New StARS framework personalizes robot actions using recommender system approach

Researchers have developed StARS, a novel framework for generating socially appropriate robot actions by treating annotators as users and robot actions as items in a preference modeling system. This approach, inspired by recommender systems, allows for personalized action selection by integrating collaborative filtering with scene representations. StARS has demonstrated consistent improvements in performance and agreement with annotators on two robotics datasets, MannersDB+ and SocNav1, and its code is publicly available. AI

IMPACT This approach could lead to more nuanced and personalized human-robot interactions by adapting robot behavior to individual user preferences.

RANK_REASON The cluster contains a research paper detailing a new framework for robot action generation. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.IR (Information Retrieval) →

• alphaXiv
• arXiv
• CatalyzeX
• CORE Recommender
• DagsHub
• Gotit.pub
• Hugging Face
• MannersDB+
• ScienceCast

• paper
• other

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →