CN114493399B - Logistics robot pickup order-oriented path planning method and system - Google Patents

Logistics robot pickup order-oriented path planning method and system Download PDF

Info

Publication number
CN114493399B
CN114493399B CN202111554662.XA CN202111554662A CN114493399B CN 114493399 B CN114493399 B CN 114493399B CN 202111554662 A CN202111554662 A CN 202111554662A CN 114493399 B CN114493399 B CN 114493399B
Authority
CN
China
Prior art keywords
area
path
units
logistics robot
unit
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.)
Active
Application number
CN202111554662.XA
Other languages
Chinese (zh)
Other versions
CN114493399A (en
Inventor
衡进
孙贇
姚郁巍
苏瑞
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Chongqing Terminus Technology Co Ltd
Original Assignee
Chongqing Terminus Technology Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Chongqing Terminus Technology Co Ltd filed Critical Chongqing Terminus Technology Co Ltd
Priority to CN202111554662.XA priority Critical patent/CN114493399B/en
Publication of CN114493399A publication Critical patent/CN114493399A/en
Application granted granted Critical
Publication of CN114493399B publication Critical patent/CN114493399B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/08—Logistics, e.g. warehousing, loading or distribution; Inventory or stock management
    • G06Q10/083—Shipping
    • G06Q10/0835—Relationships between shipper or supplier and carriers
    • G06Q10/08355—Routing methods
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/29—Geographical information databases
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
    • G06F17/10—Complex mathematical operations
    • G06F17/16—Matrix or vector computation, e.g. matrix-matrix or matrix-vector multiplication, matrix factorization
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
    • G06F17/10—Complex mathematical operations
    • G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Mathematical Physics (AREA)
  • Pure & Applied Mathematics (AREA)
  • Mathematical Optimization (AREA)
  • Mathematical Analysis (AREA)
  • Databases & Information Systems (AREA)
  • Computational Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Economics (AREA)
  • Algebra (AREA)
  • Software Systems (AREA)
  • Operations Research (AREA)
  • Development Economics (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Human Resources & Organizations (AREA)
  • Marketing (AREA)
  • Computing Systems (AREA)
  • Quality & Reliability (AREA)
  • Strategic Management (AREA)
  • Tourism & Hospitality (AREA)
  • General Business, Economics & Management (AREA)
  • Remote Sensing (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Evolutionary Biology (AREA)
  • Probability & Statistics with Applications (AREA)
  • Manipulator (AREA)
  • Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)

Abstract

The invention relates to a path planning method and a system for a logistics robot pickup order, wherein the method comprises the following steps: dividing the whole delivery service area of the logistics robot into a plurality of area units; acquiring all possible paths of the logistics robot to form a path set; calculating the transition probability of transitioning from any one area unit to other area units according to the relation between the area units and the path set; determining a destination belonging area unit according to the delivery order, and determining a coverage area unit according to the transfer probability; the order taking orders occurring in the coverage area units are assigned to the logistics robot and a path is planned according to the order taking orders. The method and the system can calculate the transfer probability of the logistics robot in advance by using an iterative algorithm, so that the coverage unit is determined, and then the path can be planned according to the picking order of the area units, so that the effect that the logistics robot can pick up the picking task in the delivery process and plan the path is achieved.

