Copyright © 2026 Authors retain the copyright of this article. This article 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.

@article{204964,
        author = {Abhishek S K and Haripriya A P},
        title = {A Wireless Hybrid Assistive Interface: Fusing Eye-Gaze Estimation with Inertial Motion for Precision Control},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {13},
        number = {no},
        pages = {262-267},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=204964},
        abstract = {The rapid evolution of digital computing has outpaced the development of inclusive input modalities, leaving a significant gap for users in sterile environments or those with limited manual dexterity. Traditional Human-Computer Interaction (HCI) peripherals, such as the mechanical mouse and keyboard, inherently rely on high-precision motor control and physical contact, which are often unfeasible in clinical surgical settings or for individuals with neurodegenerative conditions. While standalone vision-based systems have attempted to bridge this gap, they frequently suffer from MidasTouch accidental triggers and tracking instability. This research paper delineates the design, architectural synthesis, and empirical validation of a high-fidelity, hybrid human-computer interface (HCI) specifically engineered to transcend the limitations of conventional touchless navigational systems. The core innovation lies in a multi-modal Coarse-to-Fine fusion architecture that synchronizes biological gaze estimation with mechanical inertial sensing. The hardware layer utilizes an ESP32 microcontroller as a central processing hub, which leverages the Bluetooth Serial Port Profile (SPP) to establish a low-latency, cable-free communication pipe with the host workstation. Coarse-grained spatial navigation is achieved through real-time eye-gaze tracking using the Media Pipe Face Mesh framework, which maps pupil-to-nose vector displacement across a high-definition 1920x1080 display matrix. To resolve the inherent instability and jitter associated with software-based gaze estimation, a secondary refinement layer is introduced via an MPU-6050 6-axis motion sensor. This sensor enables the user to perform micro-adjustments or nudge using subtle hand-tilt gestures, effectively decoupling large-scale cursor travel from precision target selection. Furthermore, a finger-mounted resistive flex sensor provides a deterministic binary trigger for click events, overcoming the ambiguity of vision-based gesture recognition. The system demonstrates a significant enhancement in ergonomic efficiency and navigational accuracy through the application of stochastic smoothing filters and the integration of the hardware into a specialized Nitrile-coated Nylon wearable interface.},
        keywords = {Hybrid Sensor Fusion, Gaze Estimation, Human-Computer Interaction (HCI), Assistive Technology.},
        month = {June},
        }