CN112837333A - Method and equipment for cleaning welt of outdoor unmanned sweeper - Google Patents
Method and equipment for cleaning welt of outdoor unmanned sweeper Download PDFInfo
- Publication number
- CN112837333A CN112837333A CN202110156181.7A CN202110156181A CN112837333A CN 112837333 A CN112837333 A CN 112837333A CN 202110156181 A CN202110156181 A CN 202110156181A CN 112837333 A CN112837333 A CN 112837333A
- Authority
- CN
- China
- Prior art keywords
- road
- data
- cleaning
- edge
- radar data
- 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 44
- 241001417527 Pempheridae Species 0.000 title claims abstract description 42
- 238000004140 cleaning Methods 0.000 title claims abstract description 31
- 238000002310 reflectometry Methods 0.000 claims abstract description 23
- 238000005259 measurement Methods 0.000 claims description 14
- 238000010408 sweeping Methods 0.000 claims description 14
- 230000011218 segmentation Effects 0.000 claims description 13
- 238000001914 filtration Methods 0.000 claims description 4
- 238000004422 calculation algorithm Methods 0.000 description 8
- 238000000605 extraction Methods 0.000 description 6
- 239000000463 material Substances 0.000 description 4
- 238000009795 derivation Methods 0.000 description 3
- 239000010426 asphalt Substances 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 239000004568 cement Substances 0.000 description 2
- 210000004513 dentition Anatomy 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 239000000284 extract Substances 0.000 description 2
- 239000004579 marble Substances 0.000 description 2
- 230000036346 tooth eruption Effects 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 230000032683 aging Effects 0.000 description 1
- 230000003796 beauty Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000000903 blocking effect Effects 0.000 description 1
- 239000011449 brick Substances 0.000 description 1
- 239000000428 dust Substances 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 230000031700 light absorption Effects 0.000 description 1
- 238000004643 material aging Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 230000007704 transition Effects 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- E—FIXED CONSTRUCTIONS
- E01—CONSTRUCTION OF ROADS, RAILWAYS, OR BRIDGES
- E01H—STREET CLEANING; CLEANING OF PERMANENT WAYS; CLEANING BEACHES; DISPERSING OR PREVENTING FOG IN GENERAL CLEANING STREET OR RAILWAY FURNITURE OR TUNNEL WALLS
- E01H1/00—Removing undesirable matter from roads or like surfaces, with or without moistening of the surface
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S17/00—Systems using the reflection or reradiation of electromagnetic waves other than radio waves, e.g. lidar systems
- G01S17/88—Lidar systems specially adapted for specific applications
- G01S17/93—Lidar systems specially adapted for specific applications for anti-collision purposes
- G01S17/931—Lidar systems specially adapted for specific applications for anti-collision purposes of land vehicles
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10032—Satellite or aerial image; Remote sensing
- G06T2207/10044—Radar image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30248—Vehicle exterior or interior
- G06T2207/30252—Vehicle exterior; Vicinity of vehicle
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Structural Engineering (AREA)
- Civil Engineering (AREA)
- Architecture (AREA)
- Computer Networks & Wireless Communication (AREA)
- Electromagnetism (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Traffic Control Systems (AREA)
- Optical Radar Systems And Details Thereof (AREA)
Abstract
The invention discloses a welt cleaning method for an outdoor unmanned sweeper, which is used for cleaning a welt environment under the condition of outdoor road teeth. The method comprises the steps of extracting linear features in two-dimensional laser radar data, identifying road teeth based on the linear features of road boundaries, identifying redundant road teeth based on the reflectivity of the laser radar, and controlling welting vehicles based on the road teeth features.
Description
Technical Field
The invention relates to the technical field of motor sweeper, in particular to a method for cleaning a welt of an outdoor unmanned motor sweeper.
