United States

This paper proposes a street-style study method to conduct human-robot interaction studies in-the-wild where the robots conduct their own experiments by recruiting their audience, conducting the study and gathering data. This street-style study method was implemented using multi-robot comedy as the platform deployed at an arts and technology festival to validate the concept. Twelve robot comedy shows occurred over seven hours with two robots on stage, who queried the audience during and at the end of each show. The multi-robot aspect enabled the robots to act out interactions relative each other, oneself and the audience. The final street-style study method evolved from pilots at a local farmer’s market, with hardware designed for portability and easy replication. The robots conducted their own human experiments in that they queried the audience after displaying experimentally balanced episodes of relational humor, with permutations of who was the `butt of the joke.&#39; Our study results explore the relational humor of the two robots and the audience, asking the audience to agree or disagree with particular perspectives. Delivered as part of the show, the robots invite the audience to vote via a show of hands. ANOVA analyses of the percent-agreement results find that (1) audiences were generally positive about all aspects of the show unless both robots were being negative, and (2) audiences were more ready to protect the robot comedian&#39;s ego than their own, strongly supporting the statement that the robot was doing a good job.

IEEE RO-MAN 2021

Augmented Reality interface to verify Robot Learning

entertainment robots

robot comedy

human robot interaction

social robots

RO-MAN 2021's theme is trustworthiness and cooperation. We chose this term well before the pandemic put the world on edge and added a new reason for us to question our own personal safety when in the company of others. But what about in the company of social robots? What would cause us to trust, or not trust, them? How do we as researchers create that feeling, that critical component of any relationship? With social robots, it is of course largely in our power to design the physical form, the control code and the interface software to maximize trustworthiness, facilitate cooperation and enhance the quality of human-robot interaction. This theme also touches upon people's expectations and perceptions of robots, as well as other social, cognitive and cultural factors that will influence human-robot interactions. We will have a special session/track on this topic, invite targeted submissions and include plenary speakers who are specialist in this area. We sincerely hope that this focus will help enlighten the design-thinking of all of us as we fabricate and program our own various systems.

To access RO-MAN Virtual 2021, [please register here.](https://ro-man2021.org/registration/)

RO-MAN 2021's theme is trustworthiness and cooperation. We chose this term well before the pandemic put the world on edge and added a new reason for us to question our own personal safety when in the company of others. But what about in the company of social robots? What would cause us to trust, or not trust, them? How do we as researchers create that feeling, that critical component of any relationship? With social robots, it is of course largely in our power to design the physical form, the control code and the interface software to maximize trustworthiness, facilitate cooperation and enhance the quality of human-robot interaction. 

This paper proposes a street-style study method to conduct human-robot interaction studies in-the-wild where the robots conduct their own experiments by recruiting their audience, conducting the study and gathering data. This street-style study method was implemented using multi-robot comedy as the platform deployed at an arts and technology festival to validate the concept. Twelve robot comedy shows occurred over seven hours with two robots on stage, who queried the audience during and at the end of each show. The multi-robot aspect enabled the robots to act out interactions relative each other, oneself and the audience. The final street-style study method evolved from pilots at a local farmer’s market, with hardware designed for portability and easy replication. The robots conducted their own human experiments in that they queried the audience after displaying experimentally balanced episodes of relational humor, with permutations of who was the `butt of the joke.' Our study results explore the relational humor of the two robots and the audience, asking the audience to agree or disagree with particular perspectives. Delivered as part of the show, the robots invite the audience to vote via a show of hands. ANOVA analyses of the percent-agreement results find that (1) audiences were generally positive about all aspects of the show unless both robots were being negative, and (2) audiences were more ready to protect the robot comedian's ego than their own, strongly supporting the statement that the robot was doing a good job.

technical paper

This work presents our efforts to enhance the adoption of Robotics in the TV & Film Industry. Specifically, through our efforts in developing the IoT-enabled Robotic Camera Dolly (IRCD), The Pre & Post Interview Protocol, and reporting on the reaction and perception of the TV production and filming crew.

On the Expressivity of a Parametric Humanoid Emotion Model

While VR is a useful evaluation tool for HRI, it has been concerned that the human behavior may differ between VR and real environments due to the differences in cognitive characteristics. We investigated the differences of human behavior in real and VR condition for searching of hidden objects and precious manipulation. We found that precious manipulation task requires longer time in VR condition, and subjects tend to change their head posture during object search and manipulation. We also discuss the feasibility to use the findings in robot competitions.

