Swarm Extreme


Published on

Published in: Technology, Business
  • Be the first to comment

No Downloads
Total views
On SlideShare
From Embeds
Number of Embeds
Embeds 0
No embeds

No notes for slide

Swarm Extreme

  1. 1. SWARM Extreme <br />Baturalp Torun<br />baturalp@gmail.com<br />Jitendra Bothra<br />jitendrabothra@gmail.com<br />Course: CS7780 - Special Topics in Networks<br />Guide: Prof. Guevara Noubir (noubir@ccs.neu.edu)<br />College of Computer and Information Science <br />Northeastern University<br />April 2011<br />
  2. 2. Agenda<br />Hardware Used<br />A R Drone<br />Emotiv EPOC<br />Similar Works<br />Our Objective<br />Approach<br />Design <br />Problems <br />Future Enhancements<br />Conclusion<br />PAGE 2<br />
  3. 3. A. R. Drone Technical Details<br />Embedded computer system<br />ARM9 processor, 128MB RAM, Wi-Fi b/g, USB, Linux OS<br />Inertial guidance systems<br />3 axis accelerometer<br />2 axis gyro-meter<br />1 axis yaw precision gyro-meter<br />Specs:<br />Speed: 5m/s; 18km/h<br />Weight: Less than 1 pound<br />Flying time ~12 mins.<br />Ultrasound altimeter<br />Range: 6 meters – vertical stabilization<br />Camera<br />Vertical high speed camera: up to 60 fps – allows stabilization<br />PAGE 3<br />
  4. 4. Emotiv EPOC headset tech specs<br />Based on EEG, 14 sensors – positioned for accurate spatial resolution<br />Detecting facial expressions are very fast (<10ms)<br />Wireless chip is proprietary and operates on frequency 2.4GHz<br />Hacked to use via Python<br />https://github.com/daeken/Emokit/blob/master/Announcement.md<br />https://github.com/daeken/Emokit<br />PAGE 4<br />
  5. 5. Similar Works<br />http://dsc.discovery.com/videos/prototype-this-mind-controlled-car.html<br />http://www.autonomos.inf.fu-berlin.de/subprojects/braindriver<br />http://sensorlab.cs.dartmouth.edu/pubs/neurophone.pdf<br />http://www.engadget.com/2011/02/19/german-researchers-take-mind-controlled-car-for-a-carefully-cont/<br />PAGE 5<br />
  6. 6. Our Goal<br />Our goal is to control the A R Drone using thoughts via Emotive EPOC <br />Control the A.R. Drone using Computer<br />Get the commands from Emotiv EPOC and process those<br />Design an architecture to connect both and is extendable to incorporate multiple devices.<br />Establish connections and fine tune the data for smooth controlling<br />PAGE 6<br />
  7. 7. Our Approach<br />Map headset signals to reasonable commands<br />Create a channel between the commands from headset interface and A. R. Drone<br />client/server architecture<br />allows us to control multiple A. R. Drones remotely<br />programs can be extended to run on different environments<br />PAGE 7<br />
  8. 8. Design (Server)<br />Provided by Emotiv<br />PAGE 8<br />Emotiv<br />Connect<br />Emo Composer<br />Configurations<br />Server<br />Mappings<br />Emo Engine<br />Core<br />Emotiv<br />EPOC<br />
  9. 9. Design (Client)<br />PAGE 9<br />SWARM <br />CLIENT<br />(updates every 500ms)<br />Virtual <br />Input <br />Device<br />(updates every 20ms)<br />Win32 <br />A R Drone <br />Controller<br />Buffer<br />Quad-copter<br />
  10. 10. Problems<br />Emotive SDK is platform dependent<br />Headset sends many signals<br />States change very rapidly – causes noisy interstates<br />Training requires to focus and not interchangeable from person to person<br />There is no universal training method to get same results<br />PAGE 10<br />
  11. 11. Future Enhancements<br />Current System:<br />Enhance the system to connect with multiple clients<br />Enable the system to work remotely via Internet<br />Client could be made more intelligent in order to handle emergency situations<br />Long Term:<br />The technology could be used to control devices which we used in daily routine, like cars, phones, other electronics etc. <br />On long run the EEG devices could be improved to a level where controlling devices will become as natural as controlling once body parts.<br />PAGE 11<br />
  12. 12. Conclusion<br />We are able to fully control the A R Drone using earlier by facial expression and gyro-meter and later by only using the cognitive commands. Given time this system could be future enhanced to control multiple devices simultaneously with a higher accuracy.<br />The available technology for reading and processing the thoughts is pretty good to control a system with limited command set, but it needs a lot of improvement in order to be used for complex systems.<br />Great learning experience<br />PAGE 12<br />