CN117496739A - Self-adaptive double-layer garage navigation system for transfer robot - Google Patents
Self-adaptive double-layer garage navigation system for transfer robot Download PDFInfo
- Publication number
- CN117496739A CN117496739A CN202311465071.4A CN202311465071A CN117496739A CN 117496739 A CN117496739 A CN 117496739A CN 202311465071 A CN202311465071 A CN 202311465071A CN 117496739 A CN117496739 A CN 117496739A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- parked
- garage
- intelligent double
- layer
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000012546 transfer Methods 0.000 title claims abstract description 110
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 16
- 238000010845 search algorithm Methods 0.000 claims abstract description 10
- 238000000034 method Methods 0.000 claims description 43
- 238000010586 diagram Methods 0.000 claims description 21
- 230000008569 process Effects 0.000 claims description 17
- 230000003044 adaptive effect Effects 0.000 claims description 16
- 238000007726 management method Methods 0.000 claims description 15
- 238000013135 deep learning Methods 0.000 claims description 13
- 238000003860 storage Methods 0.000 claims description 13
- 238000012937 correction Methods 0.000 claims description 12
- 230000000903 blocking effect Effects 0.000 claims description 9
- 238000012545 processing Methods 0.000 claims description 9
- 206010028896 Needle track marks Diseases 0.000 claims description 4
- 230000000007 visual effect Effects 0.000 claims description 4
- 238000004891 communication Methods 0.000 claims description 2
- 238000009826 distribution Methods 0.000 claims description 2
- 239000003086 colorant Substances 0.000 claims 1
- 238000004590 computer program Methods 0.000 description 7
- 238000013527 convolutional neural network Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 238000012986 modification Methods 0.000 description 4
- 230000004048 modification Effects 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 3
- 230000004075 alteration Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 230000002068 genetic effect Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Classifications
-
- E—FIXED CONSTRUCTIONS
- E04—BUILDING
- E04H—BUILDINGS OR LIKE STRUCTURES FOR PARTICULAR PURPOSES; SWIMMING OR SPLASH BATHS OR POOLS; MASTS; FENCING; TENTS OR CANOPIES, IN GENERAL
- E04H6/00—Buildings for parking cars, rolling-stock, aircraft, vessels or like vehicles, e.g. garages
- E04H6/42—Devices or arrangements peculiar to garages, not covered elsewhere, e.g. securing devices, safety devices, monitoring and operating schemes; centering devices
- E04H6/422—Automatically operated car-parks
-
- E—FIXED CONSTRUCTIONS
- E04—BUILDING
- E04H—BUILDINGS OR LIKE STRUCTURES FOR PARTICULAR PURPOSES; SWIMMING OR SPLASH BATHS OR POOLS; MASTS; FENCING; TENTS OR CANOPIES, IN GENERAL
- E04H6/00—Buildings for parking cars, rolling-stock, aircraft, vessels or like vehicles, e.g. garages
- E04H6/08—Garages for many vehicles
- E04H6/12—Garages for many vehicles with mechanical means for shifting or lifting vehicles
- E04H6/30—Garages for many vehicles with mechanical means for shifting or lifting vehicles with means for transport in horizontal direction only
- E04H6/36—Garages for many vehicles with mechanical means for shifting or lifting vehicles with means for transport in horizontal direction only characterised by use of freely-movable dollies
-
- E—FIXED CONSTRUCTIONS
- E04—BUILDING
- E04H—BUILDINGS OR LIKE STRUCTURES FOR PARTICULAR PURPOSES; SWIMMING OR SPLASH BATHS OR POOLS; MASTS; FENCING; TENTS OR CANOPIES, IN GENERAL
- E04H6/00—Buildings for parking cars, rolling-stock, aircraft, vessels or like vehicles, e.g. garages
- E04H6/42—Devices or arrangements peculiar to garages, not covered elsewhere, e.g. securing devices, safety devices, monitoring and operating schemes; centering devices
- E04H6/426—Parking guides
-
- 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
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/09—Arrangements for giving variable traffic instructions
- G08G1/0962—Arrangements for giving variable traffic instructions having an indicator mounted inside the vehicle, e.g. giving voice messages
- G08G1/0968—Systems involving transmission of navigation instructions to the vehicle
- G08G1/096833—Systems involving transmission of navigation instructions to the vehicle where different aspects are considered when computing the route
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/14—Traffic control systems for road vehicles indicating individual free spaces in parking areas
Landscapes
- Engineering & Computer Science (AREA)
- Architecture (AREA)
- Physics & Mathematics (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Civil Engineering (AREA)
- Structural Engineering (AREA)
- General Physics & Mathematics (AREA)
- Mechanical Engineering (AREA)
- Mathematical Physics (AREA)
- Automation & Control Theory (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses a self-adaptive double-layer garage navigation system for a transfer robot. This a self-adaptation double-deck garage navigation for transfer robot, including total control platform, intelligent double-deck garage and a plurality of AGV transfer robot, and total control platform passes through wireless connection with intelligent double-deck garage, and total control platform and AGV transfer robot pass through wireless connection. According to the invention, the target parking space is determined by adopting a breadth-first search algorithm according to the vehicle type of the vehicle to be parked and the parking bitmap of the intelligent double-layer garage, and the navigation route of each AGV carrying robot for carrying the vehicle to be parked to the target parking space is planned by combining the new track map through an A-x algorithm according to the track map, the parking bitmap, the real-time state of the intelligent double-layer garage, the real-time state data of each AGV carrying robot and the target parking space data, so that the efficiency of carrying tasks is improved, and the problem of low efficiency of the currently planned navigation route is solved.
Description
Technical Field
The invention relates to the technical field of self-adaptive navigation, in particular to a self-adaptive double-layer garage navigation system for a transfer robot.
Background
With the rapid increase of urbanization and the increase of automobile popularity, the parking demands are increasing. Double-deck garages have been widely used as a solution to efficiently utilize limited space. An AGV (automated guided vehicle) handling robot in a double-deck garage is a highly intelligent autonomous robot specifically designed for handling vehicles in a complex double-deck garage environment. These robots are an important component of modern urban traffic and parking facilities and are intended to provide efficient, accurate and convenient car handling services.
Currently, adaptive double-deck garage navigation systems have been applied in some advanced parking facilities. These systems rely on advanced lidar, cameras and sensors to build a garage map and utilize SLAM algorithms for positioning. In terms of vehicle discrimination, deep learning techniques such as Convolutional Neural Networks (CNNs) are widely employed to achieve high-precision vehicle detection and classification. In the aspect of path planning, a genetic algorithm, an A-x algorithm and the like are adopted to plan the optimal path of the AGV transfer robot. Meanwhile, the intelligent double-layer garage management system is connected with the main control platform through a wireless communication technology, so that real-time task scheduling and cooperation are realized.
