[ad_1]
Paolo Pirjanian is an Armenian born in Iran and fled to Denmark as a teenager. Since he was young, he was fascinated by computers and started coding in his room. After earning his doctorate in robotics, Paolo became one of the first leaders in the field of consumer robotics with more than 16 years of experience in developing and marketing cutting-edge home robots. He worked at NASA JPL and led world-class teams and companies at iRobot®, Evolution Robotics®, and others. In 2016, Paolo founded Embodied, Inc. with the vision of building socially and emotionally smart digital partners that improve care and wellness and help people live better lives every day.
What initially attracted you to AI and robotics?
My fascination with AI and robotics goes back to my childhood. I was displaced from country to country several times until our family moved to Denmark. By accident, I discovered a computer. I was so fascinated by it that I locked myself in my room and started coding all day and night for months. My parents thought I was depressed or drugged, but it was nothing like that. I was so completely fascinated by the computer!
During that same time, I watched a Pixar television documentary. Pixar was presenting its first animated short, Luxo Jr., a two-minute short about two table lamps running and playing with a ball. I was so fascinated by that and amazed that a computer that was learning to code could generate such endearing characters on television that they evoked so much emotion in me. So from there, I decided to go to school to study robotics and finally get my PhD.
Then I moved to the USA. USA To work on Mars rovers at NASA, it was the childhood dream job. Finally, I started to develop SLAM navigation technology that now enables iRobot products.
But looking back, I realized that my inspiration for this entire trip was actually Pixar’s short animation of bringing inanimate objects to life. This is why we created Embodied: to bring robots to life that can interact with people, focusing on helping children with social and emotional development.
When did you know the concept to launch Evolution Robotics?
Evolution Robotics was originally started by Idealab’s Bill Gross in 2001 to become the Microsoft of Robotics, a bold vision that turned out to be too early and ultimately failed. I was CTO and GM at Evolution Robotics and after its failure I negotiated with Idealab to develop some of the core technologies that my team and I had developed and start a new company. In 2008, the new entity, also known as Evolution Robotics, began developing products using our core navigation technologies, including NorthStar and vSLAM, which were innovative approaches to spatial mapping and autonomous navigation similar to what we are seeing in cars. driverless but aimed at low cost consumer electronic products.
We developed a line of automatic hard floor sweeping and mopping products called Mint, which we launched in 2010. By 2011, we grew rapidly to $ 25 million in sales and were acquired by iRobot in 2012 for our product revenue and our vSLAM navigation technology. which now powers the Roomba and Braava product lines at iRobot.
At that time you became the iRobot CTO. Could you talk about your iRobot experience and what you learned from your experience?
As iRobot CTO, I was able to quickly integrate vSLAM into the Roomba product line to launch a new model that was able to consistently cover the entire floor plan without losing a place. That helped the company stay ahead of the competition like Dyson, which was coming up with systematic cleaning solutions. vSLAM is now an integral part of iRobot Roomba and Braava’s flagship product lines.
I enjoyed working closely with Colin Angel, CEO of iRobot to help establish a strategic direction to make Roomba central to the connected home ecosystem, where Roomba’s spatial awareness gives him a unique position to understand the floor plan and become the connective tissue between all connected devices. That strategy seems to have had a solid foundation since my departure in 2015.
Additionally, we decided to double down on Consumer Robotics’ business to help iRobot maintain its global leadership position. This led to the divestment of the defense business and the exit of other peripheral businesses to bring focus and intensity to the consumer business.
Additionally, we had to redesign the organization to support a heavy software strategy with connected products. This required a transformation of the company culture to adopt a more agile and iterative approach.
The list of things I learned in iRobot is long. One thing that stands out is the power of team culture. Staying agile and committed to the mission is probably the most important competitive advantage that any company can have above any patent portfolio and above trade secrets. If you have a high-performing team that feels empowered and inspired towards a clear goal, it will be difficult to stop it.
You are currently the Founder and CEO of Embodied. Can you discuss what was the inspiration behind the launch of this company?
I really enjoyed my time at iRobot as CTO, and we were working on many exciting projects and pushing the boundaries of robotics. It was exciting to launch commercially successful robots on the market that performed useful physical tasks such as vacuuming the floor.
However, in the back of my mind, I knew that I still had a lifelong dream to fulfill: to build socially and emotionally intelligent robotic companions that improve care and well-being and our daily lives. I knew we were at a tipping point in how we will interact with technology. So with that, I decided to forgo iRobot and start Embodied.
