Guru: AI-Powered Assistive Companion Robot

Abstract

Guru is AI AI-powered assistive robot for smart living. It integrates emerging technologies like Generative AI, Robotics and Autonomous mobility for a smart assistant. Unlike traditional virtual assistants such as Google Assistant, Alexa and Siri that are limited to screen or static devices, whereas our Guru offers indoor navigation, voice assistant, reminders, surveillance and safety monitoring through emotion-aware conversations. Its innovation lies in combining empathetic AI with robotics in a modular, cost-effective design. The system can operate in indoor environments, recognise wake words without the need for physical contact and ensure user safety with features like fall detection and emergency alerts. For remote user interaction, it is accompanied by a mobile application for setting reminders, location tracking, system updates and user authorisation. It uses modern computing tools such as Raspberry Pi, OpenCV, Arduino, LLMs, STTs, APIs, etc. It can be scaled to use in healthcare, elderly care and rehabilitation. The robot ultimately aims to promote independence, enhance daily living and improve the emotional well-being of its users.

Introduction

As smart automation becomes increasingly integrated into daily life, the demand for technologies that function as personal assistants—capable of supporting both functional and emotional needs—continues to grow. Traditional virtual assistants like Alexa, Siri, Google Assistant, and ChatGPT can perform digital tasks but lack physical capabilities, mobility, and independence. In contrast, assistive robots offer physical support, cognitive assistance, mobility, surveillance, and companionship, making them especially valuable for children, the elderly, and people with disabilities. The global assistive robot market is projected to expand rapidly, driven by needs in healthcare, manufacturing, and personal support, although current commercial robots each have specific limitations and specialized use cases.

The literature review highlights significant developments and challenges in assistive robotics. Studies reveal that humanoid robots show promise in aiding daily living tasks but are not yet ready for fully independent home use. Research on low-cost assistive technologies underscores the value of open-source hardware and software to improve affordability, adaptability, and scalability. Other works explore human decision-making models to enhance robot responsiveness, conversation-based medication management for older adults, and voice-driven interfaces powered by large language models—each presenting benefits but also limitations such as noise sensitivity, internet dependency, and inconsistent model behavior.

Further studies examine real-time face and emotion recognition using CNNs, adaptive human-robot interaction systems combining speech and emotional intelligence, and voice interaction systems for service robots, all of which perform well in structured environments but weaken under real-world variability such as noise, accents, and lighting changes. Additional research includes socially aware robot navigation, thermal-based fall detection, and Raspberry Pi–based voice assistants, each demonstrating potential yet facing constraints in scalability, dataset diversity, hardware capability, and environmental robustness.

Conclusion

The project represents a significant step toward using technology to enhance the quality of life for individuals who require daily assistance, such as the elderly, people with disabilities, or those living alone. By integrating features like voice command recognition, voice interaction, fall detection, smart reminders, emotional support, and emergency assistance, GURU addresses not only physical needs but also emotional and social well-being. Using Raspberry Pi, Arduino, and cloud communication, the robot efficiently bridges hardware and software integration while maintaining user-friendliness and real-time responsiveness. The project emphasises not only technical innovation but also social impact, enhancing independence and improving the quality of life for users who require assistance. This system contributes meaningfully to society by promoting independence and safety among vulnerable populations, reducing the burden on caregivers, and enabling users to live with dignity and confidence within their own homes. The robot’s intelligent interaction and adaptive behaviour make it a supportive companion capable of understanding and responding to human needs in real time.

