IRO Journals
Journal of Ubiquitous Computing and Communication Technologies

ROB-AI: An Offline Voice-Controlled Smart Home System with Context-Aware On-Device Intent Reasoning

Open Access
Published: 05 June, 2026
Pages: 161-176
  • Athishkirthik J D. , Athishkirthik J D.
    Department of Computer Science and Engineering, SRM Institute of Science and Technology, Vadapalani, Chennai, India
    Department of Computer Science and Engineering, SRM Institute of Science and Technology, Vadapalani, Chennai, India
  • Pranav Y. , Pranav Y.
    Department of Computer Science and Engineering, SRM Institute of Science and Technology, Vadapalani, Chennai, India
    Department of Computer Science and Engineering, SRM Institute of Science and Technology, Vadapalani, Chennai, India
  • Sridevi S. Sridevi S.
    Department of Computer Science and Engineering, SRM Institute of Science and Technology, Vadapalani, Chennai, India
    Department of Computer Science and Engineering, SRM Institute of Science and Technology, Vadapalani, Chennai, India
view PDF
view PDF

How to Cite

J D., Athishkirthik, Pranav Y., and Sridevi S. 2026. “ROB-AI: An Offline Voice-Controlled Smart Home System With Context-Aware On-Device Intent Reasoning ”. Journal of Ubiquitous Computing and Communication Technologies 8 (3): 161-76. https://doi.org/10.36548/jucct.2026.3.001.
ACM ACS APA ABNT Chicago Harvard IEEE MLA Turabian Vancouver AMA

Download Citation

Endnote/Zotero/Mendeley (RIS) BibTeX

Keywords

Smart Home
Voice Control
Internet of Things (IoT)
Edge Computing
Offline AI
Automation

Abstract

This work introduces Responsive-Operational-Bot (ROB-AI), a localized smart home automation system designed to function entirely offline, interpreting natural language voice commands without dependence on external cloud.  The proposed architecture seamlessly combines speech recognition on the device, a hybrid intent detection engine, and RESTful IoT-based device control over a local network.  A lightweight, context-aware reasoning layer is added to connect human language with strict machine instructions. This lets the system correctly understand indirect or incomplete commands by checking the current state of connected hardware.  The system is designed to minimize latency significantly, remove the use of all external internet connections, and protect user data. Experimental results show that ROB-AI works very well in the real world, with standard commands running almost instantly and maintaining a high accuracy rate of 92–96% for complex semantic processing. The variation in the accuracy percentage is observed in cases such as noisy environment and high-speed command input. In the future, to scale up the IoT end points and to enable seamless expansion of web-based dashboard interfaces, a modular architecture is effectively designed.

References

  1. Jeong, Donghwan, and Honguk Woo. "On-Device Intent Reasoning for Smart Home Agents Via Ontology-Augmented sLLMs." IEEE Access 2025, vol. 13: 197645-197662.
  2. K. Lee, J. Park, and H. Kim, “HARMONY: A Framework for Multimodal LLM-Powered AI Agents in Smart Homes via the Model Context Protocol,” ACM Transactions on Intelligent Systems 2024, vol. 15, no. 2, 1–22.
  3. S. Ramesh and V. Kumar, “Design and Implementation of Controller Boards to Monitor and Control Home Appliances for Future Smart Homes,” International Journal of Embedded Systems 2023, vol. 11, no. 3, 145–152.
  4. Kong, Linghe, Jinlin Tan, Junqin Huang, Guihai Chen, Shuaitian Wang, Xi Jin, Peng Zeng, Muhammad Khan, and Sajal K. Das. "Edge-computing-Driven Internet of Things: A Survey." ACM computing surveys 2022, vol. 55, no. 8, 1-41.
  5. Kochovski, Petar, and Vlado Stankovski. "Applications and Benefits of Cloud-to-Edge Computing in Enhancing Smart Home Functionalities." In Home Digital Twins 2026, Elsevier, 155-165.
  6. Nassif, Ali Bou, Ismail Shahin, Imtinan Attili, Mohammad Azzeh, and Khaled Shaalan. "Speech Recognition Using Deep Neural Networks: A Systematic Review." IEEE access 2019, vol. 7, 19143-19165.
  7. Di Leo, Stefano, Luca De Cicco, and Saverio Mascolo. "Real-Time Speech-to-Text on Edge: A Prototype System for Ultra-Low Latency Communication with AI-Powered NLP." Information 2025, vol. 16, no. 8, 685.
  8. Khan, Murad, Sadia Din, Sohail Jabbar, Moneeb Gohar, Hemant Ghayvat, and S. C. Mukhopadhyay. "Context-Aware Low Power Intelligent Smarthome Based on the Internet of Things." Computers & Electrical Engineering 2016, vol. 52, 208-222.
  9. Chamoli, Sushant, Sumitra Sangwan, and Vivudh Fore. "Smart Home Automation Using ESP8266 and Internet of Things." In 5th International Conference on Next Generation Computing Technologies (NGCT-2019). 2020..
  10. Mohamed, Khalil, and Ayman El Shenawy. "A Smart IoT-Based Home Automation System for Controlling and Monitoring Home Appliances." International Review of Automatic Control 2023, vol. 16, no. 5, 228.