The Importance of Teaching Robots to Hug
Knowing how to give good hugs is an important life skill, even for robots
Hugs make us feel warm and safe and comforted and loved. They’re pretty great, if you’re into that sort of thing. If we need a hug and another human isn’t available, we can sometimes get a little bit of satisfaction from hugging inanimate objects like stuffed animals, but it seems like robots (that can hypothetically hug us back) might be able to be somewhat more fulfilling. While we’ve seen robots that are actively huggable before, and even a few that can hug you back, it’s not clear exactly how a robot hug compares to a human hug, and whether hugging a robot can confer any of the benefits that we get from hugging people.
At the ACM/IEEE International Conference on Human Robot Interaction (HRI) earlier this year, Alexis E. Block and Katherine J. Kuchenbecker from the Haptic Intelligence Department at the Max Planck Institute for Intelligent Systems in Stuttgart, Germany, presented a paper on “Emotionally Supporting Humans Through Robot Hugs.” Their work explores how robots can be more effectively designed and taught to give the kinds of hugs that humans will love. If you hug robots every time you see them (like I do) and sometimes wish those robots could be just a little bit warmer and softer, this research is definitely for you.
The importance of hugs goes way beyond “oh that feels nice thank you.” There’s plenty of research showing that hugs offer tangible health benefits, including lowering blood pressure and increasing oxytocin levels, as well as significant improvements to mental health, like social support reinforcement and stress relief. And if that doesn’t convince you that physical affection is a really important thing, these horrific experiments with giving baby monkeys surrogate mothers made of either wire or cloth definitely will.
For many (if not most) people, hugs are a natural way of expressing affection, and giving a hug is something that comes almost instinctively. For the rest of us (myself included), hugs can be a little bit awkward at times, because they’re a deceptively simple interaction—a good hug involves proper positioning of the arms and hands and torso, along with awareness of the appropriate amount of force to use and knowing when the right moment is to let go. As humans, we get a lot of body language cues from the huggee, and as the hugger, we give our own cues too. For robots, all of this stuff needs to be made explicit, studied, and quantified, at least to the point where a robot knows how to safely hug someone without accidentally crushifying them.
Of course, simply refraining from squishing a human into a pulp is not all that a good hug requires. But for a robot, it’s not yet clear what the requirements are for a hug that will have a net positive effect on a human in need of support. The research presented at HRI is an attempt to figure some of this out, by conducting a study where participants hugged a specially modified PR2 named HuggieBot. HuggieBot could be configured with extra-soft layers of foam, cotton, and polyester, and those layers could also be heated to make them pleasingly warm. It was also programmed with a range of hug pressures (from loose to tight), and interactive hug durations (controlled by a pressure sensor behind its neck) ranging from very brief to five seconds after the participant attempts to disengage, which was long enough to sometimes result in low-key panic on the part of the human.
I could listen to that sultry monotone demanding hugs all day.
Based on a survey of the 30 participants, each of whom got to experience 12 hugs from HuggieBot (I’m so jealous), the researchers found that people generally preferred the soft and warm hugs, which were perceived to be both more comforting as well as safer. People also said that they liked “really tight hugs” the best, and that people particularly liked to be “slightly squeezed” by the robot. Hug duration was very important too: People really don’t like hugs that go on too long, and expect a hug to end when they start to let go
Interestingly, participants disliked the too short (1 second) hug the most, even more than the too long hug, suggesting (to me) that it’s better to feel like a robot might squeeze you to death than to feel like a robot doesn’t really want to be hugging you in the first place.
The other thing that the researchers found was that the act of hugging (and being hugged by) a robot made people like robots more, which is pretty awesome:
Participating in this experiment significantly increased positive user opinions about robots and robot use. Comparing responses to the same 15-question survey given both before and after the experiment, we found that users felt understood by, trusted, and liked the presence of the robot significantly more after the experiment. The results also show that people found robots to be nicer to hug, easier to use, and more of a social agent than they initially anticipated, after our experiment.
For more on why hugs are so important and what we can look forward to from HuggieBot 2.0, we spoke with first author Alexis Block via email.
IEEE Spectrum: Why is research on robot hugs important?
Alexis Block: Robot hugs are important because people love to give and receive hugs. Virginia Satir, a well-known family therapist, was famous for saying, “We need four hugs a day for survival. We need eight hugs a day for maintenance. We need 12 hugs a day for growth.” Sometimes, we are put in new or uncomfortable situations where we might not be near our loved ones, but that doesn’t mean we don’t need the support and calming effects that a hug provides. Research on robot hugs is important so we can one day use technology to provide the emotional support and health benefits of hugs to many people, wherever or whenever they need it.
