engleski

Bayesian approach to robot group control

The objective of this paper is to discus the probabilistic part of the model for robot group control applied in industrial applications. The proposed model is based on well-known concepts of Ubiquitous Computing and enables contextual perception of the environment. This model uses ontology to provide the knowledge about the domain of application and Bayesian Network to control the robot group behaviors. In the learning phase, a single robot has to observe other robots’ Behavioral Patterns to predict further steps and strategies. Bayesian Network based mechanisms can enable work without human intervention and help the system reacts in uncertain situations and scenarios.

assembly, bayesian networks, context, control, robotics

nije evidentirano