Stochastic optimal-control of moving vehicles in a dynamic environment

This article develops a fairly general framework for derivation of control strategies applying to moving objects, such as mobile robots or robot arms, in a dynamically changing environment. The basic idea is to consider stochastic terms for any uncertain future environment change and to apply stochastic dynamic programming for control strategy development. The method permits consideration of a number of possible missions such as collision avoidance or collision hitting and/or moving forward or following a trajectory. A number of examples demonstrate that the control strategies developed are capable of making efficient, human intelligence-like decisions in quite complicated conflict situations.