Background
Outdoor unmanned sweeper is often used in semi-closed environments such as industrial parks, parks and the like. In the working scene of a semi-closed outdoor road, the two sides of the road are provided with projections built by cement bricks at the two sides except large-scale fixed objects such as house trees and the like, and the projections are called road teeth for short. The road tooth is very common and can play a role in road beauty, blocking rainwater on a road surface in rainy days from being guided to a lower water opening and the like, but the road tooth is unfamiliar to an outdoor unmanned sweeper, and the road condition cannot be identified according to conventional sensors and technical means; once the road teeth can not be identified in the cleaning process of the outdoor unmanned sweeper, the brush disc and other important components on the sweeper collide with the road teeth, so that the outdoor unmanned sweeper cannot work normally, potential safety operation hazards exist, and economic loss is caused. In addition, in the outdoor road cleaning area, besides the road with a flat surface, leaves accumulated on the road teeth and dust brushed by rain are basically mixed at the included angle between the road and the road teeth, so that how to smoothly finish the operation of identifying the road teeth and cleaning along the road teeth is the problem to be solved by the invention.
The conventional unmanned driving technical method comprises three-dimensional laser radar point cloud matching positioning, visual positioning, GPS positioning matching or fusion means based on the three, the methods are feasible for identifying and positioning outdoor large working scenes, for example, automatic driving is carried out along a lane line of a road, the positioning accuracy of the technical means is generally over 10cm, but the accuracy of the operation of the cleaning vehicle along a road tooth is far insufficient, and the working condition of welting and cleaning of the unmanned cleaning vehicle needs to be accurate and can be self-adaptively operated along the road edge so as to ensure the cleaning coverage rate of the unmanned vehicle; however, the conventional positioning technology has large positioning errors, and the unmanned sweeper is very easy to collide with the edge of a road, so that the risk which is difficult to predict is caused.
Disclosure of Invention
Based on the technical problems in the background art, the invention provides an edge pasting cleaning method for an outdoor unmanned sweeper, which can automatically correct the distance between the unmanned sweeper and a road tooth and perform edge pasting and edge extension cleaning to prevent the unmanned sweeper from colliding with the edge of a road.
An edge-attaching cleaning method for an outdoor unmanned sweeper comprises the following steps:
s1: acquiring measurement data of road edges;
s2: the data obtained in the step S1 are sorted, and the linear characteristics of the measuring points are extracted based on the curvatures of the adjacent measuring points;
s3: judging whether the linear characteristics of the obtained measuring points accord with the linear characteristics of the road boundary or not by S2 so as to divide the road surface and the road teeth;
s4: comparing the boundary position of the road surface and the road teeth obtained in the step S3 with the boundary position at the last moment;
s5: based on the position comparison at S4, the advancing direction of the unmanned sweeping vehicle is corrected to perform welt cleaning.
Preferably, in S1, a two-dimensional laser radar is used for data measurement, the obtained data is 2D data, and the measured data includes a radar data start angle (minimum angle), a radar data end angle (maximum angle), a radar data angle resolution (angle increment), a time interval of each data point of the radar data, a time interval between a current frame of data and a next frame of data, a minimum value of the radar data, a maximum value of the radar data, a distance value corresponding to each point of the radar data in a polar coordinate system, and a strength value corresponding to each point of the radar data.
Preferably, the radar data collating method in S2 includes: a. reducing the weight error of the laser radar data caused by the distance measurement by a voxel filtering method; b. a square with the side length of 5cm is set as a voxel unit, and the radar data of a dense area is reduced by adopting a downsampling method.
Preferably, in S2, the curvature between adjacent measurement points is calculated, and the linear feature of the measurement point is extracted by comparing the curvature value with a preset curvature threshold.
Preferably, the straight line characteristic of the road boundary in S3 is a straight line-right angle-straight line, the measurement points are divided according to curvature values of adjacent measurement points, then a divided included angle between the road surface and the road tooth is determined according to an included angle between adjacent divided line segments, and the divided position between the road surface and the road tooth is obtained according to whether the included angle position meets the straight line characteristic of the road boundary.
