Active
This presentation is the property of its rightful owner.
Sponsored Links
1 / 47

Active SLAM : a Framework My, on-going, PhD Research PowerPoint PPT Presentation


  • 53 Views
  • Uploaded on
  • Presentation posted in: General

Active SLAM : a Framework My, on-going, PhD Research. Henry Carrillo Lindado Advised by : José A. Castellanos. Bio – Academic Background. Name: Henry David Carrillo Lindado. Hometown : Barranquilla – Colombia. Academic: PhD in Computer Science and System Engineering (2010 -2014 )

Download Presentation

Active SLAM : a Framework My, on-going, PhD Research

An Image/Link below is provided (as is) to download presentation

Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author.While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server.


- - - - - - - - - - - - - - - - - - - - - - - - - - E N D - - - - - - - - - - - - - - - - - - - - - - - - - -

Presentation Transcript


Active slam a framework my on going phd research

Active SLAM : a Framework

My, on-going, PhD Research

Henry Carrillo Lindado

Advised by:

José A. Castellanos


Bio academic background

Bio – Academic Background

  • Name: Henry David Carrillo Lindado.

  • Hometown: Barranquilla – Colombia.

  • Academic:

    • PhD in Computer Science and System Engineering (2010 -2014)

      • University of Zaragoza - Spain

    • M.Sc. in Computer Science and System Engineering

    • M.Sc. in Electronics Engineering

    • B.Eng. in Electronics Engineering

  • Funding: FPI scholarship by the Ministry of Science and Innovation of Spain. 2010-2014.

  • Contact:

    • Here: 0.59 Cartesium

    • [email protected]

    • http://webdiis.unizar.es/~hcarri/pmwiki/pmwiki.php

1


So what is my phd about

So, What is my PhD about?

  • Objective:To build an active SLAM framework.

  • Why?:

    • Where should I go in order to improve my localization and map representation?

    • If I go from A to B, will I be lost (e.g. Unable to localize)?

    • What movements should I make in order to keep my metrical error below X mm?

  • Aim at:

    • Metrical representations.

    • Topological representations.

    • Metrical+Topologicalrepresentations.

2


What have i done

Whathave I done?

Metrical

3


Preliminaries slam

Preliminaries – SLAM

  • H0:A model of the operative environment is an essential requirement for an autonomous mobile robot.

  • Three basic tasks:

    • Where am I?

    • What does the world look like?

    • Where do I go?

  • SLAM => Joint of two tasks.

  • SLAM => Does not define

    the path-trajectory of the robot.

  • Integrated approach => On the way to autonomy.

4Exploration and Mapping with Mobile Robots. CyrillStachniss. 2006.


Preliminaries active slam i

Preliminaries – Active SLAM (I)

  • Active SLAM => To integrate path planning into a SLAM process.

    • To explorer more area.

    • Navigate safely.

    • Reduce uncertainty.

  • Algorithms

    • 1º Alg. [Feder, Leonard](99)

      • Active perception [Bajacksy](86)

    • Infinite Horizon and MPC

      [Leung, Dissanayake](06)

5


Preliminaries active slam ii

Preliminaries – Active SLAM (II)

  • Pseudo-code:

    • Set of trajectories

    • Assign a score to each trajectory

      • Uncertainty of map+robot

      • Trajectory constraints

    • Execute the trajectory with

      the optimum .

6


Preliminaries active slam ii1

Preliminaries – Active SLAM (II)

  • Pseudo-code:

    • Set of trajectories

    • Assign a score to each trajectory

      • Uncertainty of map+robot

      • Trajectory constraints

    • Execute the trajectory with

      the optimum .

6


Preliminaries active slam ii2

Preliminaries – Active SLAM (II)

  • Pseudo-code:

    • Set of trajectories

    • Assign a score to each trajectory

      • Uncertainty of map+robot

      • Trajectory constraints

    • Execute the trajectory with

      the optimum .

6


Preliminaries active slam ii3

Preliminaries – Active SLAM (II)

  • Pseudo-code:

    • Set of trajectories

    • Assign a score to each trajectory

      • Uncertainty of map+robot

      • Trajectory constraints

    • Execute the trajectory with

      the optimum .

6


Uncertainty criteria for active slam i

Uncertainty Criteria for Active SLAM (I)

  • Uncertainty/Inform. Criteria =>

  • In the TOED, a design (i.e.), isbetterthan a design, if:

  • The above does not allow to quantify the improvement, therefore is desirable to:

    • It permits to quantify the uncertainty in .

  • Theory of Optimal Experiment Design (A-opt, D-opt, E-opt…).

  • Information Theory ( Entropy, MI…).

7


Uncertainty criteria for active slam ii

Uncertainty Criteria for Active SLAM (II)

  • Some possible uncertainty criteria for active SLAM are:

  • Previous works ([Simand Roy, 2005], [Mihaylovaand De Schutter, 2003]) report A-opt as the best criterion and that D-opt gives null values.

