DECISION-THEORETIC COOPERATIVE SENSOR PLANNING

This paper describes a decision-theoretic approach to cooperative sens or planning between multiple autonomous vehicles executing a military mission. For this autonomous vehicle application, intelligent cooperat ive reasoning must be used to select optimal vehicle viewing locations and select optimal camera pan and tilt angles throughout the mission. Decisions are made in such a way as to maximize the Value of informat ion gained by the sensors while maintaining vehicle stealth. Because t he mission involves multiple vehicles, cooperation can be used to bala nce the work load and to increase information gain. This paper present s the theoretical foundations of our cooperative sensor planning resea rch and describes the application of these techniques to ARPA's Unmann ed Ground Vehicle program.