Amazon Robotics is funding a new AI-powered app which could prevent warehouse workers from getting injured.
The University of Washington has used machine learning to develop a new system which can monitor warehouse workers actions and assess how risky their behaviours are.
By recording 3D videos of workers performing 17 common tasks like picking up objects from high shelves and unloading bins, the university research team gave each a calculated risk score, gauging the impact on workers’ bodies.
“The Kinect is essentially able to track a 3D skeletal model” senior author of the project report Ashis Banerjee said.
“We can then compute how the joint angles in my body are also changing as I’m moving objects around.”
The system can subsequently identify which tasks pose the biggest risk of injury for workers, and delegate them to warehouse robots.
“Now that people are starting to work in settings where robots are used, we have a unique opportunity to split up the work so that the robots are doing the risky jobs”, Banerjee added.
“Robots and humans could have an active collaboration, where a robot can say, ‘I see that you are picking up these heavy objects from the top shelf and I think you may be doing that a lot of times. Let me help you.'”
Eventually the researchers plan to put this system into an app, allowing them to monitor and assess their own risky behaviours.