Posted in | News | Humanoids | Mechatronics

Columbia Engineering Faculty Wins YIP Grant for Research on Human-Robot Collaborative Teams

Matei Ciocarlie, assistant professor of mechanical engineering at Columbia Engineering, has been awarded a three-year $637,000 Young Investigator Program (YIP) grant from the Office of Naval Research (ONR) for his work on human-in-the-loop systems in which humans and robotic manipulators work together, side by side, on the same task. He is one of 36 college and university faculty to win a 2015 grant from YIP, one of the oldest and most selective scientific research advancement programs in the country.

“Participating in the YIP program is both a great honor and a critical boost for our work,” Ciocarlie says. “This grant will help us establish a strong line of research in collaborative manipulation for human-and-robot teams, and ground our work in applications where the technology we develop can have a concrete impact.”

Ciocarlie’s work is focused on developing versatile manipulation and mobility in robotics, and particularly for tight, cluttered, or occluded settings, encountered in many application domains, such as logistics, manufacturing, and disaster response, or everyday life. He is particularly interested in robotic hands, aiming to invent new designs that combine mechanical and computational intelligence, and gather sensor data about the world (through tactile or range sensing) as well as themselves (through proprioception, the body’s ability to sense stimuli that indicate position, motion, and equilibrium). His group aims to create novel mechanisms that are simple in design yet versatile and effective.

For his YIP project, “Collaborative Dexterous Manipulation: Mechanisms and Interfaces,” Ciocarlie plans to focus on new human-in-the-loop paradigms for robotics, to help people who are non-roboticists operate co-robots in the field. He notes that, despite renewed focus over the last decade and numerous advances, robotic manipulation is not yet versatile enough for general, unscripted tasks in unstructured environments. Human-robot collaborative teams can now be used in complex scenarios more effectively than autonomous systems because the human's cognitive abilities can manage corner conditions and decisions that are still difficult for autonomous systems. But there are a number of roadblocks in developing side-by-side, or “eyes-on” collaboration and control mechanisms for manipulation. The robot must be able to translate high-level directives into concrete action items, and the person must be able to control the robot's arms and hands through simple, unobtrusive interfaces.

“For this project, we’ll be trying to do manipulation tasks ranging from routine maintenance to disaster response,” Ciocarlie says. “We want to build artificial hands and control interfaces that allow a person to manipulate the environment through a robot, while leaving his or her own hands free to engage in the task as well.”

The Young Investigator Program began in 1985 when ONR selected 10 winners. Since then, the program has grown steadily to include a total of 656 recipients, representing institutions of higher education from across the nation. This year’s candidates were selected from 383 research proposals based on merit and potential breakthrough advances for the Navy and Marine Corps.

“These recipients demonstrate the type of visionary, multidisciplinary thought that helps the U.S. Navy anticipate and adapt to a dynamic battlespace,” said Larry Schuette, ONR’s director of research. “The breadth of their research and combined value of awards underscore the significance the Navy places on ingenuity, wherever it’s harbored, and support the framework for a Naval Innovation Network built on people, ideas, and information.”

Tell Us What You Think

Do you have a review, update or anything you would like to add to this news story?

Leave your feedback
Your comment type
Submit

While we only use edited and approved content for Azthena answers, it may on occasions provide incorrect responses. Please confirm any data provided with the related suppliers or authors. We do not provide medical advice, if you search for medical information you must always consult a medical professional before acting on any information provided.

Your questions, but not your email details will be shared with OpenAI and retained for 30 days in accordance with their privacy principles.

Please do not ask questions that use sensitive or confidential information.

Read the full Terms & Conditions.