Eye-Blink-Controlled Wheelchairs: A Critical Review of Blink Detection, Command Encoding, and Safety in EOG-Based Prototypes

Abstract

A blink is one of the few voluntary actions left to wheelchair users who cannot operate a joystick, and electrooculography (EOG) records it cheaply with skin electrodes. Yet people blink all day without meaning to, so a blink-controlled chair must tell a chosen blink from a reflex. This review reads 25 papers. Twelve of them are eye-controlled wheelchair studies, published between 2007 and 2024 where a year is shown, which are analyzed in detail together with the blink-based systems they describe; the other thirteen give background and related methods. For each study it notes the sensing arrangement, blink detection, the job given to the blink, safety provisions and test method. Six of the twelve use a blink or sustained eye closure as a command (toggle, stop, reverse or mode switch), one treats the blink purely as an artifact to be rejected, and the rest report no blink command. Chosen and reflex blinks are separated by peak amplitude, pulse duration, timing windows or, in one study, a pruned decision tree. Reported command success lies between 87 and 100 percent, but the figures come from incompatible protocols and small groups, and none of the studies reports false activations from involuntary blinks per unit time, tests with motor-impaired users or measures eye fatigue. The paper closes with proposals for a shared blink-command benchmark, fail-safe command assignment and layered safety design.

Introduction

Eye-controlled smart wheelchairs are designed to help people with severe physical disabilities move independently when they cannot operate a conventional joystick. Among the available control methods, Electrooculography (EOG) is a promising approach because it detects the electrical signals produced by eye movements using surface electrodes placed around the eyes. These signals can be processed by electronic circuits and microcontrollers to convert eye movements into wheelchair commands.

The review examines 25 research papers, including 12 primary studies on eye-controlled wheelchair systems. It discusses different sensing methods, signal-processing techniques, command-decoding strategies, safety mechanisms, and reported experimental results.

The typical EOG system consists of electrodes, signal-conditioning circuits, a microcontroller or computer, a decoding algorithm, and a wheelchair motor-control unit. The electrical signals are amplified, filtered, and converted into digital values so that eye movements such as looking left, right, up, or down can be recognized.

Eye blinks are particularly useful because they are easy to detect and can serve as commands for starting, stopping, reversing, or confirming selections. However, involuntary blinking can accidentally trigger commands. Therefore, systems use techniques such as amplitude thresholds, pulse duration, timing rules, polarity patterns, and decision-tree classifiers to distinguish intentional blinks from reflex blinks and other eye movements.

The literature identifies several control approaches, including threshold-based decoding, pulse-pattern recognition, machine-learning classification, continuous gaze mapping, and hybrid interfaces combining EOG with voice commands or facial muscle signals. Some systems also incorporate autonomous navigation to help users move toward selected destinations while reducing the need for continuous gaze-based steering.

The review highlights important challenges, including variations in electrical signals between users, electrode placement, electrical noise, eye fatigue, limited freedom to look around, and accidental command activation. It also notes that many studies use small participant groups or different testing procedures, making direct comparisons of their reported results difficult.

The main research contribution is a structured comparison of existing eye-controlled wheelchair systems, focusing on how intentional blinks are detected, how commands are interpreted, and how effectively safety is addressed. The review identifies the need for more reliable blink-detection algorithms, standardized evaluation methods, larger user trials, and improved safety mechanisms.

In conclusion, EOG-based smart wheelchairs offer a promising assistive technology for people with severe motor impairments. However, reliable separation of intentional and involuntary eye movements, safe motor control, and extensive testing with intended users are essential before these systems can be considered suitable for everyday use.

Conclusion

Across the twelve primary eye-controlled wheelchair studies, the blink works as a toggle, stop, reverse, mode switch or confirmation, or is rejected as an artifact, and deliberate blinks are told from reflex blinks by amplitude, duration, timing or a learned tree. Reported success rates are high but come from small, non-comparable protocols with healthy or unspecified participants, often on scaled vehicles. The recurring weaknesses are per-user calibration, unreported false activations from involuntary blinks, blink commands that fail in the unsafe direction, safety functions that sit beside rather than inside the decoder, and missing measures of fatigue, power and long-term use. A shared benchmark, adaptive decoders that fit wheelchair hardware, layered safety design and staged validation with the intended users are the steps the evidence supports. These conclusions rest on 25 papers, twelve of them analyzed in detail, and should be re-examined against a wider, systematically collected literature.

