SlideShare a Scribd company logo
COORDINATING HUNDREDS           Automation and Control Seminar   1



       OF COOPERATIVE,
   AUTONOMOUS VEHICLES IN
        A WAREHOUSE

                   Dev Bahadur Poudel
               Automation and Control Seminar
                     Jacobs University
                          Bremen




Monday, July
 30, 2012
Structure of Presentation
2


       Overview on Multi-Agent System
       Multi Agent System in Warehouse
       Kiva System in Warehouse




                     Automation and Control Seminar   Monday, July 30, 2012
Autonomous Robot
3


       Robots that can perform desired task in
        unstructured environment without human
        guidance.
       Have some degree of autonomy
       Have control over their internal state and their
        behavior




                      Automation and Control Seminar   Monday, July 30, 2012
Agents
4


       Computer system that is capable of
        independent(autonomous) action to satisfy
        design objectives
       Problem Solving entities
       Situated in a particular environment (input
        environment through sensors and act on
        environment through effectors)



                      Automation and Control Seminar   Monday, July 30, 2012
Multi-Agent System
5


       Agent Oriented Approach to solve Complex
        Problem
        Consist of a number of agents interacting with
        each other to accomplish the goal in a
        common environment
       Problem are decentralized to different agents
       Decomposition of Knowledge and Expertise
       Distributed Intelligence

                      Automation and Control Seminar   Monday, July 30, 2012
Why and Where Multi-agents
6
                  Systems?
       Decentralization of Problems and Knowledge
       For Complex Control Systems
       Increase the productivity and decrease the
        cost
       Reliability, Robust
       Military Network-centric Operations
       Search and Rescue
       Transportation and Logistics
       Now days used in Warehouse to increase the
        efficiency
                     Automation and Control Seminar   Monday, July 30, 2012
Warehouse Scenario
7


       Goods-to- Customer




                    Automation and Control Seminar   Monday, July 30, 2012
Traditional Automation in
8                    Warehouse
       Pickers(human) move around the Warehouse
       Fetch products and return them to packing
        station
       Human have to look for the order items
       Order items in Conveyors
       Batch Processing
       Time consuming


                    Automation and Control Seminar   Monday, July 30, 2012
Modern Automation in
9
    Warehouse
       Orders’ item come in hand of picker like a
        MAGIC!
        Use of Autonomous agents
       Agents search the order fetch to the human
        Agents co-ordinate to achieve a system goal
       Many orders can be fulfilled
       Increases Productivity
       Kiva System

                     Automation and Control Seminar   Monday, July 30, 2012
Kiva System
10


        State-of-the art for modern automation in
         warehouse
        Founded on better approach for order fulfillment
         (goods to customers)
        Uses Hundreds of autonomous mobile robots
        Sophisticated control Software
        Uses the concept of Distributed Intelligence
        Founded in 2003 (Mick Mountz )
        Fielded in 2006
        Implements Distributed Intelligence
                        Automation and Control Seminar   Monday, July 30, 2012
Resources
11


        Inventory ( with dimensions and frequency)
        Inventory Pods (pods can visit one or multiple
         stations)
        Bins (pods can have 1-1000 bins)
        Order Pods
        Parking space for pods
        Robots
        Picking Stations

                       Automation and Control Seminar   Monday, July 30, 2012
Kiva System Layout
12




        Green: Storage Area
        Orange: Mobile Robots
        Blue: Stations
                                 Automation and Control Seminar   Monday, July 30, 2012
MAS Architecture in
Warehouse(Kiva)
13




          Agent 1        Job Manager




     Inventory Station                             Drive Unit

         Agent 2                                                Agent 3



                         Automation and Control Seminar   Monday, July 30, 2012
Drive Unit Agent
14


        Mobile Robots
        Fetch the Inventory pod to the picking station
        Take the Order pods to the shipping station
        Transport the Inventory Pod to replenishment
        Path Planning




                       Automation and Control Seminar   Monday, July 30, 2012
15
         Inventory Station Agent(ISA)
         Picking stations : Workers pick items
        Replenishment stations: barcodes are
         scanned and appropriate pod come to the
         station
         Report accomplishment of its tasks.
        Equipped with computer that pick lights,
         barcode scanners, laser pointers used to
         identify the pick and put locations


                      Automation and Control Seminar   Monday, July 30, 2012
Job Manager
16


        Central Server System
        Resource Allocation
        Communicate with Warehouse Management
         System
        Receives customer orders that need to be
         fulfilled
        Assigns drives, pods, and stations to carry out
         the tasks.

                       Automation and Control Seminar   Monday, July 30, 2012
Kiva Robots and Pods
17




          Automation and Control Seminar   Monday, July 30, 2012
Kiva working Mechanism
18


        JM receives orders and assign to stations to
         fulfill
        Robot(Drive Unit) carries the inventory pods
        Inventory pods come to picking stations
        Picking: Workers pick items and put in order
         pod
        Shipping : Order pod move for shipping after
         fulfilling all the orders
        Replenishment : Inventory pods go for
         replenishment Automation and Control Seminar Monday, July 30, 2012
19
     Order fetch Configuration




             Automation and Control Seminar   Monday, July 30, 2012
Path Planning
20


        Optimization of the path to fetch order from
         storage to the station
        A* Algorithm
        Travelling Salesman Problem




                       Automation and Control Seminar   Monday, July 30, 2012
21
         Resource Allocation Challenges
        Objective: Optimizing the system(keep the
         workers busy minimizing the robots and pods
         used)
        Which order to assign to which robot?
        Which pod to pick up?
        Where to keep the pod after order is fulfilled?
        Which pod to send for replenishment?
        Optimization(make all the robots and stations
         busy)
                        Automation and Control Seminar   Monday, July 30, 2012
Heuristic Technique for
22                 Optimization
        Order Allocation
          1.Time to fulfill the order must be minimized
          2. Inventories around the station and in
         queue pods must be considered
        Inventory Pod Selection
          1.Nearer pods
          2. Multiple items to be picked in one visit


                       Automation and Control Seminar   Monday, July 30, 2012
Resource Allocation
23


      Pod Storage Allocation:
       1.Slow frequency pods kept backward
       2.high frequency pods are kept nearer
      Robot Allocation:

       1.Pick More pods using less Robots
       2.Decrease the Queue in stations
      Replenishment Allocation:

       1.Maximize the cubic utilization of the pods
       2.Bin packing Problem
       3.Create faster pods and slower pods

                       Automation and Control Seminar   Monday, July 30, 2012
Advantages
24


        Increase Productivity: double the output
        Lower Cost: lower installation and operational
         costs than traditional warehouse automation
         systems
        Location free replenishment : items can be
         kept in any pods
        Adaptive storage: Pods are store using
         heuristic
        Expandability :Add inventory pods and drive
         units to increase throughput during peak2012
                        Automation and Control Seminar Monday, July 30,
         season
Challenges
25


        To the Computer Scientist
        Development of an appropriate high level
         software infrastructure/framework to support
         the building of multi-agent systems
        Efficient Algorithm for Optimization
        Path Planning for robots
        Resource Allocation
        Coordinating Robots
        Dynamic, Stochastic and hence Intractable

                       Automation and Control Seminar   Monday, July 30, 2012
Kiva in Action
26




         Automation and Control Seminar   Monday, July 30, 2012
27




     Have a Nice Day!




        Automation and Control Seminar   Monday, July 30, 2012

More Related Content

What's hot

Leaning The Warehouse
Leaning The WarehouseLeaning The Warehouse
Leaning The Warehouse
Jim Malone
 
Warehouse automation
Warehouse automationWarehouse automation
Warehouse automation
Vineet M Srivastav
 
Future of supply chain using 5G, IoT and Blockchain by Murali Venkatesh
Future of supply chain using 5G, IoT and Blockchain by Murali VenkateshFuture of supply chain using 5G, IoT and Blockchain by Murali Venkatesh
Future of supply chain using 5G, IoT and Blockchain by Murali Venkatesh
Murali Venkatesh
 
Warehouse management
Warehouse managementWarehouse management
Warehouse management
Dr. Chandan Vichoray
 
Cobots ppt
Cobots pptCobots ppt
Cobots ppt
Apsara Murugan
 
Project on scm at walmart
Project on scm at walmartProject on scm at walmart
Project on scm at walmart
Nilesh Lathigara
 
Warehouse management
Warehouse managementWarehouse management
Warehouse management
marcomteamindia
 
Material handling systems & Advancements
Material handling systems & AdvancementsMaterial handling systems & Advancements
Material handling systems & Advancements
Shreya Anand
 
Warehouse Operations.pptx
Warehouse Operations.pptxWarehouse Operations.pptx
Warehouse Operations.pptx
Hpm India
 
Supply chain management
Supply chain managementSupply chain management
Supply chain management
Riya Neupane
 
Automated Storage/Retrieval Systems - Explained
Automated Storage/Retrieval Systems - ExplainedAutomated Storage/Retrieval Systems - Explained
Automated Storage/Retrieval Systems - Explained
Krishna M Venkat
 
Operation management wal-mart
Operation management wal-martOperation management wal-mart
Operation management wal-mart
Dhaval Gurnani
 
On The Way To Smart Factory
On The Way To Smart FactoryOn The Way To Smart Factory
On The Way To Smart Factory
Dell World
 
The last mile: The next battleground for businesses adapting to changing cons...
The last mile: The next battleground for businesses adapting to changing cons...The last mile: The next battleground for businesses adapting to changing cons...
The last mile: The next battleground for businesses adapting to changing cons...
Deloitte Canada
 
Cyber physical manufacturing systems
Cyber physical manufacturing systemsCyber physical manufacturing systems
Cyber physical manufacturing systems
Dr Prashant S Humnabad
 
Lean Warehouse
Lean WarehouseLean Warehouse
Lean Warehouse
Zensar Technologies Ltd.
 
