As part of DARPA's final challenge, CMU preps its fleet of autonomous robotic vehicles for a search and rescue mission

A fleet of robots from Carnegie Mellon University is headed to Kentucky for the ultimate challenge of its capability to independently maneuver an unexpected, underground course after practicing in an abandoned limestone mine and an unfinished sanatorium outside of Pittsburgh.

The task navigates a tunnel near Louisville, Kentucky, and gathers as many objects as possible in one hour. The goal is to develop self-driving robots to complement military and first responders’ search and rescue missions.

The catch: With just one operator and a fleet of up to a dozen robots, the devices must be capable of moving and making choices individually.

Sebastian Scherer, a co-lead for CMU’s team and an associate research professor at the Robotics Institute, stated, “At the core of this issue, it’s really a problem of investigation.” “You’re approaching an unknown environment, so there is a lot of uncertainty, and the robot has to be able to decide what to do when faced with uncertainty.”

According to Martial Hebert, dean of the School of Machine Learning, DARPA has hosted roughly comparable races in the past, and CMU has made a name for itself in a variety of competitions, running the gamut from those focused o
n self-driving technology to those programming computers that aids in language translation and manuscript understanding

You might be interested in

A Pittsburgh team won the DARPA Urban Competition in 2007, a competition to develop a self-driving car that could negotiate traffic, merge, and park. As a result, advancements in self-driving vehicle research were made, prompting several team members to establish a business, such as Aurora and Argo AI.