University of Maryland’s (UMD) researchers have developed RoboSAM (ROBOtic Smart Assistant for Manufacturing), an industrial robot smart enough to know when something is wrong, to pause and to call a human for help.
In today’s world, industrial robots are used mostly for high-volume, reliably repetitive tasks with unchanging, tightly proscribed parameters, such as automobile assembly lines. These robots are custom-built and programmed specifically for the tasks at hand.
Though, they excel in such environment, the robots lack the ability to access whether they can successfully complete the given task. It can’t judge when to stop, for example, when the parts it needs are not in the exact position as it expects could lead to a chaotic mess. These limitations have limited the industrial robots usage in factories where high task reliability cannot be ensured.
However, S. K. Gupta, a professor in the A. James Clark School of Engineering, believes by giving 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, a better economic model could be designed.
He along with his team designed new ‘RoboSAM,’ based on the Baxter industrial robot platform, which can estimate the probability of completing the task before beginning it, and can ask a ‘human on call’ for help if required. These features might pay way towards creation of smarter, more versatile industrial robots and more interesting duties for the humans who work with them.
The team has successfully demonstrated RoboSAM in a ‘bin picking’ situation, where the robot was needed 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 unsure of it completing the task, it takes pictures of its situation and calls a remotely located human (the ‘human on call’) for help. Later, taking suggestion from his operator, the robot again tries to locate the needed part.
Gupta believes that his work could pave way in providing a better economic model for deploying robots, especially for small and medium sized manufacturing companies.
Excerpts, image and video courtesy of University of Maryland