When we started Embodied, from the beginning, we were rethinking and reinventing how human-machine interaction is done beyond simple verbal commands, to enable the next generation of computing and empower a new class of machines capable of seamless social interaction. Specifically, the first product was to focus on building an animated partner to help children develop social and emotional skills through play-based learning. This partner would become known as Moxie. Moxie is a new type of robot that has the ability to understand and express emotions with emotive speech, credible facial expressions, and body language, leveraging human psychology and neurology to create deeper bonds. To do this, we assembled a cross-functional team of passionate leaders in engineering, technology, entertainment, game design, and child development. For the past four years, Embodied has been working tirelessly to bring together all the latest technology to bring Moxie to life, and the team is excited to finally deliver it to families who need a co-pilot to support healthy child development.
What are some of the unique business challenges behind a robotics startup?
It is fun to do the impossible, but it can also be a little scary. We knew that if we wanted to revolutionize the way humans interact with machines, we would have to solve problems that had not been solved before. Some problems include:
- Flat screens are on devices, and we want to bring a device to life. So how do we create a face that is more realistic, rounded, and not two-dimensional?
- Today’s conversation engines only allow very limited conversation, so how do we create a solution that allows for more natural conversation?
- We don’t want the voice to sound robotic, so how do we make the voice sound natural, with contextually appropriate hues and inflections?
- We knew that eye contact was very important, so we had to figure out how to use computer vision to ensure reliable eye-tracking capabilities.
All of these questions about Moxie’s features led to many cutting-edge technological innovations.
First, a projected and rounded face. Statistics are starting to accumulate to show us that too much time in front of the screen can have devastating effects on developing minds. Worse yet, most kids’ tech devices have digital displays. That’s why we decided to invest more to make Moxie’s face fully projected, which allowed us to create a rounded face display with naturally curved edges, rather than a flat screen. This makes interacting with Moxie feel more realistic, realistic, and credible. In fact, only through this 3D look of the face, Moxie may have actual eye contact with the child. So Moxie’s face not only protects kids from excessive screen time, but also makes the interaction experience even more real.
Second, the conversation engine. Until now, smart speakers and voice assistants have required repetitive use of trigger words to initiate commands. Moxie’s conversation engine is different. Follow a natural conversation and respond to the typical flow of communication without the use of trigger words (such as “Hey Siri” or “Ok Google”). Advanced natural language processing allows Moxie to recognize, understand, and generate language seamlessly, making the interaction feel more personal and natural.
Third, speech synthesis. Moxie’s voice doesn’t have the same robotic speech and monotonous sound found in most robots and voice assistants. Instead, Moxie uses natural, emotional vocal inflections, which help communicate a wider range of emotions. This enhances the reach of the social-emotional lessons Moxie can participate in, while bringing an additional image of life and credibility to the interaction.
Fourth, the eyes. One of the most important features is Moxie’s big animated eyes. Innovative eye-tracking technology enables Moxie to maintain eye contact with the child even as the child moves across the room. This eye tracking ability not only creates an incredibly realistic interaction, but also helps your child practice eye contact. In addition, large, lively eyes help exaggerate emotional communication, making it easier for a child to recognize certain emotions. Practicing eye contact and understanding emotions are two key development goals in the socio-emotional curriculum.
Finally, all of these technological features allow interactions with Moxie to feel realistic and natural. Moxie’s multimodal sensory fusion makes Moxie aware of the environment and its users. Moxie’s computer vision and eye-tracking technology helps maintain eye contact as the child moves. Machine learning helps Moxie learn users’ preferences and needs, and recognize people, places, and things. Specially located microphones allow Moxie to hear where a voice is coming from and to easily go to the source. Touch sensors allow Moxie to recognize hugs and handshakes. All these pieces come together to make the experience very realistic.
Could you tell us some of the things that make Moxie perfect for kids?
With Moxie, kids can participate in meaningful games, every day, with content informed by best practices in child development and early childhood education. Each week is a different topic, like kindness, friendship, empathy, or respect, and kids are tasked with helping Moxie with missions that explore human experiences, ideas, and life skills. These missions are activities that include unstructured creative games such as drawing, practicing mindfulness through breathing exercises and meditation, reading with Moxie, and exploring ways to be nice to others. Moxie encourages curiosity for children to discover the world and the people around them. All of these activities help children safely learn and practice essential life skills such as taking turns, eye contact, active listening, emotion regulation, empathy, relationship management, and problem solving.
