Amy Koike
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Amy Koike has a total of 18 co-authors. Here are the top co-authors by number of shared publications:
- Bilge Mutlu
Department of Computer Sciences, University of Wisconsin-Madison, Madison, Wisconsin, USA
5 shared publications - Michael Wehner
University of Wisconsin-Madison, Madison, WI, USA
2 shared publications - Sichao Song
AI Lab, CyberAgent, Shibuya, Tokyo, Japan
2 shared publications - Yuki Okafuji
CyberAgent, Tokyo, Japan
2 shared publications - Arissa J. Sato
Department of Computer Sciences, University of Wisconsin-Madison, Madison, Wisconsin, USA
1 shared publication - Bengisu Cagiltay
Media and Visual Arts, Koc University, İstanbul, Türkiye
1 shared publication
Latest Publications
- Open Access
- 16 March 2026
- Published by Association for Computing Machinery (ACM)
- p. 158-167
Elements of Robot Morphology: Supporting Designers in Robot Form Exploration
- 16 March 2026
- Published by Association for Computing Machinery (ACM)
- p. 158-167
Open AccessElements of Robot Morphology: Supporting Designers in Robot Form Exploration
- Open Access
- 16 March 2026
- Published by Association for Computing Machinery (ACM)
- p. 1140-1149
Practical Insights into Designing Context-Aware Robot Voice Parameters in the Wild
Voice is an essential modality for human-robot interaction (HRI). The way a robot sounds plays a central role in shaping how humans perceive and engage with it, influencing factors such as intelligibility, understandability, and likability. Although prior work has examined voice design, most studies occur in controlled labs, leaving uncertainty about how results translate to real-world settings. To address this gap, we conducted two naturalistic deployment studies with a guidance robot in a shopping mall: (1) in-depth interviews with six participants, and (2) an eight-day field deployment using a 3×3 design varying speech rate and volume, yielding 725 survey responses. Our results show how real-world context shapes voice perception and inform adaptive, context-aware voice design for social robots in public spaces.
- 16 March 2026
- Published by Association for Computing Machinery (ACM)
- p. 1140-1149
Open AccessPractical Insights into Designing Context-Aware Robot Voice Parameters in the Wild
Voice is an essential modality for human-robot interaction (HRI). The way a robot sounds plays a central role in shaping how humans perceive and engage with it, influencing factors such as intelligibility, understandability, and likability. Although prior work has examined voice design, most studies occur in controlled labs, leaving uncertainty about how results translate to real-world settings. To address this gap, we conducted two naturalistic deployment studies with a guidance robot in a shopping mall: (1) in-depth interviews with six participants, and (2) an eight-day field deployment using a 3×3 design varying speech rate and volume, yielding 725 survey responses. Our results show how real-world context shapes voice perception and inform adaptive, context-aware voice design for social robots in public spaces.
- Open Access
- 16 March 2026
- Published by Association for Computing Machinery (ACM)
- p. 187-195
What You Reward Is What You Learn: Comparing Rewards for Online Speech Policy Optimization in Public HRI
Designing policies that are both efficient and acceptable for conversational service robots in open and diverse environments is non-trivial. Unlike fixed, hand-tuned parameters, online learning can adapt to non-stationary conditions. In this paper, we study how to adapt a social robot’s speech policy in the wild. During a 12-day in-situ deployment with over 1,400 public encounters, we cast online policy optimization as a multi-armed bandit problem and use Thompson sampling to select among six actions defined by speech rate (slow/normal/fast) and verbosity (concise/detailed). We compare three complementary binary rewards–Ru (user rating), Rc (conversation closure), and Rt (≥2 turns)–and show that each induces distinct arm distributions and interaction behaviors. We complement the online results with offline evaluations that analyze contextual factors (e.g., crowd level, group size) using video-annotated data. Taken together, we distill ready-to-use design lessons for deploying online optimization of speech policies in real public HRI settings.