What makes a good hug?
The results from our experiment suggest that to make a good hug whoever/whatever you hug should be compliant, warm, squeeze you, and release you immediately when you indicate you’re ready for the hug to end.
Why do you think people like hugging robots so much?
I think there are several reasons why people like to hug robots. First, hugs are a natural human expression of affection. Hugs are how we connect with each other. Humans not only instinctively connect with each other through touch but also to their surroundings and new, exciting things they see. Many people are excited about the potential of robotics lately. Perhaps, people’s interest in hugging robots is a combination of wanting to explore an interesting object and wanting to make some kind of a personal connection to a robot.
Next, while it’s just a guess at this point, I think people may like hugging robots partially because they know the robot isn’t really alive and won’t judge them for how long of a hug they want or need. I didn’t ask this question during the experiment (and it’s something I’m interested in looking into in the future), but from what I observed, it seemed like some participants actually hugged the robot longer than they might hug their friends in most social settings. Because hugs help us feel so good and supported, we crave them, but we might be self-conscious about requesting this support from a friend. Getting this support from a robot could be a great way to get what you need without any fear of being judged.
Finally, I had several self-proclaimed introverts participate in my experiment. Some of them told me that they preferred hugging the robot over hugging other people because the robot would let them go when they indicated they were done with the hug, whereas their friends and family members would sometimes hug them for too long.
Hug preferences can vary widely between individuals. How will robots be able to provide high quality hugs for everyone they meet?
The results of our experiment indicate that any future hugging robot should be soft and warm. Overall, it seemed that participants preferred when they were squeezed by the robot and when it released them from the hug immediately when they indicated they were ready. This experiment was focused more on how the robot should hug the person, and less on human preferences. While I have not run any analysis of the varying lengths of time people hugged the robot, there were some participants who preferred shorter hugs, and some who held on for a very long time. I’d be interested in seeing how hug pressure and hug duration vary for individuals.
Humans have what is called haptic intelligence; we can tell a lot of information based on our sense of touch. A robot designed to provide people with high-quality hugs could greatly benefit from using a sense of touch to determine how the user is feeling and what kind of hug they want. We want to give our hugging robot haptic intelligence via strategically placed sensors, so it can match the pressure and duration each person uses to hug it.
PR2 is a very friendly robot, but perhaps not the greatest at giving hugs. Can you describe how your next hug research robot will be different and better?
The PR2 was a great starting platform for this experiment, and using it showed a lot about what a future hugging robot should be. We are creating a robot that is more idealized for these kinds of close social-physical human-robot interactions. The PR2 has a large base that our participants had to lean over to get close to the robot during the hugs. Our future platform will have a more open base that will easily allow people to walk up close to the robot to make this interaction easier. The PR2 is also pretty bulky, so our new research robot will be much slimmer in the arms, chest, and head. A slimmer robot will make it easier for our participants to wrap their arms around the robot, and easier for us to soften and warm the robot overall. A final difference will be that while the PR2’s face is made up of cameras for the eyes, we plan to use a screen for the face, which will allow us to make our robot more expressive and even give us the possibility of showing a picture or streaming a video of a family member who might send you a customized hug in the future!
What are you working on next?
Aside from the hardware components of building our new robot, we’re interested in integrating several new software components. Using computer vision, we’d like the robot to know when a person is close enough to start lifting its arms for a hug and how to use the appropriate reciprocal arm positions. After that, there are several areas we are interested in investigating. The idea of sending customizable hugs is one that is pretty interesting to us, because we’re curious to see how we could potentially reinforce personal relationships at a distance. Remote hugs might benefit family members who live in different countries, students who are stressed in college and want a hug from a parent, children whose parents are divorced or travel frequently, or for elderly patients in nursing homes whose family members can’t visit them as frequently as they’d like to. In these cases, one person could go online and customize the duration, upload a voice/video recording, and maybe add a rub or a pat on the receiver’s back. The receiver might then get either a text message or email with a code they can scan at the robot to receive their customized hug.
We’re also interested in equipping the robot with emotional intelligence. Using machine learning, we want to enable the robot to sense a person’s mood based on their facial expressions and how they contact the robot. Using this information, the robot could respond to you accordingly, both through the way it hugs you and possibly what it says, thereby providing a person with more advanced emotional support.
“Emotionally Supporting Humans Through Robot Hugs,” by Alexis E. Block and Katherine J. Kuchenbecker from the Haptic Intelligence Department at Max Planck Institute for Intelligent Systems in Stuttgart, Germany, was presented at HRI 2018 in Chicago.