CREST-GEIMS

Subproject 1. Geospatial Informatics for Coastal Resiliency

Subproject 1 explores and develops new approaches that integrate remote sensing and autonomous systems with geospatial computing and artificial intelligence (AI) techniques for improving monitoring and vulnerability assessment of built and natural infrastructure within the coastal zone. The focus is on improving resiliency to extreme coastal hazards that threaten communities both regionally along the Texas and Northern Gulf of Mexico coastline and nationwide, and both episodic (e.g., hurricanes) and long-term (e.g., relative sea-level rise) events. Research challenges include developing algorithms for efficient exploitation of information captured in time series of “hyperspatial” resolution imagery and dense 3D point cloud data sets using AI; understanding measurement uncertainty and its impact on change detection analyses performed with geographic information systems (GIS); integrating 3D scanning and imaging techniques, including light detection and ranging (lidar) and structure-from-motion (SfM) photogrammetry, with unoccupied aerial systems (UAS) for coastal zone monitoring and rapid response mapping following storm events; effective application of air-land-sea autonomous systems for surveillance at the land-water interface. 

Subproject 1 also explores the development of strategies for team coordination of air-land-sea systems for geospatial data acquisition. Efficient surveying methods for geospatial data acquisition benefit from using data collected by a variety of autonomous systems, e.g., unmanned aerial vehicles (UAVs), unmanned ground vehicles (UGVs), unmanned underwater vehicles (UUVs), unmanned surface vehicles (USVs), etc. They can explore different scenarios utilizing a wide variety of sensors, whether they are in the air, on the ground, or in the water. These systems can perform different tasks and get close to specific locations, therefore increasing the quality of the sensors’ readings. A team formed by multiple systems can improve the efficiency of collecting high-quality information in a short period of time. However, if the team is formed by heterogeneous systems (i.e., systems with different characteristics), then the complexity of the system increases and requires an efficient means to coordinate the vehicles. When working with a multi-robot system, it is important to address multiple aspects within the sensing problem, such as the distributed autonomous area coverage and the multi-robot task allocation. This will enable different robots to determine a suitable waypoint sequence for collecting critical measurements while reducing power consumption and time. Research challenges include the development of novel approaches that will improve control and coordination techniques among teams of heterogeneous autonomous systems, and the development of offline and real-time path-planning strategies that can address dynamic and environmental changes. To validate the performance of the strategies, in addition to getting simulation results, they will be implemented and tested within a variety of unmanned autonomous systems.

To request more information on this Sub-Project, click here.