Swarm Intelligence (SI) is defined as "-the property of a system whereby the collective behaviours of (unsophisticated) agents interacting locally with their environment cause coherent functional global patterns to emerge. SI provides a basis with which it is possible to explore collective (or distributed) problem solving without centralized control or the provision of a global model. (ref;http://staff.washington.edu/paymana/swarm/)". The Wikipedia definition is: "Swarm intelligence (SI) is an artificial intelligence technique based around the study of collective behavior in decentralized, self-organized systems.
A relevant link here goes to Swarm robotics defined in Wikipedia as "- a new approach to the coordination of multirobot systems which consist of large numbers of relatively simple physical robots. The goal of this approach is to study the design of robots (both their physical body and their controlling behaviors) such that a desired collective behavior emerges from the inter-robot interactions and the interactions of the robots with the environment, inspired but not limited by the emergent behavior observed in social insects, called swarm intelligence. It has been discovered that a set of relatively primitive individual behaviors enhanced with communication will produce a large set of complex swarm behaviors."
The Wikipedia article on swarm robotics continues;
"Unlike distributed robotic systems in general, swarm robotics emphasizes a large number of robots, and promotes scalability, for instance, by using only local communication. Local communication is usually achieved by wireless transmission systems, using radio frequency or infrared communication.
Potential application for swarm robotics include tasks that demand for extreme miniaturization (nanorobotics, microbotics), on the one hand, as for instance distributed sensing tasks in micromachinery or the human body."
Swarm intelligence and swarm robotics represents an interesting perspective to large scale ubiquitous/uHealth sensor networks applied in healthcare. The need for some kind of swarm intelligence is obvious with use of large numbers of sensors (ambient of BAN-type) and the need for systems for valuable data extraction from distributed sensors like motes or Sun Spots. Some level of problem solving capabilities are likely to be needed for handling of data streams. Both Tmote Sky motes and Sun SPOTS can be manually programmed "on the fly", passing updates from unit to unit in an epidemic manner.