UAV path planning based on Bayesian optimization algorithm

A Bayesian optimization algorithm (BOA) for UAV path planning problem is presented, which involves choosing path representation and designing appropriate metric to measure the quality of the constructed network. Unlike our previous work that used genetic algorithm to implement implicit learning, the learning in the proposed algorithm is explicit, i.e. eventually, we will be able to identify and mix building blocks directly. The Bayesian optimization algorithm is applied to implement such explicit learning by building a Bayesian network of the joint distribution of solutions. The conditional probability of each variable in the network is computed according to an initial set of promising solutions. Subsequently, each new instance for each variable is generated by using the corresponding conditional probabilities, until all variables have been generated, i.e. in our case, a new path genotype string has been obtained. Another set of path genotype strings will be generated in this way, some of which will replace previous strings based on fitness selection. If stopping conditions are not met, the conditional probabilities for all nodes in the Bayesian network are updated again using the current set of promising path genotype strings. Experimental results demonstrate that this approach can overcome drawbacks of other path planning algorithm. It is also suggested that the learning mechanism in the proposed approach might be suitable for other multivariate encoding problems.