Abstract: Unmanned ground, aerial, and underwater vehicles equipped
with on-board wireless sensors are becoming crucial to both civilian and
military applications because of their ability to replace or assist humans in
carrying out dangerous yet vital missions.
As they are often required to operate in unstructured and uncertain
environments, these mobile sensor networks must be adaptive and reconfigurable,
and decide future actions intelligently based on the sensor measurements and
environmental information. In particular, our recent work on geometric path
planning has shown that the sensing performance of these sensors can be
significantly improved by planning their paths based on probabilistic sensor models,
and on the geometric characteristics of the workspace and of the sensors’ fields-of-view. This talk presents approaches based on
computational geometry and optimal control that can be used for planning the
paths of mobile sensors in order to optimize their ability to detect, classify,
and track multiple targets. A novel
framework is presented that combines Bayesian networks, information theory, and
computational geometry to automate and optimize the management of heterogeneous
sensing assets. This framework has been
demonstrated through applications such as landmine detection and
identification, and undersea surveillance, as well as computer games such as
Ms. Pacman and CLUE.
- This event has passed.