Mission energy prediction for unmanned ground vehicles

A typical unmanned ground vehicle (UGV) mission can be composed of various tasks and several alternative paths. Small UGVs commonly rely on electric rechargeable batteries for their operations. Since each battery has limited energy storage capacity, it is essential to predict the expected mission energy requirement during the mission execution and update this prediction adaptively via real-time performance measurements, e.g., the total battery power required for the mission. We proposed and compared two methods in the paper. One is a linear regression model built upon the UGV longitudinal dynamics model alone. The other is a Bayesian regression model when prior knowledge, e.g., road average grade and operator driving style, is available . In this case, the proposed Bayesian prediction can effectively combine the prior knowledge with real-time performance measurements for adaptively updating the prediction of the mission energy requirement. Our comparative simulation studies show that the Bayesian model can yield more accurate predictions than the linear regression model, particularly during the initial execution stage of a mission.