Q&A with Paolo Pirjanian, Founder and CEO of Embodied

Original article was published on Artificial Intelligence on Medium

Tell us about your career path prior to starting Embodied.

As a teenager, I was fascinated by computers and taught myself to code. After getting a Ph.D. in robotics, I was eager to work in the field of robotics and began my career at NASA Jet Propulsion Laboratory. However, I followed my curiosity about entrepreneurship and ended up creating Evolution Robotics, which we merged with iRobot in 2012, to help bring visual SLAM and cloud connectivity to its portfolio of products, including the flagship Roomba product line.

Why did you decide to found Embodied?

In 2015, I realized that I had strayed from my dream of using robotics to help improve the daily lives of people, and founded Embodied. My goal at Embodied is to build socially and emotionally intelligent animate companions that can improve care and wellness and support people in living better lives from childhood to retirement.

How has your experience at iRobot and Evolution Robotics helped you in launching Embodied and Moxie?

It was exciting to launch commercially successful robots into the marketplace that performed helpful physical tasks, such as vacuuming the floor. There are many lessons that I have learned during my last 20 years of entrepreneurship in consumer robotics.

The first thing is that cost matters. In particular, delivering the right value for the cost of your product is something that makes the technical challenges that much more challenging.

At Evolution Robotics, we worked hard for many years to develop the world’s first commercially-viable navigation technology, called vSLAM, which provided the right price/performance for navigation. A solution that used a low-cost camera, low-end computing, and glue logic at a price that you could incorporate into your consumer product for less than $20. That was, and still is, unprecedented and has led to significant value creation, first at Evolution Robotics, and now at iRobot.

We have taken that lesson and created Moxie, which provides unprecedented technologies and value for the price of a smartphone. It is not easy to create bleeding-edge technologies involving real-time conversational AI, computer vision for object recognition, body language, and much more for that price point. But, it is the right thing to do in order to create value for the consumer, while also building a sustainable business.

Another important lesson I learned from my time at iRobot and Evolution Robotics is the power of team culture. Staying agile and committed to your mission is probably the most important competitive advantage any company can have — above any patent portfolio and above trade secrets.

If you have a high-performing team who feels empowered and inspired towards a clear goal, they will be hard to stop. From the very first day at Embodied, we have worked on creating a high-performance, agile, mission-driven, and empowered team. Without that, Moxie would not have been possible!

Tell us about Moxie, and who it is intended for. What makes Moxie unique?

Moxie is a safe and engaging animate companion for children, designed to help promote social, emotional, and cognitive development through everyday play-based learning and captivating content. Moxie has the ability to understand and express emotions with emotive speech, believable facial expressions, and body language, tapping into human psychology and neurology to create deeper bonds.

To do this, we developed SocialX™, a platform that enables users to engage with Moxie through natural interaction (i.e., facial expressions, conversation, body language, etc.), evoking trust, empathy and motivation, as well as deeper engagement to promote developmental skills.

What are some of the new technologies that have been incorporated into Moxie’s features?

Thus far, smart speakers and voice assistants have required the repetitive use of wake words to initiate commands. Moxie’s conversational engine follows a natural conversation and responds to typical flow of communication without the use of wake words (like “Hey Siri” or “Ok Google”). Advanced natural language processing allows Moxie to recognize, understand, and generate language seamlessly.

Moxie’s voice doesn’t have the same robotic speech and monotone sound found in most robots and voice assistants. Instead, Moxie uses natural and emotive vocal inflections, which help communicate a broader range of emotions. This enhances the scope of social-emotional lessons Moxie can engage in.

Photo courtesy of Embodied

One of the most important features is Moxie’s large, animated eyes. Innovative eye tracking technology allows Moxie to keep eye-contact with the child even as the child moves about the room. Additionally, the large, animated eyes help exaggerate emotional communication, so the child can more easily recognize certain emotions.

After learning about the negative impact of too much screen time on children, we decided to put in the extra investment to make Moxie’s face fully-projected. This allowed us to create a face screen that is rounded with naturally-curved edges, instead of a flat display.In fact, only through this 3D appearance of the face, is it possible for Moxie to have actual eye contact with the child. So not only is Moxie’s face protecting children from excessive screen-time, but it also makes the interaction experience feel all the more real.

Yet another unique capability of Moxie is its ability to measure meaningful metrics in understanding a child’s development across multiple scales relating to social, emotional, and cognitive development. These metrics are analyzed and presented in a dashboard on the parent’s app to provide insights.

You’ve seen robotics technology evolve significantly throughout your career, taking a variety of different forms and purposes. What are the biggest trends? Where does Moxie fit in the landscape?

Technologies in robotics and related fields have advanced tremendously in the last two decades, representing a unique time in which we can now build products that can perform useful tasks, significantly beyond just cleaning the floors with a robotic vacuum cleaner.

In addition to significant advancements in autonomous navigation, which has resulted in business for delivery, logistics, self-driving cars, we have seen natural language understanding and computer vision solve decade-long technical problems.

Particularly, machine learning and deep neural networks combined with the availability of large-scale data and GPUs have enabled us to do things that were inconceivable just a few years ago.

Moxie and the SocialX™ platform, on which it is based, allow for natural human-machine interaction in a product that allows us to help promote social, emotion, and cognitive skills in children. This represents a paradigm shift in the way we will interact and interface with machines. In the entire history of computing, the human has had to adapt in using contraptions and devices like a keyboard and mouse to interact with machines. Now we are seeing the paradigm shift towards adapting machines to learn to interact with us using our “interface” — body language, fluid conversation, tone of voice, eye contact, facial expression, etc.

Moxie is the first incarnation of this breakthrough technology. Future iterations of the technology will find their way into our life in many forms, ranging from robots to provide care for our children and elderly, to automated answering services that can understand and express empathy.

Can you share a detailed example of what a child can learn from Moxie?

With Moxie, children can engage in meaningful play, every day, with content informed by the best practices in child development and early childhood education. Every week is a different theme, such as kindness, friendship, empathy or respect, and children are tasked to help Moxie with missions that explore human experiences, ideas, and life skills.

For example, Moxie will tell its child mentor that it has a mission and needs help to learn what it means to be kind. Moxie will ask the child to draw a kindness flower and then in each petal, write an example of being kind. Moxie will then ask the child to share what they wrote down and encourage the child to do some of the kind things that they put in their kindness flower.

How were Moxie’s lessons and missions created?

Moxie’s content is created by a diverse team of designers, child development, and educational specialists. The team carefully plans each weekly theme to ensure all the activities tie back to promoting social, emotional and cognitive learning.

How is Embodied ensuring child safety, and what kind of parental controls are there?

We have taken careful steps to ensure that information provided by children and families is handled with high standards of privacy and security. Moxie and its full ecosystem will be COPPA (Children’s Online Privacy Protection Act) Safe Harbor certified so parents can feel safe knowing that Moxie employs leading data integrity and security procedures, and that its systems are regularly audited to ensure full compliance. We also have The Embodied Moxie Parent App where parents can set controls and review key insights about their child’s social, emotional, and cognitive development through activities with Moxie.

What’s next for Embodied, now that Moxie has launched?

Right now, we’re focusing on continued improvement of Moxie and building out additional content as we prepare for our first shipments of Moxie this fall. In the future, we plan to expand into many areas. The sky is the limit.