Analyzing the balance of Exploration and Exploitation in Adaptive Information Sampling of Unknown Spatial Fields

Abstract

Adaptive sampling and informative path planning approaches enable efficient selection of the mobile robot’s waypoints to obtain accurate sensing and mapping of a physical process, such as the radiation or field intensity. However, it is not clear to what extent the parameters of the adaptive sampling function play a role in balancing the exploration of new information and exploitation of existing information combined with the robot’s energy consumption perspective. This paper provides this necessary perspective and uniquely analyzes the impact of the adaptive sampling algorithm’s information function used in exploration and exploitation to achieve a trade-off between balancing the mapping, localization, and energy efficiency objectives. In addition, we propose a new time-varying parameter to balance the sampling objectives dynamically during a mission. We use Gaussian process regression (GPR) to predict and estimate confidence bounds, thereby determining each point’s informativeness. Through extensive experimental data, we provide a deeper and holistic perspective on the effect of information function parameters on the prediction map’s accuracy (RMSE), confidence bound (variance), energy consumption (distance), and time spent (sample count). The results provide meaningful insights into choosing appropriate information function parameters based on sampling objectives (e.g., source localization or mapping).

Paper Preprint

Appendix Materials