References

REFERENCES [1] Prabuwono, Anton Satria & Allehaibi, Khalid & Kurnianingsih, Kurnianingsih. (2017). Assistive Robotic Technology: A Review. Computer Engineering and Applications Journal. 6. 71-78. 10.18495/comengappv6i2.203. [2] “Assistive Robotic Market Report” by Aarti Dhapte, October 2025, ID: MRFR/SEM/22960-HCR ,100 Pages, [3] J. Huang, W. Wu, Z. Zhang and Y. Chen, \"A Human Decision-Making Behavior Model for Human-Robot Interaction in Multi-Robot Systems,\" in IEEE Access, vol. 8, pp. 197853-197862, 2020, doi: 10.1109/ACCESS.2020.3035348. [4] J. Álvarez Ariza and J. M. Pearce, \"Low-Cost Assistive Technologies for Disabled People Using Open-Source Hardware and Software: A Systematic Literature Review,\" IEEE Access, vol. 10, pp. 124894–124927, Nov. 2022. [5] J. Huang and Wenhua Wu, Zhenyi Zhang and Yutao Chen \"A Human Decision-Making Behaviour Model for Human-Robot Interaction in Multi-Robot Systems,\" IEEE Transactions on Robotics. [6] Z. Su, F. Liang, H. M. Do, A. Bishop, B. Carlson and W. Sheng, \"Conversation-Based Medication Management System for Older Adults Using a Companion Robot and Cloud,\" in IEEE Robotics and Automation Letters, vol. 6, no. 2, pp. 2698-2705, April 2021, doi: 10.1109/LRA.2021.3061996. [7] Padmanabha, A., Yuan, J., Gupta, J., Karachiwalla, Z., Majidi, C., Admoni, H., & Erickson, Z. (2024, October). Voicepilot: Harnessing LMS as speech interfaces for physically assistive robots. In Proceedings of the 37th Annual ACM Symposium on User Interface Software and Technology (pp. 1-18). [8] S. Dwijayanti, M. Iqbal and B. Y. Suprapto, \"Real-Time Implementation of Face Recognition and Emotion Recognition in a Humanoid Robot Using a Convolutional Neural Network,\" in IEEE Access, vol. 10, pp. 89876-89886, 2022, doi: 10.1109/ACCESS.2022.3200762. [9] Kishor I, Mamodiya U, Saini S, Bossoufi B. Voice-enabled human-robot interaction: adaptive self-learning systems for enhanced collaboration. Robotica. 2025;43(6):2143-2171. doi:10.1017/S0263574725000438 [10] Li S-A, Liu Y-Y, Chen Y-C, Feng H-M, Shen P-K, Wu Y-C. Voice Interaction Recognition Design in Real-Life Scenario Mobile Robot Applications. Applied Sciences. 2023; 13(5):3359. https://doi.org/10.3390/app13053359 [11] C. -T. Yang, T. Zhang, L. -P. Chen and L. -C. Fu, \"Socially-Aware Navigation of Omnidirectional Mobile Robot with Extended Social Force Model in Multi-Human Environment,\" 2019 IEEE International Conference on Systems, Man and Cybernetics (SMC), Bari, Italy, 2019, pp. 1963-1968, doi: 10.1109/SMC.2019.8913844. [12] H. Fu and J. Gao, \"Human Fall Detection Based on Posture Estimation and Infrared Thermography,\" in IEEE Sensors Journal, vol. 23, no. 20, pp. 24744-24751, 15 Oct.15, 2023, doi: 10.1109/JSEN.2023.3307160. [13] Niyas Mohammed Nowshad, Akhil Santhosh, Mohammed Anaz, Abja V S, Divya V B (2025). AI Voice Assistant Using Raspberry Pi 4. International Journal of Innovative Research In Technology (IJIRT), 12(1), 4837-4846. [14] “Aasha” - Budget home-care robot for the elderly by Safira Robotics. (Bengaluru) [15] “Mitra” by Invento Robotics. (Bengaluru) [16] “Miko” - Companion robot for children by Emotix. (Mumbai) [17] “Amazon Astro” - Smart home assistant robot by Amazon Inc. (USA) [18] “Pepper” – Social humanoid robot by SoftBank Robotics, Europe. [19] “ElliQ” – AI-based companion robot for the elderly by Intuition Robotics, Israel. [20] “OhmniCare” (Ohmni Telepresence) – Telepresence and caregiving robot by OhmniLabs, USA.

Copyright

Copyright © 2025 Prof. Sachin Shinde, Janvi Ambedare, Piyusha Girase, Janhavi Khandare, Pratiksha Jadhav. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.