Alle Publikationen
- <<
- <
- 1
2018
-
(2018): Design for social accessibility: Incorporating social factors in the design of accessible technologies. ProQuest Information & Learning.
Abstract: Assistive technologies are intended to help people with disabilities accomplish everyday tasks. Yet, such technologies are traditionally designed mainly with functionality in mind, not with consideration for social situations of use. As a result, assistive technologies can be awkward-looking and socially awkward to use, leading to misperceptions about these technologies and their users. These misperceptions can impact users’ sense of self-efficacy and self-confidence, leading assistive technology users to feel self-conscious when using devices in public or social settings, ultimately limiting access. Furthermore, most technology design approaches either assume accessibility is ’someone else’s job’ or that functional accessibility is the only focus, promoting an inclination to overlook accessibility in design overall and preventing designers from fully considering social aspects of accessibility. In this dissertation, I present original empirical studies that investigate the social implications of assistive technology use. I conceptualize ’socially accessible design,’ and examine how to effectively incorporate social factors into user-centered design techniques. To address the negative and stigmatizing social perceptions associated with assistive technologies, I define Social Accessibility as a new property of accessible technologies extending our understanding of accessibility to include considerations of both functional usability and social situations of use. I present Design for Social Accessibility as a guiding perspective and a set of design tools and techniques emphasizing social factors in technology design. Through a series of design workshops, I demonstrate how designers can use Design for Social Accessibility by: focusing on functional usability and social situations of use; increasing awareness for how design can engender, rather than impede, access for people with visual impairments, particularly within social contexts; and working with users with and without visual impairments in assessing when design influences self-confidence and self-consciousness. In this dissertation, I: (1) define social accessibility as a new property of technology artifacts that extends accessibility to include functional and social factors; (2) demonstrate that Design for Social Accessibility can help improve the design of technologies usable by people with visual impairments when applied to design methods by bringing awareness to designers about how design engenders or impedes access in functional and social factors of use; and (3) develop and verify a tool that can help designers assess the social accessibility of technology design. The contributions of this dissertation are conceptual‐-motivating the need for, and defining social accessibility and how it relates to functional accessibility; and empirical and methodological‐-showing how social factors influence assistive technology use and access, and applying findings to increase awareness, change perspectives, and improve tools and techniques for the design of socially accessible technologies. (PsycINFO Database Record (c) 2017 APA, all rights reserved)
2016
-
(2016): Roboethics: Sharing Our World with Humanlike Robots. In: IEEE Potentials 35 (1), S. 24-28. DOI: 10.1109/MPOT.2014.2364491
DOI: https://doi.org/10.1109/MPOT.2014.2364491 Abstract: Major debates surround the field of robotics, making the potential development of humanlike robots one of the most controversial facets of modern technology. This is the result of the technology’s young age. A new technology must meet a number of requirements before people will reach an agreement on it; legal, social, and global considerations must be explored before robotics applications will be accepted by society.
Keywords: Artificial intelligence, ethical aspects, Ethics, global considerations, humanlike robots, Humanoid Robots, Humanoids, human-robot interaction, ieee xplore, legal considerations, Moral & Ethik, roboethics, robotics applications, Robots, social considerations, Social factors, Social implications of technology 2008
-
(2008) : Learning polite behavior with situation models: 3rd ACM/IEEE International Conference on Human-Robot Interaction (HRI): New York, NY, US: Association for Computing Machinery, S. 209-216
DOI: https://doi.org/10.1145/1349822.1349850 Abstract: In this paper, we describe experiments with methods for learning the appropriateness of behaviors based on a model of the current social situation. We first review different approaches for social robotics, and present a new approach based on situation modeling. We then review algorithms for social learning and propose three modifications to the classical Q-Learning algorithm. We describe five experiments with progressively complex algorithms for learning the appropriateness of behaviors. The first three experiments illustrate how social factors can be used to improve learning by controlling learning rate. In the fourth experiment we demonstrate that proper credit assignment improves the effectiveness of reinforcement learning for social interaction. In our fifth experiment we show that analogy can be used to accelerate learning rates in contexts composed of many situations.
Keywords: Angemessen(heit) (von Technik), Convergence, credit assignment, Humans, ieee xplore, Learning, learning (artificial intelligence), Learning by Analogy, machine learning, polite behavior, Q-Learning, Q-learning algorithm, Reinforcement learning, Robot sensing systems, Robots, situation modeling, social aspects of automation, Social factors, social interaction, social learning, Social robotic, social situation, standards 2006
-
(2006) : Learning polite behavior with situation models: 3rd International Forum on Applied Wearable Computing 2006: Bremen, Germany: IEEE, S. 209-216
DOI: https://doi.org/10.1145/1349822.1349850 Abstract: In this paper, we describe experiments with methods for learning the appropriateness of behaviors based on a model of the current social situation. We first review different approaches for social robotics, and present a new approach based on situation modeling. We then review algorithms for social learning and propose three modifications to the classical Q-Learning algorithm. We describe five experiments with progressively complex algorithms for learning the appropriateness of behaviors. The first three experiments illustrate how social factors can be used to improve learning by controlling learning rate. In the fourth experiment we demonstrate that proper credit assignment improves the effectiveness of reinforcement learning for social interaction. In our fifth experiment we show that analogy can be used to accelerate learning rates in contexts composed of many situations.
Keywords: Convergence, credit assignment, Humans, ieee xplore, Künstliche Intelligenz, Learning, learning (artificial intelligence), Learning by Analogy, machine learning, polite behavior, Q-Learning, Q-learning algorithm, Reinforcement learning, Robot sensing systems, Robots, situation modeling, social aspects of automation, Social factors, social interaction, social learning, Social robotic, social situation, standards
- <<
- <
- 1