CN110220517A - A kind of Indoor Robot robust slam method of the combining environmental meaning of one's words - Google Patents
A kind of Indoor Robot robust slam method of the combining environmental meaning of one's words Download PDFInfo
- Publication number
- CN110220517A CN110220517A CN201910610069.9A CN201910610069A CN110220517A CN 110220517 A CN110220517 A CN 110220517A CN 201910610069 A CN201910610069 A CN 201910610069A CN 110220517 A CN110220517 A CN 110220517A
- Authority
- CN
- China
- Prior art keywords
- indoor robot
- map
- data
- robot
- indoor
- 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
- 238000000034 method Methods 0.000 title claims abstract description 21
- 230000007613 environmental effect Effects 0.000 title claims abstract description 16
- 230000004927 fusion Effects 0.000 claims abstract description 16
- 230000008447 perception Effects 0.000 claims abstract description 13
- 238000005259 measurement Methods 0.000 claims abstract description 4
- 230000004807 localization Effects 0.000 claims description 7
- 230000004888 barrier function Effects 0.000 claims description 5
- 230000000007 visual effect Effects 0.000 claims description 5
- 206010048669 Terminal state Diseases 0.000 claims description 3
- 230000001154 acute effect Effects 0.000 claims description 3
- 238000004590 computer program Methods 0.000 claims description 3
- 239000002245 particle Substances 0.000 claims description 3
- 238000004886 process control Methods 0.000 claims description 3
- 230000009466 transformation Effects 0.000 claims description 3
- 238000011282 treatment Methods 0.000 claims description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000009825 accumulation Methods 0.000 description 2
- 238000012937 correction Methods 0.000 description 2
- 238000007689 inspection Methods 0.000 description 2
- NJPPVKZQTLUDBO-UHFFFAOYSA-N novaluron Chemical compound C1=C(Cl)C(OC(F)(F)C(OC(F)(F)F)F)=CC=C1NC(=O)NC(=O)C1=C(F)C=CC=C1F NJPPVKZQTLUDBO-UHFFFAOYSA-N 0.000 description 2
- 230000001133 acceleration Effects 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
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, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- 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
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- 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
- G05D1/0257—Control of position or course in two dimensions specially adapted to land vehicles using a radar
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- 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
- G05D1/0268—Control of position or course in two dimensions specially adapted to land vehicles using internal positioning means
- G05D1/027—Control of position or course in two dimensions specially adapted to land vehicles using internal positioning means comprising intertial navigation means, e.g. azimuth detector
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- 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
- G05D1/0268—Control of position or course in two dimensions specially adapted to land vehicles using internal positioning means
- G05D1/0272—Control of position or course in two dimensions specially adapted to land vehicles using internal positioning means comprising means for registering the travel distance, e.g. revolutions of wheels
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- 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
- G05D1/0276—Control of position or course in two dimensions specially adapted to land vehicles using signals provided by a source external to the vehicle
- G05D1/0278—Control of position or course in two dimensions specially adapted to land vehicles using signals provided by a source external to the vehicle using satellite positioning signals, e.g. GPS
Landscapes
- Engineering & Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Aviation & Aerospace Engineering (AREA)
- Electromagnetism (AREA)
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
- Traffic Control Systems (AREA)
Abstract
The present invention provides a kind of Indoor Robot robust slam method of combining environmental meaning of one's words, the positioning of the Indoor Robot including the fusion of GPS global signal, IMU Inertial Measurement Unit signal and laser radar signal;The perception of radar data image data, the external parameter of radar sensor calibration, the external and inherent parameter of front camera calibration, the speed of host and the Indoor Robot of angular speed fusion;The semantic map of the Indoor Robot of the fusion of the location information of the NavigationInfo of dreamview module, the LaneMarker from sensing module, locating module;The decision of obstacle information, vehicle-state, traffic lights and the Indoor Robot of cartographic information fusion;And the path planning of the Indoor Robot of positioning, perception, prediction, routing and map fusion.The invention enables robot move in the environment and decision in it is more robust to environment.
Description
Technical field
The invention belongs to technical field of computer vision, more particularly, to a kind of Indoor Robot Shandong of combining environmental meaning of one's words
Stick slam method.
