The online giant is using AI to help employees spot damaged goods before they get sent to customers.
The company has been developing its use of artificial intelligence in its fulfilment centres over the years.
The company uses a six-point visual check process which can be time consuming task that is often difficult to keep up with due to the high volume of products that are processed.
Currently developers at Amazon Fulfilment Technologies in Berlin are developing advanced artificial intelligence which can ‘spot irregularities’ and flag up defective goods before they can be delivered to the end customer.
Last year, the development team found that they could supply a machine learning model with reference images to teach it how to compare the product the AI is ‘looking at’, to an image of what the product should look like.
To do this, the team use computer vision to scan every item that passes through their warehouse.
According to Christoph Schwerdtfeger, Applied Science Manager at Amazon Fulfillment Technologies, the AI system is three times more effective than manually identifying damaged products.
He added: “We want to deploy our damage-detection software at a dozen operations in North America and Europe before the holiday season. Once in place, the technology will help scan for damage on over 40 million customer products every month, and it will be part of how we make sure people get undamaged gifts this holiday season.”
