Collaborative agents - 3
solving problems that are too large for centralised single agent (resource limits, risk)
allow for interconnection/interoperability of multiple existing legacy systems (ES, DSS)
To provide solutions to inherently distributed problems, e.g. distributed sensor networks or air-traffic control
To provide solutions which draw from distributed information sources
To provide solutions where the expertise is distributed, e.g. in health care provisioning
To enhance modularity (which reduces complexity), speed (due to parallelism), reliability (due to redundancy), flexibility (i.e. new tasks are composed more easily from the more modular organisation) and reusability at the knowledge level (hence shareability of resources)
To research into other issues, e.g. understanding interactions among human societies