Preferably, the step S3 may add or replace the following road surface and road tooth segmentation method: and dividing the road surface and the road teeth according to the reflectivity of the laser.
Preferably, the object characteristics can be extracted from the collected data and classified by setting the reflectivity segmentation range according to the collected reflectivity, and then the boundary position of the road surface and the road tooth is obtained.
Preferably, in S5, the method for correcting the advancing direction of the unmanned cleaning vehicle is: the distance from the extension line of the advancing direction of the unmanned sweeper to the edge of the road from the data junction point of the laser radar can be known to be deviated from the edge of the road or the edge of the road by comparing the change trend of the difference value of the two adjacent distance values. And obtaining the current included angle between the outdoor sweeper and the road edge through the measured segmentation position angle at a small time interval, and controlling the outdoor sweeper to carry out edge pasting sweeping through the included angle.
An inclined plane platform is arranged in the position, 80-120cm away from the ground, in front of a vehicle body of the unmanned sweeper, and a two-dimensional laser radar is mounted on the inclined plane platform.
Preferably, the inclined plane platform and the ground form an included angle of 40-50 degrees, and the two-dimensional laser radar is installed on the right side of the inclined plane platform.
In the method provided by the invention, the separation of the road surface and the road tooth according to the reflectivity of the laser is added as redundant segmentation, the TOF-based laser point is hit on objects with different materials and the absorbed energy is different, and the segmentation positions of the road tooth and the road tooth are extracted according to the difference of the reflectivity of the road tooth and the road tooth to the laser point.
The laser radar is not only used for acquiring the information of the surrounding environment, but also can acquire other information according to optical properties besides acquiring distance information because the laser radar is an instrument based on the laser ranging principle, for example, the road ground and road teeth on the ground have obvious laser reflectivity difference, and the laser radar data intensity is used for directly extracting features to identify the road teeth without the complicated algorithm. However, if the reflectivity method is used alone, the characteristic extraction fails in the reflectivity-based method under severe weather conditions, and in addition, the road ground and the road teeth are blown out by wind and rain all the year round, and the aging conditions of the road teeth on different road sections are different, so that the material reflectivity on the same road section is different, and therefore, the error of the characteristic extraction based on the laser reflectivity is increased, and the phenomenon of misrecognition easily occurs.
The invention has the following beneficial effects:
the invention provides a welt cleaning method of an outdoor unmanned sweeper, which is used for cleaning a welt environment under the condition of outdoor road teeth. The method comprises the steps of extracting linear features in two-dimensional laser radar data, identifying road teeth based on the linear features of road boundaries, identifying redundant road teeth based on the reflectivity of the laser radar, and controlling welting vehicles based on the road teeth features.
The method for identifying the road teeth can stably extract the road teeth characteristics under the unfavorable working environment that road ground and the road teeth are subjected to external wind and rain all the year round, and the road teeth on different road sections are different in material aging condition under the condition that the road teeth characteristics are complete, and is high and stable in identification precision and high in identification speed. According to the method, the road surface and the road kerbs are separated according to the reflectivity of laser as redundant segmentation while the laser radar is used for scanning the two-dimensional characteristics of the road surface, and the algorithm for identifying the road kerbs is more robust and the identification effect is more accurate through the redundant characteristic extraction.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the principles of the invention and not to limit the invention. In the drawings:
FIG. 1 is a schematic diagram of an algorithm operation flow of an edge-attaching cleaning method for an outdoor unmanned sweeper;
FIG. 2 is a schematic diagram of the basic structure of an outdoor unmanned sweeping vehicle;
FIG. 3 is a line feature graph of a road boundary;
FIG. 4 is a graph of the state transition of the road teeth segmented by the algorithm of the present invention.