Description

Logistics robot pickup order-oriented path planning method and system
Technical Field
The invention relates to the field of logistics scheduling, in particular to a path planning method and system for a logistics robot to take a piece order.
Background
With the development of the information age and the progress of intelligent robot technology, intelligent robots have been widely used in various fields. In the field of logistics scheduling, the logistics robot is used for realizing logistics distribution of articles such as packages, letters and catering for closed management office buildings, parks and communities which are inconvenient for takers and couriers to enter. The logistics robot not only needs to bear the delivery, namely receives the articles to be delivered from the gates (generally provided with transfer cabinets) of parks, communities and office buildings, then conveys the articles to a destination according to a planned path and delivers the articles to users; the picking-up device should also take the picking-up device, that is, the picking-up device is moved to the picking-up position according to the picking-up order placed by the user, the article is picked up from the user and is conveyed to the gate (the article is placed in the transfer cabinet and then picked up by the courier).
However, for the current logistics robot, the delivery path planning is single, for example, the path is planned directly according to all delivery orders (from the transfer station, all delivery addresses are routed and then returned to the transfer station), meanwhile, at the user end, the time and the delivery position of the delivery order sent by the user are all sporadic, and cannot be accurately predicted, so that when the logistics robot receives the delivery order in the delivery process, the waiting time may be too long, thereby causing waste of electric quantity, or the delivery time is overtime because the delivery order position is too far. Therefore, how to make the logistics robot can intelligently accept the order of taking the part in the way of delivering the part, the travelling path can be planned again according to the order of taking the part, the planned path of the logistics robot hopefully can cover all the positions of taking the part at maximum probability, and the logistics robot in the way of delivering the part can be ensured to flexibly and efficiently reprogram the travelling path as far as possible, so that the positions of the order of taking the part are covered, quick response of taking the part is realized, and the distribution and the efficiency of taking the part of the logistics robot are greatly improved.
Disclosure of Invention
The path planning method and system for the logistics robot picking order provided by the invention can solve the technical problems in the calibration process.
The technical scheme for solving the technical problems is as follows:
in a first aspect, the present invention provides a path planning method for a logistics robot pickup order, including:
step one: dividing the whole delivery service area of the logistics robot into a plurality of area units;
step two: acquiring all possible paths of the logistics robot for executing the task of taking and delivering the parts to form a path set;
step three: calculating the transfer probability of the logistics robot from any one area unit to other area units by using an iterative algorithm according to the relation between the divided area units and the path set;
step four: determining the area unit to which the destination of any logistics robot belongs according to the delivery order, and determining the coverage area unit of the logistics robot according to the transfer probability of the area unit to which the destination belongs and other area units;
step five: and distributing the order taking orders in the destination home area unit and the coverage area unit to the logistics robot, and planning a path according to the order taking orders.
In some embodiments, the area of the area unit is sized to ensure that the logistics robot provides service for the pick-up order in one area unit in an effective period of time.
In some embodiments, the path set includes a plurality of path samples for the logistics robot to perform the pick-and-place task.
In some embodiments, the "relationship between the segmented region unit and the path set" in the third step includes:
and determining the distribution relation of the path samples in the area units, and identifying the area units through which the path samples pass as the area units in which the path samples are distributed.
In some embodiments, the calculating the transfer probability of the flow robot from any one area unit to other area units by using the iterative algorithm in the third step includes:
according to the path set R= { R 1 ，R 2 ,…R m And region unit set s= { S } 1 ，S 2 ,…S i …S j …S n Distribution relation between the regional units and determining the same-path transfer coefficient matrix
Confirming a transition probability vector group P= { P from each area unit to other area units according to the same-path transition coefficient matrix among the area units 1 、P 2 ...P i …P j …P n }；
According to an iterative formulaFor transition probability vector P i Iterating when->And->The value difference of (2) is smaller than a preset threshold value to obtain a stabilized transition probability vector P i And is used as the transfer probability of the logistics robot from any area unit to other area units.
In some embodiments, in the fourth step, "determining the coverage area unit of the logistic robot according to the transition probabilities of the area units to which the destinations belong and other area units" includes:
and comparing the transition probability of the logistics robot from the area unit to which the destination belongs to other area units with a probability threshold, and taking the area units as coverage area units of the logistics robot if the transition probability is larger than the probability threshold.
In some embodiments, in the fifth step, "planning a path according to a pick-up order" includes:
acquiring a plurality of destinations of the logistics robot according to the delivery order of the logistics robot;
and generating an advancing path of the logistics robot according to the current position of the logistics robot and the plurality of destination positions.
In a second aspect, the present invention provides a path planning system for a logistics robot pick-up order, including: the area dividing module is used for dividing the whole delivery service area of the logistics robot into a plurality of area units;
the path acquisition module is used for acquiring all possible paths of the logistics robot for executing the picking and delivering task to form a path set;
the transfer probability acquisition module is used for calculating the transfer probability of the logistics robot from any one area unit to other area units by using an iterative algorithm according to the relation between the segmented area units and the path set;
