Time to compile: A performance installation as human-robot interaction study examining self-evaluation and perceived control

Cuan C., Pakrasi I., Berl E., LaViers A.

Performance is a vehicle to explore and modify audience experiences. The design of expressive robotic systems shares a similar goal. Toward the end of uniting these two approaches, this paper presents a collaborative academic and artistic effort to design an experimental testbed for studying human perceptions of robots, and changes therein, through dance performance. The elements of the testbed design, which allow for multiple audience experiences inside the same live event, will be outlined. Then, one instantiation of a performance using this testbed design will be summarized. In developing this testbed and instantiation, synergistic academic and artistic goals included measuring the audience's initial perception of existing technologies and further priming the audience about these technologies through the performance. These perceptions were framed through the lenses of power, valence, and acceptability; comparisons between the Rethink Robotics Baxter, Softbank NAO, and a human performer are presented. This piece (and excerpts of it) will be used to gather audience perceptions at multiple events to bring lay audience members the experience of robotics researchers and understand how that modifies their impressions of these systems.

Heimerdinger M., LaViers A.

Affective movement will likely be an important component of robotic interaction as more and more robots move into human-facing scenarios where humans are (consciously or unconsciously) constantly monitoring the motion profile of counterparts in order to make judgments about the state of their counterpart. Many current studies in affective movement recognition and generation seek to either increase a machine’s ability to correctly identify human affect or to identify and create components of robotic movement that enhance human perception. However, very few of these studies investigate the influence of environmental context on a machine’s ability to correctly identity human affect or a human’s ability to correctly identify the affective intent of a robot. This paper presents the results of a user study that investigated how human perception of stylized walking sequences (created in [1]) varied based on the environment where they were portrayed. The results show that environment context can impact a person’s ability to correctly perceive the intended style of a movement.

Knight H., Simmons R.

Dancers are human Expressive Motion experts and could theoretically help robots communicate their state to people, e.g., rushed, confused, curious. The problem is twofold: first, dancers are trained in human-motion whereas many robots are non-anthropomorphic, and second, most dancers are not programmers. This is where the present interface is useful: the robot demos a batch of motions, in person, and the dancer, who knows expressive motion when she sees it, rates each path's success at communicating a particular state. Using an evolutionary algorithm, the interface - where feedback is recorded on the robot's screen and motion is demonstrated via the robot - calculates a new batch of motions that explore variations of the top-rated paths from the previous generation. This approach addresses the challenges of visualizing the expressive potential of non-anthropomorphic robots, while also ensuring path characteristics are reproducible via the robot's motion controller. The purpose of the interface is to help a non-expert negotiate a high-dimensional space of robot motion expression. Thus, it also has interactive functionality enabling users to freeze a feature value they like, or reset all features to begin again. To illustrate the system, this paper includes the results of two dancers designing motions for an omni-directional mobile robot, showing convergence with every generation. In reality, motion designers may have many authoring styles - exploring multiple solutions before honing in, or being satisfied easily versus getting each detail exactly right. By combining human-in-the-loop machine learning with direct authoring, we create a kinetic conversation between the robot and the dancer, and gain the ability to model knowledge from complementary fields.

Fitter N.T., Knight H., Martelaro N., Sirkin D.

