Search is an essential technology for rescue and other mobile robot applications. Many robotic search and rescue systems rely on teleoperation. How to cover the search space efficiently is one of the key problems in search tasks. Search is also central to humans’ daily activities. Analyzing human search behavior through teleoperation could help improve understanding of human search strategies as well as autonomous search algorithms. This research proposes a novel framework to model and analyze humans’ search behavior. The framework is based on structure learning and K-means clustering. The analysis of the experimental data demonstrates that (1) humans are able to solve the complex search task by breaking it up into smaller tasks; and (2) humans consider both coverage and motion cost while searching. The results are used to design near optimal subgoals to guide humans in searching. Experiments showed that the humans’ search performance is improved with the subgoals assistance.