KNOBSAR: A Knowledge Based System Prototype for Robot Assisted Urban Search and Rescue

Abstract

Few disasters inspire more compassion for victims and families than those involving structural collapse situations. Media audiences also sympathize, however, with heroic rescue personnel who are faced with a tremendously complex, hazardous, and often frustrating task environment. Rescue activities in the aftermath of recent earthquakes and bombings indicate a tremendous need for greater access to denied areas within any crisis site involving collapsed structures. Recent developments in the remote inspection industry show great potential for employment of small robotic microrover systems in expanded roles for Urban Search and Rescue (USAR). Similar progress in computer science research indicates an increasing role for simulation oriented modeling and intelligent decision support tools in USAR resource management procedures. This paper discusses key issues in the application of robotic systems to Urban Search and Rescue (USAR) activities and discusses ongoing development of a knowledge based system for efficient management of automated search assets.

Directed stigmergy-based control for multi-robot systems

“…The effectiveness of stigmergy-based foraging is explored in a 3x2 full factorial experiment. The independent variables are the number of robots (2,4,6) and the presence or absence of stigmergy interactions between robots. The number of target clusters in the world is fixed at five, and distributed throughout the environment.…”

“…Mobile robots have shown the ability to traverse spaces that are too small or too dangerous for humans or rescue dogs [4]. There are advantages to using multiple robots in urban search and rescue, including more quickly searching the damaged area, using robots with different shapes in different environments, and coordinating the use of expensive thermal sensors [18].…”

Towards CSP-based mission dispatching in C2/C4I systems

“…For USAR, the identification of the search area is straightforward, but the resource demand for individual buildings is difficult to assess and has been addressed [21]. The resource allocation problem during USAR was tackled by [4] and recently, even more fundamentally in [6]. All decision support systems are limited on the one hand, by the availability of pre-incident knowledge such as resources and infrastructure and on the other hand, by the capability of the emergency team to transcribe and disseminate post-incident knowledge such as damages and progress during relief operations.…”

Rescue robots at the Collapse of the municipal archive of Cologne City: A field report

“…Furthermore some voids in the upper layers of the debris could not be reached because the ASC is missing the capability of getting over larger barriers. Regarding the application of the VGTV Xtreme, the debris did not contain voids being large enough for the VGTV Xtreme to fit into, as it was the case for other scenarios, like for instance the terrorist bombing attack in Oklahoma City [9], [10]. The combination of rain and brick dust resulted in an extreme slippery ground which made it difficult for man and machines to move around.…”