A team from US-based Georgia Institute of Technology has won the prestigious FetchIt! Mobile Manipulation Challenge, at ICRA 2019 in Montreal.

The team earned a prize package that included a Fetch Mobile Manipulation Research Robot – valued at US$100,000 – along with other prizes from co-sponsors for successfully assembling three kits in 39 minutes.

The three-day competition held at the International Conference on Robotics and Automation last week was designed to advance the state of technology for applying mobile manipulators.

As part of the competition, robotic arms are fitted onto autonomous mobile robots, for use in manufacturing and related applications.

Some industry watchers say that mobile manipulation is one of the “holy grail” in robotics, in which a single robot can grab and object from a shelf or bin, and then deliver it on a mobile platform.

Range of manufacturing activities

Four research teams competed in the event.

Each team was asked to use a Fetch Robotics Mobile Manipulator robot to navigate to stations in a work cell, pick up items with the arm, insert them into a machining tool, place the machined items into kits, and then transport the finished kit to an inspection station and drop-off location.

Fetch Robotics, which was the primary sponsor of the challenge, said this was “the first competition that encompasses the full range of activities that are commonly found in manufacturing environments.”

Teams included:

• Team Columbia: Columbia University, led by Professor Peter K. Allen, PhD, and Neil Chen
• Team DeRAILers: The Georgia Institute of Technology, led by Associate Professor Sonia Chernova, PhD, and David Kent
• Team RoboHawks: The University of Massachusetts Lowell, led by Professor Holly Yanco, PhD, Assistant Professor Reza Ahmadzadeh, PhD, and Zhao Han
• Team Fido: Independent competitors, Thomas Butterworth and Ben Jarvhi

“When setting out to create this challenge, we knew we wanted to keep it grounded to a real-word scenario,” said Russell Toris, Director of Robotics at Fetch Robotics.

“Interacting with machinery that is designed to be used by humans is no easy task,” he said.

“Piece-picking, kitting, and countless other tasks are going to require state-of-the-art perception, motion planning, navigation, and safety all seamlessly working together. The teams’ performance this week indicate that they represent some of the world’s leading experts in these skills.”

Georgia Tech’s Sonia Chernova said the prize has would allow the team to validate its research code in a complex domain.

“We can’t wait to continue our work with our newest Fetch robot.”