1 / 10

Mobile Robot Fuzzy Control

Mobile Robot Fuzzy Control. Matt Starzewski ECE 539 Project Spring 2001. ECE 539 Project. Wanted something that would be used after the course was completed. Started on stocks, but was discouraged by Prof. Hu. Besides, I needed a system with which I had

kirra
Download Presentation

Mobile Robot Fuzzy Control

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. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Mobile Robot Fuzzy Control Matt Starzewski ECE 539 Project Spring 2001

  2. ECE 539 Project • Wanted something that would be used after the course • was completed. Started on stocks, but was discouraged • by Prof. Hu. Besides, I needed a system with which I had • enough experience to be an "Expert".

  3. Meet Tommy • Maze traversal robot • Pentium-class board • Side sensors measure angle • and distance from walls

  4. Goal • Tommy needs AI to guide along walls •  Want to end up parallel with wall in moveFwd() function

  5. Tommy's Brain • Maze-level AI • navigates through grid, • calls movement functions • Fuzzy Controller (FC) • controls movement, making • sure Tommy gets from A to B -- moveFwd()

  6. System Summary • Sim Mode (using model) • fits motion very well, but still isn't the real thing • Run Mode (on Tommy) • get to see code in motion, but uptime is hard to come by

  7. Sample Output (Sim Mode)

  8. Tommy In Traction • Mostly hardware problems led to very limited testing • of the FC's "Run" mode. • Murphy's law: Hard drive crash, • batteries dying, • PWM chips burned out • Very time-consuming

  9. Assessment -- Pros • Physical Application Very Rewarding • Good Topic selection; am an "Expert" • Plenty of Resources (i.e papers) available • on Fuzzy Control • Will be used by others

  10. Problems I had • Realism takes Time! • formulating & fitting • accurate Model difficult • catch-22: must cope with unreliability • (downtime) in order to make system reliable • (robust control) • Spent way too many hours on: • Trying to Sim with Java Applet

More Related