Background technique
With artificial intelligence technology, the rapid development of especially strong intelligence, robot application scene is from extreme environment
The office work scene to interact closely with the mankind is gradually turned to industrial application scene.Based on this, we are for robot
Design and use are gradually gradually shifted from functionality to robustness, but existing Indoor Robot meets in simple environment
The demand of indoor high fine positioning and navigation, once but environment changes or high noisy, robot vision will generate not
With the accumulated error under scale, this is very unfavorable for the navigation of robot;In addition, coming into the indoor machine of human society
People can't understand environmental information and therefore complete the support that appointed task also needs subsequent path to plan, can't be referred to as real
" strong " intelligence
Merchandising machine people can complete intelligent storage and automatic material flow indoors, but often due to sealed storage ring
Border often based on white background, seriously lack textural characteristics, this can to robot navigation when cause dimensional information lose and
Destroy the positioning accuracy of visual odometry;And the environment meaning of one's words is exactly dissolved into map, using optimizations such as potential field guidance by the present invention
Means obtain a kind of robust slam method that can understand environmental map.
Summary of the invention
In view of this, the present invention is directed to propose a kind of Indoor Robot robust slam method of combining environmental meaning of one's words, with solution
The problem of being mentioned in certainly above-mentioned background technique.
In order to achieve the above objectives, the technical scheme of the present invention is realized as follows:
A kind of Indoor Robot robust slam method of the combining environmental meaning of one's words, including
The indoor machine of GPS global signal, IMU Inertial Measurement Unit signal and laser radar signal fusion
The positioning of people;
Radar data image data, the external parameter of radar sensor calibration, front camera are calibrated external and inherent
The perception of the Indoor Robot of parameter, the speed of host and angular speed fusion;
The positioning of the NavigationInfo of dreamview module, the LaneMarker from sensing module, locating module
The semantic map of the Indoor Robot of the fusion of information;
The decision of obstacle information, vehicle-state, traffic lights and the Indoor Robot of cartographic information fusion;
And the path planning of the Indoor Robot of positioning, perception, prediction, routing and map fusion;
The positioning of Indoor Robot, the perception of Indoor Robot, the semantic map of Indoor Robot, Indoor Robot certainly
Path planning is carried out in the path planning for being input to Indoor Robot of plan and obtains motion profile, and bottom control end is according to road
Diameter planning issues control command.
Further, IMU inertance element is added using whole world GPS global positioning signal in the positioning of the Indoor Robot
Prior information as laser radar.
Further, the semantic map of the Indoor Robot includes:
(1) data acquire: using laser radar acquisition full-view image data, Centimeter Level High Precision GPS Data and scanning road
The road surface scene data of section;
(2) data prediction: by collected data progress data vacuate with data multidomain treat-ment, obtaining can be further
The data format of processing;
(3) lane line and road profile line high-precision Map Vectorization: are extracted according to data obtained in the previous step;
(4) lane center generates: then progress lane center line drawing first carries out data merging, finally carries out vehicle
The format of road center line is converted;
(5) it generates orderly topological structure: carrying out artificial interpretation first, then carries out process control, generate released version
High-precision map;
(6) map quality restriction: acute for the visual effect of map, the logic of map and precision using computer program
Verifying, to generate the high-precision map of final version.
Further, the decision of the Indoor Robot includes
(1) using the amcl packet positioned in map: the probabilistic localization moved in 2D configures overall filter in ROS, swashs
Light model and odometer model parameter, input laser scanning data, tf are converted and the average value and covariance of particle filter, defeated
Out in map Indoor Robot estimation posture, realize from basic frame to milestone frame again to the transformation of map frame;
(2) using laser radar, the gmapping packet of depth camera map making: passing through sensor_msgs/
LaserScan obtains data and creates 2D grating map, inputs laser scans data and laser coordinates system, pedestal coordinate
It is converted between system, odometer coordinate system, periodically issues map metadata and cartographic information;
(3) using the move_base packet for being moved to target position: realizing that the planning to Indoor Robot path and intelligence are kept away
Barrier, can independently select optimal path by multiple study.
