Keith Evan Green

A Gesture Learning Interface for Simulated Robot Path Shaping With a Human Teacher

Recognition of human gestures is an active area of research integral for the development of intuitive human-machine interfaces for ubiquitous computing and assistive robotics. In particular, such systems are key to effective environmental designs that facilitate aging in place. Typically, gesture recognition takes the form of template matching in which the human participant is expected to emulate a choreographed motion as prescribed by the researchers. A corresponding robotic action is then a one-to-one mapping of the template classification to a library of distinct responses. In this paper, we explore a recognition scheme based on the growing neural gas (GNG) algorithm that places no initial constraints on the user to perform gestures in a specific way. Motion descriptors extracted from sequential skeletal depth data are clustered by GNG and mapped directly to a robotic response that is refined through reinforcement learning. A simple good/bad reward signal is provided by the user. This paper presents results that show that the topology-preserving quality of GNG allows generalization between gestured commands. Experimental results using an automated reward are presented that compare learning results involving single nodes versus results involving the influence of node neighborhoods. Although separability of input data influences the speed of learning convergence for a given neighborhood radius, it is shown that learning progresses toward emulation of an associative memory that maps input gesture to desired action.

Toward a "smart" nightstand prototype: an examination of nightstand table contents and preferences.

Objective: Two studies were conducted to obtain an understanding of the types of items seniors keep in their nightstands and to understand how users feel about the possibility of “smart” furniture. Background: To enable aging in place and universal design, it is vital to understand the needs of a broad range of aging individuals, especially since there is little research on nightstand usage and design. Methods: Study 1 allowed for the development of a structured inventory of nightstand use today in assisted living and rehabilitation facilities. Study 1 led to Study 2, demonstrating the need to conceptualize new ideas for smart nightstands. Feedback was obtained from intergenerational participants who could discuss their needs and preferences for a smart nightstand. Results: In Study 1, more than 150 items were recorded and categorized into 25 different groups. The authors found that participants utilized the top portion of their nightstand as opposed to the lower sections; most items were found on top of the nightstand or in the top drawer. In Study 2, the authors found that the vast majority of participants are willing to consider the use of a smart nightstand. Participants discussed key functions and design preferences, which included carefully designed storage, the ability to move the nightstand up and down, contemporary design, and interaction through voice activation. Conclusion: Existing nightstands do not meet the needs of current users. This research provides greater understanding of the existing limitations associated with nightstands. Study 2 confirmed that user-centered design and the use of technology can be used to enhance daily living. Smart furniture may play a role in promoting the health and independence of diverse user groups.

Forward kinematic model for continuum robotic surfaces

In this paper, we consider the modeling of robotic continuous “continuum” two-dimensional surfaces. We discuss the fundamental differences between such robot surfaces and traditional rigid link and continuum robots. We then introduce new kinematic models for continuum robotic surfaces. We compare the kinematic models to physical continuum surfaces and validate their performance.

An assistive robotic table for older and post-stroke adults: results from participatory design and evaluation activities with clinical staff

An inevitable new frontier for the CHI community is the development of complex, larger-scale, cyber-physical artifacts where advancements in design, computing and robotics converge. Presented here is a design exemplar: the Assistive, Robotic Table (ART), the key component of our envisioned home suite of networked, robotic furnishings for hospitals and homes, promoting wellbeing and independent living. We begin with the motivations for ART, and present our iterative, five-phase, participatory design-and-evaluation process involving clinicians at a rehabilitation hospital, focusing here on the final usability study. From our wide-ranging design-research activities, which may be characterized as research through design, we found ART to be promising but also challenging. As a design exemplar, ART offers invaluable lessons to the CHI community as it comes to design larger-scale, cyber-physical artifacts cultivating interactions across people and their surroundings that define places of social, cultural and psychological significance.

