Authors : Malve Swaraj Sanjay; Mande Priyanka Santosh; Chaugule Sonali Dyaneshwar; Chaugule Swapnali Dyaneshwar

Volume/Issue : Volume 10 - 2025, Issue 5 - May

Google Scholar : https://tinyurl.com/4su8kvrd

DOI : https://doi.org/10.38124/ijisrt/25may453

Note : A published paper may take 4-5 working days from the publication date to appear in PlumX Metrics, Semantic Scholar, and ResearchGate.

Abstract : The integration of Artificial Intelligence (AI) into assistive technologies has significantly enhanced the autonomy and quality of life for individuals with mobility impairments. This paper presents a comprehensive study on the application of AI in autonomous wheelchair navigation systems. By leveraging advanced machine learning algorithms, sensor fusion techniques, and computer vision, AI-assisted wheelchairs can perceive their surroundings, make intelligent decisions, and navigate complex environments with minimal user intervention. The study explores key AI methodologies including path planning, obstacle avoidance, environment mapping, and user intention recognition. Furthermore, it analyses the performance of different AI models and sensor configurations in real-world and simulated environments. Emphasis is placed on safety, adaptability, and user-friendliness of the system. The findings suggest that AI-powered navigation not only enhances mobility and independence but also contributes to safer and more efficient wheelchair operation. This research underlines the potential of AI to revolutionize assistive mobility devices and sets the foundation for future innovations in smart healthcare solutions.

Keywords : Computer Vision Focus (for AI Systems that Use Cameras for Navigation), Deep Learning Focus (if Our System uses Neural Networks for Decision-Making), IoT and Embedded Systems (if the Wheelchair Uses Connected Sensors/Devices), Robotics and Control Systems, Healthcare and Assistive Technology, Human-Centered AI / HCI (if the Interaction between User and Wheelchair is a Focus).

References :

1. Paneru, B., Paneru, B., Thapa, B., & Poudyal, K. N. (2024). EEG-based AI-BCI Wheelchair Advancement: A Brain-Computer Interfacing Wheelchair System Using Deep Learning Approach. arXiv preprint arXiv:2410.09763. arXiv
2. This study presents a BCI-controlled wheelchair utilizing EEG signals and deep learning models like XGBoost and SVC, achieving up to 60% accuracy in simulated navigation.
3. Sarkar, N. K., Roy, M., & Maniruzzaman, M. (2025). Brain Controlled Wheelchair with Smart Feature. arXiv preprint arXiv:2501.03371. arXiv
4. An affordable EEG-based wheelchair system integrating eye-blink detection, ultrasonic sensors, and SMS alerts for enhanced safety and usability.
5. Wang, Y., et al. (2018). Towards BCI-actuated smart wheelchair system. BioMedical Engineering OnLine, 17(1), 1-14. BioMed Central
6. This paper details a BCI-actuated smart wheelchair system employing AI for dynamic environment adaptation and intuitive user control.