<?xml version="1.0" encoding="UTF-8"?><oembed><type>video</type><version>1.0</version><html>&lt;iframe src=&quot;https://www.loom.com/embed/1517deac8dfd49a3b5b9a2aa1058e94d&quot; frameborder=&quot;0&quot; width=&quot;1662&quot; height=&quot;1246&quot; webkitallowfullscreen mozallowfullscreen allowfullscreen&gt;&lt;/iframe&gt;</html><height>1246</height><width>1662</width><provider_name>Loom</provider_name><provider_url>https://www.loom.com</provider_url><thumbnail_height>1246</thumbnail_height><thumbnail_width>1662</thumbnail_width><thumbnail_url>https://cdn.loom.com/sessions/thumbnails/1517deac8dfd49a3b5b9a2aa1058e94d-898077a49377ec12.gif</thumbnail_url><duration>91.989</duration><title>Optimizing USPS Routes Using Video Footage</title><description>This Loom demos Adas Labs’ route optimization for USPS career pickup routes in San Francisco. The team aims to identify mailboxes where there are no drops and optimize the route from a defined start to an end. They build the route using actual video footage from people approaching and dropping mail at blue mailboxes, including verifying footage where one person successfully drops and other videos where people come close but do not drop. The demo focuses on using these observations to construct the most optimized path.</description></oembed>