- 16 March 2026
- Published by Association for Computing Machinery (ACM)
- p. 187-195
Open AccessWhat You Reward Is What You Learn: Comparing Rewards for Online Speech Policy Optimization in Public HRI
Designing policies that are both efficient and acceptable for conversational service robots in open and diverse environments is non-trivial. Unlike fixed, hand-tuned parameters, online learning can adapt to non-stationary conditions. In this paper, we study how to adapt a social robot’s speech policy in the wild. During a 12-day in-situ deployment with over 1,400 public encounters, we cast online policy optimization as a multi-armed bandit problem and use Thompson sampling to select among six actions defined by speech rate (slow/normal/fast) and verbosity (concise/detailed). We compare three complementary binary rewards–Ru (user rating), Rc (conversation closure), and Rt (≥2 turns)–and show that each induces distinct arm distributions and interaction behaviors. We complement the online results with offline evaluations that analyze contextual factors (e.g., crowd level, group size) using video-annotated data. Taken together, we distill ready-to-use design lessons for deploying online optimization of speech policies in real public HRI settings.
- Open Access
- 13 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-3
HRI and UIST: Designing Socially Engaging Robot Interfaces
Human-Robot Interaction (HRI) is a field of study that focuses on the understanding, design, and evaluation of interactions between humans and robots. This workshop aims to bring together researchers interested in exploring the intersection of UIST and HRI. Our goal is to provide attendees with a deeper understanding of the synergies between the two research communities and to inspire better alignment between technical advancements in UIST and their application to social HRI contexts. The workshop will feature interactive demos, prototyping sessions, and discussions to explore key HRI concepts and considerations for designing robot interfaces that facilitate social interactions with humans.
- 13 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-3
Open AccessHRI and UIST: Designing Socially Engaging Robot Interfaces
Human-Robot Interaction (HRI) is a field of study that focuses on the understanding, design, and evaluation of interactions between humans and robots. This workshop aims to bring together researchers interested in exploring the intersection of UIST and HRI. Our goal is to provide attendees with a deeper understanding of the synergies between the two research communities and to inspire better alignment between technical advancements in UIST and their application to social HRI contexts. The workshop will feature interactive demos, prototyping sessions, and discussions to explore key HRI concepts and considerations for designing robot interfaces that facilitate social interactions with humans.
- Open Access
- 1 July 2024
- Published by Association for Computing Machinery (ACM)
- p. 459-475
Tangible Scenography as a Holistic Design Method for Human-Robot Interaction
Traditional approaches to human-robot interaction design typically examine robot behaviors in controlled environments and narrow tasks. These methods are impractical for designing robots that interact with diverse user groups in complex human environments. Drawing from the field of theater, we present the construct of scenes—individual environments consisting of specific people, objects, spatial arrangements, and social norms—and tangible scenography, as a holistic design approach for human-robot interactions. We created a design tool, Tangible Scenography Kit (TaSK), with physical props to aid in design brainstorming. We conducted design sessions with eight professional designers to generate exploratory designs. Designers used tangible scenography and TaSK components to create multiple scenes with specific interaction goals, characterize each scene’s social environment, and design scene-specific robot behaviors. From these sessions, we found that this method can encourage designers to think beyond a robot’s narrow capabilities and consider how they can facilitate complex social interactions.
- 1 July 2024
- Published by Association for Computing Machinery (ACM)
- p. 459-475
Open AccessTangible Scenography as a Holistic Design Method for Human-Robot Interaction
Traditional approaches to human-robot interaction design typically examine robot behaviors in controlled environments and narrow tasks. These methods are impractical for designing robots that interact with diverse user groups in complex human environments. Drawing from the field of theater, we present the construct of scenes—individual environments consisting of specific people, objects, spatial arrangements, and social norms—and tangible scenography, as a holistic design approach for human-robot interactions. We created a design tool, Tangible Scenography Kit (TaSK), with physical props to aid in design brainstorming. We conducted design sessions with eight professional designers to generate exploratory designs. Designers used tangible scenography and TaSK components to create multiple scenes with specific interaction goals, characterize each scene’s social environment, and design scene-specific robot behaviors. From these sessions, we found that this method can encourage designers to think beyond a robot’s narrow capabilities and consider how they can facilitate complex social interactions.
- Open Access
- 11 March 2024
- Published by Association for Computing Machinery (ACM)
- p. 83-84
Sprout: Demonstration of Soft Expressive Robot
We demonstrate a social robot named Sprout, which is capable of changing the shape of its body as a way of expression. The development of Sprout aims to explore the creation of novel expressions for social robots, leveraging techniques from the field of soft robotics. To create body deformation, we employ a fiber-embedded soft actuator as Sprout's body. We designed six expressions with four types of deformations. Visitors can experience Sprout being animated by its control system during our demonstration. Additionally, picture panels are incorporated to visually guide visitors through the fabrication process of Sprout, providing insight into the underlying scientific principles.
