Experiment design and execution is a central activity in the natural sciences. The SeqERsystem provides a general architecture for the integration of automated planning techniques with a variety of domainknowledgein order to plan scientific experiments. These planning techniques include rule-based methodsand, especially, the use of derivational analogy. Derivational analogy allows planning experience, captured as cases, to be reused. Analogy also allows the system to function in the absence of strong domain knowledge. Cases are efficiently and flexibly retrieved from a large casebase using massively parallel methods. TheSeqERsystem is initially configured to plan protein sequencing experiments. Planning is interleaved with experiment execution, simulated using the SequenceIt program. SeqERinteracts with a humanuser who analyzes the data generated by laboratory procedures and supplies SeqERwith newhypotheses. SeqEtt is a vehicle in which to test theories about howscientists reason abou...
Brian P. Kettler, Lindley Darden