SlideShare uma empresa Scribd logo
1 de 56
Baixar para ler offline
T O C S S
         B B  O B


                  Hannes Schulz

               University of Freiburg, ACS



                      Feb 2008
O


  1   I: C S  R

  2   T M I  U G S
        Idea 1: Use Config Space Structure
        Idea 2: Increase Connectivity


  3   S A

  4   E: C  S S

  5   C  C
O


  1   I: C S  R

  2   T M I  U G S
        Idea 1: Use Config Space Structure
        Idea 2: Increase Connectivity


  3   S A

  4   E: C  S S

  5   C  C
Intro        Two Main Ideas         Sampling Algorithm   Experiments    Comments and Conclusion


 C S

        World Space                                             Configuration Space




                              http://ford.ieor.berkeley.edu/cspace
Intro        Two Main Ideas         Sampling Algorithm   Experiments    Comments and Conclusion


 C S

        World Space                                             Configuration Space




                              http://ford.ieor.berkeley.edu/cspace
Intro        Two Main Ideas         Sampling Algorithm   Experiments    Comments and Conclusion


 C S

        World Space                                             Configuration Space




                              http://ford.ieor.berkeley.edu/cspace
Intro        Two Main Ideas         Sampling Algorithm   Experiments    Comments and Conclusion


 C S

        World Space                                             Configuration Space




                              http://ford.ieor.berkeley.edu/cspace
Intro        Two Main Ideas         Sampling Algorithm   Experiments    Comments and Conclusion


 C S

        World Space                                             Configuration Space




                              http://ford.ieor.berkeley.edu/cspace
Intro        Two Main Ideas         Sampling Algorithm   Experiments    Comments and Conclusion


 C S

        World Space                                             Configuration Space




                              http://ford.ieor.berkeley.edu/cspace
Intro        Two Main Ideas         Sampling Algorithm   Experiments    Comments and Conclusion


 C S

        World Space                                             Configuration Space




                              http://ford.ieor.berkeley.edu/cspace
Intro        Two Main Ideas         Sampling Algorithm   Experiments    Comments and Conclusion


 C S

        World Space                                             Configuration Space




                              http://ford.ieor.berkeley.edu/cspace
Intro        Two Main Ideas         Sampling Algorithm   Experiments    Comments and Conclusion


 C S

        World Space                                             Configuration Space




                              http://ford.ieor.berkeley.edu/cspace
Intro     Two Main Ideas   Sampling Algorithm   Experiments   Comments and Conclusion


 R M




        Config Space
        w/ Obstacles
Intro     Two Main Ideas   Sampling Algorithm   Experiments   Comments and Conclusion


 R M




        Config Space
        w/ Obstacles
        and Samples
Intro     Two Main Ideas   Sampling Algorithm   Experiments   Comments and Conclusion


 R M




        Config Space                Visibility Road Map
        w/ Obstacles
        and Samples
Intro     Two Main Ideas   Sampling Algorithm   Experiments   Comments and Conclusion


 R M




        Config Space                Visibility Road Map
        w/ Obstacles                  Planned Path
        and Samples
Intro     Two Main Ideas   Sampling Algorithm   Experiments   Comments and Conclusion


 R M




        Config Space                Visibility Road Map
        w/ Obstacles                  Planned Path
        and Samples

         How to sample quickly in high-dimensional Config Space?
Intro   Two Main Ideas   Sampling Algorithm   Experiments   Comments and Conclusion


 S A


        S

                     G
            Uniform
Intro   Two Main Ideas   Sampling Algorithm       Experiments   Comments and Conclusion


 S A


        S                           S

                     G                        G
            Uniform         Wavefront
                               single query
Intro   Two Main Ideas   Sampling Algorithm       Experiments        Comments and Conclusion


 S A


        S                           S

                     G                        G
            Uniform         Wavefront                Model- Guided
                               single query                 multi-query
Intro   Two Main Ideas   Sampling Algorithm       Experiments        Comments and Conclusion


 S A


        S                           S

                     G                        G
            Uniform         Wavefront                Model- Guided
                               single query                 multi-query
Intro   Two Main Ideas   Sampling Algorithm       Experiments        Comments and Conclusion


 S A


        S                           S                    Entropy-guided,
                                                          Model-guided,
                                                         Bridge-Sampling,
                     G                        G                 ...


