Statistical Probabilities for Planning

This paper describes a formalism, Statistical Event Logic or SEL, that adds statistical reasoning to Allen's planning language [ Allen et al., 1991 ] . Interval temporal logic supports reasoning about time and events; probability inferred from the planner's experience supports reasoning about incomplete information. Statistical Event Logic can represent knowledge that allows a planner to reason both about choices based on incomplete knowledge and about the future likely to result from these choices. We would like to thank George Ferguson, Ray Rimey and David Traum for their many insightful commments on this work. This material is based on work supported by ONR/DARPA under grant number N0014-82-K-0193 and under AF{Rome Air Development Center contract number F30602-92-C-0010.