Further, the path planning of the Indoor Robot uses the innovatory algorithm of lattice, specifically includes
(1) horizontal and vertical to spread respectively a little, according to real-time decision objective, different ends is taken in the state space of vehicle
Point.With the terminal of luminance curve link starting point and different conditions;
(2) according to body-sensing, if reach terminal state etc., the cost different for horizontal and vertical curve assign;
(3) final output meets the optimal solution of dynamics of vehicle and safety, body-sensing condition.
Compared with the existing technology, the Indoor Robot robust slam method tool of a kind of combining environmental meaning of one's words of the present invention
There is following advantage:
(1) for localization method proposed by the present invention still can be used under the indoor environment of few texture, low contrast,
Indoor Robot can be effectively promoted to the robustness of no feature environment using potential field visual odometry method;
(2) use positioning, perception, prediction, map, path planning and bottom control module that Indoor Robot is felt
Know the meaning of ambient enviroment, provides prior information more abundant for the efficient decision of robot and path planning.
Detailed description of the invention
The attached drawing for constituting a part of the invention is used to provide further understanding of the present invention, schematic reality of the invention
It applies example and its explanation is used to explain the present invention, do not constitute improper limitations of the present invention.In the accompanying drawings:
Fig. 1 is a kind of Indoor Robot robust slam method ensemble stream of the combining environmental meaning of one's words described in the embodiment of the present invention
Journey schematic diagram.
Specific embodiment
It should be noted that in the absence of conflict, the feature in embodiment and embodiment in the present invention can phase
Mutually combination.
The present invention will be described in detail below with reference to the accompanying drawings and embodiments.
As shown in Figure 1, the present invention provides a kind of Indoor Robot robust slam method of combining environmental meaning of one's words, including as follows
Step:
1, GPS global signal, IMU Inertial Measurement Unit signal and laser radar signal the positioning of Indoor Robot: are used
As original input signal, the method that priori inputs and observation is corrected is used so that Indoor Robot positioning is more accurate simultaneously
And robust.
In order to eliminate robot, corner is and this fixed there is position error caused by when on-right angle turn indoors
Position error is accumulation accumulation, and more arriving subsequent section error will all the more be amplified, and Indoor Robot robust of the invention is fixed
Position technology is positioned using the strategy of multi-thread laser sensor Global localization+IMU local correction, while global GPS is global
Positioning signal adds prior information of the IMU inertance element as laser radar, and the method that correction is inputted and observed using priori is come
So that Indoor Robot positions more accurate and robust.
2, the perception of Indoor Robot: the present invention devise with radar data image data, radar sensor calibration it is outer
External and inherent parameter, the speed of host and the angular speed that portion's parameter, front camera are calibrated are as input data;With 3D obstacle
Track course, speed and classification information;Broken line or polynomial curve;Carriageway type opsition dependent: L1 (lower-left lane line), L0 are (left
Lane line), R0 (right-lane line), R1 (bottom right lane line) are used as output data, obtain perception of the robot for external environment.
3, the semantic map of Indoor Robot: input is the NavigationInfo from dreamview module;Carry out self-induction
Know the LaneMarker of module;The location information of locating module is obtained by the grating map that robot establishes based on map
Path planning navigation information.It specifically includes:
Data acquisition: laser radar acquisition full-view image data, Centimeter Level High Precision GPS Data and scanning section are used
Road surface scene data.
Data prediction: by collected data progress data vacuate with data multidomain treat-ment, obtain further locating
The data format of reason.
High-precision Map Vectorization: lane line drawing and road profile line mainly are carried out according to data obtained in the previous step
It extracts.
Lane center generates: then progress lane center line drawing first carries out data merging, finally carries out in lane
The format of heart line is converted.
It generates orderly topological structure: carrying out artificial interpretation first, then carries out process control, generate the height of released version
Precision map.
Map quality restriction: it relates generally to using computer program for the visual effect of map, the logic of map and essence
Acute verifying is spent, to generate the high-precision map of final version.