Impact of Digital on Supply Chain
Impact of Digital on Supply ChainImpact of Digital on Supply Chain
Impact of Digital on Supply Chain
Ayantan Sikdar, CSCP
 
Warehouse organization how to set up a smooth running warehouse
Warehouse organization how to set up a smooth running warehouseWarehouse organization how to set up a smooth running warehouse
Warehouse organization how to set up a smooth running warehouse
MRPeasy
 
Demand Forecasting and Inventory Planning in Omnichannel Retail
Demand Forecasting and Inventory Planning in Omnichannel RetailDemand Forecasting and Inventory Planning in Omnichannel Retail
Demand Forecasting and Inventory Planning in Omnichannel Retail
Openbravo
 
Warehouse management and operations rfid
Warehouse management and operations rfidWarehouse management and operations rfid
Warehouse management and operations rfid
Sopagna Chan
 

What's hot (20)

Leaning The Warehouse
Leaning The WarehouseLeaning The Warehouse
Leaning The Warehouse
 
Warehouse automation
Warehouse automationWarehouse automation
Warehouse automation
 
Future of supply chain using 5G, IoT and Blockchain by Murali Venkatesh
Future of supply chain using 5G, IoT and Blockchain by Murali VenkateshFuture of supply chain using 5G, IoT and Blockchain by Murali Venkatesh
Future of supply chain using 5G, IoT and Blockchain by Murali Venkatesh
 
Warehouse management
Warehouse managementWarehouse management
Warehouse management
 
Cobots ppt
Cobots pptCobots ppt
Cobots ppt
 
Project on scm at walmart
Project on scm at walmartProject on scm at walmart
Project on scm at walmart
 
Warehouse management
Warehouse managementWarehouse management
Warehouse management
 
Material handling systems & Advancements
Material handling systems & AdvancementsMaterial handling systems & Advancements
Material handling systems & Advancements
 
Warehouse Operations.pptx
Warehouse Operations.pptxWarehouse Operations.pptx
Warehouse Operations.pptx
 
Supply chain management
Supply chain managementSupply chain management
Supply chain management
 
Automated Storage/Retrieval Systems - Explained
Automated Storage/Retrieval Systems - ExplainedAutomated Storage/Retrieval Systems - Explained
Automated Storage/Retrieval Systems - Explained
 
Operation management wal-mart
Operation management wal-martOperation management wal-mart
Operation management wal-mart
 
On The Way To Smart Factory
On The Way To Smart FactoryOn The Way To Smart Factory
On The Way To Smart Factory
 
The last mile: The next battleground for businesses adapting to changing cons...
The last mile: The next battleground for businesses adapting to changing cons...The last mile: The next battleground for businesses adapting to changing cons...
The last mile: The next battleground for businesses adapting to changing cons...
 
Cyber physical manufacturing systems
Cyber physical manufacturing systemsCyber physical manufacturing systems
Cyber physical manufacturing systems
 
Lean Warehouse
Lean WarehouseLean Warehouse
Lean Warehouse
 
Impact of Digital on Supply Chain
Impact of Digital on Supply ChainImpact of Digital on Supply Chain
Impact of Digital on Supply Chain
 
Warehouse organization how to set up a smooth running warehouse
Warehouse organization how to set up a smooth running warehouseWarehouse organization how to set up a smooth running warehouse
Warehouse organization how to set up a smooth running warehouse
 
Demand Forecasting and Inventory Planning in Omnichannel Retail
Demand Forecasting and Inventory Planning in Omnichannel RetailDemand Forecasting and Inventory Planning in Omnichannel Retail
Demand Forecasting and Inventory Planning in Omnichannel Retail
 
Warehouse management and operations rfid
Warehouse management and operations rfidWarehouse management and operations rfid
Warehouse management and operations rfid
 

Similar to KIVA system

Seminario Federico Caboni, 25-10-2012
Seminario Federico Caboni, 25-10-2012Seminario Federico Caboni, 25-10-2012
Seminario Federico Caboni, 25-10-2012
CRS4 Research Center in Sardinia
 
