Last Mile Brief is sponsored by: |
 |
Want the Last Mile Brief sent to your inbox every weekday? Sign up for free here.
Amazon has unveiled a new artificial intelligence (AI)–based technology that it says can spot even the smallest anomalies in Amazon delivery vans—from tyre deformities and undercarriage wear to bent or warped body pieces.
Amazon is launching the AVI technology in partnership with tech startup UVeye in the USA, Canada, Germany, and the UK.
At the end of every workday, van drivers drive through an AVI archway and over a series of plates equipped with sensors and cameras.
“With the vehicle rolling at 5 mph, the AI system performs a full-vehicle scan in a few seconds, identifies problems, classifies them based on severity, and immediately sends the results to a computer. From there, a DSP can determine the fixes and services they need to perform to have well-maintained vehicles on the road the next day,” says Amazon.
According to Amazon, AVI relies on machine “stereovision,” meaning that it uses two vantage points to construct a full 3D image, and deep learning, a subset of machine learning in which a layered neural network mimics the learning processes of the human brain.
“One exciting benefit of AVI is the totality of insights the technology gives fleet managers,” says Tom Chempananical, global fleet director at Amazon Logistics. “It can keep track of detected vehicle issues and see if they are repeatedly happening on particular routes.”
Amazon claims AVI has already found hidden damage patterns. For example, 35% of all issues stem from tyres. These issues include sidewall tears and debris and nails lodged in treads, issues Amazon states were not easily picked up by manual inspections previously.