In an age when machines are increasingly entering our daily lives, social robotics focuses on how robots can successfully share spaces, interface, and collaborate with people. Machines that fail to interact appropriately run the risk of becoming irritating and unwelcome; however, when personality and charm are added, functional machines can not only add value to their environment, but also engage, elicit trust, and foster bonds with their human partners. The central idea of this workshop is that even very simple robots, in terms of both sensing and degrees-of-freedom, are capable of charismatic interaction. Acting training can inform the development of such charismatic robots, but it is challenging to operationalize actor knowledge into computational systems. For example, people parse non-verbal communications intuitively, even from machines that do not look like people, and acting training contains explicit methodology for exploring the space of motion-based expression. Robotics researchers can gain insight on how to create interfaces that adapt the knowledge of human charisma experts -- such as actors and performers -- into robotics, developing robot social behaviors with humans in the loop. This workshop will be a forum for discussing minimal social robots and prototyping new ones. The program includes presentations exploring the social role of simple sensors and behaviors, a hands-on activity, and motivating talks from experts in the field. Accepted applicants will be invited to share their perspectives on minimal social robots during highlight talks, discussions, and a poster session. During the workshop, participants will work in small groups to craft an illustrative interaction for a minimalist robot whose communications they have designed. There will also be ample opportunities for early researchers to connect with experts in this field. A public website will provide an archive of accepted submissions and minimal social robot interaction videos in order to share the output of the workshop with the larger community.

Jochum E., Vlachos E., Christoffersen A., Nielsen S.G., Hameed I.A., Tan Z.

This paper describes an innovative approach for studying interaction between humans and care robots. Using live theatrical performance, we developed a play that depicts a plausible, future care scenario between a human and a socially assistive robot. We used an expanded version of the Godspeed Questionnaire to measure the audiences’ reactions to the robot, the observed interactions between the human and the robot, and their overall reactions to the performance. We present our results and propose a methodology and guidelines for using applied theatre as a platform to study human robot interaction (HRI). Unlike other HRI studies, the subject of our research is not the user who interacts with the robot but rather the audiences observing the HRI. We consider the technical and artistic challenges of designing and staging a believable care scenario that could potentially influence the perception and acceptance of care robots. This study marks a first step towards designing a robust framework for combining applied theatre with HRI research.

Dijkstra P., Barelds D.P., van Brummen-Girigori O.

The present study examined young women’s weight-influenced self-esteem (WISE) in response to imagined weight gain and weight loss, and its relations to body satisfaction, body comparisons and global self-esteem. Young women from two different regions, that is, from the north of The Netherlands (n = 157) and from the Willemstad area (the capital of Curacao; n = 162), completed a questionnaire. It was expected that Dutch women would show lower self-esteem in response to imagined weight gain than women from Curacao, and that self-esteem in response to imagined weight gain would be negatively related to general self-esteem and body satisfaction, and more so among Dutch women than among Curacaoan women. Finally, it was expected that body comparisons would be predictive of lower self-esteem in response to imagined weight gain. As expected Dutch women showed lower self-esteem in response to imagined weight gain than Curacaoan women. Moreover, findings showed that among Curacaoan women self-esteem in response to imagined weight gain was not related to general self-esteem or body satisfaction and that body comparisons were less predictive of lowered self-esteem in response to imagined weight gain than among Dutch women. Findings are discussed in light of cultural differences in ideal body shape and the supportiveness of women’s social networks.

Slowinski P., Rooke E., Di Bernardo M., Tanaseva-Atanasova K.

Knight H., Simmons R.

There is a saying that 95% of communication is body language, but few robot systems today make effective use of that ubiquitous channel. Motion is an essential area of social communication that will enable robots and people to collaborate naturally, develop rapport, and seamlessly share environments. The proposed work presents a principled set of motion features based on the Laban Effort system, a widespread and extensively tested acting ontology for the dynamics of “how” we enact motion. The features allow us to analyze and, in future work, generate expressive motion using position (x, y) and orientation (theta). We formulate representative features for each Effort and parameterize them on expressive motion sample trajectories collected from experts in robotics and theater. We then produce classifiers for different “manners” of moving and assess the quality of results by comparing them to the humans labeling the same set of paths on Amazon Mechanical Turk. Results indicate that the machine analysis (41.7% match between intended and classified manner) achieves similar accuracy overall compared to a human benchmark (41.2% match). We conclude that these motion features perform well for analyzing expression in low degree of freedom systems and could be used to help design more effectively expressive mobile robots.

Flemisch T., Viergutz A., Dachselt R.

