MIT is leading an ambitious modern project to reinvent the way robots are designed and manufactured. Funded by a $10 million grant from the National Science Foundation (NSF), the goal of the project will be to develop computer technology that would enable an average person to design, customize and print a specialized robot in a matter of hours.
“This research introduces a completely new way of thinking about robot design and production and could have a huge impact on society,” says MIT professor Daniela Rus, project leader and principal investigator at the MIT Computer Science and Artificial Intelligence Laboratory (CSAIL). “We believe it has the potential to transform manufacturing and democratize access to robots.”
“Our goal is to develop technology that will enable anyone to produce their own customized robot. This is a real game changer,” says Professor Vijay Kumar, who leads the team from the University of Pennsylvania. “This could allow for the rapid design and production of customized goods and change the way we teach science and technology in high schools.”
The five-year project, titled “An Expedition in Computing for Compiling Printable Programmable Machines,” brings together a team of researchers from MIT, the University of Pennsylvania and Harvard University and is funded by the NSF Expeditions in Computing program.
Currently, producing, programming and designing a working robot takes years and is an extremely costly process, involving hardware and software design, machine learning and vision, and advanced programming techniques. The modern project would automate the process of manufacturing functional 3D devices and enable individuals to design and build functional robots from materials as readily available as a piece of paper.
“Our vision is to develop an end-to-end process; specifically, a compiler for building physical machines that starts with a high-level feature specification and provides a programmable machine to support that feature using simple printing processes,” says Rus.
The researchers hope to create a platform that would enable an individual to identify a home problem that requires support; then go to your local print shop to select a design from the robot design library; and then customize an easy-to-use robotic device that could solve the problem. Within 24 hours, the robot will be printed, assembled, fully programmed and ready for operation.
By changing the way machines can be manufactured, designed and built, the project could have far-reaching consequences across a variety of fields.
“The goal of this project is to dramatically reduce development time for a variety of useful robots, opening the door to potential applications in manufacturing, education, personalized health care, and even natural disasters,” says Rob Wood, an associate professor at Harvard University.
Currently, project researchers are focusing their research on several areas: developing an application programming interface for uncomplicated feature specification and design; writing algorithms to control the device assembly and its operation; creating an easy-to-use programming language environment; and designing modern, programmable materials that would allow automatic production of robots.
So far, the research team has created prototypes of two design, printing and programming machines, including an insect-like robot that could be used to explore the contaminated area and a gripper that could be used by people with restricted mobility.
“It’s really exciting to think about the impact this work could have on the general population – beyond a select few people working in robotics,” says Associate Professor Wojciech Matusik, also a principal investigator at CSAIL.
In addition to Rus, other CSAIL research collaborators include visiting scientist Martin Demaine, associate professor Wojciech Matusik, professor Martin Rinard, and assistant professor Sangbae Kim of MIT’s Department of Mechanical Engineering. In addition to Wood and Kumar, the team also includes Associate Professor Andre DeHon, Professor Sanjeev Khanna and Professor Insup Lee, all from UPenn.