Students and faculty at the Maryland Robotics Center are developing a new generation of machines that are friendlier to small manufacturers. The five-year-old research facility is housed in the Institute for Systems Research at the A. James Clark School of Engineering at the University of Maryland.
“Our mission is to advance robotic systems, underlying component technologies, and applications of robotics through research and educational programs that are interdisciplinary in nature and based on a systems approach,” says Satyandra Gupta, a mechanical engineering professor who also serves as director of the Maryland Robotics Center.
“We provide an opportunity for people looking at different aspects of robotics to collaborate and learn from each other,” adds Gupta. “Research activities include the development of component technologies, such as actuators, sensors and structures; novel robotic platforms; and intelligence and autonomy for robotic systems.”
Approximately 33 faculty members and 70 students are currently involved in robotics research at the center, which consists of 20 different labs that each comprise about 1,000 square feet. In addition to experimental robots that are built in-house, the labs use a wide variety of off-the-shelf machines from Kuka Robotics Corp. and RethinkRobotics Inc.
Two years ago, Gupta and his colleagues unveiled a biologically inspired robot called the Robo Raven. It features solar panel wings and independent wing controls that allow the mechanical bird to do backflips, dives and loops. The Maryland engineers are also developing robotic boats that can work autonomously in a variety of applications, such as search-and-rescue missions.
The Maryland Robotics Center is currently focusing on developing collaborative machines that can be used in low-volume, high-mix manufacturing environments. The three-year-long project is being funded by the National Institute of Standards and Technology and the National Science Foundation.
Gupta and his colleagues recently unveiled the RoboSAM (ROBOtic Smart Assistant for Manufacturing). The robot is smart enough to know when something is wrong, to pause and to call a human for help.
“Like a driver who refuses to ask for directions when lost, today’s industrial robots don’t know when they’re in trouble and should stop and get help—which limits their usefulness in manufacturing,” claims Gupta. “Most robots have a limited ability to assess whether they can successfully complete tasks.
“The robot doesn’t know it should stop what it’s doing if, for example, the parts it needs are not in the exact position it expects,” explains Gupta. “A chaotic mess can result—one which humans must then fix. [Traditionally], that’s why robots are not used in factories where high task reliability cannot be ensured.”
Gupta believes a better method would be to give robots the ability to assess whether they can successfully complete a task, and if they sense they cannot, to stop and ask a human for help. “To use robots in small production operations or nonrepetitive assembly tasks, manufacturers need machines that are able to estimate the probability of task completion before beginning the task,” he points out.
RoboSAM is based on the Baxter robot platform, with software developed in-house at the University of Maryland. Gupta’s team has successfully demonstrated the robot in a kitting and parts-picking application.
The robot needs to find a desired object in a bin of similar objects, pick it up, and deliver it to another area in a specific placement.
If the robot is not sure whether it can complete the task—for example, if the part is buried within the bin, it takes pictures of the situation and calls a remotely located human for help. The human then tells the robot what it should do to complete the task, such as stir the contents of the bin, then try again to locate the needed part.