4, the decision of Indoor Robot: input is obstacle information, vehicle-state, traffic lights and cartographic information, defeated
Go out under the states such as overtake other vehicles, trail, avoid for the control information of vehicle, the obstacle of prediction, has been issued for barrier
Control information.It specifically includes as follows:
(a) it is wrapped using the amcl (adaptive Monte Carlo localization) positioned in map: the probabilistic localization moved in 2D,
Overall filter, laser model and odometer model parameter, input laser scanning data, tf conversion and particle filter are configured in ROS
The average value and covariance of wave device, the estimation posture of Indoor Robot in output map, are realized from basic frame to milestone frame again
To the transformation of map frame.
(b) using laser radar, the gmapping packet of depth camera map making: passing through sensor_msgs/
LaserScan obtains data and creates 2D grating map, inputs laser scans data and laser coordinates system, pedestal coordinate
It is converted between system, odometer coordinate system, periodically issues map metadata and cartographic information.
(c) using the move_base packet for being moved to target position: realizing that the planning to Indoor Robot path and intelligence are kept away
Barrier, can independently select optimal path by multiple study.
5, the path planning of Indoor Robot: input is positioning, perception, prediction, routing and map, and output is that a kind of nothing is touched
It hits and comfortable track.Indoor Robot path planning uses the innovatory algorithm of lattice, and key step is as follows:
A) horizontal and vertical to spread point respectively (totally 6 parameters: three lateral parameters, three longitudinal parameters have associated speed
And timestamp), according to real-time decision objective, such as follow the bus or stopping, different terminals is taken in the state space of vehicle.
With the terminal of luminance curve link starting point and different conditions.
B) according to body-sensing, if reach terminal state etc., the cost different for horizontal and vertical curve assign.
C) the curve bundle of transverse and longitudinal is got up to form final curve, later according to the cost after curve bundle,
It sorts from small to large, whether the curve after reexamining bundler meets various gometry constraint and pass through
collision check。
D) final output meets the optimal solution of dynamics of vehicle and safety, body-sensing condition.
Indoor Robot path planning mainly has following steps in the implementation of algorithm:
1, it obtains a reference line and is converted into PathPoint format
2, the match point of initialization planning point is calculated in obtained reference line
3, according to the match point being calculated, the initial state information for calculating Frenet frame (is primarily referred to as ptr_
prediction_querier)
4, it analytical strategy and obtains the object of planning: obtaining ptr_path_time_graph, pass through reference_line_
Info- > planning_target () obtains the object of planning.
5, the one-dimensional path beam of vertical and horizontal is generated respectively:
6, the feasibility in one-dimensional path is assessed according to dynamic constrained, and assesses feasible vertical and horizontal path, at cost
Sequence.
7, optimal path Shu Zuhe is obtained, and returns to first collisionless path of complete avoidance.
1) whether be divided to is that two kinds of situations of auto_tuning generate trajectory_pair_cost respectively;
2) a two-dimensional path is merged into two 1 dimension paths;
3) vertical and horizontal acceleration is calculated separately when considering path curvatures, is called
ConstraintChecker::ValidTrajectory makes restricted inspection, to the failure difference of various types of vehicles physical index
Make to count;
4) inspection is made to whether vehicle and barrier collide, the situation that do not collide then collides fail count+1;
5) two dimensional path is imported into tune-up data: pass through reference_line_info- > SetTrajectory,
Reference_line_info- > SetCost and reference_line_info- > SetDrivable updates tune-up data;
6) auto_tuning generates path
I) Future Path is obtained from Localization:
IscretizedTrajectory future_trajectory=GetFutureTrajectory ();
Ii existing longitude and latitude path) is mapped to following path pair:
MapFutureTrajectoryToSL(future_trajectory,
*ptr_reference_line,
&lon_future_trajectory,&lat_future_trajectory)
Iii the consumption of Future Path pair) is calculated:
trajectory_evaluator.EvaluateDiscreteTrajectory(planning_targ
et,
lon_future_trajectory,lat_future_trajectory,&future_traj_comp
onent_cost;
Iv) auto_tuning_data is copied to planning_internal::PlanningData
V) routing cost and two dimensional path point are generated: pass through reference_line_info- > PriorityCost (),
Combined_trajectory_points [i] is generated;
Vi it) if num_lattice_traj is greater than 0, plans successfully number of path+1, otherwise enters backup planning path
(FLAGS_enable_backup_trajectory=true) or prompt is without planning path.