    • A-opt, widely used:[Kollar2008] [MartinezCantin2008] [Meger2008] [Dissanayake2006].

    • Although D-opt is commonly used in the TOED because it is optimal.

Trace (A-opt)

Max(E-opt)

Determinant (D-opt)

8


Uncertainty criteria for active slam iii

Uncertainty Criteria for Active SLAM (III)

  • It is indeed possible to use D-opt in the Active SLAM context:

    • The structure of the problem needs to be taken into account (i.e. The covariance matrix varies with time).

    • It is not informative to compare the determinant of a matrix lx lwith a mx m.

      • det(l x l) is homogeneous of grade l.

    • The computation of the determinant of a highly correlated matrix(e.g. SLAM) is prone to round-off errors.

      • Processing in the logarithm space

  • D-opt for a l x l covariance matrix:

  • Stem from [Kiefer, 1974] :

9


First experiment

Firstexperiment

  • Firstexperiment: on the computation

    • Is it possible to compute D-opt from a robot doing SLAM?

    • Execute a SLAM algorithm (e.g. EKF-SLAM, iSAM).

    • Compute in each step: A-opt, E-opt , D-opt, Determinant, entropy and mutual Information.

  • Simulated Robot indoor environment : MRPT/C++

  • Real Robot indoor environment : Pioneer 3 DX - Ad-hoc

  • Real Robot indoor environment : DLR dataset

  • Real Robot outdoor environment : Victoria Park dataset

10


1e simulated robot indoor environment i

1E - Simulated Robot indoor environment (I)

Scenario:

  • Area of 25x25 m

  • 2D EKF-SLAM

  • Sensor: Odometry + Camera(360º - 3m range)

  • 180 landmarks- DA Known.

  • Gaussian errors:

    Odometry + Sensors

11


1e simulated robot indoor environment ii qualitative results

1E-Simulated Robot indoor environment (II) Qualitative results

(a)-(f) A-opt, E-opt, D-opt, determinant, entropy and MI.

12


1e real robot indoor environment @ dlr

1E-Real Robot indoor environment @ DLR

Scenario:

  • Area60x40 m

  • Sensor:

    Odometry + Camera

  • 2D EKF-SLAM

  • 576 landmarks –

    DA known.

13


1e real robot indoor environment @ dlr qualitative results

1E-Real Robot indoor environment @ DLRQualitative results

(a)-(f) A-opt, E-opt, D-opt, determinant, entropy and MI.

14


First experiment quantitative analysis

Firstexperiment – Quantitative analysis

  • Average correlation between the uncertainty criteria:

  • Variance: A-E (0,0002) / A-D (0,0540) / D-E (0,0481).

  • A-opt y E-opt=> High correlation.

    • E-opt is guided by a single eigenvalue.

  • A-opt y D-opt => Medium correlation.

    • H0: D-opt take into account more components than A-opt.

15


Second experiment

Second Experiment

  • Second experiment: Active SLAM

    • What is the effect of the uncertainty criteria in active SLAM?

    • Active SLAM => Unitary horizon (greedy).

    • Uncertainty criteria => A-opt, D-opt and Entropy.

    • Effect =>MSE y .

  • Simulated Robot with unitary horizon: MRPT / C++

16


2e simulated robot indoor environment i

2E-Simulated Robot indoor environment (I)

Scenario:

  • Area of 20x20m and 30x30m

  • 2D EKF-SLAM

  • Sensor: Odometry + Camera (360º - 3m range)

  • Gaussian errors: Odometry + sensors.

  • Path planner: Discrete (A*) and continuous (Attract-Repel).

17


2e simulated robot indoor environment ii

2E-Simulated Robot indoor environment (II)

  • Resulting paths for each uncertainty criterion: (a) D-opt, (b) A-opt y (c) Entropy. Each colour represents an executed path. 20 x 20 m map.

  • Qualitativeanalysis

18


2e simulated robot indoor environment iii

2E-Simulated Robot indoor environment (III)

  • Resulting trajectories for 10000 stepsactiveSLAMsimulation. (a). Initial trajectory. (b) A-opt. (c). D-opt.

  • Qualitative analysis.

19


2e quantitative analysis 30x30 m

2E – Quantitative Analysis 30x30 m

  • Evolution of MSE ((a)-(c)) y chi2 ((d)-(f)) ratio. Average of 10 MC simulations.

20


Take home message

Take home message

  • D-opt is the optimum criterion to measure uncertainty according to the TOED (i.e. better than A-opt (Trace)).

  • It is possible to obtain useful information regarding the uncertainty of a SLAM process with D-opt.

  • D-opt shows better performance than A-opt in our simulated experiments of active SLAM.

  • To compute D-opt in the context of a SLAM process => use the formulation presented here.