Embodied has also partnered with Encyclopaedia Britannica and Merriam-Webster to integrate the Merriam-Webster Children’s Dictionary, allowing Moxie to provide age-appropriate definitions and related information to help children learn and understand the meanings of new words. and concepts. This is the first of many integrations with Moxie that fulfill Britannica and Merriam-Webster’s shared mission of inspiring curiosity and the joy of learning.
Embodied has also developed a comprehensive ecosystem that helps parents support their child’s journey with Moxie and enables children to expand their use of Moxie in a safe and parent-approved way:
- The Embodied Moxie Parent app provides a dashboard to help parents understand their child’s development progress with Moxie. The application will provide key information for a child’s social, emotional and cognitive development through his activities with Moxie. Additionally, the app provides valuable tips and advice to parents to improve their children’s experience and progress with Moxie.
- An online children’s portal site (called the Global Robotics Laboratory, or G.R.L.) provides additional activities, games, and stories that will enhance the Moxie experience.
- Moxie’s Monthly Quest Packs are emails meant to engage kids in new activities with Moxie, and they also provide fun items like trading cards and stickers.
Over time, Moxie learns more about the child to better personalize its content to help with each child’s individual developmental goals. Embodied has taken careful steps to ensure that information provided by children and families is handled with high standards of privacy and security. We want Moxie to be COPPA Safe Harbor Certified (Online Children’s Privacy Protection Act) so parents can feel safe knowing that Moxie employs leading data security and integrity procedures and that their systems are audited regularly to ensure full compliance. Additionally, personally identifiable data and confidential information are encrypted with the highest level of security and can only be decrypted using a unique key to which only parents have access.
What are some of the natural language processing challenges Moxie faces?
At Embodied, we strive to redefine how humans interact with machines, especially in conversation through natural language processing. So, we decided to create SocialXTM, which is a platform that allows children to interact with Moxie through natural interaction (i.e. facial expressions, conversation, body language, etc.), evoking confidence, empathy, and motivation, as well as a Deeper commitment to promote developmental skills. With SocialXTM, Embodied introduces a whole new category of robots: Animated Companions. “Encouraging” means giving life and SocialXTM enables Moxie to embody the best of humanity in a new and advanced form of technology that can drive new ways of learning.
Natural language processing is at the core of our natural conversation engine, and there are many unique features for the conversation engine that we work tirelessly to create.
The key feature we worked on was Moxie’s ability to focus conversation with a single user and separate conversations and background sounds, so Moxie only responds to the user. This allows for a more focused and enjoyable interaction. This is a solution to what many call the “cocktail problem”. When you are at a cocktail party and there are many people around you talking in a room while trying to have a conversation with one person, it is not terribly difficult for humans. For a computer, this is incredibly difficult. How do we make sure that Moxie only responds to what the individual user says and is not intimidated by background noise, conversations, television, etc. There are many ways to approach the solution to this problem.
- We use our vision system to identify who is looking at and facing Moxie.
- We have several microphones on the front of Moxie that tell us where that sound is coming from.
- Then we can use machine learning to match the sound to whoever is speaking in front of Moxie. This allows us to filter other conversations and stay focused on a single user.
In general, conversation agents in the market have avoided the “cocktail party problem” by using trigger words, such as “Hey (device, followed by a question)”. This activation word allows the conversation agent to listen to the activation word and respond only when that activation word is said. However, since Moxie can focus on a single user, Moxie does not need to have trigger words to trigger a response.
We wanted to make sure that the Moxie conversation engine is so sophisticated that it is contextually aware of conversational responses. This allows for a more nuanced conversation. For example, Moxie can understand the different meanings behind “I don’t know” and “no”.
Is there anything else you would like to share about Moxie or Embodied?
We have been working on this project for four years with a dedicated team that has worked tirelessly to make the incredible inventions that are required to bring Moxie to life. We are now excited to finally bring Moxie into families to help their children with social and emotional development. Therefore, we are looking forward to the journey!
Thanks for the interview, I was delighted to hear how you were initially inspired by a Pixar short film and how you have pursued your passion for life. Readers who want more information or who wish to request a Moxie should visit Embodied, Inc.