            Uniform         Wavefront                           Guided
                               single query                 multi-query
Intro   Two Main Ideas   Sampling Algorithm       Experiments            Comments and Conclusion


 S A


        S                           S                    Entropy-guided,
                                                          Model-guided,
                                                         Bridge-Sampling,
                     G                        G                 ...


            Uniform         Wavefront                           Guided
                               single query                 multi-query

                                                      In this paper:


                                                                   ?
                                                    “utility-guided”
                                                                multi-query
O


  1   I: C S  R

  2   T M I  U G S
        Idea 1: Use Config Space Structure
        Idea 2: Increase Connectivity


  3   S A

  4   E: C  S S

  5   C  C
O


  1   I: C S  R

  2   T M I  U G S
        Idea 1: Use Config Space Structure
        Idea 2: Increase Connectivity


  3   S A

  4   E: C  S S

  5   C  C
Intro   Two Main Ideas   Sampling Algorithm   Experiments   Comments and Conclusion


 U C S S F A L
Intro     Two Main Ideas   Sampling Algorithm   Experiments   Comments and Conclusion


 U C S S F A L


        Obstacle Sample



        Free Space Sample
Intro   Two Main Ideas   Sampling Algorithm   Experiments   Comments and Conclusion


 U C S S F A L
Intro    Two Main Ideas   Sampling Algorithm   Experiments   Comments and Conclusion


 U C S S F A L




        Function Approximator: Approximate Model of Config Space
        Use Model to select next free sample
        Using all known samples aids active learning
O


  1   I: C S  R

  2   T M I  U G S
        Idea 1: Use Config Space Structure
        Idea 2: Increase Connectivity


  3   S A

  4   E: C  S S

  5   C  C
Intro         Two Main Ideas   Sampling Algorithm    Experiments   Comments and Conclusion


 D  “U”   S

               Component 1
                                          Obstacle

                                                    Component 2




        Entropy: Probability that random sample is in visibility region of
        particular component
Intro        Two Main Ideas   Sampling Algorithm    Experiments   Comments and Conclusion


 D  “U”   S

              Component 1
                                         Obstacle

                                                   Component 2




        Red Sample: Entropy unchanged, Zero information gain
Intro         Two Main Ideas   Sampling Algorithm    Experiments   Comments and Conclusion


 D  “U”   S

               Component 1
                                          Obstacle

                                                    Component 2




        Entropy: Probability that random sample is in visibility region of
        particular component
Intro         Two Main Ideas   Sampling Algorithm   Experiments   Comments and Conclusion


 D  “U”   S


                                          Obstacle




                                    Just 1 Component left
        Red Sample: Less Entropy, Large information gain, high Utility
O


  1   I: C S  R

  2   T M I  U G S
        Idea 1: Use Config Space Structure
        Idea 2: Increase Connectivity


  3   S A

  4   E: C  S S

  5   C  C
Intro         Two Main Ideas   Sampling Algorithm     Experiments   Comments and Conclusion


 E C U M  C

        Component 1
                                    Obstacle

                                                    Component 2




        Application Idea 2: Try to increase connectivity
Intro         Two Main Ideas   Sampling Algorithm     Experiments   Comments and Conclusion


 E C U M  C

        Component 1
                                    Obstacle

                                                    Component 2




        Application Idea 2: Try to increase connectivity
Intro     Two Main Ideas   Sampling Algorithm     Experiments   Comments and Conclusion


 E C U M  C

        Component 1
                                Obstacle

                                                Component 2

                                 Center Point
Intro     Two Main Ideas   Sampling Algorithm     Experiments   Comments and Conclusion


 E C U M  C

        Component 1
                                Obstacle

                                                Component 2
Intro         Two Main Ideas   Sampling Algorithm     Experiments   Comments and Conclusion


 W  P S  M

        Component 1
                                    Obstacle

                                                    Component 2




        Application Idea 1: Exploit model of config space
Intro         Two Main Ideas   Sampling Algorithm     Experiments   Comments and Conclusion


 W  P S  M

        Component 1
                                    Obstacle

                                                    Component 2




        Application Idea 1: Exploit model of config space
Intro     Two Main Ideas   Sampling Algorithm     Experiments   Comments and Conclusion