Autonomic Computing PPT
Autonomic Computing PPTAutonomic Computing PPT
1-PE-I-OOAD.pptx
1-PE-I-OOAD.pptx1-PE-I-OOAD.pptx
1-PE-I-OOAD.pptx
KALPANAC20
 
IWST12: Spec
IWST12: SpecIWST12: Spec
IWST12: Spec
ESUG
 
Mobile agent
Mobile agent Mobile agent
Mobile agent
Anjan Mondal
 
MaLeNe2021-Evolving_Autonomous_Networks-L_Ciavaglia.pdf
MaLeNe2021-Evolving_Autonomous_Networks-L_Ciavaglia.pdfMaLeNe2021-Evolving_Autonomous_Networks-L_Ciavaglia.pdf
MaLeNe2021-Evolving_Autonomous_Networks-L_Ciavaglia.pdf
Ahmed Mohamed
 
Bimodal IT : An Introduction from InfoSeption
Bimodal IT : An Introduction from InfoSeptionBimodal IT : An Introduction from InfoSeption
Bimodal IT : An Introduction from InfoSeption
InfoSeption
 
Evolving Mashup Interfaces using a Distributed Machine Learning and Model Tra...
Evolving Mashup Interfaces using a Distributed Machine Learning and Model Tra...Evolving Mashup Interfaces using a Distributed Machine Learning and Model Tra...
Evolving Mashup Interfaces using a Distributed Machine Learning and Model Tra...
Applied Computing Group
 

Similar to KIVA system (10)

Seminario Federico Caboni, 25-10-2012
Seminario Federico Caboni, 25-10-2012Seminario Federico Caboni, 25-10-2012
Seminario Federico Caboni, 25-10-2012
 
Autonomic Computing PPT
Autonomic Computing PPTAutonomic Computing PPT
Autonomic Computing PPT
 
1-PE-I-OOAD.pptx
1-PE-I-OOAD.pptx1-PE-I-OOAD.pptx
1-PE-I-OOAD.pptx
 
Module 1_A&AI.pdf
Module 1_A&AI.pdfModule 1_A&AI.pdf
Module 1_A&AI.pdf
 
IWST12: Spec
IWST12: SpecIWST12: Spec
IWST12: Spec
 
Mobile agent
Mobile agent Mobile agent
Mobile agent
 
MaLeNe2021-Evolving_Autonomous_Networks-L_Ciavaglia.pdf
MaLeNe2021-Evolving_Autonomous_Networks-L_Ciavaglia.pdfMaLeNe2021-Evolving_Autonomous_Networks-L_Ciavaglia.pdf
MaLeNe2021-Evolving_Autonomous_Networks-L_Ciavaglia.pdf
 
Bimodal IT : An Introduction from InfoSeption
Bimodal IT : An Introduction from InfoSeptionBimodal IT : An Introduction from InfoSeption
Bimodal IT : An Introduction from InfoSeption
 
Fuzzy logic
Fuzzy logicFuzzy logic
Fuzzy logic
 
Evolving Mashup Interfaces using a Distributed Machine Learning and Model Tra...
Evolving Mashup Interfaces using a Distributed Machine Learning and Model Tra...Evolving Mashup Interfaces using a Distributed Machine Learning and Model Tra...
Evolving Mashup Interfaces using a Distributed Machine Learning and Model Tra...
 

Recently uploaded

Le nuove frontiere dell'AI nell'RPA con UiPath Autopilot™
Le nuove frontiere dell'AI nell'RPA con UiPath Autopilot™Le nuove frontiere dell'AI nell'RPA con UiPath Autopilot™
Le nuove frontiere dell'AI nell'RPA con UiPath Autopilot™
UiPathCommunity
 
FIDO Alliance Osaka Seminar: The WebAuthn API and Discoverable Credentials.pdf
FIDO Alliance Osaka Seminar: The WebAuthn API and Discoverable Credentials.pdfFIDO Alliance Osaka Seminar: The WebAuthn API and Discoverable Credentials.pdf
FIDO Alliance Osaka Seminar: The WebAuthn API and Discoverable Credentials.pdf
FIDO Alliance
 
A tale of scale & speed: How the US Navy is enabling software delivery from l...
A tale of scale & speed: How the US Navy is enabling software delivery from l...A tale of scale & speed: How the US Navy is enabling software delivery from l...
A tale of scale & speed: How the US Navy is enabling software delivery from l...
sonjaschweigert1
 
Smart TV Buyer Insights Survey 2024 by 91mobiles.pdf
Smart TV Buyer Insights Survey 2024 by 91mobiles.pdfSmart TV Buyer Insights Survey 2024 by 91mobiles.pdf
Smart TV Buyer Insights Survey 2024 by 91mobiles.pdf
91mobiles
 
