3D Roadside Modelling with Road Geometry Analysis: Digital Roads New Zealand | |
| Typiak et al. | Map Building System for Unmanned Ground Vehicle |
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 | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20190617 Address after: 518055 Guangdong 28, Shenzhen, Futian District, Huafu street, No. 5001 Huanggang Road, Shenzhen Industrial upper city (two phase of the Southern District) Applicant after: Shenzhen Sanbao innovation and intelligence Co., Ltd. Address before: 518055 the 32-33 floor of block B, CNOOC building, Nanshan District Houhai road and Chuang Road Interchange, Shenzhen, Guangdong. Applicant before: Qihan Technology Co., Ltd. |
|
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20200514 Address after: Room 2803, building T2, Shenye Shangcheng (South District), No. 5001, Huanggang Road, Lianhua village, Huafu street, Futian District, Shenzhen City, Guangdong Province Applicant after: Shenzhen Sanbao innovation robot Co., Ltd Address before: 518055 Guangdong 28, Shenzhen, Futian District, Huafu street, No. 5001 Huanggang Road, Shenzhen Industrial upper city (two phase of the Southern District) Applicant before: Qihan Technology Co.,Ltd. |
|
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170825 |