Adaptive Intelligent Homes (AIH)

Project period: 2024-07-01 – 2025-12-31

Objective
Adaptive Intelligent Homes (AIH) aims to develop a suite of demonstrators, combining the cutting-edge advances made within the parent collaborative research project (AAIS) on user state recognition, human-robot handovers, multimodal referring expression generation, controllable speech synthesis, and proactively supporting users in complex tasks. AIH will extend the context-awareness and adaptiveness of those conversational robots from a laboratory environment to a real-life environment and from individual to collaborative settings, where multiple users interact with the system simultaneously. Through engaging with societal and municipal actors, the project contributes to more inclusive and accessible robotic systems with potential applications to promote healthy lifestyles and provide home care services for older adults.

Background
AI-powered agents provide an opportunity to manage, coordinate and initiate activities within and across households, contributing to healthy lifestyles and improved quality of life for users of all ages. To achieve this goal, these robotic systems must be aligned with the user’s needs, preferences, and interests, and they must adapt themselves to complex environments involving multiple users performing overlapping and interwoven household tasks, such as cooking.

Cooking in the home is not simply instruction-giving; it is a multi-party, parallelized activity requiring timing, action relevance, and adaptability from both the human and any AI assistance. The project has envisioned an adaptive intelligent kitchen assistant that could help humans prepare food and other kitchen-centric tasks to enhance healthy ageing and improve quality of life.

Cross-disciplinary collaboration
 The interdisciplinary approach will allow us to synthesize the human-centric understanding of the home and kitchen environment to the technical capabilities of dialogue systems and robotic agents. This could indicate, for instance, new modalities for personalising the intelligent kitchen assistant for different user groups or linguistic styles that could be adapted to different family members’ skill sets and preferences. An important societal aspect is to explore and design for improved inclusivity of dialogue systems by recognizing diverse ways of interacting with the system based on user’s age, gender, ethnicity, or disability and investigate the long-term impact of deployment of such systems in the home environment to the quality of life and self-efficacy among end-users. Designing for improved accessibility of dialogue systems has the potential to result in more equal access to intelligent and assistive home environments.