 W  P S  M

        Component 1
                                Obstacle

                                                Component 2
O


  1   I: C S  R

  2   T M I  U G S
        Idea 1: Use Config Space Structure
        Idea 2: Increase Connectivity


  3   S A

  4   E: C  S S

  5   C  C
Intro      Two Main Ideas   Sampling Algorithm    Experiments    Comments and Conclusion


 R




        3 or 4 Joints with 3 DOF                 Mobile base (2 DOF)
        each                                     2 Joints with 1 / 2 DOF each
        9 DOF / 12 DOF                           4 DOF / 6 DOF
          Compare only Sampling strategy until path found
          Difficulty: Analyzing Overhead of Model, Utility Evaluation
Intro        Two Main Ideas   Sampling Algorithm   Experiments   Comments and Conclusion


 R

        Runtimes: 4-DOF mobile manipulator
Intro        Two Main Ideas   Sampling Algorithm   Experiments   Comments and Conclusion


 R

        Fraction of Config Space covered: 9-DOF arm
O


  1   I: C S  R

  2   T M I  U G S
        Idea 1: Use Config Space Structure
        Idea 2: Increase Connectivity


  3   S A

  4   E: C  S S

  5   C  C
Intro         Two Main Ideas   Sampling Algorithm   Experiments       Comments and Conclusion


 A P P  U-G S?




                    Goal                                          Start




        Initially, just two Samples at start and goal, respectively. What
        happens?
Intro        Two Main Ideas   Sampling Algorithm   Experiments       Comments and Conclusion


 A P P  U-G S?




                   Goal                                          Start




        Line between two clusters
Intro        Two Main Ideas   Sampling Algorithm   Experiments       Comments and Conclusion


 A P P  U-G S?




                   Goal                                          Start




        Sample candidates around mitpoint
Intro        Two Main Ideas   Sampling Algorithm   Experiments       Comments and Conclusion


 A P P  U-G S?




                   Goal                                          Start




        Model does not provide information, choose any.
Intro        Two Main Ideas   Sampling Algorithm   Experiments       Comments and Conclusion


 A P P  U-G S?




                   Goal                                          Start




        Green: New model. Suppose same nodes chosen again. What
        happens?
Intro        Two Main Ideas   Sampling Algorithm   Experiments       Comments and Conclusion


 A P P  U-G S?




                   Goal                                          Start




        New points cluster around previous points
Intro        Two Main Ideas     Sampling Algorithm   Experiments       Comments and Conclusion


 A P P  U-G S?




                   Goal                                            Start




        “Worst case” scenario
Intro        Two Main Ideas     Sampling Algorithm   Experiments   Comments and Conclusion


 C



        Burns & Brock introduced a sampling algorithm

            for multi-query planning
            uses active learning
            maximizes utility
            outperforms other algorithms
            not thoroughly evaluated
            may have strong dependency on parameters/environment
Intro   Two Main Ideas   Sampling Algorithm   Experiments   Comments and Conclusion


 D




                                        ?

Mais conteúdo relacionado

Destaque

HH6 How the construction of large-scale dams is changing the hydropolitical r...
HH6 How the construction of large-scale dams is changing the hydropolitical r...HH6 How the construction of large-scale dams is changing the hydropolitical r...
HH6 How the construction of large-scale dams is changing the hydropolitical r...
Ana Cascao
 
Cascao_South_Sudan_Nile_Hydropolitics
Cascao_South_Sudan_Nile_HydropoliticsCascao_South_Sudan_Nile_Hydropolitics
Cascao_South_Sudan_Nile_Hydropolitics
Ana Cascao
 
Cascao&Conway Stockholm Doube Faced Cooperation Nile Basin
Cascao&Conway Stockholm Doube Faced Cooperation Nile BasinCascao&Conway Stockholm Doube Faced Cooperation Nile Basin
Cascao&Conway Stockholm Doube Faced Cooperation Nile Basin
Ana Cascao
 
Jack London Background
Jack London BackgroundJack London Background
Jack London Background
prhahn
 

Destaque (18)

HH6 How the construction of large-scale dams is changing the hydropolitical r...
HH6 How the construction of large-scale dams is changing the hydropolitical r...HH6 How the construction of large-scale dams is changing the hydropolitical r...
HH6 How the construction of large-scale dams is changing the hydropolitical r...
 
