An automation workspace with a Kuka robotic arm and a bin containing a pile of objects that need to be tightly packed into a shipping order box. The Rutgers robotic packing system is designed to overcome errors during packing. Source: Rahul Shome/Rutgers University-New Brunswick An automation workspace with a Kuka robotic arm and a bin containing a pile of objects that need to be tightly packed into a shipping order box. The Rutgers robotic packing system is designed to overcome errors during packing. Source: Rahul Shome/Rutgers University-New Brunswick Computer scientists from Rutgers University are using artificial intelligence (AI) to manipulate a robotic arm so that it can more efficiently pack boxes in warehouse settings.

To better control a Kuka robotic arm, the Rutgers’ team developed software and algorithms that enabled the robotic arm to pick up objects from a disorganized pile and pack them tightly within a small cube-shaped shipping order box. The system can take items from a bin of disorganized products using a suction cup and place them in a tightly organized fashion into the shipping order boxes. The combination of software, algorithms and sensor data enabled the robotic arm to move objects in the direction of a specific target, pushing those products together in line with other products. Using real-time monitoring, the Rutgers’ team explained that it was able to detect and avoid possible packaging failures during operation.

Largely considered a manual task, tightly packing products taken from a disorganized pile of products is critical to the efficiency of a warehouse. Consequently, automating such a task, according to the Rutgers’ team, could potentially improve costs, increase competitiveness and enable employees to focus on other less menial and physically demanding warehouse tasks.

"We can achieve low-cost, automated solutions that are easily deployable. The key is to make minimal but effective hardware choices and focus on robust algorithms and software," said the study's senior author Kostas Bekris, an associate professor in the Department of Computer Science in the School of Arts and Sciences at Rutgers University-New Brunswick.

Having developed a system that is capable of packing cube-shaped boxes, the team plans to eventually investigate avenues for packing objects into boxes of different sizes and shapes.

The scientists’ peer-reviewed study was presented recently at the IEEE International Conference on Robotics and Automation. To see the system in action, watch the accompanying video that appears courtesy of Rutgers University.

To contact the author of this article, email mdonlon@globalspec.com