Site selection during unmanned aerial system forced landings using decision-making Bayesian networks

The knowledge of a human pilot in evaluating landing sites and making site selection decisions in a forced landing is captured and implemented by a multicriteria decision-making Bayesian Networks (BN). It was identified that public safety is of greater importance; therefore, sites without people or property are given the highest priority in the network decision making. An underused method of solving the BN using diagnostic reasoning is employed that significantly improves upon computational speed over the causal reasoning method. This enables real-time decision making. The added advantage offered by this method is that it can handle uncertainty in the applied factors without extra modification or effort. A case study is presented to show the principle of the networks and verify the effectiveness of the proposed decision-making network in an emergency. Further investigation of the decision-making behavior will be conducted by generating a large number of random scenarios.