Computer Vision for Cozmo, the Cutest Toy Robot Everrrrr! with Andrew Stein

800 800 This Week in Machine Learning & AI

In this episode, I’m joined by Andrew Stein, computer vision engineer at consumer robotics company Anki, and his partner in crime Cozmo, a toy robot with tons of personality.

Andrew joined me during the hustle and bustle of CES a few weeks ago to give me some insight into how Cozmo works, plays, and learns, and how he’s different from other consumer robots you may know, such as the Roomba. We discuss the types of algorithms that help power Cozmo, such as facial detection and recognition, 3D pose recognition, reasoning, and even some simple emotional AI. We also cover Cozmo’s functionality and programmability, including a cool feature called Code Lab. This was a really fun interview, and you’ll be happy to know there’s a companion video on YouTube starring Cozmo himself, which of course we’ll link to on the show notes page.

Enter Our #MyAI Contest!

In this week’s interviews, our AI in Consumer Electronics series, you’ll hear from some great people who help me explore some of the very cool ways that machine learning and AI are being used to enhance our everyday lives.

A few of these companies have provided us with products to give away, and we’re excited to launch the #MyAI contest. To enter, we want to hear from YOU, about the role AI is playing in your home and your personal life, your favorite example of home/personal AI, and/or where you see it all going. So, fire up your webcam or smartphone camera, and get ready to tell us your story!

We’ll post the videos to Youtube and the video with the most likes wins their choice of great prizes including an Anki Cozmo, a Lighthouse smart home camera, or a Google Home Mini! (First prize gets first pick, second prize gets second pick, etc.) Submissions will be open through Feb 11th, and voting will remain open through Feb 18th.

Thanks to our sponsor!


I’d like to thank our friends at Intel AI for their continued support of the podcast. Intel was extremely active at this year’s CES, with a bunch of AI, autonomous driving and VR related announcements. One of the more interesting partnerships announced was a collaboration with the Ferrari Challenge North America race series. Along with the folks at Ferrari Challenge, Intel AI aspires to make the racing viewing experience more personalized by using deep computer vision to detect and monitor individual race cars via camera feeds, and allowing viewers choose the specific car’s feeds that they’d like to watch. Look for my conversation with Intel’s Andy Keller and Emile Chin-Dickey, episode 104 in this series, for an in-depth discussion about this project, and be sure to visit ai.intel.com where you’ll find Andy’s technical blog post on the topic!

And of course, be sure to check out some of the great names that will be at the AI Conference in New York, Apr 29–May 2, where you’ll join the leading minds in AI, Peter Norvig, George Church, Olga Russakovsky, Manuela Veloso, and Zoubin Ghahramani. Explore AI’s latest developments, separate what’s hype and what’s really game-changing, and learn how to apply AI in your organization right now. Save 20% on most passes with discount code PCTWIML. Early price ends February 2!

About Andrew

Mentioned in the Interview

“More On That Later” by Lee Rosevere licensed under CC By 4.0

Leave a Reply

Your email address will not be published.