References

[1] S. Mahmud, X. Lin, and J.-H. Kim, “Interface for human machine interaction for assistant devices: A review,” in Proc. 10th Annu. Comput. Commun. Workshop Conf. (CCWC), 2020, pp. 768–773. [2] R. Barea, L. Boquete, M. Mazo, and E. López, “System for assisted mobility using eye movements based on electrooculography,” IEEE Trans. Neural Syst. Rehabil. Eng., vol. 10, no. 4, pp. 209–218, Dec. 2002. [3] M. I. Rusydi, M. A. A. Boestari, R. Nofendra, Syafii, A. W. Setiawan, and M. Sasaki, “Wheelchair control based on EOG signals of eye blinks and eye glances based on the decision tree method,” in Proc. 12th Int. Conf. Inf. Commun. Technol. (ICoICT), 2024, pp. 152–159. [4] S. Yathunanthan, L. U. R. Chandrasena, A. Umakanthan, V. Vasuki, and S. R. Munasinghe, “Controlling a wheelchair by use of EOG signal,” in Proc. 4th Int. Conf. Inf. Autom. Sustain. (ICIAFS), Colombo, Sri Lanka, Dec. 2008, pp. 283–288. [5] C. S. L. Tsui, P. Jia, J. Q. Gan, H. Hu, and K. Yuan, “EMG-based hands-free wheelchair control with EOG attention shift detection,” in Proc. IEEE Int. Conf. Robot. Biomimetics (ROBIO), Sanya, China, Dec. 2007, pp. 1266–1271. [6] B. A. Dwajan, M. S. Sowmya, N. P. Reddy, S. Bhavani, and M. R. Usha, “Eye gaze controlled wheelchair,” Int. J. Eng. Res. Technol., vol. 9, no. 5, pp. 667–673, May 2020. [7] S. Shah and R. Kher, “Design of electrooculogram based wheelchair control,” G. H. Patel College of Engineering and Technology, Vallabh Vidyanagar, India, venue and year not shown on the copy reviewed. [8] M. A. D. Sucres, S. S. F. Pérez, I. V. G. Zavala, D. L. I. Ramírez, and N. R. Hernández, “EOG-based interface and speech recognition for wheelchair control,” Universidad de Guadalajara, Guadalajara, Mexico, 2019, conference paper; venue and pages not shown on the copy reviewed. [9] L. Rouillon-Sotomayor, J. Gutiérrez-Abanto, and C. Sotomayor-Beltran, “Implementation of a low-cost steering control system for a wheelchair based on electrooculography signals,” Int. J. Eng. Trends Technol., vol. 72, no. 3, pp. 260–267, Mar. 2024. [10] C.-H. Kuo, Y.-C. Chan, H.-C. Chou, and J.-W. Siao, “Eyeglasses based electrooculography human-wheelchair interface,” in Proc. IEEE Int. Conf. Syst., Man, Cybern. (SMC), San Antonio, TX, USA, Oct. 2009, pp. 4746–4751. [11] A. A. Al-Haddad, R. Sudirman, C. Omar, and S. Z. M. Tumari, “Wheelchair motion control guide using eye gaze and blinks based on Bug algorithms,” in Proc. IEEE EMBS Int. Conf. Biomed. Eng. Sci. (IECBES), Langkawi, Malaysia, Dec. 2012, pp. 398–403. [12] K. Kuntal, I. Banerjee, and L. P. P., “Design of wheelchair based on electrooculography,” in Proc. Int. Conf. Commun. Signal Process. (ICCSP), India, Jul. 2020, pp. 632–636. [13] S. U. Kumar and V. M. Vinod, “EOG based wheelchair control for quadriplegics,” in Proc. 2nd Int. Conf. Innov. Inf., Embedded Commun. Syst. (ICIIECS), 2015. [14] A. B. Usakli and S. Gurkan, “Design of a novel efficient human-computer interface: An electrooculogram based virtual keyboard,” IEEE Trans. Instrum. Meas., vol. 59, no. 8, pp. 2099–2108, Aug. 2010. [15] Q. Huang et al., “An EOG-based human–machine interface for wheelchair control,” IEEE Trans. Biomed. Eng., vol. 65, no. 9, pp. 2023–2032, 2018. [16] F. Bhuyain and K. M. Salim, “Design and development of an EOG-based system to control electric wheelchair for people suffering from quadriplegia or quadriparesis,” in Proc. Int. Conf. Robot., Signal Process. Techn., 2019, pp. 460–465. [17] A. M. Choudhari, P. Porwal, V. Jonnalagedda, and F. Mériaudeau, “An electrooculography based human machine interface for wheelchair control,” Biocybern. Biomed. Eng., vol. 39, no. 3, pp. 673–685, 2019. [18] Y. Li, S. He, Q. Huang, Z. Gu, and Z. L. Yu, “A EOG-based switch and its application for ‘start/stop’ control of a wheelchair,” Neurocomputing, vol. 275, pp. 1350–1357, 2018. [19] H. Mulam, M. Mudigonda, B. P. S. Kumar, and H. Kuchulakanti, “Electrooculogram based wheelchair control in real-time,” in Proc. ICETE 2023, Adv. Eng. Res., B. Raj et al., Eds., vol. 223, 2023, pp. 55–67. [20] A. Rajesh and M. Mantur, “Eyeball gesture controlled automatic wheelchair using deep learning,” in Proc. IEEE Region 10 Humanitarian Technol. Conf. (R10-HTC), 2017. [21] A. N. Rajesh, S. Chandralingam, T. Anjaneyulu, and K. Satyanarayana, “EOG controlled motorized wheelchair for disabled persons,” Int. Sch. Sci. Res. Innov., vol. 8, no. 5, pp. 302–305, 2014. [22] R. Z. Marandi, P. Madeleine, Ø. Omland, N. Vuillerme, and A. Samani, “Eye movement characteristics reflected fatigue in both young and elderly individuals,” Sci. Rep., pp. 1–10, 2018. [23] M. Vidal, A. Bulling, and H. Gellersen, “Analysing EOG signal features for the discrimination of eye movements with wearable devices,” in Proc. 1st Int. Workshop Pervasive Eye Tracking Mobile Eye-Based Interact., 2011, pp. 15–20. [24] N. M. M. Noor and S. Ahmad, “Performance analysis of an electrooculography-based on intelligent wheelchair motion control,” in Proc. 10th Asian Control Conf. (ASCC), 2015. [25] V. J. Lumelsky and A. A. Stepanov, “Dynamic path planning for a mobile automaton with limited information on the environment,” IEEE Trans. Autom. Control, vol. 31, no. 11, pp. 1058–1063, Nov. 1986.

Copyright

Copyright © 2026 Tanay Sunil Goupal, Kunal Girhale, Servesh Padhye, Utkarsh Kale, Soham Sawale, Rakesh Gharat. 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.