Despite recent advances in integrating Large Language Models (LLMs) into social robotics, two weaknesses persist. First, existing implementations on platforms like Pepper often rely on cascaded Speech-to-Text (STT)→LLM→Text-to-Speech (TTS) pipelines, resulting in high latency and the loss of paralinguistic information. Second, most implementations fail to fully leverage the LLM’s capabilities for multimodal perception and agentic control. We present an open-source Android framework for the Pepper robot that addresses these limitations through two key innovations. First, we integrate end-to-end Speech-to-Speech (S2S) models to achieve low-latency interaction while preserving paralinguistic cues and enabling adaptive intonation. Second, we implement extensive Function Calling capabilities that elevate the LLM to an agentic planner, orchestrating robot actions (navigation, gaze control, tablet interaction) and integrating diverse multimodal feedback (vision, touch, system state). The framework runs on the robot’s tablet but can also be built to run on regular Android smartphones or tablets, decoupling development from robot hardware. This work provides the HRI community with a practical, extensible platform for exploring advanced LLM-driven embodied interaction.

Colors play a crucial role in shaping perceptions and psychological responses, making them an essential consideration in robot design, particularly in the design of value-sensitive Human-Robot Interactions (HRI). Since human values guide our actions, understanding the association between robot colors and values is key to creating effective robot designs. This study employed an online survey (N = 142) to investigate the relationship between human values relevant in a hospital context and their associated colors, as well as to identify suitable robot color schemes. Our findings show that Green and Turquoise are strongly linked to values such as competence, physical well-being, and security, which are of high priority in hospital settings. Consequently, participants preferred these color schemes for hospital robots. This work expands the theoretical understanding of color-value associations in HRI and offers practical design implications, emphasizing the need for context-aligned, value-sensitive robot designs in healthcare.

Socially assistive robots (SARs) powered by Large Language Models (LLMs) can offer benefits for improving older adults’ well-being through social dialogues. However, empirical research on older adults’ experiences with LLM-enabled, open-domain conversational robots is limited. This qualitative field study investigated communication dynamics between six older adults and an LLM-powered SAR in a Swiss German nursing home. To conduct this investigation, we integrated ChatGPT-4o-realtime and Microsoft’s speech service into a SAR, specifically enabling real-time user-initiated interruptions and fast response time. Our findings reveal that participants generally found conversations pleasant, appreciating the robot’s personalized response generation. Further, we identify older adults’ interaction patterns during the conversation and uncover several technical barriers such as turn-taking difficulties, occasional misunderstandings, and repetitive response patterns. From these insights, we present design implications to guide the development of LLM-powered SARs that can sustain engaging, open-domain social dialogues with older adults.

Like in human-human interaction, people tend to interact in human-robot settings with those they like. Therefore, it is important to understand what variables affect robot likeability. The present study aims at providing insights into how robots' anthropomorphism, voice, gestures, approaching behaviors as well as perceived warmth and competence play a role in robot likeability. We conducted an online survey (N=191) studying two humanoid robots with different characteristics. Our exploratory study empirically indicates that the investigated variables are significantly correlated with robot likeability for both robots but with differing strengths. Further, the likeability of the two robots is predicted by differing variables, with robot voice being the only common predictor for both robots.