MUMBAI, India, Sept. 22 -- Intellectual Property India has published a patent application (202641105968 A) filed by Saveetha Institute Of Medical And Technical Sciences on September 03, 2026, for Ai Assisted Smart Guindance Robot.
Inventors include Pavan Challa; Dr. Karthick Raja; and Dr Ramya Mohan.
The application for the patent was published on September 18, 2026, under issue no. 38/2026.
Abstract: The AI-Assisted Smart Guidance Robot was an embedded vision-based assistive technology created to improve interior navigation for people with visual impairments. In order to enhance user safety and spatial awareness, the system employs a camera-based perception mechanism to identify impediments in real time and give auditory instruction. The system's main goal is to use lightweight embedded processing to provide proactive environmental input without the need for expensive hardware or cloud computing.The robot incorporates DC motors for platform movement, an L298N motor driver for mobility control, and an ESP32 -CAM module for image capture and processing. Voice-based notifications relating to detected impediments are provided by a DFPlayer Mini module equipped with an 852 speaker. To categorize objects as circular, rectangular, or triangular structures, geometric form identification techniques are employed, such as edge detection and contour extraction approximation.The system is suitable for indoor assistive environments like homes, classrooms, and public buildings since it places a priority on cost, flexibility, and offline operation. To assess detection accuracy, response latency, system stability, and environmental resilience, extensive testing was carried out. The robot's real-time performance was constant over a range of backdrop complexity and illumination conditions.In place of basic proximity warnings, the suggested approach offers structured spatial input, which improves autonomous mobility and navigation confidence. The existing approach creates a scalable platform for potential incorporation of TinyML-based object identification, distance estimation, and navigational autonomy capabilities, despite its emphasis on geometric categorization rather than semantic item labeling. All things considered, this effort advances the creation of intelligent, affordable, and accessible assistive robotic systems
Disclaimer: Curated by HT Syndication.
