Their new system, VR Co-Lab, allows employees to practice disassembling electronic devices in a simulated environment, fostering safer and more efficient training. Disassembly is a vital step in recycling valuable materials from used electronics, yet it often proves more complex than assembly.
"Unlike assembly, which has a very standard procedure, disassembly is slightly more complicated," said Beiwen Li, corresponding author and associate professor at UGA's College of Engineering. "It may not work out the best if we just inverse the whole assembly procedure."
VR Co-Lab addresses this by letting workers safely practice disassembly without damaging parts or risking injury. For example, in a training session, users virtually dismantle a hard disk with assistance from a robotic arm, using Meta Quest Pro headsets to replicate real-world tasks. Humans handle fine tasks like unscrewing bolts, while the robot manages larger parts, with the program providing detailed feedback on performance.
"There are a lot of tasks. It requires a complicated training for workers, typically," Li explained. "So, if we have a VR system, that will be very helpful in shortening training time. It is much easier than having pages and pages of written documents to be read by the user."
Key features include body tracking, which helps the VR system coordinate the robot's movements with the worker's actions to prevent collisions and improve safety. This ensures that the robot's movements align with the worker's tasks, reducing accidents and enhancing performance.
"Robots are going to be important for the future of the recycling industry," Li said. The team plans more extensive user testing to refine the system and expand its application beyond disassembling hard disks, potentially helping address the labor shortage in recycling.
"Because disassembly is so complicated, it involves a human to work together with a robot," Li added. "And that's basically our motivation for developing this VR system for training."
The study was published in *Machines* and supported by the National Science Foundation. Co-authors include Yashwanth Maddipatla from Iowa State University and Sibo Tian, Xiao Liang, and Minghui Zheng from Texas A and M University.
Research Report:VR Co-Lab: A Virtual Reality Platform for Human-Robot Disassembly Training and Synthetic Data Generation
Related Links
UGA College of Engineering
Space Technology News - Applications and Research
| Subscribe Free To Our Daily Newsletters |
| Subscribe Free To Our Daily Newsletters |