The present invention devises the fine of Indoor Robot positioning, perception, prediction, map, path planning and bottom control module
New architecture, in conjunction with the algorithm steps of Multi-sensor Fusion, prediction and path planning, so that robot moves in the environment and decision
In it is more robust to environment.
The foregoing is merely illustrative of the preferred embodiments of the present invention, is not intended to limit the invention, all in essence of the invention
Within mind and principle, any modification, equivalent replacement, improvement and so on be should all be included in the protection scope of the present invention.
Claims (5)
1. a kind of Indoor Robot robust slam method of combining environmental meaning of one's words, it is characterised in that: including
The positioning of the Indoor Robot of GPS global signal, IMU Inertial Measurement Unit signal and laser radar signal fusion;
The external and inherent parameter of external parameter, front camera calibration that radar data image data, radar sensor are calibrated,
The perception of the Indoor Robot of speed and the angular speed fusion of host;
The positioning tionInfo of the Naviga Indoor Robot of dreamview module, the LaneMarker from sensing module, determine
The semantic map of the Indoor Robot of the fusion of the location information of position module;
The decision of obstacle information, vehicle-state, traffic lights and the Indoor Robot of cartographic information fusion;
And the path planning of the Indoor Robot of positioning, perception, prediction, routing and map fusion;
The positioning of Indoor Robot, the perception of Indoor Robot, the semantic map of Indoor Robot, Indoor Robot decision
It is input to progress path planning in the path planning of Indoor Robot and obtains motion profile, bottom control end is advised according to path
It draws and issues control command.
2. a kind of Indoor Robot robust slam method of combining environmental meaning of one's words according to claim 1, it is characterised in that:
IMU inertance element is added as the elder generation of laser radar using whole world GPS global positioning signal in the positioning of the Indoor Robot
Test information.
3. a kind of Indoor Robot robust slam method of combining environmental meaning of one's words according to claim 1, it is characterised in that:
The semantic map of the Indoor Robot includes:
(1) data acquire: using laser radar acquisition full-view image data, Centimeter Level High Precision GPS Data and scanning section
Road surface scene data;
(2) data prediction: by collected data progress data vacuate with data multidomain treat-ment, obtain to be further processed
Data format;
(3) lane line and road profile line high-precision Map Vectorization: are extracted according to data obtained in the previous step;
(4) lane center generates: then progress lane center line drawing first carries out data merging, finally carries out in lane
The format of heart line is converted;
(5) it generates orderly topological structure: carrying out artificial interpretation first, then carries out process control, generate the height of released version
Precision map;
(6) map quality restriction: using computer program is for the visual effect of map, the logic of map and precision is acute tests
Card, to generate the high-precision map of final version.
4. a kind of Indoor Robot robust slam method of combining environmental meaning of one's words according to claim 1, it is characterised in that:
The decision of the Indoor Robot includes
(1) using the amcl packet positioned in map: the probabilistic localization moved in 2D configures overall filter, mode of laser in ROS
Type and odometer model parameter, input laser scanning data, tf are converted and the average value and covariance of particle filter, output ground
The estimation posture of Indoor Robot in figure is realized from basic frame to milestone frame again to the transformation of map frame;
(2) using laser radar, the gmapping packet of depth camera map making: passing through sensor_msgs/LaserScan
It obtains data and creates 2D grating map, input laser scans data and laser coordinates system, base coordinate system, odometer are sat
It is converted between mark system, periodically issues map metadata and cartographic information;
(3) using the move_base packet for being moved to target position: realize the planning to Indoor Robot path and intelligent barrier avoiding,
Optimal path can be independently selected by multiple study.