the coverage area unit determining module is used for determining the area unit to which the destination of any logistics robot belongs according to the delivery order, and determining the coverage area unit of the logistics robot according to the transfer probability of the area unit to which the destination belongs and other area units;
and the path planning module is used for distributing the picking orders generated in the destination attribution area unit and the coverage area unit to the logistics robot and planning a path according to the picking orders.
In some embodiments, the transition probability acquisition module includes: and the path sample analysis submodule is used for determining the distribution relation of the path samples in the area units and identifying the area units through which the path samples pass as the area units in which the path samples are distributed.
In some embodiments, the transition probability acquisition module further comprises:
a transfer coefficient matrix generation sub-module for generating a transfer coefficient matrix according to the path set r= { R 1 ，R 2 ,…R m And region unit set s= { S } 1 ，S 2 ,…S i …S j …S n Distribution relation between the regional units and determining the same-path transfer coefficient matrix
A transition probability vector group generating sub-module for confirming a transition probability vector group p= { P from each region unit to other region units according to the co-path transition coefficient matrix between the region units 1 、P 2 ...P i …P j …P n }；
An iterative computation sub-module for computing the iterative data according to an iterative formulaFor transition probability vector P i Iterating when->And->The value difference of (2) is smaller than a preset threshold value to obtain a stabilized transition probability vector P i And is used as the transfer probability of the logistics robot from any area unit to other area units.
In some embodiments, the coverage area unit determining module further comprises: and the transition probability comparison sub-module is used for comparing the transition probability of the logistics robot from the regional unit to which the destination belongs to other regional units with a probability threshold value, and if the transition probability is larger than the probability threshold value, the regional units are used as coverage region units of the logistics robot.
The beneficial effects of the invention are as follows:
1. the invention can divide the whole service area of the logistics robot into a plurality of area units in advance, combines the big data of the path of the logistics robot, calculates the transfer probability of the logistics robot from any area unit to other area units through an iterative algorithm, compares the transfer probability with a probability threshold value, thereby determining the coverage area unit of the logistics robot, further can distribute the picking order generated in the coverage area unit to the logistics robot, and re-plan the path, thereby achieving the effects that the logistics robot can pick up the picking task in the delivery process and plan the path.
2. The calculation of the transfer probability is carried out according to the relation between the historical path big data of the logistics robot and the preset regional partition, so that the transfer probability of the logistics robot can be calculated in advance, when the coverage area unit of the logistics robot is determined, the transfer probability of the regional unit to other regional units is only required to be compared with the probability threshold value, complex real-time operation is avoided, and the effect of improving the working efficiency of the logistics robot is achieved.
Drawings
Fig. 1 is a diagram of a path planning method for a logistics robot picking order according to an embodiment of the present invention;
fig. 2 is a second diagram of a path planning method for a logistics robot picking order according to an embodiment of the present invention;
fig. 3 is a third diagram of a path planning method for a logistics robot picking order according to an embodiment of the present invention;
fig. 4 is a schematic diagram of a path planning system for a logistics robot pickup order according to an embodiment of the present invention.
Detailed Description
The principles and features of the present invention are described below with reference to the drawings, the examples are illustrated for the purpose of illustrating the invention and are not to be construed as limiting the scope of the invention.
In order that the above-recited objects, features and advantages of the present application will be more clearly understood, a more particular description of the disclosure will be rendered by reference to the appended drawings and examples. It is to be understood that the described embodiments are some, but not all, of the embodiments of the present disclosure. The specific embodiments described herein are to be considered in an illustrative sense only and not a limiting sense. All other embodiments obtained by a person of ordinary skill in the art based on the described embodiments of the present application are within the scope of the protection of the present application.
It should be noted that in this document, relational terms such as "first" and "second" and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions.
Fig. 1 is a diagram of a path planning method for a logistics robot pick-up order according to an embodiment of the first aspect of the present invention.
A path planning method for a logistics robot picking order, combined with fig. 1, comprises five steps S1 to S1:
s1: dividing the whole delivery service area of the logistics robot into a plurality of area units;
s2: acquiring all possible paths of the logistics robot for executing the task of taking and delivering the parts to form a path set;
specifically, the whole taking and delivering service area of the logistics robot is divided into a plurality of area units, and all possible paths for the logistics robot to execute taking and delivering tasks are obtained, so that the pre-preparation work for transferring the logistics robot from any area unit to other area units is calculated. The area of the divided area units is divided into the sizes, and the larger the area is, the longer the working time of the logistics robot is, so that the area size is required to be standard for guaranteeing that the logistics robot can provide the service for taking and delivering the parts in an effective time period, for example, the area of the divided area units is required to guarantee that the logistics robot can finish the service for taking and delivering the parts in 10 minutes, 20 minutes or 30 minutes; all possible paths for the logistics robot to perform the picking and delivering task comprise a large number of path samples for the logistics robot to perform the picking and delivering task.