Dev Dives: Train smarter, not harder – active learning and UiPath LLMs for do...
Dev Dives: Train smarter, not harder – active learning and UiPath LLMs for do...Dev Dives: Train smarter, not harder – active learning and UiPath LLMs for do...
Dev Dives: Train smarter, not harder – active learning and UiPath LLMs for do...
UiPathCommunity
 
Epistemic Interaction - tuning interfaces to provide information for AI support
Epistemic Interaction - tuning interfaces to provide information for AI supportEpistemic Interaction - tuning interfaces to provide information for AI support
Epistemic Interaction - tuning interfaces to provide information for AI support
Alan Dix
 
Monitoring Java Application Security with JDK Tools and JFR Events
Monitoring Java Application Security with JDK Tools and JFR EventsMonitoring Java Application Security with JDK Tools and JFR Events
Monitoring Java Application Security with JDK Tools and JFR Events
Ana-Maria Mihalceanu
 
By Design, not by Accident - Agile Venture Bolzano 2024
By Design, not by Accident - Agile Venture Bolzano 2024By Design, not by Accident - Agile Venture Bolzano 2024
By Design, not by Accident - Agile Venture Bolzano 2024
Pierluigi Pugliese
 
GDG Cloud Southlake #33: Boule & Rebala: Effective AppSec in SDLC using Deplo...
GDG Cloud Southlake #33: Boule & Rebala: Effective AppSec in SDLC using Deplo...GDG Cloud Southlake #33: Boule & Rebala: Effective AppSec in SDLC using Deplo...
GDG Cloud Southlake #33: Boule & Rebala: Effective AppSec in SDLC using Deplo...
James Anderson
 
PHP Frameworks: I want to break free (IPC Berlin 2024)
PHP Frameworks: I want to break free (IPC Berlin 2024)PHP Frameworks: I want to break free (IPC Berlin 2024)
PHP Frameworks: I want to break free (IPC Berlin 2024)
Ralf Eggert
 
LF Energy Webinar: Electrical Grid Modelling and Simulation Through PowSyBl -...
LF Energy Webinar: Electrical Grid Modelling and Simulation Through PowSyBl -...LF Energy Webinar: Electrical Grid Modelling and Simulation Through PowSyBl -...
LF Energy Webinar: Electrical Grid Modelling and Simulation Through PowSyBl -...
DanBrown980551
 
Essentials of Automations: The Art of Triggers and Actions in FME
Essentials of Automations: The Art of Triggers and Actions in FMEEssentials of Automations: The Art of Triggers and Actions in FME
Essentials of Automations: The Art of Triggers and Actions in FME
Safe Software
 
Observability Concepts EVERY Developer Should Know -- DeveloperWeek Europe.pdf
Observability Concepts EVERY Developer Should Know -- DeveloperWeek Europe.pdfObservability Concepts EVERY Developer Should Know -- DeveloperWeek Europe.pdf
Observability Concepts EVERY Developer Should Know -- DeveloperWeek Europe.pdf
Paige Cruz
 
Encryption in Microsoft 365 - ExpertsLive Netherlands 2024
Encryption in Microsoft 365 - ExpertsLive Netherlands 2024Encryption in Microsoft 365 - ExpertsLive Netherlands 2024
Encryption in Microsoft 365 - ExpertsLive Netherlands 2024
Albert Hoitingh
 
The Metaverse and AI: how can decision-makers harness the Metaverse for their...
The Metaverse and AI: how can decision-makers harness the Metaverse for their...The Metaverse and AI: how can decision-makers harness the Metaverse for their...
The Metaverse and AI: how can decision-makers harness the Metaverse for their...
Jen Stirrup
 
FIDO Alliance Osaka Seminar: Passkeys and the Road Ahead.pdf
FIDO Alliance Osaka Seminar: Passkeys and the Road Ahead.pdfFIDO Alliance Osaka Seminar: Passkeys and the Road Ahead.pdf
FIDO Alliance Osaka Seminar: Passkeys and the Road Ahead.pdf
FIDO Alliance
 
FIDO Alliance Osaka Seminar: Overview.pdf
FIDO Alliance Osaka Seminar: Overview.pdfFIDO Alliance Osaka Seminar: Overview.pdf
FIDO Alliance Osaka Seminar: Overview.pdf
FIDO Alliance
 
