Title :
Towards Probabilistic Operator-Multiple Robot Decision Models
Author :
Campbell, Mark ; Bourgault, Frédéric ; Galster, Scott ; Schneider, David
Author_Institution :
Sibley Sch. of Mech. & Aerosp. Eng., Cornell Univ., Ithaca, NY
Abstract :
Coupled operator-multiple vehicle systems are modelled in a unified framework using probabilistic graphs to yield a methodology for analyzing semi-autonomous systems. The framework uses conditional probabilistic dependencies between all elements, leading to a Bayesian network (BN) with probabilistic evaluation capability. Vehicle attitude/navigation states and target/classification states can be evaluated using nonlinear estimators such as the EKF, multiple model filter, information filter, or other approaches. Discrete operator decisions are being modeled as Bayesian network blocks, with conditional dependencies on the vehicle and tracking estimators. Initial decision models use combinations of softmax and discrete probability distributions.
Keywords :
belief networks; control engineering computing; graph theory; mobile robots; multi-robot systems; navigation; statistical distributions; Bayesian network; conditional probabilistic dependencies; discrete probability distributions; nonlinear estimators; operator-multiple vehicle systems; probabilistic evaluation capability; probabilistic graphs; probabilistic operator-multiple robot decision models; vehicle attitude; vehicle navigation; Bayesian methods; Coupled mode analysis; Information filtering; Information filters; Navigation; Probability distribution; Robots; State estimation; Target tracking; Vehicles;
Conference_Titel :
Robotics and Automation, 2007 IEEE International Conference on
Conference_Location :
Roma
Print_ISBN :
1-4244-0601-3
Electronic_ISBN :
1050-4729
DOI :
10.1109/ROBOT.2007.364153