Dades i operadors
Dades i operadorsDades i operadors
Dades i operadors
 
Invoicing
InvoicingInvoicing
Invoicing
 
Callme
CallmeCallme
Callme
 
December 2009 TeachStreet Teacher Webinar & Meet-up
December 2009 TeachStreet Teacher Webinar & Meet-upDecember 2009 TeachStreet Teacher Webinar & Meet-up
December 2009 TeachStreet Teacher Webinar & Meet-up
 
Ad Campaign For Calmax
Ad Campaign For CalmaxAd Campaign For Calmax
Ad Campaign For Calmax
 
Search: The Purest Form of Interaction Design
Search: The Purest Form of Interaction DesignSearch: The Purest Form of Interaction Design
Search: The Purest Form of Interaction Design
 
Jaladas De Awebowey
Jaladas De AweboweyJaladas De Awebowey
Jaladas De Awebowey
 
Cascao_South_Sudan_Nile_Hydropolitics
Cascao_South_Sudan_Nile_HydropoliticsCascao_South_Sudan_Nile_Hydropolitics
Cascao_South_Sudan_Nile_Hydropolitics
 
Entrepreneur! london 2012 slideshare
Entrepreneur! london 2012 slideshareEntrepreneur! london 2012 slideshare
Entrepreneur! london 2012 slideshare
 
How to craft consolidated math notes
How to craft consolidated math notesHow to craft consolidated math notes
How to craft consolidated math notes
 
A life without complaints
A life without complaintsA life without complaints
A life without complaints
 
Cascao&Conway Stockholm Doube Faced Cooperation Nile Basin
Cascao&Conway Stockholm Doube Faced Cooperation Nile BasinCascao&Conway Stockholm Doube Faced Cooperation Nile Basin
Cascao&Conway Stockholm Doube Faced Cooperation Nile Basin
 
030413
030413030413
030413
 
Vladi funtzioak
Vladi funtzioakVladi funtzioak
Vladi funtzioak
 
Awebowey!!! Agosto2009
Awebowey!!! Agosto2009Awebowey!!! Agosto2009
Awebowey!!! Agosto2009
 
Jack London Background
Jack London BackgroundJack London Background
Jack London Background
 
Iui protocol -draft
Iui protocol -draftIui protocol -draft
Iui protocol -draft
 

Semelhante a Toward Optimal Configuration Space Sampling

2009 05 01 How To Build A Lean Startup Step By Step
2009 05 01 How To Build A Lean Startup Step By Step2009 05 01 How To Build A Lean Startup Step By Step
2009 05 01 How To Build A Lean Startup Step By Step
Eric Ries
 

Semelhante a Toward Optimal Configuration Space Sampling (11)

Learning Kinematics from direct Self-Observation using Nearest-Neighbour Methods
Learning Kinematics from direct Self-Observation using Nearest-Neighbour MethodsLearning Kinematics from direct Self-Observation using Nearest-Neighbour Methods
Learning Kinematics from direct Self-Observation using Nearest-Neighbour Methods
 
Andrew rusling 21 experiments to increase velocity
Andrew rusling 21 experiments to increase velocityAndrew rusling 21 experiments to increase velocity
Andrew rusling 21 experiments to increase velocity
 
21 experiments to increase velocity
21 experiments to increase velocity21 experiments to increase velocity
21 experiments to increase velocity
 
Managing Uncertainty in Value-based SE
Managing Uncertainty in Value-based SEManaging Uncertainty in Value-based SE
Managing Uncertainty in Value-based SE
 
Arbonne's Results Presentation
Arbonne's Results PresentationArbonne's Results Presentation
Arbonne's Results Presentation
 
The deep bootstrap framework review
The deep bootstrap framework reviewThe deep bootstrap framework review
The deep bootstrap framework review
 
Test Driven Development
Test Driven DevelopmentTest Driven Development
Test Driven Development
 
Web 2.0 架站工具—AJAX By Examples-馮彥文(Tempo)
Web 2.0 架站工具—AJAX By Examples-馮彥文(Tempo)Web 2.0 架站工具—AJAX By Examples-馮彥文(Tempo)
Web 2.0 架站工具—AJAX By Examples-馮彥文(Tempo)
 
2009 05 01 How To Build A Lean Startup Step By Step
2009 05 01 How To Build A Lean Startup Step By Step2009 05 01 How To Build A Lean Startup Step By Step
2009 05 01 How To Build A Lean Startup Step By Step
 
21 Experiments to Increase Throughput
21 Experiments to Increase Throughput21 Experiments to Increase Throughput
21 Experiments to Increase Throughput
 
Computational methods applications in air pollution modeling (Dr. Yadghar)
Computational methods applications in air pollution modeling (Dr. Yadghar)Computational methods applications in air pollution modeling (Dr. Yadghar)
Computational methods applications in air pollution modeling (Dr. Yadghar)
 

Mais de cijat (6)

CRF-Filters: Discriminative Particle Filters for Sequential State Estimation
CRF-Filters: Discriminative Particle Filters for Sequential State EstimationCRF-Filters: Discriminative Particle Filters for Sequential State Estimation
CRF-Filters: Discriminative Particle Filters for Sequential State Estimation
 
The ball is not just orange.
The ball is not just orange.The ball is not just orange.
The ball is not just orange.
 
