Using competitions to study human-robot interaction in urban search and rescue

interactions ◽  
2005 ◽  
Vol 12 (2) ◽  
pp. 39-41 ◽  
Author(s):  
Jill L. Drury ◽  
Holly A. Yanco ◽  
Jean Scholtz
2011 ◽  
Vol 5 (1) ◽  
pp. 3-9 ◽  
Author(s):  
Patricia L. McDermott ◽  
Jennifer M. Riley ◽  
Douglas J. Gillan ◽  
Haydee M. Cuevas

The past decade has seen a proliferation in the use of robots in a broad range of complex domains, such as urban search and rescue, military operations (including explosive ordnance disposal and intelligence, surveillance, and reconnaissance), scientific exploration in underwater and space expeditions, law enforcement (e.g., bomb squads), manufacturing, and health care (e.g., telerobotic surgery). Remotely controlled ground, aerial, sea-surface, and underwater robotic vehicles are serving as tools to safely extend the sensory and psychomotor capabilities of humans to remote environments while keeping humans safe. More importantly, with the ever-increasing technological sophistication in their design and capabilities, robots are becoming more than mere tools. They now can be seen as quasi–team members whose tasks and behaviors must be integrated with the task requirements and expectations of their human teammates. Yet without the necessary research base to inform design, sizeable investments will likely be made into developing robotic systems that are ineffective or, at best, not optimal. Toward this end, the goal of this two-part special issue is to present examples of the latest research on human-robot interaction that demonstrate how theories and empirical findings can be translated into practical, useful guidance for improving human-robot team performance across various domains.


Author(s):  
Robin R. Murphy ◽  
Jennifer L. Burke

The Center for Robot-Assisted Search and Rescue has collected data at three responses (World Trade Center, Hurricane Charley, and the La Conchita mudslide) and nine high fidelity field exercises. Our results can be distilled into four lessons. First, building situation awareness, not autonomous navigation, is the major bottleneck in robot autonomy. Most of the robotics literature assumes a single operator single robot (SOSR), while our work shows that two operators working together are nine times more likely to find a victim. Second, human-robot interaction should not be thought of how to control the robot but rather how a team of experts can exploit the robot as an active information source. The third lesson is that team members use shared visual information to build shared mental models and facilitate team coordination. This suggests that high bandwidth, reliable communications will be necessary for effective teamwork. Fourth, victims and rescuers in close proximity to the robots respond to the robot socially. We conclude with observations about the general challenges in human-robot interaction.


2006 ◽  
Author(s):  
Jean Scholtz ◽  
Jeff Young ◽  
Holly A. Yanco ◽  
Jill L. Drury

Sign in / Sign up

Export Citation Format

Share Document