5. a kind of Indoor Robot robust slam method of combining environmental meaning of one's words according to claim 1, it is characterised in that:
The path planning of the Indoor Robot uses the innovatory algorithm of lattice, specifically includes
(1) horizontal and vertical to spread respectively a little, according to real-time decision objective, different terminals is taken in the state space of vehicle,
With the terminal of luminance curve link starting point and different conditions;
(2) according to body-sensing, if reach terminal state etc., the cost different for horizontal and vertical curve assign;
(3) final output meets the optimal solution of dynamics of vehicle and safety, body-sensing condition.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910610069.9A CN110220517A (en) | 2019-07-08 | 2019-07-08 | A kind of Indoor Robot robust slam method of the combining environmental meaning of one's words |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910610069.9A CN110220517A (en) | 2019-07-08 | 2019-07-08 | A kind of Indoor Robot robust slam method of the combining environmental meaning of one's words |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110220517A true CN110220517A (en) | 2019-09-10 |
Family
ID=67812831
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910610069.9A Pending CN110220517A (en) | 2019-07-08 | 2019-07-08 | A kind of Indoor Robot robust slam method of the combining environmental meaning of one's words |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110220517A (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111258312A (en) * | 2020-01-20 | 2020-06-09 | 深圳市商汤科技有限公司 | Movable model, control method, device, system, equipment and storage medium thereof |
CN111486855A (en) * | 2020-04-28 | 2020-08-04 | 武汉科技大学 | Indoor two-dimensional semantic grid map construction method with object navigation points |
CN112711249A (en) * | 2019-10-24 | 2021-04-27 | 科沃斯商用机器人有限公司 | Robot positioning method and device, intelligent robot and storage medium |
CN113256716A (en) * | 2021-04-21 | 2021-08-13 | 中国科学院深圳先进技术研究院 | Robot control method and robot |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106681330A (en) * | 2017-01-25 | 2017-05-17 | 北京航空航天大学 | Robot navigation method and device based on multi-sensor data fusion |
CN108776474A (en) * | 2018-05-24 | 2018-11-09 | 中山赛伯坦智能科技有限公司 | Robot embedded computing terminal integrating high-precision navigation positioning and deep learning |
CN108873908A (en) * | 2018-07-12 | 2018-11-23 | 重庆大学 | The robot city navigation system that view-based access control model SLAM and network map combine |
CN108955702A (en) * | 2018-05-07 | 2018-12-07 | 西安交通大学 | Based on the lane of three-dimensional laser and GPS inertial navigation system grade map creation system |
US20190004510A1 (en) * | 2017-07-03 | 2019-01-03 | Baidu Usa Llc | Human-machine interface (hmi) architecture |
CN109410301A (en) * | 2018-10-16 | 2019-03-01 | 张亮 | High-precision semanteme map production method towards pilotless automobile |
CN109556617A (en) * | 2018-11-09 | 2019-04-02 | 同济大学 | A kind of map elements extracting method of automatic Jian Tu robot |
CN109900280A (en) * | 2019-03-27 | 2019-06-18 | 浙江大学 | A kind of livestock and poultry information Perception robot and map constructing method based on independent navigation |
-
2019
- 2019-07-08 CN CN201910610069.9A patent/CN110220517A/en active Pending
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106681330A (en) * | 2017-01-25 | 2017-05-17 | 北京航空航天大学 | Robot navigation method and device based on multi-sensor data fusion |
US20190004510A1 (en) * | 2017-07-03 | 2019-01-03 | Baidu Usa Llc | Human-machine interface (hmi) architecture |
CN108955702A (en) * | 2018-05-07 | 2018-12-07 | 西安交通大学 | Based on the lane of three-dimensional laser and GPS inertial navigation system grade map creation system |
CN108776474A (en) * | 2018-05-24 | 2018-11-09 | 中山赛伯坦智能科技有限公司 | Robot embedded computing terminal integrating high-precision navigation positioning and deep learning |
CN108873908A (en) * | 2018-07-12 | 2018-11-23 | 重庆大学 | The robot city navigation system that view-based access control model SLAM and network map combine |
CN109410301A (en) * | 2018-10-16 | 2019-03-01 | 张亮 | High-precision semanteme map production method towards pilotless automobile |