RoboCup Introduction
RoboCup IntroductionRoboCup Introduction
RoboCup Introduction
 
Local and Global Gating of Synaptic Plasticity
Local and Global Gating of Synaptic PlasticityLocal and Global Gating of Synaptic Plasticity
Local and Global Gating of Synaptic Plasticity
 
Auxiliary
AuxiliaryAuxiliary
Auxiliary
 
Affordances
AffordancesAffordances
Affordances
 

Último

Why Teams call analytics are critical to your entire business
Why Teams call analytics are critical to your entire businessWhy Teams call analytics are critical to your entire business
Why Teams call analytics are critical to your entire business
panagenda
 
Cloud Frontiers: A Deep Dive into Serverless Spatial Data and FME
Cloud Frontiers:  A Deep Dive into Serverless Spatial Data and FMECloud Frontiers:  A Deep Dive into Serverless Spatial Data and FME
Cloud Frontiers: A Deep Dive into Serverless Spatial Data and FME
Safe Software
 

Último (20)

Strategies for Landing an Oracle DBA Job as a Fresher
Strategies for Landing an Oracle DBA Job as a FresherStrategies for Landing an Oracle DBA Job as a Fresher
Strategies for Landing an Oracle DBA Job as a Fresher
 
Boost Fertility New Invention Ups Success Rates.pdf
Boost Fertility New Invention Ups Success Rates.pdfBoost Fertility New Invention Ups Success Rates.pdf
Boost Fertility New Invention Ups Success Rates.pdf
 
TrustArc Webinar - Unlock the Power of AI-Driven Data Discovery
TrustArc Webinar - Unlock the Power of AI-Driven Data DiscoveryTrustArc Webinar - Unlock the Power of AI-Driven Data Discovery
TrustArc Webinar - Unlock the Power of AI-Driven Data Discovery
 
Why Teams call analytics are critical to your entire business
Why Teams call analytics are critical to your entire businessWhy Teams call analytics are critical to your entire business
Why Teams call analytics are critical to your entire business
 
Introduction to Multilingual Retrieval Augmented Generation (RAG)
Introduction to Multilingual Retrieval Augmented Generation (RAG)Introduction to Multilingual Retrieval Augmented Generation (RAG)
Introduction to Multilingual Retrieval Augmented Generation (RAG)
 
DBX First Quarter 2024 Investor Presentation
DBX First Quarter 2024 Investor PresentationDBX First Quarter 2024 Investor Presentation
DBX First Quarter 2024 Investor Presentation
 
Apidays New York 2024 - The value of a flexible API Management solution for O...
Apidays New York 2024 - The value of a flexible API Management solution for O...Apidays New York 2024 - The value of a flexible API Management solution for O...
Apidays New York 2024 - The value of a flexible API Management solution for O...
 
Platformless Horizons for Digital Adaptability
Platformless Horizons for Digital AdaptabilityPlatformless Horizons for Digital Adaptability
Platformless Horizons for Digital Adaptability
 
DEV meet-up UiPath Document Understanding May 7 2024 Amsterdam
DEV meet-up UiPath Document Understanding May 7 2024 AmsterdamDEV meet-up UiPath Document Understanding May 7 2024 Amsterdam
DEV meet-up UiPath Document Understanding May 7 2024 Amsterdam
 
Mcleodganj Call Girls 🥰 8617370543 Service Offer VIP Hot Model
Mcleodganj Call Girls 🥰 8617370543 Service Offer VIP Hot ModelMcleodganj Call Girls 🥰 8617370543 Service Offer VIP Hot Model
Mcleodganj Call Girls 🥰 8617370543 Service Offer VIP Hot Model
 
Apidays New York 2024 - APIs in 2030: The Risk of Technological Sleepwalk by ...
Apidays New York 2024 - APIs in 2030: The Risk of Technological Sleepwalk by ...Apidays New York 2024 - APIs in 2030: The Risk of Technological Sleepwalk by ...
Apidays New York 2024 - APIs in 2030: The Risk of Technological Sleepwalk by ...
 
