CN114047750A - Express delivery warehousing method based on mobile robot - Google Patents
Express delivery warehousing method based on mobile robot Download PDFInfo
- Publication number
- CN114047750A CN114047750A CN202111245361.9A CN202111245361A CN114047750A CN 114047750 A CN114047750 A CN 114047750A CN 202111245361 A CN202111245361 A CN 202111245361A CN 114047750 A CN114047750 A CN 114047750A
- Authority
- CN
- China
- Prior art keywords
- grid
- information
- map
- express delivery
- semantic
- 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.)
- Withdrawn
Links
- 238000000034 method Methods 0.000 title claims abstract description 26
- 230000004927 fusion Effects 0.000 claims description 10
- 238000013507 mapping Methods 0.000 claims description 10
- 238000001514 detection method Methods 0.000 claims description 8
- 238000013528 artificial neural network Methods 0.000 claims description 6
- 238000012549 training Methods 0.000 claims description 4
- 230000001133 acceleration Effects 0.000 claims description 3
- 238000005286 illumination Methods 0.000 claims description 3
- 238000012952 Resampling Methods 0.000 claims description 2
- 238000012850 discrimination method Methods 0.000 claims description 2
- 238000001914 filtration Methods 0.000 claims description 2
- 230000003287 optical effect Effects 0.000 claims description 2
- 238000007781 pre-processing Methods 0.000 claims description 2
- 238000007500 overflow downdraw method Methods 0.000 abstract 2
- 230000007547 defect Effects 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
Images
Classifications
-
- 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
- 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
-
- 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
- G05D1/0212—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory
- G05D1/0221—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory involving a learning process
-
- 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
- G05D1/0212—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory
- G05D1/0223—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory involving speed control of the vehicle
-
- 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
- G05D1/0276—Control of position or course in two dimensions specially adapted to land vehicles using signals provided by a source external to the vehicle
Landscapes
- Engineering & Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Physics & Mathematics (AREA)
- Aviation & Aerospace Engineering (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Multimedia (AREA)
- Electromagnetism (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses an express delivery warehousing method based on a mobile robot, which specifically comprises the following steps: the mobile robot determines the vacant goods shelves and the positions of the vacant goods shelves according to database information of the warehouse, a grid semantic map is established and optimized through a sensor fusion method, then path planning is carried out according to the optimized final grid map and the positions of the goods shelves, the robot is controlled to convey express to the corresponding goods shelves, meanwhile, express bill numbers are scanned through cameras, then express warehousing information is notified to a pickup person, the warehouse database is updated, and the database is updated again after a user picks up the express. The invention obtains the grid semantic map by an information fusion method, and optimizes the map by semantic information, so that the mobile robot can accurately identify the position of the goods shelf in the post house to plan the path.
Description
Technical Field
The invention belongs to an express logistics technology, and particularly relates to an express warehousing method based on a mobile robot.
Background
At present, with the rapid development of electronic commerce, express storage is an indispensable part in logistics distribution. In current logistics distribution service station, will generally print out the goods shelves number after receiving the goods shelves through express delivery staff soon, then send the addressee after integrating goods shelves number and addressee information, in view of the numerous of express delivery, a large amount of manpower and materials have been utilized in whole work.
Some post house unmanned forms exist at present, such as intelligent containers, AVG trolley use and the like, and the above modes have the following defects: for intelligent containers, when the express delivery volume is increased in a special time period every year, the capacity of the intelligent containers needs to be increased, but the containers cannot be fully utilized at ordinary times, and the cost can be greatly increased. The AVG trolley is suitable for warehouses and is not suitable for common containers because a path needs to be preset and guide rails need to be laid. Post house in the real life needs often adjust post house position according to the stream of people distribution, and the laying of so frequent change guide rail can promote work load, has also promoted the cost.
The mapping positioning method applied to the mobile robot at the present stage also has some defects, for example, the performance of the laser slam is poor under the conditions of unobvious environmental characteristics, dynamic environment and the like, and the laser slam is difficult to return to a working state after tracking loss due to poor repositioning capability. Although the visual slam can well complete point cloud matching and loop detection in an environment and effectively reduce accumulated errors, the visual slam has some difficulties in application, including initialization, insufficient vision of a binocular camera, large calculation amount, loss of characteristics, easy occurrence of shielding and light source interference, and poor performance in an environment without textures or weak illumination. Some slam algorithms based on sensor fusion have appeared at present, some above problems have been solved, but under the application scene of express delivery post house, because the structural feature of goods shelves fretwork and there are goods shelves goods to put untidy scheduling problem, mobile robot often can not be accurate build the picture, leads to its to bump when navigating.