For example, bulletin numbers: the automatic guided transporting system, the control method and the automatic guided transporting device disclosed in CN104238468B comprise: dividing the plurality of automated guided transport apparatuses into a plurality of groups; setting one of a plurality of first automatic guiding and carrying devices in a first group of the plurality of groups as a first servo carrying device, and setting the other first automatic guiding and carrying devices as one or a plurality of first terminal carrying devices; and sending feeding information to the first servo carrying devices of the first group, so that the first servo carrying devices respectively assign the first terminal carrying devices to execute corresponding feeding programs according to the feeding information, wherein the first terminal carrying devices automatically plan paths and feed according to the respective corresponding feeding programs.
For example, publication No.: CN115392559a discloses an intelligent remote control method for 5G-based unmanned handling equipment, comprising: the basic environment data are collected according to the remote control instruction, a corresponding unit three-dimensional model is built by utilizing a three-dimensional modeling technology, and finally a plurality of unit three-dimensional models are arranged and spliced to form a comprehensive three-dimensional model, so that a worker can clear the environment of a working area, and the remote control precision is improved; meanwhile, the path of the carrying equipment is planned according to the transportation task, the paths with space-time intersection are tidied and optimized to generate the driving path, the driving path is planned in advance, and the occurrence of sudden accidents can be avoided.
However, in the process of implementing the technical scheme of the invention in the embodiment of the application, the inventor of the application finds that at least the following technical problems exist in the above technology:
in the prior art, when each AGV transfer robot works in a garage, the problem of route conflict among robots is easy to occur, the efficiency of transfer tasks is affected, and the problem of low planned navigation route efficiency exists.
Disclosure of Invention
According to the self-adaptive double-layer garage navigation system for the transfer robot, the problem that the planned navigation route is low in efficiency in the prior art is solved, and the efficiency of a transfer task is improved.
The embodiment of the application provides a self-adaptive double-layer garage navigation system for a transfer robot, which comprises: total control platform, intelligent double-deck garage and a plurality of AGV transfer robot, just total control platform passes through wireless connection with intelligent double-deck garage, through wireless connection between total control platform and the AGV transfer robot: wherein, the total control platform: the system comprises a vehicle management module, an AGV handling robot, a parking bitmap, a parking map, a navigation route management module and a navigation route management module, wherein the vehicle management module is used for receiving vehicle data of a vehicle to be parked, real-time state data of the intelligent double-layer garage and real-time state data of the AGV handling robot, and simultaneously analyzing the navigation route of the AGV handling robot for carrying the vehicle by combining the intelligent double-layer garage track map and the parking map, and sending the navigation route to the AGV handling robot; the intelligent double-layer garage comprises: the intelligent double-layer garage is used for acquiring vehicle data of vehicles to be parked, acquiring real-time state data of each parking space in the intelligent double-layer garage, and transmitting the vehicle data of the vehicles to be parked and the real-time state data of the intelligent double-layer garage to the main control platform; the AGV transfer robot: the intelligent double-layer garage is used for sending real-time state data to the main control platform, identifying the track on the ground of the intelligent double-layer garage, receiving the navigation route sent by the main control platform, and carrying the vehicle to be parked to the target parking space along the navigation route.
Further, the total control platform comprises a receiving module, a database, a planning adjustment module and a sending module; the received module: is used for receiving vehicle data of vehicles to be parked sent by the intelligent double-layer garage and real-time state data of the intelligent double-layer garage, receiving real-time state data of the AGV transfer robots sent by each AGV transfer robot; the database: the intelligent double-layer garage track map and the parking bitmap are used for storing vehicle type data; the planning and adjusting module is used for: the navigation route of the AGV transfer robot for transferring the vehicle is analyzed according to the vehicle data of the vehicle to be parked, the real-time state data of the intelligent double-layer garage, the real-time state data of the AGV transfer robot, the track map of the intelligent double-layer garage and the parking bitmap; the sending module: for transmitting the navigation route to the corresponding AGV handling robot.
Further, the planning and adjusting module comprises a vehicle type identification unit, a parking space allocation unit, a route planning unit and a comparison and selection unit; the vehicle type recognition unit: the method comprises the steps of obtaining the vehicle type of a vehicle to be parked according to vehicle data of the vehicle to be parked sent by an intelligent double-layer garage; the parking space distribution unit comprises: the intelligent double-layer garage is used for distributing a target parking space for the vehicle to be parked according to the type of the vehicle to be parked and the parking bitmap of the intelligent double-layer garage; the route planning unit: the system comprises a track map of an intelligent double-layer garage, real-time states of the intelligent double-layer garage, real-time state data of each AGV carrying robot and target parking space data, wherein a navigation route of each AGV carrying robot for carrying a vehicle to be parked to the target parking space is planned; the comparison selection unit: when the navigation routes of the AGV transfer robots are identical in length, the predicted used time length of the navigation routes of the AGV transfer robots with the identical length is compared, the navigation route with the shortest used time length is selected and stored, and other navigation routes are discarded.
Further, the specific process of obtaining the vehicle type of the vehicle to be parked is as follows: extracting user parking information corresponding to the vehicle to be parked from vehicle data of the vehicle to be parked sent from the intelligent double-layer garage; inquiring vehicle type data of the vehicle to be parked from the user parking information, and directly outputting the vehicle type data of the vehicle to be parked if the vehicle type data is detected; if not, extracting a vehicle to be parked picture corresponding to the vehicle to be parked from vehicle data of the vehicle to be parked sent from the intelligent double-layer garage; inputting the pictures of the vehicles to be parked into a deep learning recognition model to recognize the vehicle types, thereby obtaining the vehicle types of the vehicles to be parked, and outputting the vehicle type data of the vehicles to be parked; the deep learning recognition model is learned by using a deep learning network based on stored vehicle type data stored in a database.
Further, the specific process of allocating the target parking space for the vehicle to be parked is as follows: according to the type D of the vehicle supported by the parking spaces in the intelligent double-layer garage, the parking spaces in the intelligent double-layer garage are numbered and recorded asWhere D is the number of the vehicle type, d=1, 2 0 ，D 0 For intelligent double-deck garage to support total number of vehicle types of parking, c is the number of layers of parking stall of intelligent double-deck garage, c=1, 2, i is the plane number of parking stall, i=1, 2 0 ，i 0 The total number of parking spaces in the parking space plan of the intelligent double-layer garage; according to the vehicle type corresponding to the vehicle to be parked, searching all parking spaces supporting the vehicle type to be parked from a parking bitmap of the intelligent double-layer garage; co-extracting pre-stored time length T of vehicle to be parked from corresponding user vehicle parking information of vehicle to be parked j J is the number of the parked vehicle parked in the parking garage of the intelligent double-deck garage, j=1, 2 0 ，j 0 In order to support the total number of parked vehicles in a parking room in the intelligent double-layer garage, counting the residual vehicle storage duration delta T of the stored vehicles in the intelligent double-layer garage k K is the number of the existing vehicles in the intelligent double-layer garage, k=1, 2, and k 0 ，k 0 To calculate the total number of vehicles stored in the intelligent double-layer garage, the vehicles to be parked are stored in the intelligent double-layer garageDistance complex regularization index phi in double-layer garage j The method comprises the steps of carrying out a first treatment on the surface of the Taking the current parking room position of the vehicle to be parked as a starting node, taking all the searched parking spaces supporting the type of the vehicle to be parked as end points, taking the parked vehicle in the garage as a node interrupt position, and sequentially using a breadth-first search algorithm according to the parking bitmap of the intelligent double-layer garage to obtain the required node layers from the parking room position of the vehicle to be parked to the parking spaces respectively >The node layer number is->Ordering from high to low, r is the number of node layers, r=1, 2,.. 0 ，r 0 Obtaining the total number of node layers for the breadth-first search algorithm, and recording the parking space number corresponding to the highest node layer number as +.>The parking space number corresponding to the lowest node layer number is +.>Calculating a node complex regularization index of the estimated parking of the vehicle to be parked in the respective parking space>Calculating distance complex regularization index phi j Complex regularization index with each node>Selecting a parking space corresponding to the minimum difference as a target parking space of the vehicle to be parked; if the complex regularization indexes of the selected nodes are the same, the parking spaces with the number of layers corresponding to the parking spaces at the upper layer of the intelligent double-layer garage are preferentially selected and serve as target parking spaces for the to-be-parked vehicles.
