University Of Michigan Professors Launch Refraction, A New Last-Mile AV Delivery Platform

By Amit Chowdhry ● July 24, 2019
  • Refraction AI is a new last-mile autonomous vehicle delivery platform company founded by University of Michigan professors Matthew Johnson-Roberson and Ram Vasudevan.

Refraction AI is a new last-mile autonomous vehicle delivery platform company that was founded by Matthew Johnson-Roberson and Ram Vasudevan — who are roboticists and professors and at The University of Michigan. And Refraction is backed by eLab Ventures and Trucks Venture Capital.

What does Refraction do? Refraction makes low-cost and lightweight autonomous delivery robots that are able to operate in both bike lanes and roadways — which is called REV-1. REV-1 launched at the TechCrunch Mobility event.

“We have created the Goldilocks of autonomous vehicles in terms of size and shape,” said Johnson-Roberson — the cofounder and CEO at Refraction in a statement. “Our platform is lightweight, nimble and fast enough to operate in the bike lane and on the roadway, and we are tackling regional inclement weather patterns that inhibit or slow down other AV solutions.”


Refraction AI

Refraction’s first self-driving delivery robot is approximately the size of an electric bicycle. And it has three wheels and stands at 5 feet tall, 4.5 feet long, and 30 inches wide. And it weighs approximately 100 pounds and can reach a speed of up to 15 MPH, which is fast enough to be nimble and is able to deliver in a timely manner while having the shortest stopping distance of any AV on the road.

The inside of the REV-1 features 16 cubic feet as a specification — which is enough to hold around four or five grocery bags. As a delivery arrives at the destination, a text with a keypad code enables the recipient to retrieve their goods.

Refraction’s first test application has been set up with several restaurant partners. And Refraction expects to expand across the gamut of last-mile delivery. 

Here is a video of how the REV-1 works:

“Consumers today expect on-demand goods of every type, and timeliness of delivery is often the key to customer satisfaction. But companies are struggling to find consistent, reliable and economical ways to address that need,” said Bob Stefanski — the Managing Director of eLab Ventures and founding team member of TIBCO Software. “Refraction’s use of sturdy, smaller-sized delivery robots in the bike lane allows for faster technology development and covers a larger service area than competitors operating on the sidewalk. Their vehicles are also light-weight enough to deploy more safely than a self-driving car or large robot. The market is huge, especially in densely populated areas.” 

In terms of sensors, the REV-1 has 12 cameras as its primary sensor system along with radar and ultrasound sensors for additional safety. The whole platform costs a fraction of only one LIDAR used in other systems. Plus the system enables Refraction’s platform to navigate in rain or snow and is not dependent on traditional HD LIDAR maps. 

“Our vehicle’s low curb weight at low speeds makes deployment safer than other autonomous vehicles. For example, we have a 5-foot stopping distance, compared to the typical 45-foot stopping distance that a full-sized vehicle at the same speed would need to avoid an accident,” Johnson-Roberson continued. “Finally, our design and technical choices, particularly relying on cameras over HD-LIDAR, allow us to operate a more economical platform that gives us a significant competitive advantage on cost efficiency.”

Refraction is not the only company that is building an unmanned delivery vehicle. Nuro — a Mountain View, California-based robotics delivery company — raised more than $1 billion in funding since it was founded. And Nuro is working closely with Kroger to test unmanned grocery delivery services in Scottsdale, Arizona using a vehicle called the R1.

Featured image: Refraction AI team with former U of M and NFL football player / Heisman Trophy winner