Fast, Cheap and Out of Control
MASSACHUSETTS INST OF TECH CAMBRIDGE ARTIFICIAL INTELLIGENCE LAB
Pagination or Media Count:
Spur-of-the-moment planetary exploration missions are within our reach. Complex systems missions usually take years of planning and force launches to become incredibly expensive. The longer the planning and the more expensive the mission, the more catastrophic if it fails. Always the remedies have been thought to be ever better planning, more redundancy, more thorough testing, and higher-quality components. We argue here for cheap, fast missions using large numbers of mass produced simple autonomous robots that are small by todays standards, perhaps 1 to 2kg. Let loose upon a planet and out of control of ground-based mission planners, we argue that such robots enable the time between mission conception and implementation to be radically reduced, launch mass to be slashed, totally autonomous robots to be more reliable than ground- controlled robots, and large numbers of robots to change the tradeoff between reliability of individual components and overall mission sucess. Lastly, we suggest that within a few years it will be possible, at modest cost, to invade a planet with millions of tiny robots.