Further, the calculation is performed to ensure that the vehicle to be parked is stored in the intelligent spaceThe specific process of the distance complex regularization index in the double-layer garage comprises the following steps: according to the pre-stored time length T of the vehicle to be parked j And the residual vehicle storage time delta T of the stored vehicle in the intelligent double-layer garage k Calculating a distance complex regularization index phi through a distance complex regularization index formula j The specific distance complex regularization index formula is: e is a natural constant, < >>Delta is a correction factor of the distance complexity regularization index; the distance complexity index->The specific distance complex index formula is calculated by a distance complex index formula: />α 1 And alpha 2 The pre-parking time length of the vehicle to be parked and the residual parking time length of the stored vehicle in the intelligent double-layer garage are respectively influence weight values of the distance complex index.
Further, the specific process of calculating the node complex regularization index for predicting the vehicle to be parked in each parking space is as follows: according to the number of node layersHighest number of node layers->And lowest node layer number->Calculating the node complex regularization index ++through the node complex regularization index formula>The specific node complex regularization index formula is: the node complexity index is gamma, and the gamma is a correction factor of the node complexity regularization index; the node complexity index->The node complexity index formula is calculated, and the specific node complexity index formula is as follows:β 1 、β 2 and beta 3 The number of node layers, the number of medium range of the node layers and the average number of the node layers respectively influence weight values on the node complexity index.
Further, the specific process of planning the navigation route for each AGV to carry the to-be-parked vehicle to the target parking space is as follows: combining a track map and a parking bitmap of the intelligent double-layer garage, marking the position of each parking space on the track map as a node capable of blocking the track, and marking the marked track map as a new track map; extracting idle state data U=0, 1, U=0 of each parking space in the current intelligent double-layer garage from real-time state data of the intelligent double-layer garage, wherein U=1 indicates that no vehicle stays on the parking space, namely the node is in an unblocked state on the new track diagram, and U=1 indicates that the vehicle stays on the parking space, namely the node is in a blocking state on the new track diagram; extracting current AGV transfer robot RB from real-time status data of each AGV transfer robot n Where n is the number of the AGV transfer robot, n=1, 2, &.. 0 ，n 0 For the total number of AGV transfer robots in the intelligent double-deck garage, O=0, 1, O=0 represents the unloaded work of the current AGV transfer robot, O=1 represents the loaded work of the current AGV transfer robot,finding out each AGV carrying robot RB by adopting A-algorithm n Shortest path L to current heading target V n According to the current position of the AGV transfer robot, the shortest path L travelled by each AGV transfer robot is obtained n The remaining path DeltaL in (1) n The method comprises the steps of carrying out a first treatment on the surface of the Will leave the path DeltaL n As track obstruction RS in new track graphs n Updating in real time; combining new trajectory graph and trajectory blocking RS n AGV transfer robot RB with working states of O=0 is found out through an A-algorithm n Shortest path L to a position of a vehicle to be parked in a parking space n Selecting the shortest path L which is the smallest n The corresponding AGV transfer robot transfers the vehicle to be parked to the target parking space, meanwhile, the working state of the AGV transfer robot is adjusted to be O=1, and when the AGV transfer robot reaches the position of the vehicle to be parked in a parking room, the AGV transfer robot RB is found out through an A-by-A algorithm n Shortest path to target parking space.
Further, the specific process of comparing the predicted used duration of each AGV carrying robot navigation route with the same length is as follows: statistics AGV transfer robot straight-going average speed VS n Average speed VR of turning n Average speed VO of one-layer unloading n And a two-layer unloading average speed VT n The method comprises the steps of carrying out a first treatment on the surface of the Counting the total straight distance l, the total number x of corners and the layer number c of the unloading positions in the navigation route of each AGV carrying robot with the same length; calculating the estimated time length T by a time length estimation formula m ：ε 1 、ε 2 And epsilon 3 Weight coefficients of straight-going time length, turning time length and hierarchical unloading time length for the expected time length respectively are +.>For the time length of the layer unloading, mu is a correction factor of the predicted time length; the level unloading time length>The method is characterized in that the method is calculated through a hierarchical unloading time length formula, and the specific hierarchical unloading time length formula is as follows: />M 1 And M 2 The weight coefficients of the average speed of the first layer unloading and the average speed of the second layer unloading for the time length of the layer unloading are respectively, and the weight coefficients are respectively +.>Is a correction factor for the time length of the hierarchical unloading.
Further, the track mark which is different from the ground color is arranged on the ground of the intelligent double-layer garage, and the AGV transfer robot acquires a ground image in the running process and recognizes the track mark on the ground of the intelligent double-layer garage through visual processing.
One or more technical solutions provided in the embodiments of the present application at least have the following technical effects or advantages:
1. the vehicle type, the real-time state in the garage, the target parking space and other factors are comprehensively considered, the target parking space is determined by adopting a breadth-first search algorithm, and the navigation route is obtained by combining a new track diagram through an A-type algorithm, so that the optimal navigation route is planned, the efficiency of a carrying task is improved, and the problem that the planned navigation route in the prior art is low in efficiency is effectively solved.
2. The parking space corresponding to the minimum difference value of the distance complex regularization index and the node complex regularization index is obtained through combination to serve as the target parking space of the vehicle to be parked, so that confusion in the garage is minimized, and the vehicle is guaranteed to be distributed to the most suitable parking space.
3. The vehicle type data of the to-be-parked vehicle is directly inquired from the user vehicle storage information, if the vehicle type data of the to-be-parked vehicle is not found, a to-be-parked vehicle picture corresponding to the to-be-parked vehicle is extracted from the vehicle data of the to-be-parked vehicle sent from the intelligent garage, and the vehicle type data of the to-be-parked vehicle is identified from the to-be-parked vehicle picture, so that two layers of processes for acquiring the vehicle type data of the to-be-parked vehicle exist, the vehicle type data is obtained in a mode of avoiding all use and identification, and the calculation amount is reduced.
