advertisement

Toward Optimal Configuration Space Sampling

0 %
100 %
advertisement
Information about Toward Optimal Configuration Space Sampling
Technology

Published on September 23, 2008

Author: cijat

Source: slideshare.net

Description

Seminar talk on the paper by Burns and Brock.
advertisement

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 ?

Add a comment

Related presentations

Presentación que realice en el Evento Nacional de Gobierno Abierto, realizado los ...

In this presentation we will describe our experience developing with a highly dyna...

Presentation to the LITA Forum 7th November 2014 Albuquerque, NM

Un recorrido por los cambios que nos generará el wearabletech en el futuro

Um paralelo entre as novidades & mercado em Wearable Computing e Tecnologias Assis...

Microsoft finally joins the smartwatch and fitness tracker game by introducing the...

Related pages

Toward Optimal Configuration Space Sampling

Toward Optimal Configuration Space Sampling ... figuration space dictates a number of optimal sets of ... planners can heuristically bias sampling toward
Read more

CiteSeerX — Toward Optimal Configuration Space Sampling

Abstract. Abstract — Efficient motion planning is obtained by focusing computation on relevant regions of configuration space. In the following we ...
Read more

Toward Optimal Configuration Space Sampling.

Toward Optimal Configuration Space Sampling. on ResearchGate, the professional network for scientists.
Read more

Toward Optimal Configuration Space Sampling

Title: Toward Optimal Configuration Space Sampling Author: Yan Ke Last modified by: Yan Ke Created Date: 9/17/2006 7:48:59 AM Document presentation format
Read more

CiteSeerX — Toward Optimal Configuration Space Sampling

CiteSeerX - Document Details (Isaac Councill, Lee Giles, Pradeep Teregowda): Abstract — Sampling-based motion planning discovers the implicit ...
Read more

Toward Optimal Configuration Space Sampling

Toward Optimal Configuration Space Sampling Presented by: Yan Ke Sampling Problem Tool: Sample points. Target: Construct a roadmap representing the ...
Read more

Toward Optimal Configuration Space Sampling

Toward Optimal Configuration Space Sampling Brendan Burns Oliver Brock ... can guide the selection of samples toward the optimal set. Fig. 1.
Read more

Toward Optimal Configuration Space Sampling

Toward Optimal Configuration Space Sampling name lab affiliation ... learning directs sampling toward regions of high variance.
Read more

Toward Optimal Sampling In the Space of Paths

Toward Optimal Sampling In the Space of Paths ... to optimal search space design. ... toward zero, the swept volumes of ...
Read more