Overview
Abstract
Homebot is a locally deployable AI agent for conversational household assistance and automation. It accepts voice and instant-messaging requests through a shared runtime that combines language-model responses with registered tools and task-specific skills. The design separates common request processing from session ownership, messaging history remains scoped to a channel and chat, whereas voice interaction is bounded by wake-word activation. For hands-free use,Homebot combines local wake-word detection, streaming speech recognition and synthesis, and an explicit dialoguestate protocol for ending, following up, or continuing a conversation. Clear channel, tool, and skill contracts support practical customization for household use.
Shengyuan Ye
Ph.D. in Computer Science
Shengyuan Ye obtained his Ph.D. degree from the School of Computer Science and Engineering, Sun Yat‑sen University. His research interests include AI for Power System and Power Dispatching Automation.
Liekang Zeng
Ph.D., Sun Yat-sen University
He obtained Ph.D. degree at School of Computer Science and Engineering, Sun Yat-sen University. His research interest lies in building edge intelligence systems with real-time responsiveness, systematic resource efficiency, and theoretical performance guarantee.
Jiangsu Du
Assistant Professor, Sun Yat-sen University
He obtained Ph.D. degree at School of Computer Science and Engineering, Sun Yat-sen University. He is now a Assistant Professor at the Sun Yat-sen University, working on High Performance Computing, and Distributed Artificial Intelligence System.
Mu Yuan
Ph.D., USTC
He received PhD degree from University of Science and Technology of China in 2024, advised by Prof. Xiang-Yang Li and Prof. Lan Zhang. He was a postdoctoral fellow at CUHK, working with Prof. Guoliang Xing.His research interest lie in designing theory-backed algorithms and building innovative systems for AI workloads.