Drawings
Fig. 1 is a schematic structural diagram of an adaptive double-deck garage navigation system for a transfer robot according to an embodiment of the present application;
fig. 2 is a schematic structural diagram of a general control platform in the adaptive double-layer garage navigation system for a transfer robot according to the embodiment of the present application;
fig. 3 is a schematic structural diagram of a planning adjustment module in the adaptive double-layer garage navigation system for a transfer robot according to an embodiment of the present application.
Detailed Description
According to the self-adaptive double-layer garage navigation system for the transfer robot, the problem that the planned navigation route is low in efficiency in the prior art is solved, the target parking space is determined by comprehensively considering factors such as the type of a vehicle, the real-time state in the garage and the target parking space, a breadth-first search algorithm is adopted, the navigation route is obtained by combining a new track diagram through an A-type algorithm, and the efficiency of a transfer task is improved.
The technical scheme in the embodiment of the application aims to solve the problem that the planned navigation route has low efficiency, and the overall thought is as follows:
the vehicle type of the to-be-parked vehicle is obtained according to the vehicle data of the to-be-parked vehicle sent by the intelligent double-layer garage, a target parking space is allocated for the to-be-parked vehicle according to the vehicle type of the to-be-parked vehicle and the parking bitmap of the intelligent double-layer garage, and a navigation route of each AGV carrying robot for carrying the to-be-parked vehicle to the target parking space is planned according to the track map of the intelligent double-layer garage, the real-time state data of each AGV carrying robot and the target parking space data, so that the efficiency of carrying tasks is improved.
In order to better understand the above technical solutions, the following detailed description will refer to the accompanying drawings and specific embodiments.
As shown in fig. 1, a structural schematic diagram of an adaptive double-deck garage navigation system for a transfer robot according to an embodiment of the present application includes: total control platform, intelligent double-deck garage and a plurality of AGV transfer robot, and total control platform passes through wireless connection with intelligent double-deck garage, passes through wireless connection between total control platform and the AGV transfer robot: wherein, the total control platform: the system comprises a vehicle management module, an AGV handling robot, a parking bitmap, a parking map, a navigation route management module and a navigation route management module, wherein the vehicle management module is used for receiving vehicle data of a vehicle to be parked, real-time state data of the intelligent double-layer garage and real-time state data of the AGV handling robot, and simultaneously analyzing the navigation route of the AGV handling robot for carrying the vehicle by combining the intelligent double-layer garage track map and the parking map, and sending the navigation route to the AGV handling robot; intelligent double-layer garage: the intelligent double-layer garage is used for acquiring vehicle data of vehicles to be parked, acquiring real-time state data of each parking space in the intelligent double-layer garage, and transmitting the vehicle data of the vehicles to be parked and the real-time state data of the intelligent double-layer garage to the main control platform; AGV transfer robot: the intelligent double-layer garage is used for sending real-time state data to the main control platform, identifying the track on the ground of the intelligent double-layer garage, receiving the navigation route sent by the main control platform, and carrying the vehicle to be parked to the target parking space along the navigation route.
Further, as shown in fig. 2, a schematic structural diagram of a general control platform in the adaptive double-layer garage navigation system for a transfer robot according to an embodiment of the present application is shown, where the general control platform includes a receiving module, a database, a planning adjustment module and a sending module; the received module: is used for receiving vehicle data of vehicles to be parked sent by the intelligent double-layer garage and real-time state data of the intelligent double-layer garage, receiving real-time state data of the AGV transfer robots sent by each AGV transfer robot; database: the intelligent double-layer garage track map and the parking bitmap are used for storing vehicle type data; and a planning and adjusting module: the navigation route of the AGV transfer robot for transferring the vehicle is analyzed according to the vehicle data of the vehicle to be parked, the real-time state data of the intelligent double-layer garage, the real-time state data of the AGV transfer robot, the track map of the intelligent double-layer garage and the parking bitmap; and a sending module: for transmitting the navigation route to the corresponding AGV handling robot.
In this embodiment, total control platform, intelligent double-deck garage and a plurality of AGV transfer robot have constituted a self-adaptation double-deck garage navigation jointly, and this system has realized high-efficient, automatic vehicle transport and parking process through accurate data interaction and intelligent navigation to promote the parking experience of parking management's efficiency and user. Through intelligent navigation and transport, this system can be fast, high-efficient with the vehicle transport from the room of parking to the parking stall, furthest reduces the transport time, improves the transport efficiency in garage.
Further, as shown in fig. 3, the schematic structural diagram of a planning and adjusting module in the adaptive double-layer garage navigation system for a transfer robot provided in the embodiment of the present application is shown, where the planning and adjusting module includes a vehicle type recognition unit, a parking space allocation unit, a route planning unit, and a comparison selection unit; vehicle type recognition unit: the method comprises the steps of obtaining the vehicle type of a vehicle to be parked according to vehicle data of the vehicle to be parked sent by an intelligent double-layer garage; parking space allocation unit: the intelligent double-layer garage is used for distributing a target parking space for the vehicle to be parked according to the type of the vehicle to be parked and the parking bitmap of the intelligent double-layer garage; route planning unit: the system comprises a track map of an intelligent double-layer garage, real-time states of the intelligent double-layer garage, real-time state data of each AGV carrying robot and target parking space data, wherein a navigation route of each AGV carrying robot for carrying a vehicle to be parked to the target parking space is planned; an alignment selection unit: when the navigation routes of the AGV transfer robots are identical in length, the predicted used time length of the navigation routes of the AGV transfer robots with the identical length is compared, the navigation route with the shortest used time length is selected and stored, and other navigation routes are discarded.
In this embodiment, the units cooperate to maximize the efficiency and speed of vehicle handling within the garage. Through intelligent path planning and navigation, the system can ensure quick and efficient transportation of vehicles, reduces transportation time and improves garage management efficiency.
Further, the specific flow of obtaining the vehicle type of the vehicle to be parked is as follows: extracting user parking information corresponding to the vehicle to be parked from vehicle data of the vehicle to be parked sent from the intelligent double-layer garage; inquiring vehicle type data of the vehicle to be parked from the user parking information, and directly outputting the vehicle type data of the vehicle to be parked if the vehicle type data is detected; if not, extracting a vehicle to be parked picture corresponding to the vehicle to be parked from vehicle data of the vehicle to be parked sent from the intelligent double-layer garage; inputting the pictures of the vehicles to be parked into a deep learning recognition model to recognize the vehicle types, thereby obtaining the vehicle types of the vehicles to be parked, and outputting the vehicle type data of the vehicles to be parked; the deep learning recognition model is learned using a deep learning network based on stored vehicle type data stored in a database.
