Probability-Based Robot Search Paths

The aim of this work is to show that robots can be improved using knowledge present or gained in previous executions of the task. Here, this knowledge is used to create search paths tailored to the problem at hand. We describe two approaches to create such paths automatically which enable robots to find an unknown position faster than standard paths. The solution presented here is not limited to the robotic domain, but can also be used for other purposes such as searching for injured persons after accidents. Our approach is evaluated through simulations and we show that these paths perform adequately well or even better than standard paths.