Children with complex health conditions require care from a large, diverse set of caregivers that includes parents and community support organizations as well as multiple types of medical professionals. Coordination of their care is essential for good outcomes, and  extensive  research has shown that the use of integrated, team-based care plans improves care coordination. Care plans, however, are rarely deployed in practice. This paper describes barriers to effective implementation of care plans in complex care revealed by a study of care providers treating such children. It draws on teamwork theories, identifying ways AI capabilities could enhance care plan use; describes the design of GoalKeeper, a system to support providers use of care plans; and describes  initial work toward information sharing algorithms for such systems.

The tight long-run fit of the learning curve has led to its use as a tool to predict the future cost of solar panels. Nemet (2006) is skeptical of the view that learning has been an important driver of cost reduction, and uses data during 1975-2002 to show that increases in plant size has been the most important driver of reduction in cost per watt.

As astronauts move deeper into space they must also become more autonomous from mission control on Earth. As a result, astronauts must take on additional responsibilities for jobs typically performed by flight controllers today, and crew workload and training requirements are expected to increase. Robotic automation has potential to reduce crew workload and training needs. Additionally robots with some level of autonomy can reduce human risk by per-forming hazardous tasks that crew would otherwise have to perform. We are working with NASA to investigate new concepts of operation for astronauts interacting with autonomous robots in space, including remote supervision of a planetary robot by an astronaut orbiting the planet and remote understanding of robotic activities without eyes-on monitoring. We also are developing techniques for computing and analyzing agent performance for the roles and responsibilities needed for these ConOps, and have developed software to compute these performance measures for humans and robots in-line during mission operations. We describe results of using this software to monitor rover performance during multiple NASA robotic field tests and analog mission simulations.

Vocalics is the study of the nonverbal aspects of speech, such as volume, pitch, and rate. Our contribution is a parametric We present an overview of the control, recognition, decision-making, vocalic behavior controller that autonomously adjusts and learning techniques utilized by the Interaction the robot speaker volume based on models of how a Lab (robotics.usc.edu/interaction) at the University human user will hear speech produced by the robot. These of Southern California (USC) to enable autonomy in sociable models vary with distance, orientation, and perceived environmental and socially assistive robots. These techniques are implemented interference (Mead & Matarić 2014). Our future with two software libraries: 1) the Social Behavior work will investigate adapting the pitch and rate of speech Library (SBL) provides autonomous social behavior produced by a robot to improve user speech perception.

This paper describes our ongoing research effort to explore how personality types factor into HRI; in particular, the degree of patience a person has when teaching an error-prone robot in a learning from demonstration setting.Our goal is to establish personality metrics that will ultimately allow for the design of algorithms that automatically tune robot behavior to best suit user preferences based on personality.

Engagement is a key factor in every social interaction, be it between humans or humans and robots. Many studies were aimed at designing robot behavior in order to sustain human engagement. Infants and children, however, learn how to engage their caregivers to receive more attention.We used a social robot platform, DragonBot, that learned which of its social behaviors retained human engagement. This was achieved by implementing a reinforcement learning algorithm, wherein the reward is the proximity and number of people near the robot. The experiment was run in the World Science Festival in New York, where hundreds of people interacted with the robot. After more than two continuous hours of interaction, the robot learned by itself that making a sad face was the most rewarding expression. Further analysis showed that after a sad face, people's engagement rose for thirty seconds. In other words, the robot learned by itself in two hours that almost no-one leaves a sad DragonBot.

For robots to effectively interact with human users, it is necessary that they recognize what people in the environment are doing. This is especially the case when robots are performing complementary tasks since the human users are not following any specific process. There is much uncertainty in how people act and the duration of time they need to perform their actions. In this work, we discuss the use of topic models for such plan and activity recognition tasks. We begin with the development of a domain-independent representation of human postural information obtained from RGB-D sensor data. This representation may be used with Latent Dirichlet Allocation (LDA) topic models as an integration of plan and activity recognition. This is followed by a proposition of extensions to LDA that allow temporal and object relational information to also be used in plan and activity recognition tasks.

Adaptation is a critical component of collaboration. Nevertheless, online learning is not yet used in most successful human-robot interactions, especially when the human's and robot's goals are not fully aligned. There are at least two barriers to the successful application of online learning in HRI. First, typical machine-learning algorithms do not learn at time scales that support effective interactions with people. Algorithms that learn at sufficiently fast time scales often produce myopic strategies that do not lead to good long-term collaborations. Second, random exploration, a core component of most online-learning algorithms, can be problematic for developing collaborative relationships with a human partner. We anticipate that a new genre of online-learning algorithms can overcome these two barriers when paired with (cheap-talk) communication. In this paper, we overview our efforts in these two areas to produce a situation-independent, learning system that quickly learns to collaborate with a human partner.

In order to successfully interact with multiple humans in social situations, an intelligent robot should have the ability to track multi-humans, and understand their motion intentions. We formalize this problem as a hidden Markov model, and estimate the posterior densities by particle filtering over sets approach. Our approach avoids directly performing observation-to-target association by defining a set as a joint state. The human identification problem is then solved in an expectation-maximization way. We evaluate the effectiveness of our approach by both benchamark test and real robot experiments.

Teamwork requires mutual trust among team members. Establishing and maintaining trust depends upon alignment of mental models, an aspect of shared awareness. We present a theory of how maintenance of model alignment is integral to fluid changes in relative control authority (i.e., adaptive autonomy) in human-robot teamwork.