In this embodiment, using the extracted user parking information, the system attempts to find the corresponding vehicle type data in the database. If such information is contained in the database, the system can directly output vehicle type data of the vehicle to be parked without image recognition. If there is no relevant vehicle type data in the database, the system will extract a vehicle picture from the vehicle data of the vehicle to be parked. This may be accomplished by a vehicle camera or other image acquisition device. The extracted picture of the vehicle to be parked is input into the deep learning identification model. This model uses deep learning techniques, such as Convolutional Neural Networks (CNNs), to identify vehicle types by learning to extract features from a large number of vehicle images. The deep learning recognition model recognizes the vehicle type of the vehicle to be parked according to the vehicle type data learned from the database by training thereof, and outputs the result. This result can be used for subsequent allocation of parking spaces and path planning.
Further, the specific process of allocating the target parking space for the vehicle to be parked is as follows: according to the type D of the vehicle supported by the parking spaces in the intelligent double-layer garage, the parking spaces in the intelligent double-layer garage are numbered and recorded asWhere D is the number of the vehicle type, d=1, 2 0 ，D 0 The total number of vehicle types supported to be parked for the intelligent double-layer garage is c is intelligentThe number of parking stall layers of double-deck garage, c=1, 2, i is the plane number of parking stall, i=1, 2 0 ，i 0 The total number of parking spaces in the parking space plan of the intelligent double-layer garage; according to the vehicle type corresponding to the vehicle to be parked, searching all parking spaces supporting the vehicle type to be parked from a parking bitmap of the intelligent double-layer garage; co-extracting pre-stored time length T of vehicle to be parked from corresponding user vehicle parking information of vehicle to be parked j J is the number of the parked vehicle parked in the parking garage of the intelligent double-deck garage, j=1, 2 0 ，j 0 In order to support the total number of parked vehicles in a parking room in the intelligent double-layer garage, counting the residual vehicle storage duration delta T of the stored vehicles in the intelligent double-layer garage k K is the number of the existing vehicles in the intelligent double-layer garage, k=1, 2, and k 0 ，k 0 To calculate the complex distance regularization index phi of the to-be-parked vehicles to be stored in the intelligent double-layer garage according to the total number of the stored vehicles in the intelligent double-layer garage j The method comprises the steps of carrying out a first treatment on the surface of the Taking the current parking room position of the vehicle to be parked as a starting node, taking all the searched parking spaces supporting the type of the vehicle to be parked as end points, taking the parked vehicle in the garage as a node interrupt position, and sequentially using a breadth-first search algorithm according to the parking bitmap of the intelligent double-layer garage to obtain the required node layers from the parking room position of the vehicle to be parked to the parking spaces respectively>The node layer number is->Ordering from high to low, r is the number of node layers, r=1, 2,.. 0 ，r 0 Obtaining the total number of node layers for the breadth-first search algorithm, and recording the parking space number corresponding to the highest node layer number as +.>The parking space number corresponding to the lowest node layer number is +.>Calculating a node complex regularization index of the estimated parking of the vehicle to be parked in the respective parking space>Calculating distance complex regularization index phi j Complex regularization index with each node>Selecting a parking space corresponding to the minimum difference as a target parking space of the vehicle to be parked; if the complex regularization indexes of the selected nodes are the same, the parking spaces with the number of layers corresponding to the parking spaces at the upper layer of the intelligent double-layer garage are preferentially selected and serve as target parking spaces for the to-be-parked vehicles.
In this embodiment, by comprehensively considering a plurality of factors, the utilization of the parking space is optimized, congestion is reduced, and the use efficiency of the parking space is improved. And calculating a distance complex regularization index of the vehicle to be stored in the garage. This index takes into account the vehicle location, the length of time the stored vehicle is stored, and other factors to assess the complexity of the stored vehicle location.
Further, the specific process for calculating the distance complex regularization index of the vehicle to be stored in the intelligent double-layer garage comprises the following steps: according to the pre-stored time length T of the vehicle to be parked j And the residual vehicle storage time delta T of the stored vehicle in the intelligent double-layer garage k Calculating a distance complex regularization index phi through a distance complex regularization index formula j The specific distance complex regularization index formula is:e is a natural constant, < >>Delta is a correction factor of the distance complexity regularization index; distance complexity index->The specific distance complex index formula is calculated by a distance complex index formula: />α 1 And alpha 2 The pre-parking time length of the vehicle to be parked and the residual parking time length of the stored vehicle in the intelligent double-layer garage are respectively influence weight values of the distance complex index.
In this embodiment, a number of factors are taken into account, including the time of storage of the vehicle, the remaining time of storage of the vehicle stored in the garage, to determine the complexity of the storage location. By calculating the distance complex regularization index, the system can more accurately allocate parking spaces, ensure that each vehicle is allocated to the most appropriate position, thereby reducing congestion and optimizing parking layout.
Further, the specific process of calculating the complex regularization index of the nodes for predicting the parking of the vehicle to be parked in each parking space is as follows: according to the number of node layersHighest number of node layers->And lowest node layer number->Calculating the node complex regularization index ++through the node complex regularization index formula>The specific node complex regularization index formula is: the node complexity index is gamma, and the gamma is a correction factor of the node complexity regularization index; node complex fingerCount->The node complexity index formula is calculated, and the specific node complexity index formula is as follows:β 1 、β 2 and beta 3 The number of node layers, the number of medium range of the node layers and the average number of the node layers respectively influence weight values on the node complexity index.
In this embodiment, the system calculates a complex regularization index for each node to measure the complexity of the inventory location. This helps to evaluate the suitability of each parking space.
Further, the specific flow of planning the navigation route for each AGV carrying robot to carry the to-be-parked vehicle to the target parking space is as follows: combining a track map and a parking bitmap of the intelligent double-layer garage, marking the position of each parking space on the track map as a node capable of blocking the track, and marking the marked track map as a new track map; extracting idle state data U=0, 1, U=0 of each parking space in the current intelligent double-layer garage from real-time state data of the intelligent double-layer garage, wherein U=1 indicates that no vehicle stays on the parking space, namely the node is in an unblocked state on the new track diagram, and U=1 indicates that the vehicle stays on the parking space, namely the node is in a blocking state on the new track diagram; extracting current AGV transfer robot RB from real-time status data of each AGV transfer robot n Where n is the number of the AGV transfer robot, n=1, 2, &.. 0 ，n 0 For the total number of AGV transfer robots in the intelligent double-deck garage, O=0, 1, O=0 represents the unloaded work of the current AGV transfer robot, O=1 represents the loaded work of the current AGV transfer robot,finding out each AGV carrying robot RB by adopting A-algorithm n Shortest path L to current heading target V n According to the current position of the AGV transfer robotObtaining the shortest path L travelled by each AGV carrying robot n The remaining path DeltaL in (1) n The method comprises the steps of carrying out a first treatment on the surface of the Will leave the path DeltaL n As track obstruction RS in new track graphs n Updating in real time; combining new trajectory graph and trajectory blocking RS n AGV transfer robot RB with working states of O=0 is found out through an A-algorithm n Shortest path L to a position of a vehicle to be parked in a parking space n Selecting the shortest path L which is the smallest n The corresponding AGV transfer robot transfers the vehicle to be parked to the target parking space, meanwhile, the working state of the AGV transfer robot is adjusted to be O=1, and when the AGV transfer robot reaches the position of the vehicle to be parked in a parking room, the AGV transfer robot RB is found out through an A-by-A algorithm n Shortest path to target parking space.
Further, the specific flow of comparing the predicted used duration of each AGV carrying robot navigation route with the same length is as follows: statistics AGV transfer robot straight-going average speed VS n Average speed VR of turning n Average speed VO of one-layer unloading n And a two-layer unloading average speed VT n The method comprises the steps of carrying out a first treatment on the surface of the Counting the total straight distance l, the total number x of corners and the layer number c of the unloading positions in the navigation route of each AGV carrying robot with the same length; calculating the estimated time length T by a time length estimation formula m ：ε 1 、ε 2 And epsilon 3 Weight coefficients of straight-going time length, turning time length and hierarchical unloading time length for the expected time length respectively are +.>For the time length of the layer unloading, mu is a correction factor of the predicted time length; hierarchical unloading duration +.>The method is characterized in that the method is calculated through a hierarchical unloading time length formula, and the specific hierarchical unloading time length formula is as follows:M 1 and M 2 The weight coefficients of the average speed of the first layer unloading and the average speed of the second layer unloading for the time length of the layer unloading are respectively, and the weight coefficients are respectively +.>Is a correction factor for the time length of the hierarchical unloading.
Further, the track mark which is different from the ground color is arranged on the ground of the intelligent double-layer garage, the AGV transfer robot acquires a ground image in the driving process, and the track mark on the ground of the intelligent double-layer garage is identified through visual processing.
In this embodiment, the AGV handling robot is equipped with a camera or other visual sensor for capturing images of the garage floor. These images are transmitted to the vision processing system of the robot for analysis. The vision processing system will identify the track marks on the garage floor using computer vision techniques including color recognition, shape detection, pattern matching, etc. to determine the location and type of the marks. Once the track markings are identified, the AGV transfer robot can adjust its navigation path in real time based on these markings, i.e., it can follow a particular color or shape of the markings to follow the correct route, avoid obstacles, or find the correct parking spot. The positioning accuracy of the AGV handling robot can be improved by using the track marks. This is important for high precision navigation in complex environments such as double-deck garages. The use of track markers also helps to increase the safety of the handling task, as it can help the robot avoid obstacles, follow the correct route, and reduce the occurrence of accidents.
The technical scheme in the embodiment of the application at least has the following technical effects or advantages: relative to the bulletin number: according to the automatic guiding and carrying system, the control method and the automatic guiding and carrying device disclosed by CN104238468B, the factors such as the type of a vehicle, the real-time state in a garage and a target parking space are comprehensively considered, a breadth-first search algorithm is adopted to determine the target parking space, and a navigation route is obtained by combining a new track diagram through an A-type algorithm, so that an optimal navigation route is planned, and further efficiency of carrying tasks is improved; relative to publication No.: according to the intelligent remote control method of the unmanned carrying equipment based on 5G disclosed by CN115392559A, the parking space corresponding to the minimum difference value of the distance complex regularization index and the node complex regularization index is obtained through combination as the target parking space of the vehicle to be parked, so that confusion in a garage is minimized, and further, the fact that the vehicle is distributed to the most suitable parking space is achieved.
It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of systems, apparatuses (systems) and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
While preferred embodiments of the present invention have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. It is therefore intended that the following claims be interpreted as including the preferred embodiments and all such alterations and modifications as fall within the scope of the invention.
It will be apparent to those skilled in the art that various modifications and variations can be made to the present invention without departing from the spirit or scope of the invention. Thus, it is intended that the present invention also include such modifications and alterations insofar as they come within the scope of the appended claims or the equivalents thereof.
Claims (10)
1. A self-adaptation double-deck garage navigation for transfer robot, a serial communication port, including total control platform, intelligent double-deck garage and a plurality of AGV transfer robot, just total control platform passes through wireless connection with intelligent double-deck garage, passes through wireless connection between total control platform and the AGV transfer robot:
Wherein, the total control platform: the system comprises a vehicle management module, an AGV handling robot, a parking bitmap, a parking map, a navigation route management module and a navigation route management module, wherein the vehicle management module is used for receiving vehicle data of a vehicle to be parked, real-time state data of the intelligent double-layer garage and real-time state data of the AGV handling robot, and simultaneously analyzing the navigation route of the AGV handling robot for carrying the vehicle by combining the intelligent double-layer garage track map and the parking map, and sending the navigation route to the AGV handling robot;
the intelligent double-layer garage comprises: the intelligent double-layer garage is used for acquiring vehicle data of vehicles to be parked, acquiring real-time state data of each parking space in the intelligent double-layer garage, and transmitting the vehicle data of the vehicles to be parked and the real-time state data of the intelligent double-layer garage to the main control platform;
the AGV transfer robot: the intelligent double-layer garage is used for sending real-time state data to the main control platform, identifying the track on the ground of the intelligent double-layer garage, receiving the navigation route sent by the main control platform, and carrying the vehicle to be parked to the target parking space along the navigation route.
2. The adaptive double-deck garage navigation system for a transfer robot of claim 1, wherein: the total control platform comprises a receiving module, a database, a planning adjustment module and a sending module;
the received module: is used for receiving vehicle data of vehicles to be parked sent by the intelligent double-layer garage and real-time state data of the intelligent double-layer garage, receiving real-time state data of the AGV transfer robots sent by each AGV transfer robot;
The database: the intelligent double-layer garage track map and the parking bitmap are used for storing vehicle type data;
the planning and adjusting module is used for: the navigation route of the AGV transfer robot for transferring the vehicle is analyzed according to the vehicle data of the vehicle to be parked, the real-time state data of the intelligent double-layer garage, the real-time state data of the AGV transfer robot, the track map of the intelligent double-layer garage and the parking bitmap;
the sending module: for transmitting the navigation route to the corresponding AGV handling robot.
3. An adaptive double-deck garage navigation system for a transfer robot as set forth in claim 2, wherein: the planning and adjusting module comprises a vehicle type identification unit, a parking space allocation unit, a route planning unit and a comparison and selection unit;
the vehicle type recognition unit: the method comprises the steps of obtaining the vehicle type of a vehicle to be parked according to vehicle data of the vehicle to be parked sent by an intelligent double-layer garage;
the parking space distribution unit comprises: the intelligent double-layer garage is used for distributing a target parking space for the vehicle to be parked according to the type of the vehicle to be parked and the parking bitmap of the intelligent double-layer garage;
the route planning unit: the system comprises a track map of an intelligent double-layer garage, real-time states of the intelligent double-layer garage, real-time state data of each AGV carrying robot and target parking space data, wherein a navigation route of each AGV carrying robot for carrying a vehicle to be parked to the target parking space is planned;
The comparison selection unit: when the navigation routes of the AGV transfer robots are identical in length, the predicted used time length of the navigation routes of the AGV transfer robots with the identical length is compared, the navigation route with the shortest used time length is selected and stored, and other navigation routes are discarded.