S3: calculating the transfer probability of the logistics robot from any one area unit to other area units by using an iterative algorithm according to the relation between the divided area units and the path set;
specifically, in order to determine the final coverage area unit of the logistics robot, the probability of the logistics robot moving from the current area unit to other area units during operation must be determined first, so in this embodiment, an iterative algorithm and a large number of path data samples are utilized, and according to the relationship between the path data samples and the segmented area units, the probability of the logistics robot transferring from one area unit to other area units can be calculated, so that a basis is made for determining the final coverage area unit of the logistics robot.
S4: determining the area unit to which the destination of any logistics robot belongs according to the delivery order, and determining the coverage area unit of the logistics robot according to the transfer probability of the area unit to which the destination belongs and other area units;
s5: distributing the order taking orders generated in the destination attribution area unit and the coverage area unit to the logistics robot, and planning a path according to the order taking orders;
specifically, after the transfer probability of the logistics robot from one area unit to other area units is obtained, whether the logistics robot is transferred to the other area units with high probability or not can be judged according to the relation between the transfer probability and the probability threshold value, namely, whether the other area units should be used as coverage area units of the logistics robot or not is judged; after the coverage area units of the logistics robot are determined, the picking orders generated in the area units can be distributed to the logistics robot, so that paths are planned according to the picking orders.
In some embodiments, the area of the area unit is sized to ensure that the logistics robot provides service for the pick-up order in one area unit in an effective period of time.
Specifically, in the embodiment of the present application, the area of the divided area unit is divided into two areas, and the larger the area is, the longer the working time of the logistics robot is, so that the area of the divided area unit should be standard to ensure that the logistics robot can provide the service of taking and delivering the parts in an effective time period, for example, the area of the divided area unit should ensure that the logistics robot completes the service of taking and delivering the parts in 3 hours or 6 hours or 24 hours.
It should be understood that the effective time period in the embodiments of the present application may be flexibly determined according to practical situations, and is not limited to the protection scope of the present invention.
In some embodiments, the path set includes a plurality of path samples for the logistics robot to perform the pick-and-place task.
Specifically, all possible paths of the logistics robot for executing the task of taking and delivering the workpiece comprise a large number of path samples of the logistics robot for executing the task of taking and delivering the workpiece, and the more the number of the path samples is, the more accurate and the closer the calculated transfer probability of the logistics robot from any area unit to other area units is to reality.
In some embodiments, the "relationship between the segmented region unit and the path set" in the step S3 includes:
and determining the distribution relation of the path samples in the area units, and identifying the area units through which the path samples pass as the area units in which the path samples are distributed.
Specifically, according to the route of the path sample on the service area map, the area unit through which the path sample passes can be intuitively obtained, i.e. the area unit distributed by the path sample can be considered, for example, the path sample R 2 Via area unit S 4 ，S 5 Consider the path sample R 2 Distributed in regional units S 4 ，S 5 Denoted as R 2 ∈S 4 ，R 2 ∈S 5 . Further, the subsequent calculation of transition probabilities is completed according to the distribution relation of the path samples in the area units.
Fig. 2 is a second diagram of a path planning method for a logistics robot picking order according to an embodiment of the present invention.
In some embodiments, in conjunction with fig. 2, the step S3 of calculating the transfer probability of the flow robot from any one area unit to other area units by using an iterative algorithm includes three steps of S31, S32, and S33:
s31: according to the path set R= { R 1 ，R 2 ,…R m And region unit set s= { S } 1 ，S 2 ,…S i …S j …S n Distribution relation between the regional units and determining the same-path transfer coefficient matrix
S32: confirming a transition probability vector group P= { P from each area unit to other area units according to the same-path transition coefficient matrix among the area units 1 、P 2 ...P i …P j …P n }；
S33: according to an iterative formulaFor transition probability vector P i Iterating when->And->The value difference of (2) is smaller than a preset threshold value to obtain a stabilized transition probability vector P i And is used as the transfer probability of the logistics robot from any area unit to other area units.
Specifically, the path set r= { R 1 ，R 2 ,…R m The set of region units s= { S } is a set of all path samples 1 ，S 2 ,…S i …S j …S n -a set of all region units; element W in transfer coefficient matrix W ij (i,j∈[1,2…n]) Representation area unit S i And S is j Transfer coefficients with the same track, andwherein c i To be in the path set r= { R 1 ，R 2 ，…R m In the region unit S j A set of paths within c i To be in the path set r= { R 1 ，R 2 ,…R m In the region unit S i A set of paths within c i ∩c j C for the intersection of the two i ∪c j For a union of the two, NUM (x) represents the number of paths in the set; p (P) i Is a transition probability vector of dimension n x 1,
wherein p is ij Representing the same track from S i Departure route S j Probability of (2); iterative formula In (I)>Is vector P i Each element of the vector is initially assigned 1/n,/for>For the probability of the same track starting from one area unit and entering any adjacent area unit, and +.>The probability that the same track starts from an area unit and still remains in the area unit is represented; />And->Respectively represent the vector P i The value of the first iteration and the first (plus 1) iteration is taken; after a certain number of iterations, a steady state can be entered, i.e. +.>And->The value difference of the (a) is smaller than a preset threshold value; for the stabilized vector P i I.e. the probability of transition of each region unit to other region units can be represented.