FIDO Alliance Osaka Seminar: FIDO Security Aspects.pdf
FIDO Alliance Osaka Seminar: FIDO Security Aspects.pdfFIDO Alliance Osaka Seminar: FIDO Security Aspects.pdf
FIDO Alliance Osaka Seminar: FIDO Security Aspects.pdf
FIDO Alliance
 
zkStudyClub - Reef: Fast Succinct Non-Interactive Zero-Knowledge Regex Proofs
zkStudyClub - Reef: Fast Succinct Non-Interactive Zero-Knowledge Regex ProofszkStudyClub - Reef: Fast Succinct Non-Interactive Zero-Knowledge Regex Proofs
zkStudyClub - Reef: Fast Succinct Non-Interactive Zero-Knowledge Regex Proofs
Alex Pruden
 
The Art of the Pitch: WordPress Relationships and Sales
The Art of the Pitch: WordPress Relationships and SalesThe Art of the Pitch: WordPress Relationships and Sales
The Art of the Pitch: WordPress Relationships and Sales
Laura Byrne
 

Recently uploaded (20)

Le nuove frontiere dell'AI nell'RPA con UiPath Autopilot™
Le nuove frontiere dell'AI nell'RPA con UiPath Autopilot™Le nuove frontiere dell'AI nell'RPA con UiPath Autopilot™
Le nuove frontiere dell'AI nell'RPA con UiPath Autopilot™
 
FIDO Alliance Osaka Seminar: The WebAuthn API and Discoverable Credentials.pdf
FIDO Alliance Osaka Seminar: The WebAuthn API and Discoverable Credentials.pdfFIDO Alliance Osaka Seminar: The WebAuthn API and Discoverable Credentials.pdf
FIDO Alliance Osaka Seminar: The WebAuthn API and Discoverable Credentials.pdf
 
A tale of scale & speed: How the US Navy is enabling software delivery from l...
A tale of scale & speed: How the US Navy is enabling software delivery from l...A tale of scale & speed: How the US Navy is enabling software delivery from l...
A tale of scale & speed: How the US Navy is enabling software delivery from l...
 
Smart TV Buyer Insights Survey 2024 by 91mobiles.pdf
Smart TV Buyer Insights Survey 2024 by 91mobiles.pdfSmart TV Buyer Insights Survey 2024 by 91mobiles.pdf
Smart TV Buyer Insights Survey 2024 by 91mobiles.pdf
 
Dev Dives: Train smarter, not harder – active learning and UiPath LLMs for do...
Dev Dives: Train smarter, not harder – active learning and UiPath LLMs for do...Dev Dives: Train smarter, not harder – active learning and UiPath LLMs for do...
Dev Dives: Train smarter, not harder – active learning and UiPath LLMs for do...
 
Epistemic Interaction - tuning interfaces to provide information for AI support
Epistemic Interaction - tuning interfaces to provide information for AI supportEpistemic Interaction - tuning interfaces to provide information for AI support
Epistemic Interaction - tuning interfaces to provide information for AI support
 
Monitoring Java Application Security with JDK Tools and JFR Events
Monitoring Java Application Security with JDK Tools and JFR EventsMonitoring Java Application Security with JDK Tools and JFR Events
Monitoring Java Application Security with JDK Tools and JFR Events
 
By Design, not by Accident - Agile Venture Bolzano 2024
By Design, not by Accident - Agile Venture Bolzano 2024By Design, not by Accident - Agile Venture Bolzano 2024
By Design, not by Accident - Agile Venture Bolzano 2024
 
GDG Cloud Southlake #33: Boule & Rebala: Effective AppSec in SDLC using Deplo...
GDG Cloud Southlake #33: Boule & Rebala: Effective AppSec in SDLC using Deplo...GDG Cloud Southlake #33: Boule & Rebala: Effective AppSec in SDLC using Deplo...
GDG Cloud Southlake #33: Boule & Rebala: Effective AppSec in SDLC using Deplo...
 
PHP Frameworks: I want to break free (IPC Berlin 2024)
PHP Frameworks: I want to break free (IPC Berlin 2024)PHP Frameworks: I want to break free (IPC Berlin 2024)
PHP Frameworks: I want to break free (IPC Berlin 2024)
 
LF Energy Webinar: Electrical Grid Modelling and Simulation Through PowSyBl -...
LF Energy Webinar: Electrical Grid Modelling and Simulation Through PowSyBl -...LF Energy Webinar: Electrical Grid Modelling and Simulation Through PowSyBl -...
LF Energy Webinar: Electrical Grid Modelling and Simulation Through PowSyBl -...
 