Disclosure of Invention
The invention aims to provide an express delivery warehousing method based on a mobile robot, which solves the following problems:
1. the express courier station changes the position frequently, the express quantity is very different in different time periods, the goods shelf needs to be adjusted frequently, and the traditional intelligent goods cabinet and the AVG trolley used in the warehouse have certain limitations and cannot meet the requirements well;
2. under the application scene of express delivery post house, because the structural feature of goods shelves fretwork and there be goods shelves goods and put untidy scheduling problem, mobile robot often can not be accurate build the picture, leads to its to bump when the navigation.
The technical solution for realizing the invention is as follows: an express delivery warehousing method based on a mobile robot comprises the following steps:
step 1, establishing a database comprising express delivery information, information of a goods shelf where the express delivery is located and information of a pickup person, determining an unoccupied goods shelf by using database information of a warehouse when the express delivery is put in storage, and determining the position of the unoccupied goods shelf according to the information of the goods shelf;
step 3, fusing the local grid map obtained through the binocular camera and the preliminary grid map obtained through the laser radar to obtain an intermediate grid map, and mapping semantic information obtained through target detection performed by the camera to obtain a grid semantic map;
step 4, optimizing the hollow part of the shelf in the grid semantic map by utilizing the semantic information to obtain a final grid map:
step 5, planning paths according to the final grid map and the pose information of the mobile robot, wherein the global path planning uses an A-x algorithm, the local path planning uses a dynamic window algorithm, and then, a bottom layer motion control instruction is obtained according to the pose information of the mobile robot, the planned path information and the motion parameters of the robot; the motion parameters of the robot comprise a maximum steering angle, a turning radius, an expansion coefficient, a maximum speed and a maximum acceleration;
step 6, the mobile robot moves to a corresponding shelf position according to the bottom layer motion control instruction, and the lifting platform cooperates with the mechanical arm to clamp and store express items into corresponding shelves according to the height of the shelves;
step 7, photographing an express delivery placing position in the express delivery clamping process, identifying an express delivery bill number and addressee information according to a bar code, notifying a user of express delivery arrival information and placed shelf information, and updating a database of a warehouse according to express delivery information, shelf information and delivery taking information;
and 8, after the user takes the express delivery, updating the database of the warehouse again to ensure that the real-time property of the database information is convenient for judging the vacant shelf according to the database information when the express delivery is put in the warehouse.
Compared with the prior art, the invention has the remarkable advantages that:
(1) the system has the capability of self-drawing and navigation, and can still deliver the quick-release data to the vacant shelves when the shelves of the post station are adjusted.
(2) The grid semantic map is obtained through sensor fusion, and the map is optimized through semantic information, so that the mobile robot can accurately identify the position of the goods shelf in the map to plan the path.
Drawings
Fig. 1 is a flow chart of an express delivery warehousing method based on a mobile robot.
FIG. 2 is a flow chart of the invention for building a grid semantic map based on sensor fusion and optimizing the map according to semantic information.
Fig. 3 is a schematic structural diagram of a mobile robot implementing the present invention.
Detailed Description
The present invention is described in further detail below with reference to the attached drawing figures.
With reference to fig. 1 to 3, the express delivery warehousing method based on the mobile robot is characterized in that the mobile robot is provided with a camera 1, a manipulator 2, a lifting platform 3, a laser radar 4 and a binocular camera 5, the manipulator 2 is used for grabbing express delivery, the lifting platform 3 adjusts the height of the manipulator 2 according to the number of layers of a goods shelf after the mobile robot moves to the position of the goods shelf, so that the manipulator can conveniently grab the express delivery to a target goods shelf, the binocular camera 5 is used for shooting image information of an environment in real time, the laser radar 4 is used for scanning point cloud information, and the camera 1 is used for scanning an express delivery order number; the method comprises the following specific steps:
step 1, establishing a database comprising express delivery information, goods shelf information where express delivery is located and pickup information, determining vacant goods shelves by using database information of a warehouse when express delivery is put in storage, and determining the positions of the vacant goods shelves according to the goods shelf information.