In the figure: the road surface cleaning method comprises the following steps of 1-an unmanned sweeper, 2-a two-dimensional laser radar, 3-a road surface, 301-a road surface straight line characteristic, 4-a road tooth, 401-a road tooth straight line characteristic A, 402-a road tooth straight line characteristic B, 5-right angle A and 6-right angle B.
Detailed Description
The present invention will be further illustrated with reference to the following specific examples.
The invention provides a method for sweeping an edge of an outdoor unmanned sweeper, as shown in figure 1, a two-dimensional laser radar 2 is arranged on an inclined platform which is one meter high away from the ground in front of a sweeper body of the unmanned sweeper 1, and the platform forms an angle of 45 degrees with the ground. The laser radar is in a scanning angle of 180 degrees, and the unmanned sweeper only extracts the boundary position of the road and the road teeth on the right side of the sweeper according to the driving rule of driving to the right. When the outdoor unmanned sweeper detects that the vehicle position is within the range of the road edge position, the outdoor unmanned sweeper extends out of the edge sweeping mechanism to perform a sweeping task.
Fig. 2 is an overall flow chart of the method, and data of the laser radar is acquired from the sensor through the network port. Because the closer to the laser radar, the more measurement points on the scanned obstacle and the greater the influence on the curvature extraction, the laser radar data is obtained by scanning the two-dimensional laser radar once, the laser points reflected back after scanning different objects according to the 2D data are processed, setting a square with the side length of 5cm as a voxel unit during curvature calculation, reducing laser points in a dense area by adopting a down-sampling method, calculating the derivation between two adjacent points by the processed laser points, obtaining the curvature between two adjacent points by performing derivation on the derived value, fitting the curvature between the adjacent points into a segment of a small segment, using a preset curvature threshold as an initial value, and distinguishing whether the line sections are the same by comparing the curvature value of the line sections with the curvature threshold value, if the same line sections are integrated together, and if the line sections are different, extracting a new line section, so that different straight line characteristics in the laser radar data are extracted.
The road comprises a road surface 3 and a road tooth 4, and the road comprises a road surface straight line characteristic 301, a right angle A5, a road tooth straight line characteristic A401, a right angle B6 and a road tooth straight line characteristic B402 in sequence. Therefore, the straight line characteristic of the road boundary can be obtained to accord with the rule of straight line-right angle-straight line, and the boundary position is obtained by judging whether the data point meets the rule or not.
For asphalt roads, cement pavements, marble curbs and green belts, the reflectivity of each material to the laser point is different, and asphalt roads and green belts have higher light absorption capacity, so the reflectivity is lower, and marble curbs have higher reflectivity. The object characteristics of the collected laser radar data can be extracted and classified by setting the reflectivity segmentation range of the reflectivity in the collected laser radar data, and then the boundary position is obtained. The reflectivity is an intensity value corresponding to each point of radar data in the laser radar 2D data, and whether the corresponding road tooth or road surface can be distinguished easily according to the intensity value corresponding to each point of the radar data, so that different linear characteristics can be extracted from different materials. Therefore, the method does not need to extract the linear characteristics of the road teeth and the road surface by a reflectivity technical means like the above complex algorithm, and belongs to a redundancy strategy, so that the extraction error of the linear characteristics of the road teeth is smaller and more reliable.
The straight line of the intersection of the road tooth and the road surface is used as the driving direction of the edge-extending cleaning operation of the outdoor unmanned sweeper, the two-dimensional laser radar of the outdoor unmanned sweeper is used as a coordinate center, the distance perpendicular to the straight line of the intersection of the road tooth and the road surface is used as a distance value obtained at one time, the current distance value is obtained at intervals of a small time, the deviation of the sweeper to the edge or the deviation of the sweeper to the edge of the road can be known by comparing the change trend of the difference value of the two adjacent distance values, and the direction of the unmanned sweeper is controlled so that the unmanned sweeper can clean garbage on the edge of the road surface along the edge. The distance values obtained once are cached, the current distance values are obtained at intervals of a small time, the deviation of the sweeper to the edge or the deviation to the road edge can be known by comparing the variation trend of the difference value of the two adjacent distance values, and then the direction of the unmanned sweeper is controlled so that the unmanned sweeper can clean the garbage on the edge of the road surface along the edge.
