Heterogeneous robot teams for modeling and prediction of multiscale environmental processes
This work addresses the challenge of monitoring complex environmental systems for applications like environmental science or robotics, but it appears incremental as it builds on existing robot sensing and data fusion methods.
The paper tackles the problem of modeling and predicting multiscale environmental processes by proposing a framework for heterogeneous robot teams to collect and fuse high- and low-fidelity measurements, resulting in a model that determines optimal sensing locations and predicts process evolution, as demonstrated with artificial plasma clouds and physical marine robots in water tank tests.
This paper presents a framework to enable a team of heterogeneous mobile robots to model and sense a multiscale system. We propose a coupled strategy, where robots of one type collect high-fidelity measurements at a slow time scale and robots of another type collect low-fidelity measurements at a fast time scale, for the purpose of fusing measurements together. The multiscale measurements are fused to create a model of a complex, nonlinear spatiotemporal process. The model helps determine optimal sensing locations and predict the evolution of the process. Key contributions are: i) consolidation of multiple types of data into one cohesive model, ii) fast determination of optimal sensing locations for mobile robots, and iii) adaptation of models online for various monitoring scenarios. We illustrate the proposed framework by modeling and predicting the evolution of an artificial plasma cloud. We test our approach using physical marine robots adaptively sampling a process in a water tank.