Step 3, fusing the local grid map obtained through the binocular camera and the preliminary grid map obtained through the laser radar to obtain an intermediate grid map, and mapping semantic information obtained through target detection performed by the camera to obtain a grid semantic map, wherein the grid semantic map specifically comprises the following steps:
step 3-1, establishing a local grid map by using a binocular camera 5: firstly setting the size of a map and the size of grids, initializing a local map according to the action range of a binocular camera 5, then acquiring three-dimensional points within a certain height range through the binocular camera 5, then counting the projection of the point clouds on the initialized map, calculating the number of times each grid is projected by obstacles, judging whether each grid is an obstacle or not by using a threshold value, acquiring a discrete grid obstacle map, and then radially scanning the discrete grid obstacle maps at all angles by taking the optical center of the binocular camera 5 as a starting point to form the local grid map.
3-2, establishing a preliminary grid map by using a laser radar 4: and establishing a preliminary grid map through Gmapping by combining the point cloud information scanned by the laser radar and the pose information of the robot, wherein the preliminary grid map is a two-dimensional map.
Step 3-3, fusing the local grid map and the preliminary grid map: firstly, extracting a local grid map obtained by a binocular camera 5 and a preliminary grid map obtained by a laser radar to a feature space, measuring the similarity according to the feature space by an Euclidean distance discrimination method, searching similar feature points of feature points to be matched in the feature space, and aligning the local grid map with the preliminary grid map after matching is successful. The specific fusion mode after alignment is as follows, and the grid map attributes are divided into three categories: occupied (1), unoccupied (-1), and unknown (0), the grid attribute of the map after the fusion is determined by referring to the following table according to the grid attribute before the fusion.
Step 3-4, obtaining semantic information through a binocular camera 5: the method comprises the steps of preprocessing a real-time image shot by a binocular camera 5 through illumination balance, contrast enhancement and noise removal, detecting a target through a training neural network to obtain semantic information, and outputting the image information shot by the binocular camera 5 as input and the position size and the type of the target.
The specific implementation steps for obtaining the semantic information through the binocular camera are as follows:
1) an image is divided into 7 x 7 grids, which are responsible for predicting the detected object if the center of the detected object falls within the grid.
2) Each grid predicts 2 sliding windows, and each sliding window needs to predict x, y, w, h and confidence coefficient with 5 values in total (wherein x and y are the center coordinates of the sliding window, w is the width of the sliding window, and h is the height of the sliding window).
3) Each grid predicts a category of information, for a total of 4 categories including ground, wall, shelf and courier.
4) The network outputs a tensor of 7 × 7 × (5 × 2+4), i.e., 7 × 7 meshes, each of which predicts 2 sliding windows and 4 classes.
5) And (4) combining the coordinate prediction loss, the confidence coefficient prediction loss and the class prediction loss as a loss function, and training the neural network through back propagation.
6) And inputting the real-time image obtained by the binocular camera 5 into a neural network to perform target detection so as to obtain semantic information.
Step 3-5, mapping the semantic information to a middle grid map to obtain a grid semantic map: and performing feature matching according to the position and size of the target in the semantic information and the obstacles in the grid map, mapping the matched semantic point cloud into the grid map, and incrementally constructing the grid semantic map by a Bayesian filtering method.
Step 4, optimizing the hollow part of the shelf in the grid semantic map by utilizing the semantic information to obtain a final grid map:
because the goods shelf has a special hollow structure, the goods shelf can not be accurately represented in the grid map, and therefore the established grid semantic map needs to be optimized. The method comprises the steps of optimally filling the hollow part of the shelf by utilizing semantic information by means of a geometric feature matching method, identifying the semantic information in a grid semantic map as grid blocks of the shelf, optimizing the grid blocks into regular rectangles, and determining the size of the rectangles in the map according to the size of the grid and the standard length and width of the shelf.