This demonstration on the Nao robot uses the selection of behavior based on a feedback type and an expressivity value to generate and execute appropriate feedback. It aims to ease the authoring process by using variable gestures.

Keller A.C., Meier L.L., Gross S., Semmer N.K.

High self-esteem often predicts job-related outcomes, such as high job satisfaction or high status. Theoretically, high quality jobs (HQJs) should be important for self-esteem, as they enable people to use a variety of skills and attribute accomplishments to themselves, but research findings are mixed. We expected reciprocal relationships between self-esteem and HQJ. However, as work often is more important for the status of men, we expected HQJ to have a stronger influence on self-esteem for men as compared to women. Conversely, task-related achievements violate gender stereotypes for women, who may need high self-esteem to obtain HQJs. In a 4-year cross-lagged panel analysis with 325 young workers, self-esteem predicted HQJ; the lagged effect from HQJ on self-esteem was marginally significant. In line with the hypotheses, the multigroup model showed a significant path only from self-esteem to HQJ for women, and from HQJ to self-esteem for men. The reverse effect was not found for women, and only marginally significant for men. Overall, although there were some indications for reciprocal effects, our findings suggest that women need high self-esteem to obtain HQJs to a greater degree than men, and that men base their self-esteem on HQJs to a greater extent than women.

Lindgren R., Johnson-Glenberg M.

The authors describe an emerging paradigm of educational research that pairs theories of embodied learning with a class of immersive technologies referred to as mixed reality (MR). MR environments merge the digital with the physical, where, for example, students can use their bodies to simulate an orbit around a virtual planet. Recent research supports the idea that body activity can be an important catalyst for generating learning, and new technologies are being developed that use natural human physicality and gesture as input. However, existing research on embodied learning technologies has been disparate, driven largely by specific technical innovations and constraints, and often lacking a clear focus on establishing their efficacy in educational contexts. On the basis of the unique characteristics of these technologies and on their own experiences conducting research in this area, the authors put forth six precepts for embodied learning technology researchers that pertain to the rationale, design, and execution of empirical studies.

Sprecher S., Brooks J.E., Avogo W.

The major purpose of this study was to examine the joint effects of race and gender on the self-esteem of young adults. Data came from a large sample of undergraduate students (N = 7,552; 2,785 men and 4,767 women) enrolled at a Midwestern U.S. University over the period 1990–2012. Consistent with prior research, we found that men had higher self-esteem than women and that Blacks had higher self-esteem than Whites, Hispanics, and Asians. The analyses, however, revealed that the gender differences in self-esteem were not found among Blacks and that the higher self-esteem of Blacks relative to other races was greater among women than among men. The effects of race and gender did not change controlling for social class and other demographic variables, did not differ across domains of self-esteem, and were not affected by period of time. This study deepens our knowledge of social group differences in self-esteem, providing evidence that the higher self-esteem of men (relative to women) and of Blacks (relative to other races) persisted across the past two decades.

Kontra C., Goldin-Meadow S., Beilock S.L.

EYSSEL F., HEGEL F.

Previous research on gender effects in robots has largely ignored the role of facial cues. We fill this gap in the literature by experimentally investigating the effects of facial gender cues on stereotypical trait and application ascriptions to robots. As predicted, the short-haired male robot was perceived as more agentic than was the long-haired female robot, whereas the female robot was perceived as more communal than was the male counterpart. Analogously, stereotypically male tasks were perceived more suitable for the male robot, relative to the female robot, and vice versa. Taken together, our findings demonstrate that gender stereotypes, which typically bias social perceptions of humans, are even applied to robots. Implications for design-related decisions are discussed. jasp_937 2213..2230 Imagine the following scenario that takes place several decades in the future: By then, both authors of this work might be senior citizens, and the same might hold true for our readers. In spite of grieving lost youth, however, imagine that each senior citizen of this future society would be equipped with a personal robot assistant that would take care of everyday life chores, such as personal care, household maintenance, and other conveniences for you. Your personal robot assistant would facilitate everyday life by being able to support you in any possible way. What could your robot assistant look like, and why did designers opt for this particular appearance? Would your companion’s look affect your perceptions of its “personality” and capabilities? The present research focuses on exactly these questions, as we address the issues of design choices in robots and their consequences for the perception of those robots. It is clear that, to date, the scenario outlined here has not yet been fully realized. Nevertheless, taking into account the interdisciplinary effort of international scientists in social robotics, engineering, computer sciences, psychology, and related fields, such a vision will sooner or later become

Miller S., van den Berg J., Fritz M., Darrell T., Goldberg K., Abbeel P.

