Abstract
Walking is an essential aspect of daily life, while walking with companions offers numerous benefits. Recently developed mobile robots, through their ability to navigate challenging terrains, open new possibilities for outdoor walking companionship. Yet, little is known about how such companions shape the human walking experience. In this study, nine participants walked outdoors with a robot and later reflected on their walking experience in semi-structured interviews. Thematic analysis showed that the robot influenced how participants related to it, how they managed proximity, and how their attention, control, and social presence were affected. Building on these insights, we identify five key dimensions of human–robot walking: attunement, awareness mediation, proxemics, social perception, and playful curiosity. These dimensions capture how walking with robots transforms this ordinary activity into a co-experienced practice and additionally offer concrete design implications for designing and creating more meaningful, comfortable, and socially attuned human-robot walking interactions.
Role: Supervisor
Type: Full Paper
Conference: Proceedings of the 2026 CHI Conference on Human Factors in Computing Systems
Stats: Acceptance rate: 25.1%, h5-index: 134
Date: 2026
Co-Authors: Eshtiak Ahmed, Çağlar Genç, Velvet Spors and Juho Hamari
Abstract
Companion robots are increasingly envisioned as social partners beyond indoor settings, yet little is known about how companionship unfolds in outdoor environments. This study investigates how robot engagement (active vs. passive) and authority (leader vs. follower) shape human–robot companionship during forest-based walking experiences. We conducted a mixed-design field experiment in which participants walked with a mobile robot under different engagement and authority conditions. Companionship was assessed through connection and coordination rapport, with human–robot trust and robot social presence examined as mediating mechanisms. Results show that robot engagement and authority did not directly enhance companionship. Instead, trust and social presence emerged as strong predictors of companionship, with robot authority positively influencing trust. These findings suggest that companionship in outdoor contexts arises primarily through relational perceptions rather than overt behavioral cues, highlighting the importance of designing outdoor companion robots that emphasize reliability and social presence over expressive interaction.
Role: Supervisor
Type: Extended Abstract (Poster)
Conference: Proceedings of the Extended Abstracts of the 2026 CHI Conference on Human Factors in Computing Systems
Stats: Acceptance rate: 38.4%, h5-index: 134
Date: 2026
Co-Authors: Eshtiak Ahmed, Narda De la Flor Enciso, Isak De Villiers Bosman, Iuliia Avgustis, Shiva Jabari and Juho Hamari
Abstract
As robots move from controlled laboratory environments to real-world settings, it is increasingly important to understand how people perceive and respond to their behaviors in dynamic and uncontrolled contexts (e.g., forest), more specifically how the communication unfolds between robots and humans. This study investigates how humans interpret the gestural behaviors of a quadruped robot during a forest walk, aiming to understand how these interpretations shape their responses. Through thematic analysis of interviews with eight participants walking with the robot, we generated three key themes. Findings show that participants interpreted ambiguous movements meaningfully, guided by the robot's animal-like appearance and the surrounding context. Moreover, gestural communication facilitated subtle exploration, and lastly, non-intrusive exploration and interaction were shaped not only by participants’ actions but also by their attribution of the robot's agency and intentionality. These results contribute valuable insights into human-robot interaction dynamics in uncontrolled outdoor settings.
Role: Supervisor
Type: Extended Abstract (Poster)
Conference: Proceedings of the Extended Abstracts of the 2026 CHI Conference on Human Factors in Computing Systems
Stats: Acceptance rate: 38.4%, h5-index: 134
Date: 2026
Co-Authors: Narda De la Flor Enciso, Eshtiak Ahmed and Aino Ahtinen
Abstract
As robots increasingly enter social and domestic environments, their ability to generate context-aware and expressive behaviors becomes essential for meaningful and believable human-robot interaction. Traditional behavior generation often relies on static rules or scripted routines, limiting adaptability and nuance. In this workshop, we present a novel system that leverages Large Language Models (LLMs) to generate dynamic, embodied responses for robots. Our system integrates a defined robot persona, an affordance profile based on physical capabilities, and a response mapping framework that converts conversational inputs into sequences of expressive movement markers. Participants will engage in a hands-on experience with this system, beginning with an introduction to behavior generation in robotics and a live demonstration. Working in small groups, they will design their own LLM prompts and response scenarios for daily life interactions, implement them using the framework, and test the results directly on a quadruped robot, Spot from Boston Dynamics. The workshop drives participants and practitioners to critically reflect on expressive AI and robot interaction design.
