Research improves smart warehouse technology and material handling options


A group of professor-researchers built a prototype autonomous forklift with integrated systems to advance intelligent warehouse systems. Credit: Elizabeth Lamark/RIT

Soon, industrial robots in warehouses will be smart enough to know who has priority in busy aisles.

Researchers at the Rochester Institute of Technology are developing a smart materials handling system for warehouses that incorporates smart technologies including LiDAR sensors and artificial intelligence.

With the supply chain challenges brought about by the pandemic and the increased demands of e-commerce, technology can provide the support businesses need to improve productivity, efficiency and safety in a warehouse.

“This is an area where robotics and autonomous material handling can help,” said Michael Kuhl, professor of industrial and systems engineering at RIT’s Kate Gleason College of Engineering. “Robots can work longer, not necessarily to replace tasks, but for some manual tasks without added value. This means a shift in focus for jobs, with people needed to design and maintain fleets of vehicles and robots.

Kuhl and the project team received a grant for “Effective and Efficient Driving for Material Handling,” a one-year, $300,000 project sponsored by The Raymond Corp. robot (AMR).

New work focuses on advanced avoidance and communication strategies for multiple robots and humans in the warehouse environment.

In warehousing operations, there is often a mix of self-contained and human-operated equipment. Avoidance strategies should be incorporated into task options, path planning, and recognition of multiple robots that can communicate with each other in real time and recognize humans who are also interacting in the warehouse space.

“We have location information, the different types of sensors that we use in the warehouse to try to identify where the robots are, and the actual movement of the robot,” Kuhl said. “Can they plan to get from the current location to the destination safely and efficiently? They may have a short path, but they still have to avoid other bots and people.

Using deep neural network strategies (types of machine learning techniques), system components are trained to make specific, sequenced decisions based on common tasks, but also infrequent or unusual actions that may to occur in the warehouse environment.

The team is also investigating communication networks within the warehouse (Wi-Fi technology and cellular network functions) as viable solutions. New standards for cellular technologies allow for increased one-to-one cellular communication between individual devices, Kuhl explained.

“In terms of the interaction between people and vehicles, could we take advantage of the sensors of multiple vehicles moving through the warehouse?” he said. “If a vehicle is coming down a path and it sees a person or another vehicle coming out of a driveway, can they communicate and make a decision on what to do next? Who has the right of way?

The team discovered that the robots will be able to react.

During field experiments at Simcona Electronics Corp., a Rochester-based company that sources electrical and mechanical components for manufacturing, the team tests robotic technology in its 50,000 square foot facility.

“We needed a real framework to be able to do this work and move it forward. They provide us with an extremely valuable resource,” Kuhl said. He worked with campus partners Amlan Ganguly, Associate Professor and Head of Department, and Andres Kwasinksi, Professor, both in the Department of Computer Engineering at RIT’s Kate Gleason College of Engineering; and Clark Hochgraf, associate professor in the Department of Electrical and Computer Engineering Technology at RIT’s College of Engineering Technology. Maojia Li, a recent graduate with a doctorate in engineering from RIT, is also part of the project team.

Share the article on social networks or by e-mail:

Source link


Comments are closed.