It should be understood that the threshold value in the embodiment of the present application may be flexibly determined according to practical situations, and is not limited to the protection scope of the present invention.
In some embodiments, in the step S4, "determining the coverage area unit of the logistic robot according to the transition probabilities of the area units to which the destinations belong and other area units" includes:
and comparing the transition probability of the logistics robot from the area unit to which the destination belongs to other area units with a probability threshold, and taking the area units as coverage area units of the logistics robot if the transition probability is larger than the probability threshold.
Specifically, when the probability of the transfer of the logistics robot from one area unit to another area unit is obtained, it may be determined whether the logistics robot is transferred to the other area unit with a high probability, that is, whether the other area unit should be used as a coverage area unit of the logistics robot according to the relationship between the probability of the transfer and the probability threshold, for example, if the probability threshold is 50%, the unit where the delivery destination of the logistics robot is located is the first area unit, the probability of the transfer of the first area unit to the second area unit is 40%, and the probability of the transfer of the first area unit to the third area unit is 60%, it may be determined that the probability of the transfer of the logistics robot to the second area unit is less than the probability threshold, and the probability of the transfer of the first area unit to the third area unit is greater than 60%, that is, and therefore, the total service area unit of the logistics robot is the area unit where the delivery destination of the logistics robot is located plus the coverage area unit.
It should be understood that the probability threshold in the embodiment of the present application may be flexibly determined according to practical situations, and may be 40%, 50%, 60%, etc., which does not limit the protection scope of the present invention.
Fig. 3 is a third diagram of a path planning method for a logistics robot picking order according to an embodiment of the present invention.
In some embodiments, in conjunction with fig. 3, the step S5, "planning a path according to a pick order" includes:
s51: acquiring a plurality of destinations of the logistics robot according to the delivery order of the logistics robot;
s52: and generating an advancing path of the logistics robot according to the current position of the logistics robot and the plurality of destination positions.
Specifically, in the embodiment of the present application, the overall path planning procedure is as follows: dividing a service area into a collection of area units in advance, and acquiring a large number of logistics robot path samples in advance; calculating the transfer probability of the logistics robot from any area unit to other area units through the relation between a large number of path samples and the area units, determining the area units to which all delivery order destinations of the current logistics robot belong, based on the destination belonging area units, combining the transfer probability of the logistics robot from the destination belonging area units to other area units, and comparing the probability with a probability threshold value to obtain a coverage area unit of the logistics robot; when the covered area unit generates the picking orders, the picking orders can be distributed to the logistics robot, and then the whole advancing path of the logistics robot can be adjusted according to the picking orders and the destination positions of all delivery orders, so that the purposes of executing the picking tasks together and reasonably planning the path when the logistics robot executes the delivery tasks are achieved.
Fig. 4 is a schematic diagram of a path planning system for a logistics robot pick-up order according to a second aspect of the present invention, and in combination with fig. 4, a path planning system for a logistics robot pick-up order includes: the area dividing module 61 is configured to divide the entire delivery service area of the logistics robot into a plurality of area units;
the path acquisition module 62 is configured to acquire all possible paths of the logistics robot for performing the task of picking and delivering the workpiece, so as to form a path set;
specifically, the whole taking and delivering service area of the logistics robot is divided into a plurality of area units, and all possible paths for the logistics robot to execute taking and delivering tasks are obtained, so that the pre-preparation work for transferring the logistics robot from any area unit to other area units is calculated. The area of the divided area units is divided into the sizes, and the larger the area is, the longer the working time of the logistics robot is, so that the area size is required to be standard for guaranteeing that the logistics robot can provide the service for taking and delivering the parts in an effective time period, for example, the area of the divided area units is required to guarantee that the logistics robot can finish the service for taking and delivering the parts in 10 minutes, 20 minutes or 30 minutes; all possible paths for the logistics robot to perform the picking and delivering task comprise a large number of path samples for the logistics robot to perform the picking and delivering task.
A transition probability obtaining module 63, configured to calculate a transition probability of the logistics robot from any one of the area units to other area units by using an iterative algorithm according to a relationship between the segmented area units and the path set;
specifically, in order to determine the final coverage area unit of the logistics robot, the probability of the logistics robot moving from the current area unit to other area units during operation must be determined first, so in this embodiment, an iterative algorithm and a large number of path data samples are utilized, and according to the relationship between the path data samples and the segmented area units, the probability of the logistics robot transferring from one area unit to other area units can be calculated, so that a basis is made for determining the final coverage area unit of the logistics robot.
The coverage area unit determining module 64 is configured to determine, according to the delivery order, an area unit to which a destination of any one of the logistics robots belongs, and determine, according to transfer probabilities of the area units to which the destination belongs and other area units, a coverage area unit of the logistics robot;
