MUMBAI, India, Jan. 9 -- Intellectual Property India has published a patent application (202541133557 A) filed by Nitte Meenakshi Institute Of Technology, Nitte; Chandu R; Trisha S; Sowmya; Sudeep A. S; Ms. Deepthi Shetty; Dr. Uma R; Dr. Poornima Panduranga Kundapur; and Dr. Vinay T. R, Bangalore, Karnataka, on Dec. 30, 2025, for 'vision-based intelligent robotic car integrating multi-modal detection for autonomous navigation.'
Inventor(s) include Nitte Meenakshi Institute Technology, Nitte; Chandu R.; Trisha S.; Sowmya; Sudeep A. S.; Ms. Deepthi Shetty; Dr. Uma R.; Dr. Poornima Panduranga Kundapur; and Dr. Vinay T. R.
The application for the patent was published on Jan. 9, under issue no. 02/2026.
According to the abstract released by the Intellectual Property India: "The invention relates to an integrated vision-based intelligent robotic car capable of autonomous navigation through consolidation of multiple complementary detection modalities within a single cost-effective educational and research platform. The system comprises a Raspberry Pi single-board computer (1.2-1.8 GHz ARM processor, 1-8 GB RAM) executing comprehensive Python-based software framework, Raspberry Pi Camera Module (8-megapixel, 640 480 resolution) providing forward visual perception, HC-SR04 ultrasonic sensors (2-4 units) providing proximity detection, L298N motor driver controlling differential drive system with two DC motors, optional GPS receiver for coordinate logging, optional USB microphone for voice commands, and rechargeable battery system enabling 60+ minutes portable operation. The software implements simultaneous multi-modal perception: lane detection through systematic computer vision pipeline (ROI extraction, grayscale conversion, Gaussian blur, Canny edge detection, Hough line transformation) achieving 10 fps real-time execution and 90% lane-following success; pothole detection through parallel processing analyzing image gradients and contours achieving 85% detection accuracy for potholes 10 cm diameter; ultrasonic obstacle detection at 20-50 Hz polling frequency with safety override logic achieving 95% collision avoidance success; and modular software architecture with independent subsystem modules for vision processing, ultrasonic sensing, GPS logging, voice commands, and motor control enabling individual testing, validation, and enhancement. The present invention provides cost-effective autonomous navigation platform ($100-150 USD) representing 100-200 cost reduction versus high-end platforms ($20000-50000+) while delivering substantially greater capability than basic IR sensor robots, with modular design facilitating educational adoption for hands-on learning, senior design projects, and research exploration of advanced autonomous navigation techniques including potential integration of deep learning models, LiDAR sensors, and multi-agent coordination algorithms."
Disclaimer: Curated by HT Syndication.