Step 5, path planning: and planning paths according to the final grid map and the pose information of the mobile robot, wherein the global path planning uses an A-algorithm, the local path planning uses a dynamic window algorithm, and then obtaining a bottom layer motion control instruction according to the pose information of the mobile robot, the planned path information and the motion parameters (including a maximum steering angle, a turning radius, an expansion coefficient, a maximum speed, a maximum acceleration and the like) of the robot.
And 6, moving the mobile robot to a corresponding shelf position according to the bottom layer motion control instruction, and clamping express items and storing the express items in the corresponding shelf by the aid of the lifting platform and the mechanical arm in cooperation according to the height of the shelf.
And 7, photographing the express delivery placing position in the express delivery clamping process, identifying the express delivery bill number and the addressee information according to the bar code, notifying a user of express delivery arrival information and placed shelf information, and updating a database of the warehouse according to the express delivery information, the shelf information and the delivery taking information.
And 8, after the user takes the express delivery, updating the database of the warehouse again to ensure that the real-time property of the database information is convenient for judging the vacant shelf according to the database information when the express delivery is put in the warehouse.
In summary, the present invention has the capability of self-mapping and navigation, and can still deliver the data to the vacant shelves when the shelves of the post house are adjusted. The grid semantic map is obtained through sensor fusion, and the map is optimized through semantic information, so that the mobile robot can accurately identify the position of the goods shelf in the map to plan the path.
Claims (6)
1. An express delivery warehousing method based on a mobile robot is characterized by comprising the following steps:
step 1, establishing a database comprising express delivery information, information of a goods shelf where the express delivery is located and information of a pickup person, determining an unoccupied goods shelf by using database information of a warehouse when the express delivery is put in storage, and determining the position of the unoccupied goods shelf according to the information of the goods shelf;
step 2, pose estimation is carried out on the mobile robot:
step 3, fusing the local grid map obtained through the binocular camera and the preliminary grid map obtained through the laser radar to obtain an intermediate grid map, and mapping semantic information obtained through target detection performed by the camera to obtain a grid semantic map;
step 4, optimizing the hollow part of the shelf in the grid semantic map by utilizing the semantic information to obtain a final grid map:
step 5, planning paths according to the final grid map and the pose information of the mobile robot, wherein the global path planning uses an A-x algorithm, the local path planning uses a dynamic window algorithm, and then, a bottom layer motion control instruction is obtained according to the pose information of the mobile robot, the planned path information and the motion parameters of the robot; the motion parameters of the robot comprise a maximum steering angle, a turning radius, an expansion coefficient, a maximum speed and a maximum acceleration;
step 6, the mobile robot moves to a corresponding shelf position according to the bottom layer motion control instruction, and the lifting platform cooperates with the mechanical arm to clamp and store express items into corresponding shelves according to the height of the shelves;
step 7, photographing an express delivery placing position in the express delivery clamping process, identifying an express delivery bill number and addressee information according to a bar code, notifying a user of express delivery arrival information and placed shelf information, and updating a database of a warehouse according to express delivery information, shelf information and delivery taking information;
and 8, after the user takes the express delivery, updating the database of the warehouse again to ensure that the real-time property of the database information is convenient for judging the vacant shelf according to the database information when the express delivery is put in the warehouse.
2. The express delivery warehousing method based on the mobile robot as claimed in claim 1, wherein: in step 2, pose estimation is performed on the mobile robot, specifically as follows:
and continuously and iteratively estimating the pose of the robot at each moment by a resampling algorithm by virtue of the point cloud information scanned by the odometer and the laser radar.