the path planning module 65 is configured to assign the pick-up order occurring in the destination home area unit and the coverage area unit to the logistics robot, and plan a path according to the pick-up order.
Specifically, after the transfer probability of the logistics robot from one area unit to other area units is obtained, whether the logistics robot is transferred to the other area units with high probability or not can be judged according to the relation between the transfer probability and the probability threshold value, namely, whether the other area units should be used as coverage area units of the logistics robot or not is judged; after the coverage area units of the logistics robot are determined, the picking orders generated in the area units can be distributed to the logistics robot, so that paths are planned according to the picking orders.
In some embodiments, the transition probability acquisition module 63 includes: the path sample analysis sub-module 631 is configured to determine a distribution relationship of the path sample in the area unit, and identify the area unit through which the path sample passes as the area unit in which the path sample is distributed.
In some embodiments, the transition probability acquisition module further comprises:
a transfer coefficient matrix generation sub-module 632 for generating a set of paths r= { R 1 ，R 2 ,…R m And region unit set s= { S } 1 ，S 2 ,…S i …S j …S n Distribution relation between the regional units and determining the same-path transfer coefficient matrix
A transition probability vector group generating sub-module 633 for determining a transition probability vector group p= { P from each region unit to other region units according to the co-path transition coefficient matrix between the region units 1 、P 2 ...P i …P j …P n }；
An iterative computation sub-module 634 for computing an iterative formulaTo transfer probabilityRate vector P i Iterating when->And->The value difference of (2) is smaller than a preset threshold value to obtain a stabilized transition probability vector P i And is used as the transfer probability of the logistics robot from any area unit to other area units.
Specifically, the path set r= { R 1 ，R 2 ,…R m The set of region units s= { S } is a set of all path samples 1 ，S 2 ,…S i …S j …S n -a set of all region units; element W in transfer coefficient matrix W ij (i,j∈[1,2…n]) Representation area unit S i And S is j Transfer coefficients with the same track, andwherein c i To be in the path set r= { R 1 ，R 2 ,…R m In the region unit S j A set of paths within c i To be in the path set r= { R 1 ，R 2 ,…R m In the region unit S i A set of paths within c i ∩c j C for the intersection of the two i ∪c j For a union of the two, NUM (x) represents the number of paths in the set; p (P) i Is a transition probability vector of dimension n x 1,
wherein p is ij Representing the same track from S i Departure route S j Probability of (2); iterative formula In (I)>Is vector P i Each element of the vector is initially assigned 1/n,/for>For the probability of the same track starting from one area unit and entering any adjacent area unit, and +.>The probability that the same track starts from an area unit and still remains in the area unit is represented; />And->Respectively represent the vector P i The value of the first iteration and the first (plus 1) iteration is taken; after a certain number of iterations, a steady state can be entered, i.e. +.>And->The value difference of the (a) is smaller than a preset threshold value; for the stabilized vector P i I.e. the probability of transition of each region unit to other region units can be represented.
In some embodiments, the coverage area unit determining module 64 further includes: the transition probability comparison sub-module 641 is configured to compare a transition probability of the logistics robot from the area unit to which the destination belongs to other area units with a probability threshold, and if the transition probability is greater than the probability threshold, take the area units as coverage area units of the logistics robot.
Specifically, when the probability of the transfer of the logistics robot from one area unit to another area unit is obtained, it may be determined whether the logistics robot is transferred to the other area unit with a high probability, that is, whether the other area unit should be used as a coverage area unit of the logistics robot according to the relationship between the probability of the transfer and the probability threshold, for example, if the probability threshold is 50%, the unit where the delivery destination of the logistics robot is located is the first area unit, the probability of the transfer of the first area unit to the second area unit is 40%, and the probability of the transfer of the first area unit to the third area unit is 60%, it may be determined that the probability of the transfer of the logistics robot to the second area unit is less than the probability threshold, and the probability of the transfer of the first area unit to the third area unit is greater than 60%, that is, and therefore, the total service area unit of the logistics robot is the area unit where the delivery destination of the logistics robot is located plus the coverage area unit.
Those skilled in the art will appreciate that while some embodiments described herein include some features but not others included in other embodiments, combinations of features of different embodiments are meant to be within the scope of the present application and form different embodiments.
Those skilled in the art will appreciate that the descriptions of the various embodiments are each focused on, and that portions of one embodiment that are not described in detail may be referred to as related descriptions of other embodiments.
Although the embodiments of the present invention have been described with reference to the accompanying drawings, those skilled in the art may make various modifications and alterations without departing from the spirit and scope of the present invention, and such modifications and alterations fall within the scope of the appended claims, which are to be construed as merely illustrative of this invention, but the scope of the invention is not limited thereto, and various equivalent modifications and substitutions will be readily apparent to those skilled in the art within the scope of the present invention, and are intended to be included within the scope of the invention. Therefore, the protection scope of the invention is subject to the protection scope of the claims.
The present invention is not limited to the above embodiments, and various equivalent modifications and substitutions can be easily made by those skilled in the art within the technical scope of the present invention, and these modifications and substitutions are intended to be included in the scope of the present invention. Therefore, the protection scope of the invention is subject to the protection scope of the claims.

