- Amazon robots managed 224 units/hour, compared to humans at 243 units/hour
- Robots are more consistent, but humans can be faster in some cases
- More research is needed to prevent damage
After a series of robotics ads in recent years, including its latest Vulcan robot that has a sense of touch, Amazon is testing next generation models called ‘Stow’ and ‘Choose’, and their names say it all: they are designed to help in the storage and selection processes in the compliance centers.
However, the company has recognized that current robot technology is not instead of replacing human workers despite achieving promising results.
According to their performance tests, humans averaged 243 units per hour compared to robots, 224 units per hour. The difference is small, but Amazon also highlighted some nuances.
Amazon robots are good, but not good
Where robots stand out is consistency. “It was also discovered that humans had a greater variation in storage rates: people can quickly save many small items efficiently, but they are slower with large items, crouched for lower containers or when they use a ladder to reach the upper containers,” said Amazon.
The company also observed how humans can perform multiple tasks at the same time with two hands, such as getting a storage container with one hand and saving an article with the other, something that the current generation of robots cannot do.
Even so, the gap is closing, with Amazon robots stored with more than 85% success at a chest rate similar to humans in more than half a million tests.
That said, there are some challenges with the implementation of robotics in Amazon stores, including damage caused by product falling, insert products into stowage containers and crush light boxes.
As such, although complete human replacement is not yet feasible, hybrid systems are demonstrating to be highly effective, with more work necessary to improve the management and reduction of damage caused by robots.
“A deeper investigation may be required to predict the complex interaction of items to climb the most general manipulation,” Amazon researchers added.
