Graduate Course to Develop Mobile Robot to Map Hazardous Abandoned Mines
Graduate students taking "Mobile Robot Development" this fall will draw on unique mapping, planning and mobility technologies to prototype a robot capable of exploring and mapping abandoned mines.
Mines are vulnerable to flooding and accidents because complete, accurate maps for many of them do not exist. That fact struck home in Pennsylvania last month, when the Quecreek Mine flooded and nine miners were trapped.
Flooding, roof fall, rotted timbers and environmental factors make old mines unsafe for people, but they offer an excellent opportunity to use robots, said William L. "Red" Whittaker, the Fredkin Research Professor in the Robotics Institute and a veteran developer of mobile robots for hazardous environments.
"Mine subsidence is a big issue in Pennsylvania and nationally. We believe this kind of prototype robot has enormous potential in helping many organizations understand what's beneath the ground we stand on. We've been successfully creating technologies for exploring hazardous environments for years now. Accidents like Quecreek are compelling motivation for a safe, robotic solution to mapping mines," said Whittaker.
Reclamation and conservation groups in Pennsylvania say correcting the state's problems could cost at least $15 billion.
"The robot could help us find out about problems and develop an approach to its solution. This is a national priority," Whittaker said.
Whittaker is teaching "Mobile Robot Development" with Robotics Institute Systems Scientist Scott Thayer. They have recruited students from various disciplines, including mechanical, electrical and civil engineering, robotics, computer science and human-computer interaction. The students will work as a team to develop a robot capable of exploring and evaluating the boundaries and conditions similar to those that may have contributed to the recent Quecreek accident.
To fulfill its mission, the robot will need perception technology to build maps from sensor data. If it is to operate without a tether, then autonomy is necessary for it to make decisions about where to go, how to get there, and more important, how to return. Locomotion technology will be important because of the unevenness of floors in abandoned mines. The robot also must contain computer interfaces enabling people to view the results of its explorations and use the maps it develops.
The robot will incorporate a key technology developed at Carnegie Mellon called Simultaneous Localization and Mapping (SLAM). It enables robots to create maps in real time as they explore an area for the first time. The technology can be applied both indoors and out.
Carnegie Mellon researchers pioneered robotic mapping of underground mines in the 1980s. Whittaker described the early robots as "cumbersome power hogs, limited in their computing capability and lacking autonomy. But despite the primitive technology of the time, the early maps they created exhibited amazing fidelity.
"Now advances in computing, laser sensors, batteries and gyroscopes make it possible to develop robots capable of mapping abandoned mines on a routine basis and participating in accident response operations. We have the ability to integrate robots small enough to go down well pipes and durable enough to operate as tools," Whittaker said.
The robotic technology required to solve problems in mining could also impact other industries and other areas of scientific inquiry. It could serve military intelligence and commercial purposes in caves, sewer pipes, petroleum tanks and disaster rubble. The technology could even be used for exploring lava tubes on other planets.
Other areas of study at Carnegie Mellon, such as data mining and entrepreneurship, will benefit from the course in robotics. Scientists in the area of probabilistic robotics, which involves the science of how to integrate data, hope to use the data generated by the robot, while an entrepreneurship course in the business school will use the project to generate plans to develop a commercial robot to serve the mining industry.
Whittaker has been teaching Carnegie Mellon's graduate course in mobile robot development since the mid 1980s. The class has served as a platform for developing robots that have explored the interior of volcanoes and searched for and discovered meteorites in Antarctica. Whittaker himself developed three robots that assisted in the exploration and cleanup of the nuclear disaster at Three Mile Island.
For additional information on the Mobile Robot Development course, see www-2.cs.cmu.edu/afs/cs.cmu.edu/academic/class/16861-f02/www/ Information on SLAM can be viewed at: www-2.cs.cmu.edu/~thrun/3D/, www-2.cs.cmu.edu/~thrun/3D/lit11.html and www-2.cs.cmu.edu/~3dvision/MineMapping/index.html.
Chriss Swaney and Anne Watzman
This Issue's Headlines || Carnegie Mellon News Home || Carnegie Mellon Home