21


What have i done1

Whathave I done?

Metrical: an example using D-opt

22


Famus fast minimum uncertainty search

FaMUS: Fast Minimum Uncertainty Search

  • Minimum uncertainty path between A to B in a graph.

  • Exhaustive search.

17


Famus fast minimum uncertainty search1

FaMUS: Fast Minimum Uncertainty Search

  • Minimum uncertainty path between A to B in a graph.

  • Exhaustive search.

17


Famus fast minimum uncertainty search2

FaMUS: Fast Minimum Uncertainty Search

  • Experiment: Are the minimum uncertainty path and the shortest path necessarily equal?

    • Select two points A and B, and compare the final uncertainty.

    • 1000 times x 4 datasets. (Biccoca, Intel , New colleges and Manhattan).

24


Famus fast minimum uncertainty search3

FaMUS: Fast Minimum Uncertainty Search

  • Examples of paths.

25


Famus fast minimum uncertainty search4

FaMUS: Fast Minimum Uncertainty Search

  • Summary of results

  • Improvement of a least 50% in timing respect to the state of the art. [Valencia2011]

26


What have i done2

Whathave I done?

Topological

27


Topological

Topological

  • Guiding question:

    • Where should I go in order to improve my topological map?

  • Challenges: well-posed and egocentricimages.

    • Execute a SLAM algorithm (e.g. EKF-SLAM, iSAM).

    • Compute in each step: A-opt, E-opt , D-opt, Determinant, entropy and mutual Information.

28


Topological1

Topological

  • One solution:

    • Textons (a.k.a gist)- Undelaying Structure- Probabilistic decision

29


What have i done3

Whathave I done?

TBD

30


Active slam a framework my on going phd research

TBD

  • Which are the confidence intervals in the active predictions?

  • When do I stop the active behaviour?

    • Find a relationship between uncertainty and metrical error.

  • Use other constraints other than uncertainty.

  • Speed up the decision process.

    • Real experiments.

31


Active slam a framework my on going phd research

Active SLAM : a FrameworkMy, on-going, PhD Research

Thanks!!!

[email protected]

http://webdiis.unizar.es/~hcarri

32


Experimentos

Experimentos

  • Primer experimento : acerca del cálculo

  • Segundo experimento : SLAM activo

  • Robot simulado ambiente interior : MRPT / C++

  • Robot real ambiente interior : Pioneer 3 DX - Ad-hoc

  • Robot real ambiente interior : DLR dataset

  • Robot real ambiente exterior : Victoria Park dataset

  • Robot simulado con horizonte unitario : MRPT / C++

7


1e robot en ambiente exterior @ vp i

1E-Robot en ambiente exterior @ VP (I)

Escenario:

  • Área de 350 x 350 m

  • iSAM

  • Sensor: Odometría + Laser

  • 150 landmarks– DA conocida.

13


1e robot en ambiente exterior @ vp ii resultados cualitativos

1E-Robot en ambiente exterior @ VP (II) – Resultados cualitativos

(a)-(f) A-opt, E-opt, D-opt, determinante, entropía y MI.

14


1e robot en ambiente interior ad hoc i

1E-Robot en ambiente interior ad-hoc (I)

Escenario:

  • Área 6x4 m

  • 2D EKF-SLAM

  • Sensor: Odometría + Kinect

  • 5 landmarks– DA conocida

15


1e robot en ambiente interior ad hoc ii resultados cualitativos

1E-Robot en ambiente interior ad-hoc (II) – Resultados cualitativos

(a)-(f) A-opt, E-opt, D-opt, determinante, entropía y MI.

16


2e an lisis cuantitativo 20x20 m

2E - Análisis cuantitativo 20x20 m

  • Evolución del MSE ((a)-(c)) y chi2 ((d)-(f)). Promedio de 10 MC.

18


Determinante

Determinante

Operación algebraica que transforma una matriz en un escalar.

  • Propiedades (matriz n x n)

    • Geométrica: Volumen del paralelepípedo

      definido en el espacio n-dimensional.

    • Homogéneo de grado n.

      Si,

15


Art culos

Artículos

  • “Experimental Comparison of Optimum Criteria for Active SLAM”. Oral presentation in the “III Workshop de Robótica: Robótica Experimental (ROBOT’11)”.

  • “On the Comparison of Uncertainty Criteria for Active SLAM”. Submitted to ICRA’12.

  • “Planning Minimum Uncertainty Paths Over Pose/Feature Graphs Constructed Via SLAM” . Submitted to ICRA’12.

18


On the comparison of uncertainty criteria for active slam

OntheComparisonof UncertaintyCriteriafor Active SLAM

Thanks!!!

[email protected]

http://webdiis.unizar.es/~hcarri

19


Famus fast minimum uncertainty search5

FaMUS: Fast Minimum Uncertainty Search

17


  • Login