Understanding the FAA Part 107 License ..
Understanding the FAA Part 107 License ..Understanding the FAA Part 107 License ..
Understanding the FAA Part 107 License ..
 
Artificial Intelligence Chap.5 : Uncertainty
Artificial Intelligence Chap.5 : UncertaintyArtificial Intelligence Chap.5 : Uncertainty
Artificial Intelligence Chap.5 : Uncertainty
 
Cloud Frontiers: A Deep Dive into Serverless Spatial Data and FME
Cloud Frontiers:  A Deep Dive into Serverless Spatial Data and FMECloud Frontiers:  A Deep Dive into Serverless Spatial Data and FME
Cloud Frontiers: A Deep Dive into Serverless Spatial Data and FME
 
"I see eyes in my soup": How Delivery Hero implemented the safety system for ...
"I see eyes in my soup": How Delivery Hero implemented the safety system for ..."I see eyes in my soup": How Delivery Hero implemented the safety system for ...
"I see eyes in my soup": How Delivery Hero implemented the safety system for ...
 
EMPOWERMENT TECHNOLOGY GRADE 11 QUARTER 2 REVIEWER
EMPOWERMENT TECHNOLOGY GRADE 11 QUARTER 2 REVIEWEREMPOWERMENT TECHNOLOGY GRADE 11 QUARTER 2 REVIEWER
EMPOWERMENT TECHNOLOGY GRADE 11 QUARTER 2 REVIEWER
 
Apidays New York 2024 - The Good, the Bad and the Governed by David O'Neill, ...
Apidays New York 2024 - The Good, the Bad and the Governed by David O'Neill, ...Apidays New York 2024 - The Good, the Bad and the Governed by David O'Neill, ...
Apidays New York 2024 - The Good, the Bad and the Governed by David O'Neill, ...
 
Vector Search -An Introduction in Oracle Database 23ai.pptx
Vector Search -An Introduction in Oracle Database 23ai.pptxVector Search -An Introduction in Oracle Database 23ai.pptx
Vector Search -An Introduction in Oracle Database 23ai.pptx
 
Repurposing LNG terminals for Hydrogen Ammonia: Feasibility and Cost Saving
Repurposing LNG terminals for Hydrogen Ammonia: Feasibility and Cost SavingRepurposing LNG terminals for Hydrogen Ammonia: Feasibility and Cost Saving
Repurposing LNG terminals for Hydrogen Ammonia: Feasibility and Cost Saving
 
Polkadot JAM Slides - Token2049 - By Dr. Gavin Wood
Polkadot JAM Slides - Token2049 - By Dr. Gavin WoodPolkadot JAM Slides - Token2049 - By Dr. Gavin Wood
Polkadot JAM Slides - Token2049 - By Dr. Gavin Wood
 

