Amazon reportedly is developing computer vision technology that will be able to detect imperfections in fresh produce, as well as testing for ripeness and sweetness, using AI to conduct "millions of assessments per day at a cost that is far below compared to any other method."
Business Standard reports that "Amazon plans to develop a conveyor belt based automatic grading and packing machine. It would leverage hardware and machine learning to pack produce into predetermined quality grades such as premium-grade A. The gradient pack machine will reduce grading cost by 78 per cent compared to manual grading."
The story quotes Rajeev Rastogi, vice president, machine learning, Amazon India, as saying that "quality is one of the key drivers of fruit and vegetable purchasing decisions and a critical factor in achieving customer satisfaction. Having humans grade the quality of fruits and vegetables by manually examining each individual piece of produce like tomato or onion is not scalable to millions of quality assessments per day.”
- KC's View:
Interesting - but not entirely surprising - that even as Walmart gets rid of some of its robotic equipment, Amazon is investing in equipment that can, virtually at least, squeeze the melons and appraise the apples.
It is almost quaint to remember that back in the early days of Amazon Fresh, the company would hire experts in the produce field to make sure that the items being sent out met certain quality standards and were what the customer had requested. Amazon has abandoned this approach as it has grown … and maybe this new technology is a way of recapturing it, even if only virtually.