3. The express delivery warehousing method based on the mobile robot as claimed in claim 1, wherein: in step 3, fusing the local grid map obtained by the binocular camera and the preliminary grid map obtained by the laser radar to obtain an intermediate grid map, and mapping semantic information obtained by target detection performed by the camera to obtain a grid semantic map, wherein the method specifically comprises the following steps:
3-1, establishing a local grid map by using a binocular camera;
3-2, establishing a preliminary grid map by using a laser radar:
establishing a preliminary grid map through Gmapping by combining point cloud information scanned by a laser radar and pose information of a robot;
step 3-3, fusing the local grid map and the preliminary grid map:
firstly, extracting a local grid map obtained by a binocular camera and a primary grid map obtained by a laser radar to a feature space, measuring the similarity according to the feature space by an Euclidean distance discrimination method, searching similar feature points of feature points to be matched in the feature space, and aligning the local grid map with the primary grid map after matching is successful; the specific fusion mode after alignment is as follows, the grid map attributes are divided into three categories: and the occupied is represented by 1, the unoccupied is represented by-1, and the unknown is represented by 0, and the grid attribute of the map after fusion is determined according to the grid attribute before fusion and the following table:
step 3-4, obtaining semantic information through a binocular camera: firstly, preprocessing a real-time image shot by a binocular camera through illumination balance, contrast enhancement and noise removal, then carrying out target detection through a training neural network so as to obtain semantic information, and taking the image information shot by the binocular camera as input and identifying the position size and the type of a target as output;
step 3-5, mapping the semantic information to a middle grid map to obtain a grid semantic map:
and performing feature matching according to the position and size of the target in the semantic information and the obstacles in the grid map, mapping the matched semantic point cloud into the grid map, and incrementally constructing the grid semantic map by a Bayesian filtering method.
4. The express delivery warehousing method based on the mobile robot as claimed in claim 3, wherein: in step 3-1, a local grid map is established by using a binocular camera, specifically as follows:
firstly setting the size of a map and the size of a grid, initializing a local map according to the action range of a binocular camera, then acquiring three-dimensional points within a certain height range through the binocular camera, then counting the projection of the point cloud on the initialized map, calculating the number of times each grid is projected by an obstacle, judging whether each grid is an obstacle or not by using a threshold value, acquiring a discrete grid obstacle map, and then carrying out radial scanning on the discrete grid obstacle maps at all angles by taking the optical center of the binocular camera as a starting point to form the local grid map.
5. The express delivery warehousing method based on the mobile robot as claimed in claim 3, wherein: in step 3-4, the specific implementation steps for obtaining the semantic information through the binocular camera are as follows:
1) dividing an image into 7 x 7 grids, and if the center of a detected object falls in the grid, the grid is responsible for predicting the detected object;
2) predicting 2 sliding windows in each grid, wherein x, y, w, h and confidence coefficient of each sliding window are 5 values in total, wherein x and y are central coordinates of the sliding window, w is the width of the sliding window, and h is the height of the sliding window;
3) each grid predicts a category information, and the total number is 4 categories including ground, wall, shelf and express;
4) the network outputs a tensor of 7 × 7 × (5 × 2+4), i.e., 7 × 7 meshes, each of which predicts 2 sliding windows and 4 classes;
5) combining the coordinate prediction loss, the confidence coefficient prediction loss and the category prediction loss as a loss function, and training the neural network through back propagation;
6) and inputting the real-time image obtained by the binocular camera into a neural network to perform target detection so as to obtain semantic information.
6. The express delivery warehousing method based on the mobile robot as claimed in claim 3, wherein: in step 4, optimizing the hollow part of the shelf in the grid semantic map by utilizing the semantic information to obtain a final grid map, which is as follows:
and optimally filling the hollow part of the shelf by utilizing semantic information by means of a geometric feature matching method, namely identifying the semantic information in the grid semantic map as grid blocks of the shelf, and optimizing the grid blocks into regular rectangles.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111245361.9A CN114047750A (en) | 2021-10-26 | 2021-10-26 | Express delivery warehousing method based on mobile robot |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111245361.9A CN114047750A (en) | 2021-10-26 | 2021-10-26 | Express delivery warehousing method based on mobile robot |
