Study on path planning of UCAV based on dynamic Bayesian network

A new path planning algorithm for unmanned combat air vehicle (UCAV) is proposed for achieving optimal local path replanning under complicated air-battle environment Firstly, an improved Voronoi diagram based on different locations land grades of threats is constructed By utilizing our improved Voronoi diagram, the Dijkstra algorithm is implemented to find an initial threat-avoiding UCAV path. For matching dynamic battlefield situations and tracking the status of different threats, dynamic Bayesian network(DBN) model is exploited based on multi-sensor data fusion. The Viterbi algorithm is then used to estimate the grade of threat Local path replanning of UCAV is done while local improved Voronoi diagram is reconstructed for enhancing the chance of survival. Our experimental results demonstrate the improved accuracy and efficiency of local path replanning.