Claims (6)

1. A path planning method for a logistics robot picking order is characterized by comprising the following steps:
step one: dividing the whole delivery service area of the logistics robot into a plurality of area units;
step two: acquiring all possible paths of the logistics robot for executing the task of taking and delivering the parts to form a path set;
step three: calculating the transfer probability of the logistics robot from any one area unit to other area units by using an iterative algorithm according to the relation between the divided area units and the path set;
the "relationship between the divided area units and the path set" in the third step includes:
determining the distribution relation of the path sample in the area units, and identifying the area units through which the path sample passes as the area units in which the path sample is distributed;
the step three, calculating the transfer probability of the flow robot from any one area unit to other area units by using an iterative algorithm, includes:
according to the path set R= { R 1 ，R 2 ,…R m And region unit set s= { S } 1 ，S 2 ,…S i …S j …S n Distribution relation between the regional units and determining the same-path transfer coefficient matrix
Confirming a transition probability vector group P= { P from each area unit to other area units according to the same-path transition coefficient matrix among the area units 1 、P 2 ...P i …P j …P n }；
According to an iterative formulaFor transition probability vector P i Iterating whenAnd->The value difference of (2) is smaller than a preset threshold value to obtain a stabilized transition probability vector P i And is used as the transfer probability of the logistics robot from any area unit to other area units;
wherein,is vector P i Each element of the vector is initially assigned 1/n,/for>For the probability of the same track starting from one area unit and entering any adjacent area unit, and +.>The probability that the same track starts from an area unit and still remains in the area unit is represented; />And->Respectively represent the vector P i At the first round of iterationAnd the iteration of the first round (1+1) takes the value; after a certain number of iterations, a steady state can be entered, i.e. +.>And->The value difference of the (a) is smaller than a preset threshold value; for the stabilized vector P i I.e. the transition probability of each region unit to other region units can be represented;
the path set r= { R 1 ，R 2 ,…R m The set of region units s= { S } is a set of all path samples 1 ，S 2 ,…S i …S j …S n -a set of all region units; element W in transfer coefficient matrix W ij Representation area unit S i And S is j Co-track transfer coefficients, where i, j E [1,2 … n]And (2) andwherein c j To be in the path set r= { R 1 ，R 2 ,…R m In the region unit S j A set of paths within c i To be in the path set r= { R 1 ，R 2 ,…R m In the region unit S i A set of paths within c i ∩c j C for the intersection of the two i ∪c j For a union of the two, NUM (x) represents the number of paths in the set;
step four: determining the area unit to which the destination of any logistics robot belongs according to the delivery order, and determining the coverage area unit of the logistics robot according to the transfer probability of the area unit to which the destination belongs and other area units;
step five: and distributing the order taking orders in the destination home area unit and the coverage area unit to the logistics robot, and planning a path according to the order taking orders.
2. The path planning method for taking orders for logistics robots according to claim 1, wherein the area of the area units is sized to ensure that the logistics robots provide service for taking orders in one area unit in an effective time period.
3. The method for path planning for a pick-up order of a logistics robot of claim 1, wherein the set of paths comprises a plurality of path samples for the logistics robot to perform the pick-up task.
4. The method for planning a path for a pick-up order for a physical distribution robot according to claim 1, wherein in the fourth step, "determining the coverage area unit of the physical distribution robot according to the probability of transition between the area unit to which the destinations belong and other area units" includes:
and comparing the transition probability of the logistics robot from the area unit to which the destination belongs to other area units with a probability threshold, and taking the area units as coverage area units of the logistics robot if the transition probability is larger than the probability threshold.
5. A path planning system for a logistics robot pick-up order, comprising: the area dividing module is used for dividing the whole delivery service area of the logistics robot into a plurality of area units;
the path acquisition module is used for acquiring all possible paths of the logistics robot for executing the picking and delivering task to form a path set;
the transfer probability acquisition module is used for calculating the transfer probability of the logistics robot from any one area unit to other area units by using an iterative algorithm according to the relation between the segmented area units and the path set;
the transition probability acquisition module comprises: the path sample analysis submodule is used for determining the distribution relation of the path samples in the area units and identifying the area units through which the path samples pass as the area units in which the path samples are distributed;
the transition probability acquisition module further includes:
a transfer coefficient matrix generation sub-module for generating a transfer coefficient matrix according to the path set r= { R 1 ，R 2 ,…R m And region unit set s= { S } 1 ，S 2 ,…S i …S j …S n Distribution relation between the regional units and determining the same-path transfer coefficient matrix
A transition probability vector group generating sub-module for confirming a transition probability vector group p= { P from each region unit to other region units according to the co-path transition coefficient matrix between the region units 1 、P 2 ...P i …P j …P n }；
An iterative computation sub-module for computing the iterative data according to an iterative formula For transition probability vector P i Iterating when->And->The value difference of (2) is smaller than a preset threshold value to obtain a stabilized transition probability vector P i And is used as the transfer probability of the logistics robot from any area unit to other area units;
wherein,is vector P i Initial assignment of (a)Each element of the vector is initially assigned a value of 1/n +>For the probability of the same track starting from one area unit and entering any adjacent area unit, and +.>The probability that the same track starts from an area unit and still remains in the area unit is represented; />And->Respectively represent the vector P i The value of the first iteration and the first (plus 1) iteration is taken; after a certain number of iterations, a steady state can be entered, i.e. +.>And->The value difference of the (a) is smaller than a preset threshold value; for the stabilized vector P i I.e. the transition probability of each region unit to other region units can be represented;
the path set r= { R 1 ，R 2 ,…R m The set of region units s= { S } is a set of all path samples 1 ，S 2 ,…S i …S j …S n -a set of all region units; element W in transfer coefficient matrix W ij Representation area unit S i And S is j Co-track transfer coefficients, where i, j E [1,2 … n]And (2) andwherein c j To be in the path set r= { R 1 ，R 2 ，...R m In the region unit S j A set of paths within c i To be in the path set r= { R 1 ，R 2 ，...R m In the region unit S i A set of paths within c i ∩c j C for the intersection of the two i ∪c j For a union of the two, NUM (x) represents the number of paths in the set;
the coverage area unit determining module is used for determining the area unit to which the destination of any logistics robot belongs according to the delivery order, and determining the coverage area unit of the logistics robot according to the transfer probability of the area unit to which the destination belongs and other area units;
and the path planning module is used for distributing the picking orders generated in the destination attribution area unit and the coverage area unit to the logistics robot and planning a path according to the picking orders.
6. The logistic robot pickup order oriented path planning system according to claim 5, wherein the coverage area unit determining module further comprises: and the transition probability comparison sub-module is used for comparing the transition probability of the logistics robot from the regional unit to which the destination belongs to other regional units with a probability threshold value, and if the transition probability is larger than the probability threshold value, the regional units are used as coverage region units of the logistics robot.
CN202111554662.XA 2021-12-17 2021-12-17 Logistics robot pickup order-oriented path planning method and system Active CN114493399B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202111554662.XA CN114493399B (en) 2021-12-17 2021-12-17 Logistics robot pickup order-oriented path planning method and system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202111554662.XA CN114493399B (en) 2021-12-17 2021-12-17 Logistics robot pickup order-oriented path planning method and system