We consider the problem of autonomous robotic laundry folding, and propose a solution to the perception and manipulation challenges inherent to the task. At the core of our approach is a quasi-static cloth model which allows us to neglect the complex dynamics of cloth under significant parts of the state space, allowing us to reason instead in terms of simple geometry. We present an algorithm which, given a 2D cloth polygon and a desired sequence of folds, outputs a motion plan for executing the corresponding manipulations, deemed g-folds, on a minimal number of robot grippers. We define parametrized fold sequences for four clothing categories: towels, pants, short-sleeved shirts, and long-sleeved shirts, each represented as polygons. We then devise a model-based optimization approach for visually inferring the class and pose of a spread-out or folded clothing article from a single image, such that the resulting polygon provides a parse suitable for these folding primitives. We test the manipulation and perception tasks individually, and combine them to implement an autonomous folding system on the Willow Garage PR2. This enables the PR2 to identify a clothing article spread out on a table, execute the computed folding sequence, and visually track its progress over successive folds.

Cuan C., Fisher E., Okamura A., Engbersen T.

As robots enter everyday spaces like offices, the sounds they create affect how they are perceived. We present “Music Mode,” a novel mapping between a robot’s joint motions and sounds, programmed by artists and engineers to make the robot generate music as it moves. Two experiments were designed to characterize the effect of this musical augmentation on human users. In the first experiment, a robot performed three tasks while playing three different sound mappings. Results showed that participants observing the robot perceived it as more safe, animate, intelligent, anthropomorphic, and likable when playing the Music Mode Orchestra software. To test whether the results of the first experiment were due to the Music Mode algorithm, rather than music alone, we conducted a second experiment. Here, the robot performed the same three tasks, while a participant observed via video, but the Orchestra music was either linked to its movement or random. Participants rated the robots as more intelligent when the music was linked to the movement. Robots using Music Mode logged approximately 200 hours of operation while navigating, wiping tables, and sorting trash, and bystander comments made during this operating time served as an embedded case study. This article has both designerly contributions and engineering contributions. The contributions are as follows: (1) an interdisciplinary choreographic, musical, and coding design process to develop a real-world robot sound feature, (2) a technical implementation for movement-based sound generation, and (3) two experiments and an embedded case study of robots running this feature during daily work activities that resulted in increased likeability and perceived intelligence of the robot.

Brill D., Schnugg C., Stary C.

Mullis E.

Informed by scholarship in dance studies, this essay examines the popular phenomenon of the dancing robot. It begins with an analysis of social robotics experiments that use techniques of contemporary experimental theater to frame human–robot interactions. With elements of theater history in mind, it becomes evident that such experimental designs fruitfully destabilize common understandings of social robots, theatrical performance, and dance movement. This sets up a discussion of a co-creative approach to developing robot choreography which utilizes compositional techniques from experimental dance to, among other things, avoid cultural appropriation. Taken together, these points show that, because dance movement is culturally laden, scholarship in dance studies should be considered when designing dancing robots.

Brill D., Schnugg C., Stary C., Rayzhekov A.

Mendoza Y.L., Duarte E.F., de Queiroz M.J., Baranauskas M.C.