4. The adaptive double-deck garage navigation system for a transfer robot of claim 3, wherein the specific procedure for deriving the vehicle type of the vehicle to be parked is:
extracting user parking information corresponding to the vehicle to be parked from vehicle data of the vehicle to be parked sent from the intelligent double-layer garage;
inquiring vehicle type data of the vehicle to be parked from the user parking information, and directly outputting the vehicle type data of the vehicle to be parked if the vehicle type data is detected;
if not, extracting a vehicle to be parked picture corresponding to the vehicle to be parked from vehicle data of the vehicle to be parked sent from the intelligent double-layer garage;
inputting the pictures of the vehicles to be parked into a deep learning recognition model to recognize the vehicle types, thereby obtaining the vehicle types of the vehicles to be parked, and outputting the vehicle type data of the vehicles to be parked;
the deep learning recognition model is learned by using a deep learning network based on stored vehicle type data stored in a database.
5. The adaptive double-deck garage navigation system for a transfer robot of claim 4, wherein the specific process of allocating a target parking space for a vehicle to be parked is:
according to the type D of the vehicle supported by the parking spaces in the intelligent double-layer garage, the parking spaces in the intelligent double-layer garage are used for carrying outNumbering asWhere D is the number of the vehicle type, d=1, 2 0 ，D 0 For intelligent double-deck garage to support total number of vehicle types of parking, c is the number of layers of parking stall of intelligent double-deck garage, c=1, 2, i is the plane number of parking stall, i=1, 2 0 ，i 0 The total number of parking spaces in the parking space plan of the intelligent double-layer garage;
according to the vehicle type corresponding to the vehicle to be parked, searching all parking spaces supporting the vehicle type to be parked from a parking bitmap of the intelligent double-layer garage;
co-extracting pre-stored time length T of vehicle to be parked from corresponding user vehicle parking information of vehicle to be parked j J is the number of the parked vehicle parked in the parking garage of the intelligent double-deck garage, j=1, 2 0 ，j 0 In order to support the total number of parked vehicles in a parking room in the intelligent double-layer garage, counting the residual vehicle storage duration delta T of the stored vehicles in the intelligent double-layer garage k K is the number of the existing vehicles in the intelligent double-layer garage, k=1, 2, and k 0 ，k 0 To calculate the complex distance regularization index phi of the to-be-parked vehicles to be stored in the intelligent double-layer garage according to the total number of the stored vehicles in the intelligent double-layer garage j ；
Taking the current parking room position of the vehicle to be parked as a starting node, taking all the searched parking spaces supporting the type of the vehicle to be parked as end points, taking the parked vehicle in the garage as a node interrupt position, and sequentially using a breadth-first search algorithm according to the parking bitmap of the intelligent double-layer garage to obtain the required node layers from the parking room position of the vehicle to be parked to the parking spaces respectively
Layer number of nodesOrdering from high to low, r is the number of node layers, r=1, 2,.. 0 ，r 0 Obtaining the total number of node layers for the breadth-first search algorithm, and recording the parking space number corresponding to the highest node layer number as +.>The parking space number corresponding to the lowest node layer number is +.>Calculating a node complex regularization index of the estimated parking of the vehicle to be parked in the respective parking space>
Calculating distance complex regularization index phi j Complex regularization index with each nodeSelecting a parking space corresponding to the minimum difference as a target parking space of the vehicle to be parked;
If the complex regularization indexes of the selected nodes are the same, the parking spaces with the number of layers corresponding to the parking spaces at the upper layer of the intelligent double-layer garage are preferentially selected and serve as target parking spaces for the to-be-parked vehicles.
6. The adaptive double-deck garage navigation system for a transfer robot of claim 5, wherein the calculating a distance complex regularization index for a vehicle to be deposited in the intelligent double-deck garage is performed by:
according to the pre-stored time length T of the vehicle to be parked j And the residual vehicle storage time delta T of the stored vehicle in the intelligent double-layer garage k Calculating a distance complex regularization index phi through a distance complex regularization index formula j The specific distance complex regularization index formula is:e is a natural constant, < >>Delta is a correction factor of the distance complexity regularization index;
the distance complexity indexThe specific distance complex index formula is calculated by a distance complex index formula:α 1 and alpha 2 The pre-parking time length of the vehicle to be parked and the residual parking time length of the stored vehicle in the intelligent double-layer garage are respectively influence weight values of the distance complex index.
7. The adaptive double-deck garage navigation system for a transfer robot of claim 6, wherein the calculating of the node complex regularization index that predicts parking of the vehicle to be parked in each parking space is:
According to the number of node layersHighest number of node layers->And lowest node layer number->Calculating the node complex regularization index ++through the node complex regularization index formula>The specific node complex regularization index formula is: the node complexity index is gamma, and the gamma is a correction factor of the node complexity regularization index;
the node complexity indexThe node complexity index formula is calculated, and the specific node complexity index formula is as follows:β 1 、β 2 and beta 3 The number of node layers, the number of medium range of the node layers and the average number of the node layers respectively influence weight values on the node complexity index.
8. The adaptive double-deck garage navigation system for transfer robots of claim 7, wherein the specific procedure for planning a navigation route for each AGV transfer robot to transfer a vehicle to be parked to a target parking space is as follows:
combining a track map and a parking bitmap of the intelligent double-layer garage, marking the position of each parking space on the track map as a node capable of blocking the track, and marking the marked track map as a new track map;
extracting idle state data U=0, 1, U=0 of each parking space in the current intelligent double-layer garage from real-time state data of the intelligent double-layer garage, wherein U=1 indicates that no vehicle stays on the parking space, namely the node is in an unblocked state on the new track diagram, and U=1 indicates that the vehicle stays on the parking space, namely the node is in a blocking state on the new track diagram;
Extracting current AGV transfer robot RB from real-time status data of each AGV transfer robot n Where n is the number of the AGV transfer robot, n=1, 2, &.. 0 ，n 0 To at the same timeThe total number of AGV transfer robots in the intelligent double-layer garage, O=0, 1, O=0 represents the unloaded vehicle work of the current AGV transfer robot, O=1 represents the loaded vehicle work of the current AGV transfer robot,
finding out each AGV carrying robot RB by adopting A-algorithm n Shortest path L to current heading target V n According to the current position of the AGV transfer robot, the shortest path L travelled by each AGV transfer robot is obtained n The remaining path DeltaL in (1) n ；
Will leave the path DeltaL n As track obstruction RS in new track graphs n Updating in real time;
combining new trajectory graph and trajectory blocking RS n AGV transfer robot RB with working states of O=0 is found out through an A-algorithm n Shortest path L to a position of a vehicle to be parked in a parking space n Selecting the shortest path L which is the smallest n The corresponding AGV transfer robot transfers the vehicle to be parked to the target parking space, meanwhile, the working state of the AGV transfer robot is adjusted to be O=1, and when the AGV transfer robot reaches the position of the vehicle to be parked in a parking room, the AGV transfer robot RB is found out through an A-by-A algorithm n Shortest path to target parking space.