Publications (2)

Publication Number Publication Date
CN114493399A CN114493399A (en) 2022-05-13
CN114493399B true CN114493399B (en) 2024-04-09

Family

ID=81493317

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202111554662.XA Active CN114493399B (en) 2021-12-17 2021-12-17 Logistics robot pickup order-oriented path planning method and system

Country Status (1)

Country Link
CN (1) CN114493399B (en)

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105677780A (en) * 2014-12-31 2016-06-15 Tcl集团股份有限公司 Scalable user intent mining method and system thereof
CN109902990A (en) * 2019-01-16 2019-06-18 江苏玄通供应链股份有限公司 A kind of supply chain logistics distribution routing planning system
CN109920535A (en) * 2019-02-28 2019-06-21 彭明德 A kind of mobile Chinese medical discrimination analysis method and device
CN110807236A (en) * 2018-08-03 2020-02-18 深圳先进技术研究院 Warehouse logistics simulation system based on multiple robots
CN111260129A (en) * 2020-01-15 2020-06-09 深圳大学 Multi-yard vehicle path planning method and device, computer equipment and storage medium
CN112085288A (en) * 2020-09-16 2020-12-15 浙江财经大学 Logistics distribution route recommendation method and system based on two-stage optimization
CN112904842A (en) * 2021-01-13 2021-06-04 中南大学 Mobile robot path planning and optimizing method based on cost potential field

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
FR3040899B1 (en) * 2015-09-15 2017-09-01 Solystic METHOD FOR COLLECTING OBJECTS WITH SHUTTLE ROBOTS
CN109598457A (en) * 2017-09-30 2019-04-09 北京京东尚科信息技术有限公司 Material-flow method and system, unmanned plane, unmanned vehicle, dispatching platform and handover method

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105677780A (en) * 2014-12-31 2016-06-15 Tcl集团股份有限公司 Scalable user intent mining method and system thereof
CN110807236A (en) * 2018-08-03 2020-02-18 深圳先进技术研究院 Warehouse logistics simulation system based on multiple robots
CN109902990A (en) * 2019-01-16 2019-06-18 江苏玄通供应链股份有限公司 A kind of supply chain logistics distribution routing planning system
CN109920535A (en) * 2019-02-28 2019-06-21 彭明德 A kind of mobile Chinese medical discrimination analysis method and device
CN111260129A (en) * 2020-01-15 2020-06-09 深圳大学 Multi-yard vehicle path planning method and device, computer equipment and storage medium
CN112085288A (en) * 2020-09-16 2020-12-15 浙江财经大学 Logistics distribution route recommendation method and system based on two-stage optimization
CN112904842A (en) * 2021-01-13 2021-06-04 中南大学 Mobile robot path planning and optimizing method based on cost potential field

Non-Patent Citations (5)

* Cited by examiner, † Cited by third party
Title
A Path-Integral-Based Reinforcement Learning Algorithm for Path Following of an Autoassembly Mobile Robot;Wei Zhu 等;《IEEE Transactions on Neural Networks and Learning Systems》;20191224;第31卷(第11期);第4487-4499页 *
Multi-obstacle path planning and optimization for mobile robot;Xin Deng 等;《Expert Systems with Applications》;20210623;第183卷;第1-16页 *
基于仿生算法的灾后救援路径选择;张伟 等;《辽宁工程技术大学学报(自然科学版)》;20170630;第36卷(第6期);第651-656页 *
有限线性时态逻辑程序综合的理论与算法研究;朱淑芳;《中国博士学位论文全文数据库 信息科技辑》;20200615(第6期);第I138-2页 *
移动机器人全覆盖路径规划与自主导航算法研究;马云飞;《中国优秀硕士学位论文全文数据库 信息科技辑》;20190815(第8期);第I140-339页 *

Also Published As

Publication number Publication date
CN114493399A (en) 2022-05-13

Similar Documents

Publication Publication Date Title
CN109034468B (en) Logistics distribution path planning method with time window based on cuckoo algorithm
WO2020030028A1 (en) Delivery dispatch
CN108861276B (en) Follow-up warehouse goods picking method based on AGV
CN110807236A (en) Warehouse logistics simulation system based on multiple robots
Wang et al. A comprehensive framework for the design of modular robotic mobile fulfillment systems
CN108960519A (en) Time based on big data analysis most short transportation route selection method
CN112200523A (en) E-commerce commodity logistics storage center intelligent management platform based on big data analysis
CN112036696A (en) Task allocation method, task allocation device, storage medium, and electronic apparatus
TW201816363A (en) Method and system for generating navigation data and transporting object
Caputo et al. A model for planning and economic comparison of manual and automated kitting systems
CN114493399B (en) Logistics robot pickup order-oriented path planning method and system
Cano et al. Solving the order batching and sequencing problem with multiple pickers: A grouped genetic algorithm
Wang et al. Towards minimum fleet for ridesharing-aware mobility-on-demand systems
Zhang et al. A performance analytical model of automated material handling system for semiconductor wafer fabrication system
Simić et al. Evolutionary approach in inventory routing problem
Im et al. Effective vehicle dispatching method minimising the blocking and delivery times in automatic material handling systems of 300 mm semiconductor fabrication
Li et al. Optimal online dispatch for high-capacity shared autonomous mobility-on-demand systems
CN116050967B (en) Distribution management system and method of distribution robot for community
CN113705850A (en) Order distribution method and device, readable storage medium and electronic equipment
CN117479235B (en) Scheduling management method and system for terminal network facilities
Bhosekar et al. Simulation optimization of automated guided vehicle system in a health care facility
CN114493405B (en) Commodity circulation robot motion trail-based dispatch method and system
CN113689017A (en) Logistics transportation management system
Zheng et al. Research on express delivery vehicle route planning method for stochastic customer demand
CN113849693A (en) Scheduling information modeling method, device, equipment and storage medium for edge interaction

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