Efficient object motion prediction using Fuzzy Petri Net based modelling in a robot navigational environment

Predicting the next instance position of a moving object in a dynamic navigational environment is a critical issue as it involves uncertainty. This paper proposes a fuzzy rule-based motion prediction algorithm for predicting the next instance position of a moving object. The algorithm is robust in handling the uncertain data of real-life situation. The fuzzy rule base modeling is done using Fuzzy Petri Net (FPN) formalism. The prediction algorithm is tested for real-life bench-marked data sets and compared with existing motion prediction techniques. The performance of the algorithm is comparable to the existing prediction methods.