Behaviour based searching of human using MDP

Motivation -- To develop a methodology for cognitive search of elderly person in home environment that will help in reaching the inhabitant to determine health situations. Research approach -- A behaviour based Markov decision process (MDP) has been developed to build up cognitive information of the human at home. A simulated environment was also created to simulate the presence of human and prove the validity of the approach implemented. Design -- The idea is to enable the robot to comprehend when it is required to find the human being on its own. To achieve this task, behaviour based approach has been adapted where behaviour represents the desire to find the human and the policy for finding human is determined using MDP. Research limitations -- A simulated environment has been developed for the generation of dataset and afterwards verification of the implemented methodology. This simulated environment also gives the liberty of observing the human being as many times as is required which in real scenario is difficult to accomplish. Originality/Value -- The research promotes the need of developing behaviour based cognitive approach for finding human being in the environment. Take away message -- Using learning methodology along with behaviour based architecture might help in developing better cognitive robots.