AI and robotics researchers aim at having robots in our environments coexisting with humans, as artificial creatures that will help humans and collaborate with humans to improve our societies. There will be more than one robot. Robots will not interact with some humans just once, or a few times, but many times. Humans will interact with robots to change their requests and to teach and correct their behaviors. This abstract briefly discusses a few issues for AI and HRI for such challenging repeated interactions in space and time between robots and humans. We have made different levels of research progress on these issues, as we discuss. Our presentation is motivated by our work with the CoBot mobile service robots, which have been running in our environments for the last three years, and for more than 500kms.

The ability to make decisions that balance conflicting needs and variable-quality inputs is a skill that is inherently human. In emergency situations, such capabilities are tested under pressure, as needs and inputs change---often rapidly---and deliberation must take place quickly or else opportunities are lost. This short paper identifies challenges faced when emergency services personnel are supported by human/multi-robot systems. Several strategies are proposed to address these challenges, with deployment geared toward emergency services agencies within the next 5-10 years.

We are looking at new ways of building algorithms for synthesizing and rendering animation in social robots that can keep them as interactive as necessary, while still following on principles and practices used by professional animators. We will be studying the animation process side by side with professional animators in order to understand how these algorithms and tools can be used by animators to achieve animation capable of correctly adapting to the environment and the artificial intelligence that controls the robot. Figure 1: Two example scenarios featuring a touch-based Robotic characters are becoming widespread as useful multimedia application, sensors, and different robots.

CoBot is a service mobile robot that has been continuously Frame: GoTo deployed for extended periods of time in a multi-floor - Parameters: destination office-style building (Biswas and Veloso 2013). While moving in the building CoBot, is able to perform multiple tasks Frame: DeliverObject for its users; the robot is able to autonomously navigate to - Parameters: object, source, destination any of the rooms in the building, to deliver objects and messages and to escort visitors to their destination. While apparently Figure 1: Semantic frames of the two task CoBot is able to very different, all the tasks CoBot is able to perform execute from spoken commands. Often, only being able to move, is not enough to accomplish the task required; if CoBot needs to deliver an object, given that it does not have arms, it cannot pick it up by itself, similarly when it needs to travel across floors it cannot push the elevator button. In order to overcome its limitation CoBot ask for help to humans, either the user or bypasser, achieving symbiotic autonomy (Rosenthal, Biswas, and Veloso 2010).

Empirical studies with humans and agents demonstrate that the nature and forms of information required by the human differ depending on the design of the relationship between the participants — a relationship that is sometimes characterised using the concept of levels of autonomy, though the usefulness of that characterisation has recently been questioned. Therefore, understanding how people work with automation and how to design automated systems to better support people, is a field long studied, but of growing importance. Our current work seeks to contribute to the design of representations and algorithms that can be deployed in such contexts.

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.

Over the last five years, and while developing an architecture for autonomous service robots in human environments, we have identified several key decisional issues that are to be tackled for a cognitive robot to share space and tasks with a human. We introduce some of them here: situation assessment and mutual modelling, management and exploitation of each agent (human and robot) knowledge in separate cognitive models, natural multi-modal communication, "human-aware" task planning, and human and robot interleaved plan achievement. As a general "take home" message, it appears that explicit knowledge management, both symbolic and geometric, proves to be a successful key while attempting to address these challenges, as it pushes for a different, more semantic way to address the decision-making issue in human-robot interactions.

As human-robot teamwork becomes increasingly common, a key challenge is to fluidly and intuitively coordinate team members' interactions. In this work, we explore two modalities of human-robot coordination: active, where agents intentionally attempt to understand and influence the plans of human teammates, and passive, where agents simply react to their human teammates' varying behavior. In our Productivity and Wellness Pal (PaWPal) project, we seek to develop an agent that actively elicits a teammate's constraints, preferences, and goals in order to nudge them towards better behavior. Conversely, in our Coordinating Human-Robot Teamwork project, we take a distributed approach to scheduling where agents passively adapt to teammates' plan executions. Our research hypothesis is that human-robot coordination Figure 1: Screenshots from our ESM study, conducted using techniques will lead to more natural and effective PACO on Android (http://www.pacoapp.com/).

The lure of understanding biological intelligence has long occupied researchers. Success has always been measured in peer review, number of citations, or how influential some piece of work is in inspiring the next generation of re- searchers. What human-robot interaction (HRI) and artificial intelligence (AI) promises is a metric of believability that is not intrinsic to the values of the researcher or community of practice but to the utility and successful function of the robotic artifact within a larger society. This paper is a reflec- tion and response to the hypothesis that HRI is a pure, funda- mental art of artificial intelligence and the last great successor to a domain fraught with the trappings of an art that lost its way.

This paper presents an experiment investigating what type of progress feedback users prefer in verbal updates by a robot about remotely performed tasks. Of primary concern is that users find the information presented useful. But as users in their home may be engaged in other activities while they wait for a service, it is also important that information is presented in a way and at a frequency that they do not find distracting or disruptive. We explore these issues through a human-robot interaction experiment involving a simulated food delivery service. We also discuss future research directions that involve giving naive users more input into the planning process.