A vision of the patient room as an architectural-robotic ecosystem

Healthcare is becoming more digital and technological, but healthcare environments have not yet become embedded with digital technologies to support the most productive (physical) interaction between medical patients, clinical staff and the physical artifacts that surround and envelop them. This shortcoming is an opportunity for the architecture and robotics communities to interface with each other and the everyday users of healthcare environments. Our extended lab focused ten weeks on sketching in hardware a robotic, patient-room ecosystem we call home+ with the help of clinicians at the Roger C. Peace Rehabilitation Hospital of the Greenville Hospital System University Medical Center [GHS]. This early prototyping effort represents our vision for the larger robotic patient room, and identifies opportunities for more focused work on an Assistive Robotic Table (ART).

Group differences in preferences for a novel nightstand.

Objective: Multiple user groups (patients and employees at a rehabilitation facility, community-dwelling seniors, and university students) participated in a study that examined their preferences for the features and functions of three novel nightstand prototypes. Background: It is valuable to get input from different user groups in order to improve furniture usefulness and usability, especially furniture prevalent in clinical settings where users of all age groups are found. Methods: Feedback was obtained from different user groups in both clinical (rehabilitation facility) and nonclinical (university) settings. This was done using structured interviews to ask participants about multiple features of the novel nightstand designs. Results: There were several features that all groups preferred. There were also some distinctly opposing opinions between groups. In general, the patient group showed the most similarities to the other groups. Conclusion: This research explores differences and similarities in preferences for nightstand design across a variety of user groups. It yields ideas for improving the nightstand design to be useful for a wider group of people.

“Architectural Robotics”: An interdisciplinary course rethinking the machines we live in

We discuss disciplinary barriers which have traditionally prevented robotics from significantly impacting the built (architectural) environment we inhabit. Specifically, we describe the implementation of, and lessons learned from, a multidisciplinary graduate-level course in Architectural Robotics. The results from class interactions and projects provide insight into novel ways in which robotics expertise can be effectively leveraged in architecture. Conversely, our outcomes suggest ways in which the knowledge and perspective of architects could stimulate significant innovations in robotics.

An interactive, cyber-physical read-aloud environment: results and lessons from an evaluation activity with children and their teachers

As we come to live, work and play in an increasingly digital society, the future of interactive systems research, design, and practice will be shaped partly by larger-scale, cyber-physical systems. The cyber-physical LIT KIT enhances childrens picturebook reading, both during and after interactive read-alouds, creating a multi-media, mixed-reality experience that transforms everyday environments into an environment evocative of the picturebook being read. The room-filled audio-visual-spatial effects of the LIT KIT contextualize language and provide feedback to the participants. The LIT KIT also acts as a story-extension tool, allowing children to customize environmental effects towards interpreting picturebooks for themselves. This paper offers a scenario of the child-computer interaction afforded by the LIT KIT, elucidates the motivations for its design, and focuses on an evaluation activity and its results. Particularly for DIS researchers in the educational domain, the LIT KIT represents a design exemplar that supports childrens enjoyment of learning and meaning-making.

A networked suite of mixed-technology robotic artifacts for advancing literacy in children

Illiteracy is a global problem that impacts societal and economic growth and development, and is directly correlated with the financial success, health and overall well-being of individuals. Studies indicate that picture-book reading within a facilitated story-time setting is an important tool for language acquisition in children. We hypothesize that in an increasingly digital society, literacy can be cultivated in a robot-embedded environment that is, at once, physical, digital and evocative of the picture-book being read. Inspired by concepts of embodied interaction, our developing LIT ROOM is an intelligent, fine-tunable suite of architectural-robotic artifacts distributed at room-scale in a public library setting. Presented here are motivations for and design overview of this developing interactive artifact. Through a reconfigurable, co-adaptive learning environment, the LIT ROOM aims to augment the dialogical reading of picture-books within an engaging and exploratory space for the advancement of literacy and learning.

Ar-CHI-Tecture: architecture and interaction

The rise of ubiquitous computing leads to a natural convergence between the areas of architectural design (the design of buildings, spaces and experience of being in and moving through them) and HCI. We suggest that Architecture and CHI have much to learn from each other in terms of research and practice. This workshop will bring together these communities to explore the benefits of architecture envisioned as integral to an expanded CHI community. The workshop organizers aim to create a framework for future collaboration and identify new directions for research in this multidisciplinary field. This promises significant impacts on both interaction research and its real-world applications.