/
FUZZ y   T im E -critical FUZZ y   T im E -critical

FUZZ y T im E -critical - PowerPoint Presentation

cheryl-pisano
cheryl-pisano . @cheryl-pisano
Follow
344 views
Uploaded On 2019-11-23

FUZZ y T im E -critical - PPT Presentation

FUZZ y T im E critical S patio T emporal FUZZTEST Project 3 Brandon Cook 3 rd Year Aerospace Engineering ACCEND Student Dr Kelly Cohen Faculty Mentor Sponsored by NSF Type 1 STEP Grant Grant ID No DUE0756921 ID: 767206

type fuzzy intelligent research fuzzy type research intelligent time simulation create robots game aiaa autonomous pong inference logic ball

Share:

Link:

Embed:

Download Presentation from below link

Download Presentation The PPT/PDF document "FUZZ y T im E -critical" 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

FUZZy TimE-critical Spatio-Temporal (FUZZ-TEST): Project #3 Brandon Cook – 3rd Year Aerospace Engineering ACCEND Student Dr. Kelly Cohen – Faculty MentorSponsored by: NSF Type 1 STEP Grant, Grant ID No.: DUE-0756921Continuation of: Fuzzy Logic Inference for Pong (FLIP) Research 1

OutlineProject Goal & ObjectivesProject Research TasksProject Time ScheduleIntroduction to Fuzzy LogicCurrent ProgressFuture Work2

Project GoalGrasp understanding of intelligent robots and systems while expanding on abilities for real world applications.3

Overall ObjectivesCreate a Doubles-PONG game simulation in MATLABLearn about Type II Fuzzy Logic Create an AIAA conference paperWork with Sophia Mitchell to create a joint journal publication 4

Project Research TasksConduct Literature survey Create an “Intelligent Team” of two autonomous agentsSuccessfully implement additional rotation DOF (Degree of Freedom)Test the effectiveness of the “Intelligent Team” Summarize results into a Technical Report 5

Fuzzy LogicAllows classification of variables for more human-like reasoning.Common termsInputsRulesOutputsMembership FunctionFuzzy Inference System (FIS) 6

7Fuzzy Decision Making

Type II Fuzzy LogicBrings 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 quantified8

9Example of Type 2 Fuzzy Membership Functions

AccomplishmentsKnowledge on Type II Fuzzy LogicRotational DOF added to human and Fuzzy paddlesEnhanced bounce characteristicOptimized boundary conditionsAbility to rotate and translate simultaneouslyLess delay between commands and responseAllows Fuzzy paddle to rotate fully to desired outputImplemented new design into FLIP (singles game)New Fuzzy Rules10

Fuzzy Paddle11

Fuzzy Inference System12

Simulation: Robots vs. Robots13

Results: Robots vs. Robots14 Methods:Ran simulation for 30 servesConclusions:Each “volley” lasted nearly 3 minutesIntelligent teams are equally matchedHighly effective at calculating the ball trajectory to find intersection pointVery challenging to score a point on the fuzzy team

Simulation: Humans vs. Robots15

Results: Humans vs. Robots16 Methods:Two veteran “gamers” selected to test the effectiveness of the fuzzy logicConclusions:Fuzzy team is superb at collaborating effectively to defeat the opposing teamHighly effective at communicating in a time-critical mannerExcellent at making adjustments to the infinite gameplay scenarios to defeat opponent

ConclusionsFuzzy logic is an effective tool for collaboration between autonomous agents in a time-critical spacio-temporal environmentA completely autonomous, robotic, intelligent team (or swarm) would be very useful in applications including:Space roboticsCelestial body exploration and colonizationUnmanned Aerial Vehicles (UAVs)Homeland security Disaster relief programs.17

Future WorkExpand on game to incorporate more advanced features:Modify FIS for extreme offensive moves capability (limits reaction time)Passing from back to front paddleSpeeding up ball between paddlesBoth go for ball with different paddle anglesAdd additional inputs/outputs to take opponents current rotation in to accountPresent work at International AIAA conference in January (Dallas, TX) Create a joint AIAA publication with Sophia Mitchell18

Future Plans Continue research in intelligent systemsComplete my Bachelors and Masters degrees through the ACCEND programPursue a PhDNASA Jet Propulsion LaboratoryUpcoming Coop: NASA Marshall (U.S. Space and Rocket CenterGo to space.19 19

AcknowledgementsUC Academic Year – Research Experience for Undergraduates (AY-REU) ProgramSophia Mitchell (Base Pong Script)Dr. Kelly Cohen20

Questions?21