An Information-Theoretic Approach to Persistent Environment Monitoring Through Low Rank Model Based Planning and Prediction
This work addresses the challenge of persistent environment monitoring for robotics and ecology applications, offering an incremental improvement over existing sampling methods.
The paper tackles the problem of efficiently monitoring large environmental regions with robots by selecting a limited number of observation points to predict unobserved states, using a low rank model combined with an information-maximizing planner. It outperforms baselines in Fisher information gain and achieves comparable reconstruction error in simulations on real-world datasets with up to two million sampling locations.
Robots can be used to collect environmental data in regions that are difficult for humans to traverse. However, limitations remain in the size of region that a robot can directly observe per unit time. We introduce a method for selecting a limited number of observation points in a large region, from which we can predict the state of unobserved points in the region. We combine a low rank model of a target attribute with an information-maximizing path planner to predict the state of the attribute throughout a region. Our approach is agnostic to the choice of target attribute and robot monitoring platform. We evaluate our method in simulation on two real-world environment datasets, each containing observations from one to two million possible sampling locations. We compare against a random sampler and four variations of a baseline sampler from the ecology literature. Our method outperforms the baselines in terms of average Fisher information gain per samples taken and performs comparably for average reconstruction error in most trials.