Role: Supervisor
Type: Extended Abstract (Workshop)
Conference: Proceedings of the 28th International Academic Mindtrek Conference
Stats: h5-index: 18
Date: 2025
Co-Authors: Eshtiak Ahmed, Bakhtawar Khan, Jiangnan Xu, Linas Kristupas Gabrielaitis and Juho Hamari
Abstract
As robots move beyond industrial and assistive roles into everyday human environments, the ability to communicate naturally and responsively becomes increasingly important. This paper presents a system that enables a quadruped robot, Boston Dynamics’ Spot, to respond to human voice inputs with expressive, dog-like physical behaviors. By integrating voice recognition, large language models (LLMs), and a structured response mapping framework, the robot interprets conversational inputs and generates sequences of behavior markers aligned with its physical capabilities. The system defines a robot persona and prompts the LLM with contextual constraints, including movement affordances and limitations, to ensure realistic and semantically appropriate responses. Our study highlights the potential of using LLMs not only for dialogue generation but also for embodied interaction design. While the limited expressivity and subtlety of robotic movement pose challenges, this work demonstrates a promising step toward more intuitive and engaging human-robot interaction. We discuss the implications for generalizing this approach to different robot morphologies and outline future directions for expanding behavioral nuance, emotional interpretation, and multimodal engagement.
Role: Supervisor
Type: Full Paper
Conference: International Conference on Social Robotics
Stats: h5-index: 20
Date: 2025
Co-Authors: Eshtiak Ahmed and Juho Hamari
Abstract
This paper presents a speculative design workshop that represents an initial attempt to explore playful methods for envisioning more-than-human forest-robot interactions. Bringing together game designers, researchers, and technologists, the two-day workshop used creative games, such as a forest-themed fake news card game and AI-generated PowerPoint karaoke, to provoke imaginative thinking. Participants developed speculative concepts through bodystorming, storyboarding, and the creation of short videos, featuring a Boston Dynamics Spot robot. Our analysis, grounded in visual thematic analysis, highlights how play facilitated ideation, visualization, and the making of more-than-human forest-robot concepts. As a work-in-progress, we learned that some game elements proved to be too abstract; however, the iterative making and acting processes helped participants ground and refine their ideas. The outcomes of the workshop, in the form of forest-robot concepts, represent a wide array of more-than-human design considerations. We also discuss the implications from the concepts through a critical more-than-human lens.
Role: Supervisor
Type: Extended Abstract (Work in Progress)
Conference: Companion Proceedings of the Annual Symposium on Computer-Human Interaction in Play
Stats: h5-index: 27
Date: 2025
Co-Authors: Eshtiak Ahmed, Philip Chambers, Timo Nummenmaa, Mari Selkimäki, Teppo Hujala and Juho Hamari
Abstract
Autonomous systems such as robots are permeating our daily lives increasingly every day, which are now adorned with social elements, bringing them closer to synthetic companions. While used in fields like well-being, education, guidance, and entertainment, companion robots also hold great potential for outdoor uses, particularly accompanying people in the wild with numerous potential benefits. However, current studies lack a comprehensive understanding of the possible uses, functions, and behavior of companion robots outdoors. To explore this area, we have run a co-design study consisting of 5 design workshops with 30 participants, including interaction designers, product development experts, engineers, robotics experts, and frequent forest goers. The study resulted in nine valuable design themes, transferred into five design concepts, which were then interpreted into a comprehensive design space that can be leveraged by designers and researchers in creating companion robots for the wild.