Toward Optimal Configuration Space Sampling

  • 1. T O C S S B B  O B Hannes Schulz University of Freiburg, ACS Feb 2008
  • 2. O 1 I: C S  R 2 T M I  U G S Idea 1: Use Config Space Structure Idea 2: Increase Connectivity 3 S A 4 E: C  S S 5 C  C
  • 3. O 1 I: C S  R 2 T M I  U G S Idea 1: Use Config Space Structure Idea 2: Increase Connectivity 3 S A 4 E: C  S S 5 C  C
  • 4. Intro Two Main Ideas Sampling Algorithm Experiments Comments and Conclusion C S World Space Configuration Space http://ford.ieor.berkeley.edu/cspace
  • 5. Intro Two Main Ideas Sampling Algorithm Experiments Comments and Conclusion C S World Space Configuration Space http://ford.ieor.berkeley.edu/cspace
  • 6. Intro Two Main Ideas Sampling Algorithm Experiments Comments and Conclusion C S World Space Configuration Space http://ford.ieor.berkeley.edu/cspace
  • 7. Intro Two Main Ideas Sampling Algorithm Experiments Comments and Conclusion C S World Space Configuration Space http://ford.ieor.berkeley.edu/cspace
  • 8. Intro Two Main Ideas Sampling Algorithm Experiments Comments and Conclusion C S World Space Configuration Space http://ford.ieor.berkeley.edu/cspace
  • 9. Intro Two Main Ideas Sampling Algorithm Experiments Comments and Conclusion C S World Space Configuration Space http://ford.ieor.berkeley.edu/cspace
  • 10. Intro Two Main Ideas Sampling Algorithm Experiments Comments and Conclusion C S World Space Configuration Space http://ford.ieor.berkeley.edu/cspace
  • 11. Intro Two Main Ideas Sampling Algorithm Experiments Comments and Conclusion C S World Space Configuration Space http://ford.ieor.berkeley.edu/cspace
  • 12. Intro Two Main Ideas Sampling Algorithm Experiments Comments and Conclusion C S World Space Configuration Space http://ford.ieor.berkeley.edu/cspace
  • 13. Intro Two Main Ideas Sampling Algorithm Experiments Comments and Conclusion R M Config Space w/ Obstacles
  • 14. Intro Two Main Ideas Sampling Algorithm Experiments Comments and Conclusion R M Config Space w/ Obstacles and Samples
  • 15. Intro Two Main Ideas Sampling Algorithm Experiments Comments and Conclusion R M Config Space Visibility Road Map w/ Obstacles and Samples
  • 16. Intro Two Main Ideas Sampling Algorithm Experiments Comments and Conclusion R M Config Space Visibility Road Map w/ Obstacles Planned Path and Samples
  • 17. Intro Two Main Ideas Sampling Algorithm Experiments Comments and Conclusion R M Config Space Visibility Road Map w/ Obstacles Planned Path and Samples How to sample quickly in high-dimensional Config Space?
  • 18. Intro Two Main Ideas Sampling Algorithm Experiments Comments and Conclusion S A S G Uniform
  • 19. Intro Two Main Ideas Sampling Algorithm Experiments Comments and Conclusion S A S S G G Uniform Wavefront single query
  • 20. Intro Two Main Ideas Sampling Algorithm Experiments Comments and Conclusion S A S S G G Uniform Wavefront Model- Guided single query multi-query
  • 21. Intro Two Main Ideas Sampling Algorithm Experiments Comments and Conclusion S A S S G G Uniform Wavefront Model- Guided single query multi-query
  • 22. Intro Two Main Ideas Sampling Algorithm Experiments Comments and Conclusion S A S S Entropy-guided, Model-guided, Bridge-Sampling, G G ... Uniform Wavefront Guided single query multi-query
  • 23. Intro Two Main Ideas Sampling Algorithm Experiments Comments and Conclusion S A S S Entropy-guided, Model-guided, Bridge-Sampling, G G ... Uniform Wavefront Guided single query multi-query In this paper: ? “utility-guided” multi-query
  • 24. O 1 I: C S  R 2 T M I  U G S Idea 1: Use Config Space Structure Idea 2: Increase Connectivity 3 S A 4 E: C  S S 5 C  C
  • 25. O 1 I: C S  R 2 T M I  U G S Idea 1: Use Config Space Structure Idea 2: Increase Connectivity 3 S A 4 E: C  S S 5 C  C
  • 26. Intro Two Main Ideas Sampling Algorithm Experiments Comments and Conclusion U C S S F A L
  • 27. Intro Two Main Ideas Sampling Algorithm Experiments Comments and Conclusion U C S S F A L Obstacle Sample Free Space Sample
  • 28. Intro Two Main Ideas Sampling Algorithm Experiments Comments and Conclusion U C S S F A L
  • 29. Intro Two Main Ideas Sampling Algorithm Experiments Comments and Conclusion U C S S F A L Function Approximator: Approximate Model of Config Space Use Model to select next free sample Using all known samples aids active learning
