Free Flying Micro Platform (FFMP): The Phases.
From dumb to ultra-intelligent

The following table is an outline. If you have some comments or ideas, please let me know!

And do not forget where I am right now: "Get used to the way of thinking in which the hardware of the realisation of an idea is much less important than the idea itself." (Valentino Braitenberg in Vehicles: Experiments in Synthetic Psychology, p. 2)



Overview

Please click on the numbers to see the details of each phase.

Phase
Main goal
Primary Motivation
Domains
Problems to solve
1
Standing still in air with automatic self stabilization Building a small (< 10 in) and quiet (< 70 dBA) entity, which is able to stay still in the air, stabilize itself automatically, and move in three-dimensional space. Make it as autonomous as possible.
Mechanical engineering
Electrical engineering
Aerial robotics
Micro Air Vehicles
Micro Modeling, Indoor Flying
Because of indoor use, it has to be mechanically safe, e.g., no big rotors like helicopters
Is it possible to do it without wires for energy transmissions and control? (All electronics on board, the batteries light enough?) If not, consider ground station.
2
Passive vision Adding a wireless camera for conveying pictures from otherwise impossible camera positions, e.g., close above crowds of people, as well as complex camera movements like fast and seamless camera travels through narrow and obstacle rich areas.
Aerial video and photography
AV technology
Electronic News Gathering (ENG), Video and TV productions
Camera and sender as small a possible
Vibration problem
3
Simple listening capability Making it respond to simple verbal requests like Up! Down! Turn left! and Zoom in!
Speech recognition
Is speech recognition on board possible?
Direct listening: noisy environment problem!
Indirect listening: What sort of remote listening device?
Distinction between different speakers?
What about feedback?
4
Active vision
Simple tasks
Simple morality
Adding sensors to improve its perception of the environment for human and non-human obstacle avoidance, as well as for evasive behavior
Making it able to understand and carry out tasks like Come here! and Leave me alone!
Implementing simple moral prime directive Do not harm anybody or anything
Sensing technology
What is the accuracy and range of the sensors?
What is the evasion strategy?
How does it recognize and localize a speaker?
Reactions of uninvolved humans to FFMP
5
Complex tasks Adding more vision and natural language understanding to make it behave like an artificial pet; understanding complex verbal requests like Follow me! Follow this man in a distance of 5 meters! Give me a close up of John!
Vision processing
Natural language processing
Psychological, sociological, and journalistic implications of widespread use of FFMPs, e.g. in Electronic News Gathering: acceptance, perceived annoyance, etc.
6
Adaptation to environment, emergent robotic behavior Creating an adaptive, behavior-based autonomous mobot, which learns from interaction with the environment about dangerous objects and situations, as well as about its power management and flying behavior.
Artificial life, Adaptive behavior
Genetic Algorithms, Classifier Systems, Genetic Programming
 
7
Use of tools Modifying it so that it can use external physical tools for simple self repair and self reproduction    
8
Intellect
Cross cultural morality
Improving the intelligence up to Artilect stage (artificial intellect, ultra-intelligent machine)
Connecting an Artificial Multi Ethical Advisor System (AMEAS, Cross Cultural Ethical Knowledge) to make sure its behavior is always ethically correct
Neuro Engineering
Philosophy, ethics; expert systems
Can we trust it?



Back to FFMP homepage


Send me some comments! Stefan Marti Last updated May 23 1998.

Copyright © 1997 - 2007 by Stefan Marti and MIT Media Lab. All rights reserved.