Hugging a loved one g has significant social and physical health benefits for humans. Not only does a hug help lower blood pressure, but also alleviates stress, so a hug a day helps us feel much better. Unfortunately, ever more interactions are happening remotely and online, especially during this unprecedented time of physical distancing due to COVID-19. An increasing number of people are suffering from loneliness and depression due to increased workload and population aging.
So, a team of researchers at the Max Planck Institute for Intelligent Systems (MPI-IS) and ETH Zürich have recently come up with HuggieBot 2.0, a hugging robot sized similar to an adult human that can hug users at their request.
The robot builds on a previous system created by Alexis E. Block, one of the developers, inspired by her family members who were far away whom she wanted to hug. As the name suggests, it is a second version of the robot. The previous PR2-based HuggieBot 1.0 was too bulky to give a proper hug and also only had a touch sensor located on the back, so it was not a very advanced device. Now, HuggieBot 2.0 is on its way to becoming an excellent hugger.
HuggieBot 2.0 has a soft, warm, inflatable chest that includes haptic sensors to deliver closed-loop hugging. This new platform uses two Kinova JACO 6-DOF arms, which are slimmer, quieter, and smoother than the arms of the PR2. The developers claim that it uses the sensors on the arms to detect when the user wants to leave the hug. It also has a sensor on the torso to detect when a user has removed their arms from their back, thus indicating their desire to end the hug as well.
A purple robe and a grey sweatshirt have also been added to make it as human as possible. A final element of HuggieBot 2.0 is a face screen that can show both animated faces or pre-recorded video messages to make the hug experience more personal, more enjoyable, and less mechanical for the user. The robot also has a built-in depth detection camera, a speaker, and a microcontroller.
Block and her colleagues conducted an in-person experiment in which 32 users each exchanged eight hugs with HuggieBot 2.0, experiencing all combinations of visual hug initiation, haptic sizing, and haptic releasing. Using the feedbacks collected through studies, they are constantly updating the robot to get the perfect hugger. Now, they even have a newer version of their system, called HuggieBot 3.0, which shows hardware and software improvements. It enables the robot to detect, classify and respond to intra-hug gestures like rubs, pats, and squeezes.
To make the hug even more personal, the researchers are working on an HuggieApp that will allow users to remotely send each other customized hugs via the HuggieBot robot.
