MUMBAI, India, Nov. 2 -- Intellectual Property India has published a patent application (202641124139 A) filed by B Jyothi; and Koneru Lakshmaiah Education Foundation on October 16, 2026, for Lightweight Adaptive Sensor Fusion Framework For Real-Time Obstacle Detection For Autonomous Vehicle.
Inventors include B Jyothi; T. Sai Srujana; P. Bhavana; and K. Nithin Reddy.
The application for the patent was published on October 30, 2026, under issue no. 44/2026.
Abstract: Reliable obstacle detection is essential for autonomous mobile robots operating in dynamic environments. This paper proposes a Lightweight Adaptive Sensor Fusion (LASF) framework for real-time obstacle detection using a Raspberry Pi 5. The system integrates a USB camera with the YOLOv8 object detection model and an HC- SR04 ultrasonic sensor. Camera reliability is evaluated using YOLOv8 confidence scores, while ultrasonic reliability is estimated using measurement error. Adaptive sensor weights are calculated according to the estimated reliability of each sensor. The weighted sensor outputs are combined to generate a fused obstacle score. This information supports obstacle-priority assignment and adaptive safety-distance estimation. The system generates Move, Slow, and Stop commands based on the fused information and safety requirements. An L298N motor driver controls the DC motors according to the generated commands. The framework provides a lightweight, low-cost approach to intelligent obstacle detection and navigation on embedded robotic platforms.
Disclaimer: Curated by HT Syndication.
