9 min read
The opinions expressed by the entrepreneur's contributors are their own.
If someone has ever laughed at your ideas, Alexis Block doesn't want you to be discouraged. She is the creator of HuggieBot, the first human hugging robot with visual and tactile sensing, and she says she has to believe in herself and her idea to get where she is today. She is a doctoral candidate at the Max Planck ETH Center for Learning Systems and has her B.S.E. in Mechanical Engineering and Applied Mechanics with double minors in Mathematics and Entrepreneurship. She then earned an M.S.E. in robotics from the University of Pennsylvania. She co-founded the MPI Athena Group to serve women in science, technology, engineering, math, robotics, intelligent systems and related fields. Her research has been published around the world, including in the New York Times and the Late Show with Seth Meyers. She sat down with Jessica Abo to discuss her career path and the importance of being true to yourself.
Jessica Abo: Alexis, tell us where were you in your studies when you came up with this idea?
Alexis Block: I started this project in autumn 2016 as my master's thesis. I had a difficult time emotionally. My dad had died when I was a freshman and I was still struggling with it and I really wanted a hug but a hug from someone who understood the depth of the emotions I was dealing with and me up this way I really needed it. I wanted a hug from my mom or my grandmother.
I spoke to my professor and we said, "Wouldn't it be wonderful if we could come up with a way that people could send customized hugs to each other so that you could receive that comfort from that special loved one, regardless of distance between the two of you? " I was so passionate and excited about this topic that I continued doing what I'm working on until I got my PhD.
What was the first step you took to make this HuggieBot a reality?
First I started with a commercially available robot called PR2, which stands for Personal Robot 2, and it was made by a company called Willow Garage. This company doesn't exist anymore but I gave this robot custom hardware and software upgrades to see if I could hug this robot and if people would accept that. So that was my master's thesis, and I also tested various parameters, e.g. B. whether the robot was soft or warm and how tight and how long the robot would hug a person. After finding the optimal parameters for my PhD, I decided that there weren't any commercially available robot platforms that were really ideal for this kind of close, social, physical human-robot interaction, and I naively thought, perhaps, the best idea was designing and building my own robot for me, which was just so much work, but very, very rewarding.
It's all so fascinating. How does your HuggieBot work?
The first thing that happens when people hug is that you see someone approaching you and you can tell by their forward movement and the way they raise their arms that they want to hug you. You can also easily and very quickly estimate their size and height. That's the first thing my robot has to do. With the camera, I am using an Intel RealSense depth-sensing camera that is on top of the robot's head. I notice an approaching user with his arms outstretched for a hug that goes forward and I quickly estimate the height of the user and interpolate that to find the joint angles at which the robot should raise its arms to determine how high the robot should hug the person to make sure they are at an appropriate height for them.
Then the robot uses torque sensors on each joint of its arms to grasp a person, much like two types of robotic grippers could grasp an object. That way it can be adjusted to fit the size and also the position if someone is not hugging in the front. Still, if they step to the side a little, it will ensure that someone is captured very well, tightly, but not too tightly. I use torque thresholds to ensure a safe hug that won't leave air gaps or put undue pressure on the user's body. Then I also developed a new kind of inflatable sensor torso. The cool thing about it is that it serves a dual purpose. It softens the robot and acts as a detection system at the same time. I use this to detect contacts the user is making on the torso of the robot. This helps me tell when the person starts hugging the robot and when they let go, but it also tells me if the person is doing any actions on the robot, such as pulling a button. B. patting the robot, squeezing it or rubbing its back.
Then I also developed a behavioral algorithm after doing a long user study to find out how the robot should react to these actions. I have a bit of variety, a bit of spontaneity, in order to make the robot appear less robotic but more natural where the robot reacts to these actions. When a person pushes, the robot usually pushes too, but occasionally there is a little variety in what it will do. Then there are two ways to share. Either let go of the robot or you can lean against your arms and the robot will let go of you in either direction.
You said earlier that you could personalize the hugs. How does this work?
I'm still working on that. It's not finished yet, but that has been kind of a driving force for all these years. I'm working on developing a mobile app that will allow you to send custom hugs to someone else. You can record a video. So your mother's face could replace the animated face and she could say, "Oh, I love you so much" or "Everything will be fine." The customizer can also determine how long the hug should last and whether the robot should perform gestures on the person. You will receive a notification on your phone and scan a QR code on the robot.
Who has access to your HuggieBot?
The robot is currently physically located in Stuttgart at the Max Planck Institute for Intelligent Systems. At the moment I've got people to come to the institute by simply posting an expat on the Stuttgart Facebook group and saying, "I'm doing a user study. If anyone is interested, please contact me." We plan a time and they come to the institute and hug.
What's next for you and next for HuggieBot?
I want to do a long term study over a three month period of allowing users to send custom hugs using this application and I want to see if this robot can possibly help strengthen personal relationships that are separated by a physical distance originally on the idea. I live in Europe and my family lives in the US, but now, in times of COVID, it is even more relevant than I could ever have imagined.
What advice would you like to give to the aspiring entrepreneurs out there who feel like everyone is laughing at their ideas?
Working on a project that really has a lasting impact or impact takes years. Whenever you come up with an idea on a subject that you are passionate about, you need to think 20 years into the future, not just five. It takes a lot of hard work and dedication over a long period of time to make something truly visionary happen. So when you first share your idea with people, they might laugh and think it's funny, but only because they can't see that far into the future. But if it's something that you are really passionate about and work for on time, they will catch up with you and your vision.
Take HuggieBot, for example. When I started my project four years ago, some of my professors even laughed at me. Then three years ago when I was presenting my work at an academic conference, someone actually came up to my poster and laughed in my face and said to me, "This is the stupidest thing I've ever seen. I can't believe it, you have actually spent time building a hugging robot. "You see, these people could never have imagined a world without social touch.
Look forward to the Covid pandemic, and unfortunately, people are now realizing how hard it is not to be able to hug their loved ones. I never imagined this kind of future, but I've seen other uses for this robot, other examples where people are physically separated by a distance that would benefit from social touch, but that the rest of society doesn't really care took care of: elderly people in nursing homes, prisoners, students who are far from their families, perhaps for the first time in their lives. These groups of people are exposed to high levels of depression for a number of reasons. One factor that contributes to this is the lack of social affective touch. Thanks in part to the pandemic, people are now beginning to realize its importance and to take my research more seriously.