The algorithm of fig. 4 is implemented as follows:
the first step is as follows: converting the distance value under the polar coordinate system in the two-dimensional laser radar data into the distance value under the Euclidean coordinate corresponding to each data point
P(i)＝P(l*cosθ，l*sinθ)
Wherein P (I) is the distance value of the ith point in the two-dimensional plane under the Euclidean coordinate, I is the distance value under the polar coordinate system in the two-dimensional laser radar data, theta is the included angle theta between the current beam of laser radar data and the scanning starting axis of the laser radar, and theta belongs to [0,2 pi ].
The second step is that: voxel filtering downsampling is carried out on the point coordinate data to obtain laser point data under the condition of distance weight removal
Only data points in the first and second quadrants of the two-dimensional plane may be considered by the mounting location of the lidar. And establishing a filter space of x ∈ [ -d, d ], y ∈ [0, d ] by taking the maximum distance d measured by the laser radar as an edge. And simultaneously, dividing the filtering space into M grids by a square with the side length of dl, wherein M is composed of U and V voxels, U is floor (2d/dl), V is floor (d/dl), and floor (·) is a downward rounding symbol. Finding the voxel space to which each point cloud in P (i) belongs and numbering each voxel, and the process can be expressed as
Wherein P isfilter(i) To a point cloud point on the voxel space, P (i)yAnd P (i)yThe x-axis coordinate and the y-axis coordinate of the ith point of the origin cloud are respectively. The point clouds in the same grid in the original point cloud space after the processing are divided into the same voxel grid Pfilter(i) And (4) showing. And finally, the midpoint of the voxel grid is used as a substitute of the original point cloud mapped to the grid and is remapped back to the original two-dimensional coordinate system to obtain a new point cloud set O.
The third step: extracting curvature under a laser point data sequence
And (3) deriving the new point cloud set O to obtain O':
O(j)′＝(O(j+1)y-O(j)y)/(O(j+1)x-O(j)x)
and O ' is expressed as a derivative between adjacent point clouds, and O ' is subjected to derivation again to obtain a slope change rate change derivative O ' between the adjacent point clouds:
O(k)″＝(O′(k+1)y-O′(k)y)/(O′(k+1)x-O′(k)x)
and O' reflects the change smoothness degree between adjacent point clouds, and can be used as the curvature of the point clouds for segmentation and extraction. The straight line corresponds to O "approaching 0, while the straight angle will show a larger value.
The fourth step: according to the extracted curvature, setting a threshold value to divide the laser point data
From empirical data, a curvature threshold Th is set, all O 'are traversed, when the absolute value of the z-Th curvature point is greater than the threshold, i.e., Abs (O' (z)) > Th
The point is the extracted segmentation point. Abs (. cndot.) is an absolute value operation.
FIG. 4 is a drawing illustrating:
A. b, C is a visual chart obtained by simulating the same road tooth and calculating the algorithm after laser radar scanning at different stages.
Stage A represents a segmentation point extracted after scanning right road teeth through a two-dimensional laser radar, and a circle point represents a segmentation point position obtained through algorithm calculation;
b, obtaining a segmentation line of the road and the road dentition;
and C, fitting the relatively close line segments in the same vertical direction into a straight line, and finally obtaining a boundary between the road dentition and the road.
The above description is only for the preferred embodiment of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art should be considered to be within the technical scope of the present invention, and the technical solutions and the inventive concepts thereof according to the present invention should be equivalent or changed within the scope of the present invention.
