An Behavior-based Robotics
Markov Decision Processes in Artificial Intelligence
Markov Decision Processes in Artificial Intelligence
| Hi-index | 0.00 |
In this paper, we propose a modeling framework of rational human actions in human-environment systems by evaluating probable human actions in physical and psychological dimensions. In the affordance theoretic perspective, an environment offers certain physical and psychological limitations to filter a finite number of feasible human actions that lead to desired system states in a spatio-temporal dimension. By integrating physical and psychological constraints in human decision making processes, a value-based Bayesian-affordance model is proposed using Markov Decision Model. To this ends, two different types of filters, 'F1' and 'F2' are proposed, where 'F1' is a preference-based numerical filter conceived at the planning level for psychological constraints and 'F2' an affordance-based numerical filter at the execution level in which agent's perception of physical action availability plays a big role. Finally, a simple example based on the proposed model is illustrated to verify the proposed framework and the analysis results are discussed.