RobotEQ 3.0 enables personalized social actions for embodied agents
RobotEQ 3.0: Towards Personalized Social Proactive Intelligence in Embodied Agents
Human-Computer Interaction
Summary
Helping robots understand what any one person wants is hard because people expect different things. The researchers created RobotEQ 3.0, a dataset that links people's personal backgrounds and traits with the actions they prefer robots to take. Instead of guessing what most people want, their system predicts what a specific person prefers based on who they are. This helps robots become more personalized and socially aware in how they assist people.
What this means in practice
- •For robot developers: Create robots that adapt their social behaviors to match individual user preferences using personal traits as input.
- •For smart home system designers: Design smart assistants that proactively choose actions based on the diverse expectations of different household members.
Authors
Shufan Zhang, Xinyi Che, Kuofei Fang, Xuehao Wang, Liyi Liu, Junqing Wu, Jiayi Cao, Ziyanghui Wang, Yanhan Huang, Chuyu Wu, Zheng Lian
Abstract
Social Proactive Intelligence (SPI) is an emerging research area, aiming to shift embodied agents from reactive assistance toward proactively understanding human needs and executing socially desirable actions. Prior work has largely centered on the average user. However, human expectations are inherently diverse, and prior work overlooks individual nuances. To bridge this gap, we introduce RobotEQ 3.0, a benchmark for Personalized SPI. (Dataset) We first profile participants via a structured questionnaire covering factors that are correlated with human expectations of embodied agents, such as basic demographics and personality traits. Participants then select their preferred actions from a set of candidates. Unlike prior SPI benchmarks that focus on assessing behavioral appropriateness, our task centers on predicting the actions preferred by a specific user, thereby capturing human subjectivity. The resulting dataset establishes explicit links between individual traits and behavioral preferences. (Solution) We observe substantial inter-annotator variance, confirming that user preferences over actions are highly individualized. This motivates our exploration of Personalized SPI, in which user traits serve as additional inputs to predict individual preferences. Experimental results show that incorporating user traits can aid personalized prediction. This work aims to shift the research paradigm from developing agents suited for the average user to designing systems tailored to specific individuals.