CN109556617A (en) * | 2018-11-09 | 2019-04-02 | 同济大学 | A kind of map elements extracting method of automatic Jian Tu robot |
CN109900280A (en) * | 2019-03-27 | 2019-06-18 | 浙江大学 | A kind of livestock and poultry information Perception robot and map constructing method based on independent navigation |
Non-Patent Citations (2)
Title |
---|
天涯0508: "ROS开发笔记(7)——利用amcl、move_base 进行导航、基于Python编写巡逻机器人导航代码", 《HTTPS://BLOG.CSDN.NET/WSC820508/ARTICLE/DETAILS/81627858》 * |
许珂诚: "lattice planner规划详解", 《HTTPS://WWW.CNBLOGS.COM/FUHANG/P/9563884.HTML》 * |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112711249A (en) * | 2019-10-24 | 2021-04-27 | 科沃斯商用机器人有限公司 | Robot positioning method and device, intelligent robot and storage medium |
WO2021077941A1 (en) * | 2019-10-24 | 2021-04-29 | 科沃斯商用机器人有限公司 | Method and device for robot positioning, smart robot, and storage medium |
CN111258312A (en) * | 2020-01-20 | 2020-06-09 | 深圳市商汤科技有限公司 | Movable model, control method, device, system, equipment and storage medium thereof |
CN111258312B (en) * | 2020-01-20 | 2024-04-02 | 深圳市商汤科技有限公司 | Movable model, control method, device, system, equipment and storage medium thereof |
CN111486855A (en) * | 2020-04-28 | 2020-08-04 | 武汉科技大学 | Indoor two-dimensional semantic grid map construction method with object navigation points |
CN111486855B (en) * | 2020-04-28 | 2021-09-14 | 武汉科技大学 | Indoor two-dimensional semantic grid map construction method with object navigation points |
CN113256716A (en) * | 2021-04-21 | 2021-08-13 | 中国科学院深圳先进技术研究院 | Robot control method and robot |
WO2022222490A1 (en) * | 2021-04-21 | 2022-10-27 | 中国科学院深圳先进技术研究院 | Robot control method and robot |
CN113256716B (en) * | 2021-04-21 | 2023-11-21 | 中国科学院深圳先进技术研究院 | Control method of robot and robot |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
JP7020728B2 (en) | System, method and program | |
JP7077520B2 (en) | A system that determines lane assignments for autonomous vehicles, computer-implemented methods for determining lane assignments for autonomous vehicles, and computer programs. | |
JP7432285B2 (en) | Lane mapping and navigation | |
KR102565533B1 (en) | Framework of navigation information for autonomous navigation | |
CN107144285B (en) | Pose information determination method and device and movable equipment | |
CN111912417B (en) | Map construction method, map construction device, map construction equipment and storage medium | |
CN110220517A (en) | A kind of Indoor Robot robust slam method of the combining environmental meaning of one's words | |
JP7082545B2 (en) | Information processing methods, information processing equipment and programs | |
US9255989B2 (en) | Tracking on-road vehicles with sensors of different modalities | |
CN110057373A (en) | For generating the method, apparatus and computer storage medium of fine semanteme map | |
WO2018126228A1 (en) | Sign and lane creation for high definition maps used for autonomous vehicles | |
CN109991984A (en) | For generating the method, apparatus and computer storage medium of fine map | |
CN106980657A (en) | A kind of track level electronic map construction method based on information fusion | |
JP2022542289A (en) | Mapping method, mapping device, electronic device, storage medium and computer program product | |
US20200033155A1 (en) | Method of navigating an unmaned vehicle and system thereof | |
CN109541535A (en) | A method of AGV indoor positioning and navigation based on UWB and vision SLAM | |
CN110211228A (en) | For building the data processing method and device of figure | |
CN105204510A (en) | Generation method and device for probability map for accurate positioning | |
CN115639823B (en) | Method and system for controlling sensing and movement of robot under rugged undulating terrain | |
US11035679B2 (en) | Localization technique | |
CN109443368A (en) | Air navigation aid, device, robot and the storage medium of unmanned machine people | |
JP2008065087A (en) | Apparatus for creating stationary object map | |
CN112068152A (en) | Method and system for simultaneous 2D localization and 2D map creation using a 3D scanner | |
Li et al. | Hybrid filtering framework based robust localization for industrial vehicles | |
CN116047565A (en) | Multi-sensor data fusion positioning 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 | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190910 |