Two state-of-the-art robots are helping computer science and engineering researchers at the University of Nevada, Reno better understand how humans and autonomous systems could work together, thanks to a $312,000 grant from the Department of Defense to purchase the advanced research robots.

The robots, a PR2 and a Baxter Research Robot, will enable existing research programs in intent recognition, human-robot interaction and computer vision to address new questions that would not be possible without the next generation of robots. Together, these robots offer significantly enhanced data sensors, better mobility and improved ability to manipulate objects in the environment.

"They are capable of so many things," said Principle Investigator Monica Nicolescu, associate professor of computer science and engineering. "This will open up lots of new directions for research that will be crucial to the development of more general, robust intelligent systems and in particular for robotic systems used in security and service applications."

Mircea Nicolescu, associate professor of computer science and engineering and David Feil-Seifer, assistant professor of computer science and engineering, are co-PIs on the project.

The goal of the research is to give robots the ability to engage in and sustain long-term, natural interactions with humans and other robots in scenarios that might be found in a workplace or manufacturing setting. The advanced robots will also support an NSF proposal the team is developing to study human-robot collaboration and robot-robot collaboration.

The PR2 is a $282,000 mobile robot with a maximum height of nearly 5'5". The PR2 also comes equipped with a wide range of sensors, including five cameras in various locations, multiple accelerometers and pressure sensor arrays. The advanced robot is in use in fewer than 40 university and research labs worldwide.

The Baxter Research Robot was just released to the public in 2013. Baxter is a six-foot-tall robot with 360 degree sonar; torque, position and velocity sensing; and integrated head and wrist cameras.

The sensors can be used to further research into how a robot perceives and understands its environment. They are complemented by significant computing power on board the robot that enables real-time processing of that sensory data.

"The new sensors will address some of the limitations we have previously encountered, as well as open many new directions of research," said Mircea Nicolescu. "The impressive computation power of the new robots is very important, especially for computer vision algorithms, which tend to be computationally expensive. That was a recurring problem in the past, where limitations in processing speed were impacting the naturalness of the interaction,"

That improved computer power will also support Feil-Seifer's work on improving human-robot interaction. Feil-Seifer is particularly interested in the type of feedback a robot gives a human and how that feedback changes over the course of an interaction. Generating socially appropriate behavior requires both sophisticated models for human interaction and the computing power for a robot to process those models and respond in a timely manner.

"This research will extend the capabilities of robots to engage in time-extended, flexible interactions and give feedback in a more intelligent manner," he said. "We expect that this will increase human-robot coordination in manufacturing tasks that require repetitive and long-term interaction."

The grant is part of the Defense University Research Instrumentation Program, or DURIP, which allows universities to purchase state-of-the art equipment that enhances research related to defense. The award is highly competitive, and in 2014 more than 735 proposals were received and 149 awards were granted. The University of Nevada, Reno's award was given by the Office of Naval Research, which is currently funding research in the University's Robotics Research Lab and Computer Vision Lab.

The award was one of two DURIP grants given to the Computer Science and Engineering department in 2014; Murat Yuksel also received an award to fund his research into mobile networking.