Long Term Operation in Subsumption

Long Term Operation in Subsumption

Subsumption agents were designed to operate autonomously in environments that are both complex and dynamic and also possibly hostile. Given these considerations, and the fact that there is no symbolic representation of state in subsumption nor any significant addition of knowledge over the time that the agent operates (i.e., traditional learning), the subsumption agents should be able to operate very well over extended periods of time, practically limited only by their power supplies and/or their ability to renew this power.


Return to the Issues Index for this Architecture.

Return to the top of this architecture.

Go to a Discussion of this issue for multiple architectures.


Current Location: Subsumption - Issues - Long Term Operation

Go to NEXT page.