Urban search and rescue (USAR) focuses on locating and extracting people trapped in collapsed or damaged structures. Rescuers are under extreme time pressure; after 48 hours, victim mortality drastically increases owing to exposure and lack of food, water, and medical treatment. Rescuing can be as dangerous to the workers and the victims as the initial event. Moving through the structure or widening entry points for humans and equipment can cause further collapse, injuring or killing the trapped survivors or rescuers. Gas leaks and explosions are also possible. Rescue dogs can help reduce human risk and can enter smaller voids in the rubble than a human can, but they cannot replace a video camera or structural assessment equipment. Lightweight mobile robots could benefit USAR while reducing the risk to humans and dogs. For example, they could: conduct tedious searches for survivors with a level of rigor that is normally fatiguing to humans; insert specialized sensors into the rubble and position them; collect visual and seismic data to assess structural damage; deposit radio transmitters or small amounts of food and medication with the survivors; guide the insertion of jaws-of-life tools, and identify the location of limbs to prevent workers from damaging a victim's arm or leg during extraction. Toward that end, the author has been developing USAR mobile robot hardware and software. Two promising technologies have emerged that present interesting challenges for artificial intelligence: shape-shifting, marsupial robots.
[1]
Robin R. Murphy,et al.
Strategies for Searching an Area with Semi-Autonomous Mobile Robots
,
1996
.
[2]
Robin R. Murphy,et al.
Marsupial-like mobile robot societies
,
1999,
AGENTS '99.
[3]
Robin R. Murphy,et al.
Lessons learned in integrating sensing into autonomous mobile robot architectures
,
1997,
J. Exp. Theor. Artif. Intell..
[4]
Damian Diaz,et al.
1997 AAAI Find Life on Mars Competition
,
1998
.
[5]
Robin R. Murphy,et al.
Agent-based expert assistance for visual problem solving
,
1997,
AGENTS '97.
[6]
Lynne E. Parker,et al.
Case study for life-long learning and adaptation in coopertive robot teams
,
1999,
Optics East.