Literature in the field of human–computer interaction (HCI) has shown a long tradition of evaluation methods for and along with interactive systems design. We have experienced in the last years an impressive development in ubiquitous and pervasive systems, motivated by technological development, low cost of sensors and actuators, and a rise in the maker culture for the construction of computational systems. While such systems naturally inherit methods for evaluating the user interaction from previous interaction paradigms, it is not clear whether they reach specificities of the interaction of people within ubiquitous and pervasive systems scenarios. This work aimed at shedding light on this subject by conducting a systematic literature review on ubiquitous and pervasive technology scenarios of interactive installations. Results have shown that most of the selected contributions use classical methods of data collection and analysis, and combinations of these methods. Analysis of results also points out some new aspects to be considered in evaluation methods, regarding the human (social) actions promoted or afforded by ubiquitous and pervasive systems.

Singh A., Tholia S.

For humans, Artificial Intelligence operates more like a Rorschach test, as it is expected that intelligent machines will reflect humans' cognitive and physical behaviours. The concept of intelligence, however, is often confused with consciousness, and it is believed that the progress of intelligent machines will eventually result in them becoming conscious in the future. Nevertheless, what is overlooked is how the exploration of Artificial Intelligence also pertains to the development of human consciousness. An excellent example of this can be seen in the film Being John Malkovich (1999). In the film, different characters have their perceptions altered as a result of hacking into the mind of John Malkovich, which produces sensations that may have remained hidden to their consciousness due to their dis-abilities. This article engages with the research question: Can the symbiotic relationship between humans and machines trigger an artificial consciousness for humans? An artificially created consciousness is the premise that a machine can generate knowledge about an individual that is not already present in the person. For the same purpose, the article takes the cinematic text Being John Malkovich by Spike Jonze for exploring concepts such as human/robot rights, virtual sex, virtual rape, and bodily disability, which are essential topics in the midst of increasing human- Artificial Intelligence interaction. The purpose of this article is to contribute towards the creation of a better understanding of Artificial Intelligence, particularly from the perspective of film studies and philosophy, by highlighting the potential of Artificial Intelligence as a vessel for exploring human consciousness.

Cuan C.

What does it feel like to dance with a robot? How do you choreograph one? Working with robots during three artistic residencies and two research projects has raised questions about agency and generative processes, revealing how dancing with robots may provoke a more interanimate everyday world.

Ladenheim K., LaViers A.

Representations of gender in new technologies like the Siri, Pepper, and Sophia robotic assistants, as well as the commodification of features associated with gender on platforms like Instagram, inspire questions about how and whether robotic tools can have gender and what it means to people if they do. One possible response to this is through artistic creation of dance performance. This paper reports on one such project where, along the route to this inquiry, creation of machine augmentation – of both the performer and audience member – was necessary to communicate the artistic ideas grappled with therein. Thus, this article describes the presentation of Babyface, a machine-augmented, participatory contemporary dance performance. This work is a reaction to feminized tropes in popular media and modern technology, and establishes a parallel between the ways that women and machines are talked about, treated, and – in the case of machines – designed to look and behave. This paper extends prior reports on the creation of this piece and its accompanying devices to describe extensions with audience member participation, and reflect on the responses of these audience members. These fabricated elements alongside the actions of the performer and a soundscape that quotes statements made by real “female” robots create an otherwordly, sad cyborg character that causes viewers to question their assumptions about and pressures on the feminine ideal.

Cuan C., Hoffswell J., LaViers A.

Anxiety about automation of large classes of jobs creates an area of research around how to evolve the workforce in parallel to advances in robotic technology. Gaining meaningful experience with robots, such as studying them in school, is not an option for every American, leaving media and stories to fill the void. This paper first presents analysis of popular narratives about robots, finding largely negative and violent depictions in popular movies. Then, the paper reports on an initial experiment with human participants on existing attitudes about robots and how those may change with meaningful, non-narrative exposure to these machines. A pilot study with 12 participants was designed and deployed in a targeted community. Initial findings, along with directions for future work, are discussed. The accessible, exhibit-like design of this work, may be a scalable framework that can make it possible for more people to gain real-life experiences with robots.