Essentials of Automations: The Art of Triggers and Actions in FME
Essentials of Automations: The Art of Triggers and Actions in FMEEssentials of Automations: The Art of Triggers and Actions in FME
Essentials of Automations: The Art of Triggers and Actions in FME
 
Observability Concepts EVERY Developer Should Know -- DeveloperWeek Europe.pdf
Observability Concepts EVERY Developer Should Know -- DeveloperWeek Europe.pdfObservability Concepts EVERY Developer Should Know -- DeveloperWeek Europe.pdf
Observability Concepts EVERY Developer Should Know -- DeveloperWeek Europe.pdf
 
Encryption in Microsoft 365 - ExpertsLive Netherlands 2024
Encryption in Microsoft 365 - ExpertsLive Netherlands 2024Encryption in Microsoft 365 - ExpertsLive Netherlands 2024
Encryption in Microsoft 365 - ExpertsLive Netherlands 2024
 
The Metaverse and AI: how can decision-makers harness the Metaverse for their...
The Metaverse and AI: how can decision-makers harness the Metaverse for their...The Metaverse and AI: how can decision-makers harness the Metaverse for their...
The Metaverse and AI: how can decision-makers harness the Metaverse for their...
 
FIDO Alliance Osaka Seminar: Passkeys and the Road Ahead.pdf
FIDO Alliance Osaka Seminar: Passkeys and the Road Ahead.pdfFIDO Alliance Osaka Seminar: Passkeys and the Road Ahead.pdf
FIDO Alliance Osaka Seminar: Passkeys and the Road Ahead.pdf
 
FIDO Alliance Osaka Seminar: Overview.pdf
FIDO Alliance Osaka Seminar: Overview.pdfFIDO Alliance Osaka Seminar: Overview.pdf
FIDO Alliance Osaka Seminar: Overview.pdf
 
FIDO Alliance Osaka Seminar: FIDO Security Aspects.pdf
FIDO Alliance Osaka Seminar: FIDO Security Aspects.pdfFIDO Alliance Osaka Seminar: FIDO Security Aspects.pdf
FIDO Alliance Osaka Seminar: FIDO Security Aspects.pdf
 
zkStudyClub - Reef: Fast Succinct Non-Interactive Zero-Knowledge Regex Proofs
zkStudyClub - Reef: Fast Succinct Non-Interactive Zero-Knowledge Regex ProofszkStudyClub - Reef: Fast Succinct Non-Interactive Zero-Knowledge Regex Proofs
zkStudyClub - Reef: Fast Succinct Non-Interactive Zero-Knowledge Regex Proofs
 
The Art of the Pitch: WordPress Relationships and Sales
The Art of the Pitch: WordPress Relationships and SalesThe Art of the Pitch: WordPress Relationships and Sales
The Art of the Pitch: WordPress Relationships and Sales
 