9. The adaptive double-deck garage navigation system for a transfer robot of claim 8, wherein the specific procedure for comparing the estimated time durations of the respective AGV transfer robot navigation routes of the same length is as follows:
statistics AGV transfer robot straight-going average speed VS n Average speed VR of turning n Average speed VO of one-layer unloading n And a two-layer unloading average speed VT n ；
Counting the total straight distance l, the total number x of corners and the layer number c of the unloading positions in the navigation route of each AGV carrying robot with the same length;
calculating the estimated time length T by a time length estimation formula m ：ε 1 、ε 2 And epsilon 3 Weight coefficients of straight-going time length, turning time length and hierarchical unloading time length for the expected time length respectively are +.>For the time length of the layer unloading, mu is a correction factor of the predicted time length;
the hierarchical unloading time lengthThe method is characterized in that the method is calculated through a hierarchical unloading time length formula, and the specific hierarchical unloading time length formula is as follows:M 1 and M 2 The weight coefficients of the average speed of the first layer unloading and the average speed of the second layer unloading for the time length of the layer unloading are respectively, and the weight coefficients are respectively +.>Is a correction factor for the time length of the hierarchical unloading.
10. The adaptive double-deck garage navigation system for a transfer robot of claim 9, wherein: the intelligent double-layer garage is characterized in that track marks different from ground colors are arranged on the ground of the intelligent double-layer garage, and the AGV transfer robot acquires ground images in the running process and recognizes the track marks on the ground of the intelligent double-layer garage through visual processing.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311465071.4A CN117496739B (en) | 2023-11-07 | 2023-11-07 | Self-adaptive double-layer garage navigation system for transfer robot |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311465071.4A CN117496739B (en) | 2023-11-07 | 2023-11-07 | Self-adaptive double-layer garage navigation system for transfer robot |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117496739A true CN117496739A (en) | 2024-02-02 |
| CN117496739B CN117496739B (en) | 2024-04-09 |
Family
ID=89679564
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311465071.4A Active CN117496739B (en) | 2023-11-07 | 2023-11-07 | Self-adaptive double-layer garage navigation system for transfer robot |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117496739B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118131773A (en) * | 2024-03-20 | 2024-06-04 | 上海智远慧智能技术股份有限公司 | Transfer robot path planning system for new energy charging parking lot |
| CN118274849A (en) * | 2024-06-04 | 2024-07-02 | 江苏智搬机器人科技有限公司 | Intelligent transfer robot positioning method and system based on multi-feature fusion |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2018113602A1 (en) * | 2016-12-20 | 2018-06-28 | 纳恩博（北京）科技有限公司 | Parking management robot, and parking management method and system |
| WO2020233657A1 (en) * | 2019-05-22 | 2020-11-26 | 态好停停车设备科技(无锡)有限公司 | Method and apparatus for controlling stereo garage, and intelligent stereo garage |
| CN114464009A (en) * | 2022-01-25 | 2022-05-10 | 深圳鹊巢停车科技有限公司 | Intelligent parking lot system with robot |
| CN114495563A (en) * | 2021-12-30 | 2022-05-13 | 上海智远弘业智能技术股份有限公司 | Intelligent parking management system and intelligent parking management method |
| CN115116254A (en) * | 2022-05-26 | 2022-09-27 | 安徽鸿杰威尔停车设备有限公司 | AGV double-deck parking robot driving and parking track monitored control system |
-
2023
- 2023-11-07 CN CN202311465071.4A patent/CN117496739B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2018113602A1 (en) * | 2016-12-20 | 2018-06-28 | 纳恩博（北京）科技有限公司 | Parking management robot, and parking management method and system |
| WO2020233657A1 (en) * | 2019-05-22 | 2020-11-26 | 态好停停车设备科技(无锡)有限公司 | Method and apparatus for controlling stereo garage, and intelligent stereo garage |
| CN114495563A (en) * | 2021-12-30 | 2022-05-13 | 上海智远弘业智能技术股份有限公司 | Intelligent parking management system and intelligent parking management method |
| CN114464009A (en) * | 2022-01-25 | 2022-05-10 | 深圳鹊巢停车科技有限公司 | Intelligent parking lot system with robot |
| CN115116254A (en) * | 2022-05-26 | 2022-09-27 | 安徽鸿杰威尔停车设备有限公司 | AGV double-deck parking robot driving and parking track monitored control system |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118131773A (en) * | 2024-03-20 | 2024-06-04 | 上海智远慧智能技术股份有限公司 | Transfer robot path planning system for new energy charging parking lot |
| CN118274849A (en) * | 2024-06-04 | 2024-07-02 | 江苏智搬机器人科技有限公司 | Intelligent transfer robot positioning method and system based on multi-feature fusion |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117496739B (en) | 2024-04-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN117496739B (en) | Self-adaptive double-layer garage navigation system for transfer robot | |
| US10775184B2 (en) | Systems and methods for routing a fleet of vehicles | |
| CN109767646B (en) | Parking method and device | |
| CN112149555B (en) | Global vision-based multi-warehouse AGV tracking method | |
| CN111474926B (en) | Waste smoke recycling method based on multi-AGV time window path optimization algorithm | |
| Yang et al. | Hierarchical planning for multiple AGVs in warehouse based on global vision | |
| CN111762519B (en) | Method and system for guiding picking robot operation and scheduling device | |
| CN109445438A (en) | Cruise control method and system based on the cruising device that map is shared | |
| US20230147624A1 (en) | Autonomous mobile robots for coverage path planning | |
| CN111161545B (en) | Intersection region traffic parameter statistical method based on video | |
| Li et al. | Simulation analysis of a deep reinforcement learning approach for task selection by autonomous material handling vehicles | |
| CN117320945A (en) | Method and system for determining a motion model for motion prediction in autonomous vehicle control | |
| Berriel et al. | Heading direction estimation using deep learning with automatic large-scale data acquisition | |
| Zheng et al. | Research on AGV trackless guidance technology based on the global vision | |
| CN116817957A (en) | Unmanned vehicle driving path planning method and system based on machine vision | |
| US20220162001A1 (en) | Predicting a path of material handling equipment and determining an obstacle-free path | |
| CN115268424A (en) | Mobile robot docking method, device, terminal and storage medium | |
| CN118168573B (en) | Automatic-driving unmanned delivery vehicle navigation and path planning method and system | |
| CN117933515B (en) | Transfer robot cluster scheduling method and device based on task merging | |
| CN116592906B (en) | Lane line identification navigation method and system | |
| CN117636641A (en) | Inter-vehicle cooperative carrying method and device for vehicle carrying robot | |
| CN118258406B (en) | Automatic guided vehicle navigation method and device based on visual language model | |
| Wu et al. | An evaluation of information sharing parking guidance policies using a bayesian approach | |
| CN113066294A (en) | Intelligent parking lot system based on cloud edge fusion technology | |
| CN116524757A (en) | Intelligent parking regulation and control system and method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |