- Have any questions?
- 02 9247 6000
- media@commsroom.co
- Have any questions?
- 02 9247 6000
- media@commsroom.co
Menu
This research has the potential to significantly improve automation in industries such as manufacturing, agriculture, and warehousing.
It was also recognised as a finalist for Best Paper Award on Multi-Robot Systems at the IEEE International Conference on Robotics and Automation 2024.
“There’s a long history of debate on whether we want to build a single, powerful humanoid robot that can do all the jobs, or we have a team of robots that can collaborate,” says co-author Hao Zhang, associate professor at UMass Amherst’s Manning College of Information and Computer Sciences and director of the Human-Centered Robotics Lab.
In manufacturing, a team of robots can be more cost-effective by optimising each robot’s unique abilities. However, coordinating a diverse set of robots presents a challenge, as some may be stationary while others are mobile; some may lift heavy materials, while others handle smaller tasks.
To tackle this, Zhang and his team developed a learning-based approach called learning for voluntary waiting and subteaming (LVWS). “Robots have big tasks, just like humans,” says Zhang. “For example, they have a large box that cannot be carried by a single robot. The scenario will need multiple robots to collaboratively work on that.”
Read also: Australian businesses enhance resilience with advanced AI protection
Another crucial behaviour is voluntary waiting. Zhang explains, “We want the robot to be able to actively wait because, if they just choose a greedy solution to always perform smaller tasks that are immediately available, sometimes the bigger task will never be executed.”
The researchers tested their LVWS approach in a computer simulation involving six robots and 18 tasks. Their method proved highly effective, achieving only 0.8% suboptimality compared to a perfect solution, significantly outperforming other methods, which ranged from 11.8% to 23% suboptimality.
Williard Jose, a doctoral student and co-author of the study, explains, “Instead of that big robot performing that task, it would be more beneficial for the small robot to wait for the other small robot and then they do that big task together because that bigger robot’s resource is better suited to do a different large task.”
This research, supported by the DARPA Director’s Fellowship and a U.S. National Science Foundation CAREER Award, promises significant advancements in multi-robot systems, especially in large-scale industrial environments where specialised tasks are essential.
A new knowledge platform and website aimed at assisting the communications industry and its professionals. Contribute your op-ed, press releases, how-to articles, videos and infographics at media@commsroom.co
