Mobile Robot SLAM Methods Improved for Adapting to Search and Rescue Environments

Robotic simultaneous localization and mapping (SLAM) confronts extreme challenge in collapsed, cluttered, GPS-signal unreliable environments of search and rescue (SAR). Our improved SLAM methods aim to mobile robot performing SAR requirements which comprise the significant objects identification, loop closure perceiving, exploration area coverage, and the other performances. We developed efficient SLAM methods adapting to SAR cluttered environments, which are listed as follows: the 3-D mapping reconstruction extracts the features of significant object; the hierarchical perception-driven approach dramatically improves the loops closure performance; the local wireless Ad hoc network deployment addressed the signal absence and unreliable of harsh environment; robot arm perceived and identified the objects of interest. The fusion of these efficient strategies forms the SAR SLAM methods that adapt to the cluttered and harsh condition. In this paper, we evaluate the improved SAR SLAM qualitatively on available data measurements. The simulations and experimental results demonstrate that the improved SLAM performances methods are obviously adapted to SAR environment.