- 11 March 2024
- Published by Association for Computing Machinery (ACM)
- p. 83-84
Open AccessSprout: Demonstration of Soft Expressive Robot
We demonstrate a social robot named Sprout, which is capable of changing the shape of its body as a way of expression. The development of Sprout aims to explore the creation of novel expressions for social robots, leveraging techniques from the field of soft robotics. To create body deformation, we employ a fiber-embedded soft actuator as Sprout's body. We designed six expressions with four types of deformations. Visitors can experience Sprout being animated by its control system during our demonstration. Additionally, picture panels are incorporated to visually guide visitors through the fabrication process of Sprout, providing insight into the underlying scientific principles.
- Open Access
- 11 March 2024
- Published by Association for Computing Machinery (ACM)
- p. 403-412
Sprout: Designing Expressivity for Robots Using Fiber-Embedded Actuator
In this paper, we explore how techniques from soft robotics can help create a new form of robot expression. We present Sprout, a soft expressive robot that conveys its internal states by changing its body shape. Sprout can extend, bend, twist, and expand using fiber-embedded actuators integrated into its construction. These deformations enable Sprout to express its internal states, for example, by expanding to express anger and bending its body sideways to express curiosity. Through two user studies, we investigated how users interpreted Sprout's expressions, their perceptions of Sprout, and their expectations from future iterations of Sprout's design. We argue that the use of soft actuators opens a novel design space for robot expressions to convey internal states, emotions, and intent.
- 11 March 2024
- Published by Association for Computing Machinery (ACM)
- p. 403-412
Open AccessSprout: Designing Expressivity for Robots Using Fiber-Embedded Actuator
In this paper, we explore how techniques from soft robotics can help create a new form of robot expression. We present Sprout, a soft expressive robot that conveys its internal states by changing its body shape. Sprout can extend, bend, twist, and expand using fiber-embedded actuators integrated into its construction. These deformations enable Sprout to express its internal states, for example, by expanding to express anger and bending its body sideways to express curiosity. Through two user studies, we investigated how users interpreted Sprout's expressions, their perceptions of Sprout, and their expectations from future iterations of Sprout's design. We argue that the use of soft actuators opens a novel design space for robot expressions to convey internal states, emotions, and intent.
- Open Access
- 10 July 2023
- Published by Association for Computing Machinery (ACM)
- p. 2689-2706
Exploring the Design Space of Extra-Linguistic Expression for Robots
- 10 July 2023
- Published by Association for Computing Machinery (ACM)
- p. 2689-2706
Open AccessExploring the Design Space of Extra-Linguistic Expression for Robots
- Open Access
Sonovortex: Aerial Haptic Layer Rendering by Aerodynamic Vortex and Focused Ultrasound
In this paper, a method of rendering aerial haptics that uses an aerodynamic vortex and focused ultrasound is presented. Significant research has been conducted on haptic applications based on multiple phenomena such as magnetic and electric fields, focused ultrasound, and laser plasma. By combining multiple physical quantities; the resolution, distance, and magnitude of force are enhanced. To combine multiple tactile technologies, basic experiments on resolution and discrimination threshold are required. Separate user studies were conducted using aerodynamic and ultrasonic haptics. Moreover, the perception of their superposition, in addition to their resolution, was tested. Although these fields cause no direct interference, the system enables the simultaneous perception of the tactile feedback of both stimuli. The results of this study are expected to contribute to expanding the expression of aerial haptic displays based on several principles.
Open AccessSonovortex: Aerial Haptic Layer Rendering by Aerodynamic Vortex and Focused Ultrasound
In this paper, a method of rendering aerial haptics that uses an aerodynamic vortex and focused ultrasound is presented. Significant research has been conducted on haptic applications based on multiple phenomena such as magnetic and electric fields, focused ultrasound, and laser plasma. By combining multiple physical quantities; the resolution, distance, and magnitude of force are enhanced. To combine multiple tactile technologies, basic experiments on resolution and discrimination threshold are required. Separate user studies were conducted using aerodynamic and ultrasonic haptics. Moreover, the perception of their superposition, in addition to their resolution, was tested. Although these fields cause no direct interference, the system enables the simultaneous perception of the tactile feedback of both stimuli. The results of this study are expected to contribute to expanding the expression of aerial haptic displays based on several principles.