A Two-Layered Approach to Adaptive Dialogues for Robotic Assistance

In this paper, we introduce BabyNet, a light-weight (in
terms of trainable parameters) network structure to recognize
infant reaching action from off-body stationary cameras. We
develop an annotated dataset that includes diverse reaches
performed while in a sitting posture by different infants in
unconstrained environments (e.g., in home settings, etc.). 
BabyNet can attain solid performance in terms of (average)
testing accuracy that exceeds that of other larger networks,
and can hence serve as a light-weight data-driven framework
for video-based infant reaching action recognition.

BabyNet: A Lightweight Network for Infant Reaching Action Recognition in Unconstrained Enviroments to Support Future Pediatric Rehabilitation Applications

Novel framework to create legible movements in multi-party interactions

Human robot skill transfer systems for mobile robot based on multi sensor fusion

We present Cozmo behaviors that could function as the action space of a future robot learning strategy, evaluated via an online video-based study with N = 113 participants. Participants' ratings generally match the intended valence and energy level, and valence strongly affects interaction appeal, trustworthiness, and safety. Facial expression and loudness acted as important covariates, which may help generalize these results to other behaviors and robots. These results can benefit those who are interested in robot emotional expression and assistive robots.

Designing and Validating Expressive Cozmo Behaviors for Accurately Conveying Emotions

This study proposes a novel measurement of the perceived assertiveness of a robot using both objective assessment of a person’s compliance to a robot’s suggestions in a math quiz task and subjective assessments of a person’s perception and expectation of a robot in different hypothetical scenarios. The proposed measurement evaluates perceived assertiveness of a robot in three dimensions
inspired by social behavioral studies on human-human interaction, namely social assertiveness, directiveness, and independence.


Benchmarks for evaluating human-robot interaction: Lessons learned from human-animal interactions

Making an agent’s intentions clear from its observed behavior is crucial for seamless human-agent interaction and for increased transparency and trust in AI systems. Existing methods that address this challenge and maximize legibility of
behaviors are limited to deterministic domains. We develop a technique for maximizing legibility in stochastic environments and illustrate that using legibility as an objective improves interpretability of agent behavior in several scenarios. We provide initial empirical evidence that human subjects can better interpret legible behavior.

A Virtual Reality-Based Framework for Enhancing Walking Abilities Using Exoskeleton

This research proposed a remote conversation assisting system for those unbalanced condition by utilizing both physical and virtual aspects of sharing the nonverbal behavior of remote-paticipating interlocutor.
The proposed system is constructed with a rotatable screen which project the life-size avatar of remote interlocutor where the rotation of the screen alternate as body posture and projected avatar show the gesture.

A General Methodology for Teaching Norms to Social Robots

In this study, we aim to verify whether expanding a robot's embodiment influences the ease of inducing behavioral changes in passersby. We conducted a field experiment in a real shop using robots with various embodiments. The results show that expanding the robot's embodiment induces behavioral changes to the desired action, such as stopping in front of the robot and disinfecting their hands. These results indicate that expanding the robot's embodiment was an important factor in inducing behavioral changes in passersby.

Behavioral Changes in Passersby by Expanding Embodiment of a Calling Robot

With more social robots entering different industries such as educational systems, health-care facilities, and even airports, it is important to tackle problems that may hinder high quality interactions in a wild setting including group conversations. This paper presents an autonomous group conversational role coordinator system based on the proxemics of participants in the group with the robot including their distances and orientations. The system accordingly assigns to the group participants around the robot three different statuses: active, bystander, and overhearer. Once the statuses are estimated, the robot autonomously adjusts its gaze pattern in order to adapt to the group dynamics and attributes its attention in relation to the role the member in the group is playing. This system was evaluated through a pilot study (N=16), in which two participants at a time played a trivia game with the robot and had different roles to play within the interaction. The primary results imply that the participants interacting with a robot having this adaptive gaze behavior based on conversational role coordination are more likely to stand closer to the robot. In addition, the robot was perceived as more adaptable, sociable, and socially present as well as more likely to make the participants feel more attended to.

Premium content

Downloads

Next from IEEE RO-MAN 2021

On the Expressivity of a Parametric Humanoid Emotion Model

Similar lecture

Conditional Generative Adversarial Network for Generating Communicative Robot Gestures