Claims (10)
1. An edge-pasting cleaning method for an outdoor unmanned sweeper is characterized by comprising the following steps:
s1: acquiring measurement data of road edges;
s2: the data obtained in the step S1 are sorted, and the linear characteristics of the measuring points are extracted based on the curvatures of the adjacent measuring points;
s3: judging whether the linear characteristics of the obtained measuring points accord with the linear characteristics of the road boundary or not by S2 so as to divide the road surface and the road teeth;
s4: comparing the boundary position of the road surface and the road teeth obtained in the step S3 with the boundary position at the last moment;
s5: based on the position comparison at S4, the advancing direction of the unmanned sweeping vehicle is corrected to perform welt cleaning.
2. The method for cleaning the edge of an outdoor unmanned sweeper according to claim 1, wherein in step S1, a two-dimensional laser radar is used for data measurement, and the measurement data includes a radar data start angle, a radar data end angle, a radar data angle resolution, a time interval of each data point of radar data, a time interval of a current frame data and a next frame data, a minimum value of radar data, a maximum value of radar data, a distance value corresponding to each point of radar data in a polar coordinate system, and a strength value corresponding to each point of radar data.
3. The method for cleaning the edge of an outdoor unmanned sweeping vehicle according to claim 2, wherein the method for collating radar data in S2 comprises the following steps: a. reducing the weight error of the laser radar data caused by the distance measurement by a voxel filtering method; b. a square with the side length of 5cm is set as a voxel unit, and the radar data of a dense area is reduced by adopting a downsampling method.
4. The method as claimed in claim 2, wherein in S2, the curvature between adjacent measurement points is calculated, and the linear feature of the measurement points is extracted by comparing the curvature value with a predetermined curvature threshold.
5. The method as claimed in claim 4, wherein the straight line characteristic of the road boundary in S3 is straight line-right angle-straight line, the measuring points are divided according to the curvature values of the adjacent measuring points, then the dividing angle between the road surface and the road tooth is determined according to the included angle between the adjacent dividing line segments, and the dividing position between the road surface and the road tooth is obtained according to whether the included angle position meets the straight line characteristic of the road boundary.
6. The method for cleaning the edge of an outdoor unmanned sweeping vehicle according to claim 1, wherein the step S3 is implemented by adding or replacing the following methods for dividing road surfaces and road teeth: and dividing the road surface and the road teeth according to the reflectivity of the laser.
7. The method for cleaning the edge of the outdoor unmanned sweeper truck according to claim 6, wherein the collected reflectivity is used for setting a reflectivity segmentation range, so that object characteristics of the collected data can be extracted and classified, and the boundary position of the road surface and the road teeth can be obtained.
8. The method for cleaning the edge of the outdoor unmanned sweeping vehicle according to claim 1, wherein the method for correcting the advancing direction of the unmanned sweeping vehicle in the step S5 comprises the following steps: the distance from the extension line of the advancing direction of the unmanned sweeper to the edge of the road from the data junction point of the laser radar can be known to be deviated from the edge of the road or the edge of the road by comparing the change trend of the difference value of the two adjacent distance values.
9. The device for using the welt cleaning method of the outdoor unmanned sweeping vehicle as claimed in any one of claims 1 to 6, wherein a slope platform is arranged in front of the vehicle body of the unmanned sweeping vehicle and is 80-120cm away from the ground, and a two-dimensional laser radar is mounted on the slope platform.
