A Theoretical Cooperative Work-Flow Net-Based Framework for Odometric and Probabilistic SLAM

Abstract

In robotic mapping and localization, simultaneous localization and mapping (SLAM) is defined as the computational problem of constructing or updating a map while simultaneously keeping track of the agent's location. In this paper, We present a formal framework for Work-flow net using SLAM and Odometric-based probabilistic approach. We also propose a new extension for work-flow nets, which themselves are an extension of Petri-Nets, to be learned by the robot to model the environment. The learned Workflow net is then used to facilitate navigation through this environment. We propose a theory of soundness for the extended work-flow net.