Imagine you need a screwdriver to make a repair in your home. The job might require a screwdriver with a specialized end, such as a standard or Phillips screwdriver. Rather than own a number of different, single-type screwdrivers, it would be handy if you owned a convertible screwdriver that, when switched out with different ends, could turn different types of screws for different types of materials. It would be even more impressive if your screwdriver used AI (artificial intelligence) to also “see” the requirements of the job with sensors without your needing to inspect the project yourself.
Now, imagine if that screwdriver that uses AI sensors were a large, multipurpose robotic arm used on a jobsite to construct buildings.
Robotic arms use their “hands” to complete tasks. The hand portion of a robot is known as an “end effector” and they can be customized, depending on the task. Jiansong Zhang, assistant professor of construction management technology in the Purdue Polytechnic Institute, and the undergraduate researchers in the Automation and Intelligent Construction (AutoIC) Lab are adding computer vision sensing technology to robotic end effectors.
“By basing the sensing for our robotic arm around computer vision technology, rather than more limited-scope and expensive sensing systems, we have the capability to complete many sensing tasks with a single affordable sensor,” Zhang said. “This allows us to implement a more robust and versatile system at a lower cost.”
Zhang and his students worked with the Purdue Research Foundation’s Office of Technology Commercialization to patent the technology. It was developed with support from the National Science Foundation.
Read the full Purdue Research Foundation story by Chris Adam.
Additional information
- Emerging robotics technology may lead to better buildings in less time (Purdue Research Foundation)