10. The method for cleaning the edge of an outdoor unmanned sweeping vehicle according to claim 9, wherein the inclined platform forms an included angle of 40-50 degrees with the ground, and the two-dimensional laser radar is installed on the right side of the inclined platform.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110156181.7A CN112837333A (en) | 2021-02-04 | 2021-02-04 | Method and equipment for cleaning welt of outdoor unmanned sweeper |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110156181.7A CN112837333A (en) | 2021-02-04 | 2021-02-04 | Method and equipment for cleaning welt of outdoor unmanned sweeper |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112837333A true CN112837333A (en) | 2021-05-25 |
Family
ID=75932130
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110156181.7A Pending CN112837333A (en) | 2021-02-04 | 2021-02-04 | Method and equipment for cleaning welt of outdoor unmanned sweeper |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112837333A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117449236A (en) * | 2023-09-12 | 2024-01-26 | 广东神州智绘环境科技有限公司 | Cleaning method and system for cleaning curb, storage and electronic equipment |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| ES2328320A1 (en) * | 2007-08-23 | 2009-11-11 | Medio Ambiente Tercer Milenio S.L. | System of control of the mechanical scale of steel and footwear (Machine-translation by Google Translate, not legally binding) |
| CN103696381A (en) * | 2013-12-20 | 2014-04-02 | 长沙中联重科环卫机械有限公司 | Control method, control device, control system and sweeping vehicle for road edge cleaning |
| US20160026184A1 (en) * | 2014-07-24 | 2016-01-28 | GM Global Technology Operations LLC | Curb detection using lidar with sparse measurements |
| CN105911553A (en) * | 2016-04-15 | 2016-08-31 | 北京信息科技大学 | Determination method and system for road feasible region |
| KR101773372B1 (en) * | 2017-04-20 | 2017-08-31 | 한국건설기술연구원 | Method and Apparatus for Measuring Road Shoulder Width |
| CN107742091A (en) * | 2016-08-22 | 2018-02-27 | 腾讯科技（深圳）有限公司 | A kind of method and device of curb extraction |
| WO2018205119A1 (en) * | 2017-05-09 | 2018-11-15 | 深圳市速腾聚创科技有限公司 | Roadside detection method and system based on laser radar scanning |
| US20190340447A1 (en) * | 2018-05-02 | 2019-11-07 | Tusimple, Inc. | Curb detection by analysis of reflection images |
| WO2020080088A1 (en) * | 2018-10-15 | 2020-04-23 | 三菱電機株式会社 | Information processing device |
| CN111383464A (en) * | 2018-12-28 | 2020-07-07 | 沈阳美行科技有限公司 | Vehicle lane change recognition method and device, electronic equipment and medium |
| CN111736603A (en) * | 2020-06-22 | 2020-10-02 | 广州赛特智能科技有限公司 | Unmanned sweeper and long-distance welting sweeping method thereof |
| CN112081046A (en) * | 2020-09-10 | 2020-12-15 | 芜湖酷哇机器人产业技术研究院有限公司 | Intelligent cleaning device and method suitable for sanitation vehicle |
| CN112258566A (en) * | 2020-12-22 | 2021-01-22 | 中智行科技有限公司 | Pavement collection point identification method and device and server |
-
2021
- 2021-02-04 CN CN202110156181.7A patent/CN112837333A/en active Pending
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| ES2328320A1 (en) * | 2007-08-23 | 2009-11-11 | Medio Ambiente Tercer Milenio S.L. | System of control of the mechanical scale of steel and footwear (Machine-translation by Google Translate, not legally binding) |
| CN103696381A (en) * | 2013-12-20 | 2014-04-02 | 长沙中联重科环卫机械有限公司 | Control method, control device, control system and sweeping vehicle for road edge cleaning |
| US20160026184A1 (en) * | 2014-07-24 | 2016-01-28 | GM Global Technology Operations LLC | Curb detection using lidar with sparse measurements |
| CN105911553A (en) * | 2016-04-15 | 2016-08-31 | 北京信息科技大学 | Determination method and system for road feasible region |
| CN107742091A (en) * | 2016-08-22 | 2018-02-27 | 腾讯科技（深圳）有限公司 | A kind of method and device of curb extraction |
