When Henny Admoni tells people she's a roboticist who primarily studies humans, she gets strange looks. "It might seem a little weird," Admoni says, "but the goal of my research is to understand how to make robots good for people." Admoni leads the Human and Robot Partners Lab at Carnegie Mellon University, where, along with a team of researchers, she studies the ways robots and AI can improve people's lives. The lab has worked on robotic arms that assist people in eating food and preparing meals; they've observed robots that encourage artists to think outside the box, and they've looked at how robots can help search and rescue teams collaborate more effectively. With a library of published papers, awards, and international speaking engagements under her belt, one might think that, for Admoni, robotics has been a lifelong passion.

The field of socially assistive robotics (SAR) aims to build robots that help people through social interaction. Human social interaction involves complex systems of behavior, and modeling these systems is one goal of SAR. Nonverbal behaviors, such as eye gaze and gesture, are particularly amenable to modeling through machine learning because the effects of the system--the nonverbal behaviors themselves--are inherently observable. Uncovering the underlying model that defines those behaviors would allow socially assistive robots to become better interaction partners. Our research investigates how people use nonverbal behaviors in tutoring applications. We use data from human-human interactions to build a model of nonverbal behaviors using supervised machine learning. This model can both predict the context of observed behaviors and generate appropriate nonverbal behaviors.

In typical human interactions, nonverbal behaviors such as eye gazes and gestures serve to augment and reinforce spoken communication. To use similar nonverbal behaviors in human-robot interactions, researchers can apply artificial intelligence techniques such as machine learning, cognitive modeling, and computer vision. But knowledge of nonverbal behavior can also benefit artificial intelligence: because nonverbal communication can reveal human mental states, these behaviors provide additional input to artificial intelligence problems such as learning from demonstration, natural language processing, and motion planning. This article describes how nonverbal communication in HRI can benefit from AI techniques as well as how AI problems can use nonverbal communication in their solutions.

Shared autonomy combines user control of a robot with intelligent autonomous robot behavior to help people perform tasks more quickly and with less effort. Current shared autonomy frameworks primarily take direct user input, for example through a joystick, that directly controls the robot's actions. However, indirect input, such as eye gaze, can be a useful source of information for revealing user intentions and future actions. For example, when people perform manipulation tasks, their gaze centers on the objects of interest before the corresponding movements even begin. This implicit information contained in eye gaze can be used to improve the goal prediction of a shared autonomy system, improving its overall assistive capability. In this paper, we describe how eye gaze behavior can be incorporated into shared autonomy. Building on previous work that represents user goals as latent states in a POMDP, we describe how gaze behavior can be used as observations to update the POMDP's probability distributions over goal states, solving for the optimal action using hindsight optimization. We detail a pilot implementation that uses a head-mounted eye tracker to collect eye gaze data.

There's a concept in artificial intelligence called "the singularity." It refers to the idea that AI will one day be able to reproduce and improve upon itself at increasingly rapid speeds, resulting in a computerized brain exponentially more powerful than human intelligence, capable of transforming civilization as we know it. Some scholars are confident the singularity is only a matter of time. Others say it's pure science fiction. For the time being, let's leave the issue to the Ph.D.s and focus on a few simpler questions.

Boston Dynamics is letting its first major robot out of the lab. Since June, the company has been talking about a public release for its Spot robot (formerly SpotMini), and today, it finally gave some details about what's in store. The Spot isn't going on sale exactly, but if you're a company with a good idea (and some money), you'll be able to get one. That also means, for the average person on the street, that the odds of seeing a Spot in the wild just got a lot better. The capabilities are more or less what the company showed off in June, but it's still impressive to see them in person.

Imagine standing in an elevator as the doors begin to close and suddenly seeing a couple at the end of the corridor running toward you. Even before they call out, you know from their pace and body language they are rushing to get the same elevator. Being a charitable person, you put your hand out to hold the doors. In that split second you interpreted other people's intent and took action to assist; these are instinctive behaviors that designers of artificially intelligent machines can only envy. But that could eventually change as researchers experiment with ways to create artificial intelligence (AI) with predictive social skills that will help it better interact with people.

The cold, steely arm of Fernando the Barista swirled the foam of my matcha latte, set it down gently and waved goodbye from inside a glass case. Where you can get robot pizza and robot salad, and now, a robot matcha. There were humans inside the small coffee shop on Market Street, but only some of them ordered drinks. Some of them came in just to gawk at Fernando: The machine was sleek and white, like an Apple product, and its glass enclosure made it seem like a small animal on display. "They all have'it' pronouns," said Sam Blum, Cafe X's community manager.

As our population ages, these caregiver robots will also be useful for the old as well as the young. This is not a rhetorical question. So-called robot nannies are already a hit in Japan and China, and are now beginning to appear stateside. The numbers show why this is an attractive proposition. According to the U.S. Center for Disease Control and Prevention, approximately 4 million babies are born annually in the United States. What's more, 62% percent of women who gave birth within the last year work outside of the home, according to the U.S. Department of Labor.