Publications (1)
Publication Number | Publication Date |
---|---|
CN114047750A true CN114047750A (en) | 2022-02-15 |
Family
ID=80205963
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202111245361.9A Withdrawn CN114047750A (en) | 2021-10-26 | 2021-10-26 | Express delivery warehousing method based on mobile robot |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114047750A (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114627192A (en) * | 2022-03-17 | 2022-06-14 | 武昌工学院 | Machine vision and Arduino control system of express delivery receiving and dispatching robot |
CN115351803A (en) * | 2022-10-20 | 2022-11-18 | 湖北信通通信有限公司 | Path planning method and device for warehouse logistics robot |
CN115586748A (en) * | 2022-11-24 | 2023-01-10 | 苏州德机自动化科技有限公司 | Mobile intelligent flexible motion control system and method thereof |
CN115965900A (en) * | 2023-03-09 | 2023-04-14 | 杭州也得智能有限公司 | Express item identification and search system and method |
CN116443527A (en) * | 2023-06-13 | 2023-07-18 | 上海木蚁机器人科技有限公司 | Pallet fork method, device, equipment and medium based on laser radar |
-
2021
- 2021-10-26 CN CN202111245361.9A patent/CN114047750A/en not_active Withdrawn
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114627192A (en) * | 2022-03-17 | 2022-06-14 | 武昌工学院 | Machine vision and Arduino control system of express delivery receiving and dispatching robot |
CN114627192B (en) * | 2022-03-17 | 2024-04-02 | 武昌工学院 | Machine vision and Arduino control system for receiving and dispatching express robot |
CN115351803A (en) * | 2022-10-20 | 2022-11-18 | 湖北信通通信有限公司 | Path planning method and device for warehouse logistics robot |
CN115586748A (en) * | 2022-11-24 | 2023-01-10 | 苏州德机自动化科技有限公司 | Mobile intelligent flexible motion control system and method thereof |
CN115586748B (en) * | 2022-11-24 | 2023-03-10 | 苏州德机自动化科技有限公司 | Mobile intelligent flexible motion control system and method thereof |
CN115965900A (en) * | 2023-03-09 | 2023-04-14 | 杭州也得智能有限公司 | Express item identification and search system and method |
CN115965900B (en) * | 2023-03-09 | 2023-06-09 | 杭州也得智能有限公司 | Express item identification searching system and method |
CN116443527A (en) * | 2023-06-13 | 2023-07-18 | 上海木蚁机器人科技有限公司 | Pallet fork method, device, equipment and medium based on laser radar |
CN116443527B (en) * | 2023-06-13 | 2023-09-08 | 上海木蚁机器人科技有限公司 | Pallet fork method, device, equipment and medium based on laser radar |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN114047750A (en) | Express delivery warehousing method based on mobile robot | |
CN112014857B (en) | Three-dimensional laser radar positioning and navigation method for intelligent inspection and inspection robot | |
CN111563442B (en) | Slam method and system for fusing point cloud and camera image data based on laser radar | |
CA2982044C (en) | Method and device for real-time mapping and localization | |
CN104536445B (en) | Mobile navigation method and system | |
CN111664843A (en) | SLAM-based intelligent storage checking method | |
CN109186606B (en) | Robot composition and navigation method based on SLAM and image information | |
CN108921947A (en) | Generate method, apparatus, equipment, storage medium and the acquisition entity of electronic map | |
CN112486171B (en) | Robot obstacle avoidance method based on vision | |
CN106647738A (en) | Method and system for determining docking path of automated guided vehicle, and automated guided vehicle | |
Fruh et al. | Fast 3D model generation in urban environments | |
WO2022052660A1 (en) | Warehousing robot localization and mapping methods, robot, and storage medium | |
CN112363158B (en) | Pose estimation method for robot, robot and computer storage medium | |
CN110716559B (en) | Comprehensive control method for shopping mall and supermarket goods picking robot | |
JP7280450B2 (en) | Image search for walkthrough videos | |
CN110726413B (en) | Multi-sensor fusion and data management method for large-scale SLAM | |
CN115699098A (en) | Machine learning based object identification using scale maps and three-dimensional models | |
CN116295412A (en) | Depth camera-based indoor mobile robot dense map building and autonomous navigation integrated method | |
CN114387576A (en) | Lane line identification method, system, medium, device and information processing terminal | |
CN115454055B (en) | Multi-layer fusion map representation method for indoor autonomous navigation and operation | |
CN110618700A (en) | Three-dimensional geographic information system for community distribution and unmanned aerial vehicle track path planning application method | |
CN115494845A (en) | Navigation method and device based on depth camera, unmanned vehicle and storage medium | |
CN113310484A (en) | Mobile robot positioning method and system | |
Zhao et al. | The construction method of the digital operation environment for bridge cranes | |
CN112338910A (en) | Space map determination method, robot, storage medium and 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 | ||
WW01 | Invention patent application withdrawn after publication | ||
WW01 | Invention patent application withdrawn after publication |
Application publication date: 20220215 |