| KR101773372B1 (en) * | 2017-04-20 | 2017-08-31 | 한국건설기술연구원 | Method and Apparatus for Measuring Road Shoulder Width |
| WO2018205119A1 (en) * | 2017-05-09 | 2018-11-15 | 深圳市速腾聚创科技有限公司 | Roadside detection method and system based on laser radar scanning |
| US20190340447A1 (en) * | 2018-05-02 | 2019-11-07 | Tusimple, Inc. | Curb detection by analysis of reflection images |
| WO2020080088A1 (en) * | 2018-10-15 | 2020-04-23 | 三菱電機株式会社 | Information processing device |
| CN111383464A (en) * | 2018-12-28 | 2020-07-07 | 沈阳美行科技有限公司 | Vehicle lane change recognition method and device, electronic equipment and medium |
| CN111736603A (en) * | 2020-06-22 | 2020-10-02 | 广州赛特智能科技有限公司 | Unmanned sweeper and long-distance welting sweeping method thereof |
| CN112081046A (en) * | 2020-09-10 | 2020-12-15 | 芜湖酷哇机器人产业技术研究院有限公司 | Intelligent cleaning device and method suitable for sanitation vehicle |
| CN112258566A (en) * | 2020-12-22 | 2021-01-22 | 中智行科技有限公司 | Pavement collection point identification method and device and server |
Non-Patent Citations (1)
| Title |
|---|
| 赵海鹏;习晓环;王成;雷钊;: "基于车载激光扫描数据的城区道路自动提取", 中国科学院大学学报, no. 06, 15 November 2018 (2018-11-15) * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117449236A (en) * | 2023-09-12 | 2024-01-26 | 广东神州智绘环境科技有限公司 | Cleaning method and system for cleaning curb, storage and electronic equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111551958B (en) | Mining area unmanned high-precision map manufacturing method | |
| CN109684921B (en) | Road boundary detection and tracking method based on three-dimensional laser radar | |
| CN114842438B (en) | Terrain detection method, system and readable storage medium for automatic driving automobile | |
| CN111273305B (en) | Multi-sensor fusion road extraction and indexing method based on global and local grid maps | |
| CN106997688B (en) | Parking lot parking space detection method based on multi-sensor information fusion | |
| CN111006655B (en) | Multi-scene autonomous navigation positioning method for airport inspection robot | |
| CN108398672B (en) | Forward-tilting 2D laser radar mobile scanning-based pavement and obstacle detection method | |
| CN108280840B (en) | Road real-time segmentation method based on three-dimensional laser radar | |
| CN111142116B (en) | Road detection and modeling method based on three-dimensional laser | |
| Hervieu et al. | Road side detection and reconstruction using LIDAR sensor | |
| US20230334776A1 (en) | Sensor calibration with environment map | |
| CN103714538A (en) | Road edge detection method, device and vehicle | |
| CN112674646B (en) | Self-adaptive welting operation method based on multi-algorithm fusion and robot | |
| Knoeppel et al. | Robust vehicle detection at large distance using low resolution cameras | |
| CN114808649B (en) | Highway scribing method based on vision system control | |
| Kellner et al. | Road curb detection based on different elevation mapping techniques | |
| CN113640822A (en) | High-precision map construction method based on non-map element filtering | |
| CN115861968A (en) | Dynamic obstacle removing method based on real-time point cloud data | |
| Meis et al. | A new method for robust far-distance road course estimation in advanced driver assistance systems | |
| Miyazaki et al. | Line-based planar structure extraction from a point cloud with an anisotropic distribution | |
| CN112837333A (en) | Method and equipment for cleaning welt of outdoor unmanned sweeper | |
| CN112085101A (en) | High-performance and high-reliability environment fusion sensing method and system | |
| CN113947665B (en) | Method for constructing map of spherical hedge trimmer based on multi-line laser radar and monocular vision | |
| Nurunnabi et al. | Robust locally weighted regression for ground surface extraction in mobile laser scanning 3D data | |
| Bai et al. | An extended hyperbola model for road tracking for video-based personal navigation |
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 |