Adaptive Sampling: Algorithmic vs. Human Waypoint Selection
This addresses the problem of optimizing sample collection in robotics for environmental monitoring, showing that algorithmic methods can match or exceed human performance under ideal conditions, but it is incremental as it builds on existing adaptive sampling techniques.
The paper compared human and adaptive informative sampling algorithm performance in selecting waypoints for spatial field modeling, finding that the robot performed better than the average human and as well as the best human when model assumptions matched the field, but both performed no better than random when assumptions did not match.
Robots are used for collecting samples from natural environments to create models of, for example, temperature or algae fields in the ocean. Adaptive informative sampling is a proven technique for this kind of spatial field modeling. This paper compares the performance of humans versus adaptive informative sampling algorithms for selecting informative waypoints. The humans and simulated robot are given the same information for selecting waypoints, and both are evaluated on the accuracy of the resulting model. We developed a graphical user interface for selecting waypoints and visualizing samples. Eleven participants iteratively picked waypoints for twelve scenarios. Our simulated robot used Gaussian Process regression with two entropy-based optimization criteria to iteratively choose waypoints. Our results show that the robot can on average perform better than the average human, and approximately as good as the best human, when the model assumptions correspond to the actual field. However, when the model assumptions do not correspond as well to the characteristics of the field, both human and robot performance are no better than random sampling.