  • 30. O 1 I: C S  R 2 T M I  U G S Idea 1: Use Config Space Structure Idea 2: Increase Connectivity 3 S A 4 E: C  S S 5 C  C
  • 31. Intro Two Main Ideas Sampling Algorithm Experiments Comments and Conclusion D  “U”   S Component 1 Obstacle Component 2 Entropy: Probability that random sample is in visibility region of particular component
  • 32. Intro Two Main Ideas Sampling Algorithm Experiments Comments and Conclusion D  “U”   S Component 1 Obstacle Component 2 Red Sample: Entropy unchanged, Zero information gain
  • 33. Intro Two Main Ideas Sampling Algorithm Experiments Comments and Conclusion D  “U”   S Component 1 Obstacle Component 2 Entropy: Probability that random sample is in visibility region of particular component
  • 34. Intro Two Main Ideas Sampling Algorithm Experiments Comments and Conclusion D  “U”   S Obstacle Just 1 Component left Red Sample: Less Entropy, Large information gain, high Utility
  • 35. O 1 I: C S  R 2 T M I  U G S Idea 1: Use Config Space Structure Idea 2: Increase Connectivity 3 S A 4 E: C  S S 5 C  C
  • 36. Intro Two Main Ideas Sampling Algorithm Experiments Comments and Conclusion E C U M  C Component 1 Obstacle Component 2 Application Idea 2: Try to increase connectivity
  • 37. Intro Two Main Ideas Sampling Algorithm Experiments Comments and Conclusion E C U M  C Component 1 Obstacle Component 2 Application Idea 2: Try to increase connectivity
  • 38. Intro Two Main Ideas Sampling Algorithm Experiments Comments and Conclusion E C U M  C Component 1 Obstacle Component 2 Center Point
  • 39. Intro Two Main Ideas Sampling Algorithm Experiments Comments and Conclusion E C U M  C Component 1 Obstacle Component 2
  • 40. Intro Two Main Ideas Sampling Algorithm Experiments Comments and Conclusion W  P S  M Component 1 Obstacle Component 2 Application Idea 1: Exploit model of config space
  • 41. Intro Two Main Ideas Sampling Algorithm Experiments Comments and Conclusion W  P S  M Component 1 Obstacle Component 2 Application Idea 1: Exploit model of config space
  • 42. Intro Two Main Ideas Sampling Algorithm Experiments Comments and Conclusion W  P S  M Component 1 Obstacle Component 2
  • 43. O 1 I: C S  R 2 T M I  U G S Idea 1: Use Config Space Structure Idea 2: Increase Connectivity 3 S A 4 E: C  S S 5 C  C
  • 44. Intro Two Main Ideas Sampling Algorithm Experiments Comments and Conclusion R 3 or 4 Joints with 3 DOF Mobile base (2 DOF) each 2 Joints with 1 / 2 DOF each 9 DOF / 12 DOF 4 DOF / 6 DOF Compare only Sampling strategy until path found Difficulty: Analyzing Overhead of Model, Utility Evaluation
  • 45. Intro Two Main Ideas Sampling Algorithm Experiments Comments and Conclusion R Runtimes: 4-DOF mobile manipulator
  • 46. Intro Two Main Ideas Sampling Algorithm Experiments Comments and Conclusion R Fraction of Config Space covered: 9-DOF arm
  • 47. O 1 I: C S  R 2 T M I  U G S Idea 1: Use Config Space Structure Idea 2: Increase Connectivity 3 S A 4 E: C  S S 5 C  C
  • 48. Intro Two Main Ideas Sampling Algorithm Experiments Comments and Conclusion A P P  U-G S? Goal Start Initially, just two Samples at start and goal, respectively. What happens?
  • 49. Intro Two Main Ideas Sampling Algorithm Experiments Comments and Conclusion A P P  U-G S? Goal Start Line between two clusters
  • 50. Intro Two Main Ideas Sampling Algorithm Experiments Comments and Conclusion A P P  U-G S? Goal Start Sample candidates around mitpoint
  • 51. Intro Two Main Ideas Sampling Algorithm Experiments Comments and Conclusion A P P  U-G S? Goal Start Model does not provide information, choose any.
  • 52. Intro Two Main Ideas Sampling Algorithm Experiments Comments and Conclusion A P P  U-G S? Goal Start Green: New model. Suppose same nodes chosen again. What happens?
  • 53. Intro Two Main Ideas Sampling Algorithm Experiments Comments and Conclusion A P P  U-G S? Goal Start New points cluster around previous points
  • 54. Intro Two Main Ideas Sampling Algorithm Experiments Comments and Conclusion A P P  U-G S? Goal Start “Worst case” scenario
  • 55. Intro Two Main Ideas Sampling Algorithm Experiments Comments and Conclusion C Burns & Brock introduced a sampling algorithm for multi-query planning uses active learning maximizes utility outperforms other algorithms not thoroughly evaluated may have strong dependency on parameters/environment
  • 56. Intro Two Main Ideas Sampling Algorithm Experiments Comments and Conclusion D ?