Role: Co-author, Supervisor
Type: Full Paper
Journal: International Journal of Human-Computer Interaction
Stats: h5-index: 83
Date: 2025
Co-Authors: Eshtiak Ahmed, Laura Diana Cosio, Çağlar Genç and Juho Hamari
Abstract
Walking is an integral part of daily human lives which also has a great influence on happiness and wellbeing. Walking with a dog companion is one of the most popular forms of recreational walking that has similar benefits. The recent development of mobile zoomorphic robots, especially robot dogs has opened up new opportunities in the landscape of walking with companions. This led us to investigate how such robots can accompany humans in walking, and how the mobility and behavior of robots in a daily-life walking scenario affect humans’ walking experience. We interviewed nine participants who took a 15–20-minute walk with a companion robot around a university campus, to understand how diverse walking behaviors of a companion robot influence their perceived experiences. We have generated four key themes through thematic analysis. They imply that affective relationalities between humans and robots can build intimacy and empathy, whereas personal space and physical proximity need to be thought carefully to ensure interaction comfort and spontaneity. Additionally, the robot influenced people’s self-reflection and social values refraining them from enjoying an unknown experience, while ambiguity in communication led to less confidence and trust.
Role: Supervisor
Type: Full Paper
Conference: 33rd IEEE International Conference on Robot and Human Interactive Communication
Stats: h5-index: 31
Date: 2024
Co-Authors: Eshtiak Ahmed, Çağlar Genç, Velvet Spors and Juho Hamari
Abstract
The field of robotics has grown exponentially over the years, especially the social aspect, which has enabled robots to interact with humans meaningfully. Robots are now used in many domains, such as manufacturing, healthcare, education, entertainment, rehabilitation, etc. Along with their widespread use in many real-life environments, robots have been used as companions to humans. With the increased amount of research done on human–robot partnership (HRC), it is important to understand how this domain is developing, in which direction, and what the future might hold. There is also a need to understand the influenza factors and what kind of empirical results are in the literature. To address these questions, we conducted a systematic literature review and analyzed a final number of 134 relevant articles. The findings suggest that anthropomorphic and zoomorphic robots are more popular as human companions, while there is a lack of interest in functional and caricatured robots. Also, human-like and animal-like features are implemented more in companion robots. Studies rarely exploit the mobility available in these robots in companionship scenarios, especially in outdoor settings. In addition to that, co-existence and co-performance-based implementation with people have been observed rarely. Based on the results, we propose a future research agenda that includes thematic, theoretical, methodological, and technological agendas. This study will help us understand the current state and use of robotic companies which will then potentially aid in determining how HRC can be leveraged and integrated more seamlessly into human lives for better effectiveness.
*the image of this project was created by robots (obviously) since the research itself did not produce nice images
Role: Supervisor
Type: Full Paper
Journal: International Journal of Social Robotics
Stats: h5-index: 56, impact factor: 3.8
Date: 2024
Co-Authors: Eshtiak Ahmed and Juho Hamari
Abstract
Socially Assistive Robots (SARs) are becoming very popular every day because of their effectiveness in handling social situations. However, social robots are perceived as intelligent, and thus their decision-making process might have a significant effect on how they are perceived and how effective they are. In this paper, we present the findings from a participatory design study consisting of 5 design workshops with 30 participants, focusing on several decision-making scenarios of SARs in the wild. Through the findings of the PD study, we have discussed 5 directions that could aid the design of decision-making systems of SARs in the wild.
*image here was illustrated by Laura D. Cosio
Role: Supervisor
Type: Extended Abstract (Workshop Paper)
Conference: CHI 2023 Workshop on Socially Assistive Robots as Decision Makers: Transparency, Motivations, and Intentions
Date: 2023
Co-Authors: Ahmed Eshtiak, Laura Cosio and Juho Hamari
Abstract
The field of robotics has grown exponentially over the years, especially the social aspect has been given a lot of attention. Although there is a significant amount of research on robots being used as social human companions, there is a lack of a comprehensive study. The lack of knowledge includes the types of robots used, their features, interaction modalities and deployment scenarios. To address this knowledge gap, we have conducted a systematic literature review of 98 relevant articles. The findings suggest that anthropomorphic and zoomorphic robots are more popular as human companions while there is a lack of interest in functional and caricatured robots. Also, human-like and animal-like features are implemented more in them. A lack of utilizing the mobility of robots can be seen in the research and thus outdoor implementation of companion robots is seen very rarely. Moreover, the understanding of Human-Robot Companionship needs a clearer definition.
Role: Supervisor
Type: Full Paper
Conference: Pacific Asia Conference on Information Systems
Stats: h5-index: 24
Date: 2022
Co-Authors: Eshtiak Ahmed and Juho Hamari