KIVA system

  • 1. COORDINATING HUNDREDS Automation and Control Seminar 1 OF COOPERATIVE, AUTONOMOUS VEHICLES IN A WAREHOUSE Dev Bahadur Poudel Automation and Control Seminar Jacobs University Bremen Monday, July 30, 2012
  • 2. Structure of Presentation 2  Overview on Multi-Agent System  Multi Agent System in Warehouse  Kiva System in Warehouse Automation and Control Seminar Monday, July 30, 2012
  • 3. Autonomous Robot 3  Robots that can perform desired task in unstructured environment without human guidance.  Have some degree of autonomy  Have control over their internal state and their behavior Automation and Control Seminar Monday, July 30, 2012
  • 4. Agents 4  Computer system that is capable of independent(autonomous) action to satisfy design objectives  Problem Solving entities  Situated in a particular environment (input environment through sensors and act on environment through effectors) Automation and Control Seminar Monday, July 30, 2012
  • 5. Multi-Agent System 5  Agent Oriented Approach to solve Complex Problem  Consist of a number of agents interacting with each other to accomplish the goal in a common environment  Problem are decentralized to different agents  Decomposition of Knowledge and Expertise  Distributed Intelligence Automation and Control Seminar Monday, July 30, 2012
  • 6. Why and Where Multi-agents 6 Systems?  Decentralization of Problems and Knowledge  For Complex Control Systems  Increase the productivity and decrease the cost  Reliability, Robust  Military Network-centric Operations  Search and Rescue  Transportation and Logistics  Now days used in Warehouse to increase the efficiency Automation and Control Seminar Monday, July 30, 2012
  • 7. Warehouse Scenario 7  Goods-to- Customer Automation and Control Seminar Monday, July 30, 2012
  • 8. Traditional Automation in 8 Warehouse  Pickers(human) move around the Warehouse  Fetch products and return them to packing station  Human have to look for the order items  Order items in Conveyors  Batch Processing  Time consuming Automation and Control Seminar Monday, July 30, 2012
  • 9. Modern Automation in 9 Warehouse  Orders’ item come in hand of picker like a MAGIC!  Use of Autonomous agents  Agents search the order fetch to the human  Agents co-ordinate to achieve a system goal  Many orders can be fulfilled  Increases Productivity  Kiva System Automation and Control Seminar Monday, July 30, 2012
  • 10. Kiva System 10  State-of-the art for modern automation in warehouse  Founded on better approach for order fulfillment (goods to customers)  Uses Hundreds of autonomous mobile robots  Sophisticated control Software  Uses the concept of Distributed Intelligence  Founded in 2003 (Mick Mountz )  Fielded in 2006  Implements Distributed Intelligence Automation and Control Seminar Monday, July 30, 2012
  • 11. Resources 11  Inventory ( with dimensions and frequency)  Inventory Pods (pods can visit one or multiple stations)  Bins (pods can have 1-1000 bins)  Order Pods  Parking space for pods  Robots  Picking Stations Automation and Control Seminar Monday, July 30, 2012
  • 12. Kiva System Layout 12  Green: Storage Area  Orange: Mobile Robots  Blue: Stations Automation and Control Seminar Monday, July 30, 2012
  • 13. MAS Architecture in Warehouse(Kiva) 13 Agent 1 Job Manager Inventory Station Drive Unit Agent 2 Agent 3 Automation and Control Seminar Monday, July 30, 2012
  • 14. Drive Unit Agent 14  Mobile Robots  Fetch the Inventory pod to the picking station  Take the Order pods to the shipping station  Transport the Inventory Pod to replenishment  Path Planning Automation and Control Seminar Monday, July 30, 2012
  • 15. 15 Inventory Station Agent(ISA)  Picking stations : Workers pick items  Replenishment stations: barcodes are scanned and appropriate pod come to the station  Report accomplishment of its tasks.  Equipped with computer that pick lights, barcode scanners, laser pointers used to identify the pick and put locations Automation and Control Seminar Monday, July 30, 2012
  • 16. Job Manager 16  Central Server System  Resource Allocation  Communicate with Warehouse Management System  Receives customer orders that need to be fulfilled  Assigns drives, pods, and stations to carry out the tasks. Automation and Control Seminar Monday, July 30, 2012
  • 17. Kiva Robots and Pods 17 Automation and Control Seminar Monday, July 30, 2012
  • 18. Kiva working Mechanism 18  JM receives orders and assign to stations to fulfill  Robot(Drive Unit) carries the inventory pods  Inventory pods come to picking stations  Picking: Workers pick items and put in order pod  Shipping : Order pod move for shipping after fulfilling all the orders  Replenishment : Inventory pods go for replenishment Automation and Control Seminar Monday, July 30, 2012
  • 19. 19 Order fetch Configuration Automation and Control Seminar Monday, July 30, 2012
  • 20. Path Planning 20  Optimization of the path to fetch order from storage to the station  A* Algorithm  Travelling Salesman Problem Automation and Control Seminar Monday, July 30, 2012
  • 21. 21 Resource Allocation Challenges  Objective: Optimizing the system(keep the workers busy minimizing the robots and pods used)  Which order to assign to which robot?  Which pod to pick up?  Where to keep the pod after order is fulfilled?  Which pod to send for replenishment?  Optimization(make all the robots and stations busy) Automation and Control Seminar Monday, July 30, 2012
  • 22. Heuristic Technique for 22 Optimization  Order Allocation 1.Time to fulfill the order must be minimized 2. Inventories around the station and in queue pods must be considered  Inventory Pod Selection 1.Nearer pods 2. Multiple items to be picked in one visit Automation and Control Seminar Monday, July 30, 2012
  • 23. Resource Allocation 23  Pod Storage Allocation: 1.Slow frequency pods kept backward 2.high frequency pods are kept nearer  Robot Allocation: 1.Pick More pods using less Robots 2.Decrease the Queue in stations  Replenishment Allocation: 1.Maximize the cubic utilization of the pods 2.Bin packing Problem 3.Create faster pods and slower pods Automation and Control Seminar Monday, July 30, 2012
  • 24. Advantages 24  Increase Productivity: double the output  Lower Cost: lower installation and operational costs than traditional warehouse automation systems  Location free replenishment : items can be kept in any pods  Adaptive storage: Pods are store using heuristic  Expandability :Add inventory pods and drive units to increase throughput during peak2012 Automation and Control Seminar Monday, July 30, season
  • 25. Challenges 25  To the Computer Scientist  Development of an appropriate high level software infrastructure/framework to support the building of multi-agent systems  Efficient Algorithm for Optimization  Path Planning for robots  Resource Allocation  Coordinating Robots  Dynamic, Stochastic and hence Intractable Automation and Control Seminar Monday, July 30, 2012
  • 26. Kiva in Action 26 Automation and Control Seminar Monday, July 30, 2012
  • 27. 27 Have a Nice Day! Automation and Control Seminar Monday, July 30, 2012