/
Project #3: Collaborative Learning using Fuzzy Logic (CLIFF) Project #3: Collaborative Learning using Fuzzy Logic (CLIFF)

Project #3: Collaborative Learning using Fuzzy Logic (CLIFF) - PowerPoint Presentation

lois-ondreau
lois-ondreau . @lois-ondreau
Follow
342 views
Uploaded On 2019-11-23

Project #3: Collaborative Learning using Fuzzy Logic (CLIFF) - PPT Presentation

Project 3 Collaborative Learning using Fuzzy Logic CLIFF Sophia Mitchell PreJunior Aerospace Engineering ACCEND College of Engineering and Applied Science University of Cincinnati Cincinnati OH ID: 767208

fuzzy type membership logic type fuzzy logic membership functions robotic team problem benchmark applications matlab coach research results learning

Share:

Link:

Embed:

Download Presentation from below link

Download Presentation The PPT/PDF document "Project #3: Collaborative Learning using..." is the property of its rightful owner. Permission is granted to download and print the materials on this web site for personal, non-commercial use only, and to display it on your personal computer provided you do not modify the materials and that you retain all copyright notices contained in the materials. By downloading content from our website, you accept the terms of this agreement.


Presentation Transcript

Project #3: Collaborative Learning using Fuzzy Logic (CLIFF) Sophia Mitchell, Pre-Junior, Aerospace Engineering ACCENDCollege of Engineering and Applied Science, University of Cincinnati, Cincinnati, OHDr. Kelly Cohen, School of Aerospace Systems An Extension of Fuzzy Collaborative Robotic Pong (FLIP) Sponsored by The National Science Foundation Grant ID No: DUE-0756921 1

Outline Goals & ObjectivesIntroductionFuzzy LogicLiterature ReviewScenarioMethods Current Progress & ResultsDiscussionFuture WorkTimeline 2

Mission Control Overall Objective Exploring and exploiting the interactions between humans and intelligent robots to create a synergetic team.3

Research Goal Develop a robotic coach that learns from its opponent in order to coach its team to a win in the game of PONG. Human players provide uncertainty. Collaborative robots4 Robotic Coach

Robotic Team A GOOD PLAYER Human or Robotic Team B Robotic Coach 5Research ObjectiveCoach a “bad” robotic FLIP team until they beat the “good” teamat least 75% of the time

Research Objective 6

Fuzzy Logic Allows classification of variables for more human-like reasoning. Common termsInputsRulesOutputsMembership FunctionFuzzy Inference System (FIS)7

Fuzzy Decision Making 8 BaldNot Bald Percent of hair on head0 25 50 75 100

Type 2 Fuzzy Logic Brings uncertainty into the membership functions of a fuzzy setLinguistic uncertainties can be modeled that were not visible in Type 1 fuzzy setsAllows for more noisy measurements to be quantified9

Gaussian Singleton Interval Type-2 Fuzzy Inference System (Gauss-INST2-FIS)10 Uses a Gaussian primary membership function (μA(x)) Constant mean (m)Variable standard deviation (σ, σ1, σ2)Equation 1: Variable Gaussian Membership Function

Literature Review Shown us several things:Type -2 Fuzzy logic is being (slowly) still developedNo paper could be found so far that has both the idea of a coach and type-2 logic.Learning many helpful tips with type 2 logic Benchmark problem resulted from one literature review articleOne MATLAB code is published for Type-2 fuzzy logic systemsExample problems from textbook Spotty topicsNot all types and functions were coded 11

Methods 12

Methods Chose environment (MATLAB)Complete the Benchmark ProblemUse MATLAB development to create T-2 Fuzzy playersCreate the coachDevelop the team with the coachTestRefine13 Chose environment (MATLAB)Complete the Benchmark ProblemUse MATLAB development to create T-2 Fuzzy players Create the coachDevelop the team with the coachTestRefine

Benchmark Problem Methods Model the problemSolve using type-1 fuzzy logicCreate the type-2 fuzzy logic toolbox in MATLABTest the type-2 logic14

Benchmark Problem 15

The Problem “Genetic learning and performance evaluation of interval type-2 fuzzy logic controllers” [2]Filling a drum with water (controls)Use pump 1 to control water level in tank 216

Equations 17A = Cross-sectional drum areaH = Liquid levelQ = Volumetric f low rate into the drumα = Discharge coefficients

The method Use the dynamic equations outlined in the research paperCreate the Type 2 functions outlined in the paperCarefully note changes in result due to changes in m, δ and membership function position. Work with the Type 2 functions to replicate results 18

Why?Development of Type-2 Fuzzy Logic Software Needed for work on CLIFFIncreased familiarityKnown results verify the created softwareSoftware will be directly translated into researchAllows added sophistication due to better understanding of the method 19

Results 20

Their Membership Functions - e 21

My Membership Functions - e 22

Their Membership Functions - edot 23

My Membership Functions - edot 24

25

Results 26

Discussion 27

Discussion 28Type two system produces sensible resultsBenchmark problem simulator brings up a good point about type 1 logicCompare best possible solutions

ConclusionsBoth type-1 and type-2 fuzzy logic are very useful in controls applications Still not convinced if type-2 is betterFuzzy logic is a great tool to use for emulating human reasoningCreating a type-2 fuzzy logic toolbox is very time consuming29

Future WorkOptimizing type-1 and type-2 results in the benchmark problem Bringing T-2FIS into FLIPChange only part of the membership functions to type-2Cascading logic using Type-2Coach will use Type -230

Future WorkConferences Undergraduate Research ForumAIAA Aerospace Sciences Meeting (ASM) 201431

Future Plans Continue research in aerospace engineering Complete my Bachelors and Masters degrees through the ACCEND program at the University of CincinnatiPursue a PhDNASA - JPL Go to space.32

Acknowledgements UC AY-REU programDr. Kelly CohenMOST-Aerospace Labs33

References [1] Baklouti, Nesrine, Robert John, and Adel Alimi. "Interval Type-2 Fuzzy Logic Control of Mobile Robots."Journal of Intelligent Learning Systems and Applications. 4.November 2012 (2012): 291-302. Web. 18 Feb. 2013. [2] Dongrui Wu, Woei Wan Tan, Genetic learning and performance evaluation of interval type-2 fuzzy logic controllers, Engineering Applications of Artificial Intelligence, Volume 19, Issue 8, December 2006, Pages 829-841, ISSN 0952-1976, 10.1016/j.engappai.2005.12.011. (http://www.sciencedirect.com/science/article/pii/S0952197606000388)[3] Mendel, Jerry. Uncertain Rule-Based Fuzzy Logic Systems: Introduction and New Directions. Upper Saddle River, NJ: Prentice Hall PTR, 2001. Print.[4] Castillo, Oscar, and Patricia Melin. Type-2 Fuzzy Logic: Theory and Applications. 1. Heidelberg: Springer, 2008. Print.[5] Castillo, Oscar. Type-2 Fuzzy Logic in Intelligent Control Applications. 1. Heidelberg: Springer, 2012. eBook.34