MUMBAI, India, Jan. 23 -- Intellectual Property India has published a patent application (202641001597 A) filed by Dayananda Sagar University, Bengaluru, Karnataka, on Jan. 7, for 'advanced autonomous vehicle system using behaviour cloning for path optimisation.'

Inventor(s) include Dr. Gousia Thahniyath; K Radhika; S. Annapurna Shobitha; Dr. Damodharan D; Fenita F; Dr. Gayathtri; Soham Ghosh; and Dr. Santosh Kumar J.

The application for the patent was published on Jan. 23, under issue no. 04/2026.

According to the abstract released by the Intellectual Property India: "An advanced autonomous vehicle system using behaviour cloning for path optimisation is disclosed. The system employs computer vision and convolutional neural networks to predict steering angles directly from camera images, enabling real-time autonomous navigation. Driving data collected from a simulator is used to train the model to replicate human driving behaviour. Experimental results demonstrate effective lane keeping and significant reduction in training and validation loss, indicating strong generalization. The camera-only, cost-efficient approach makes the system suitable for ADAS, robotics, and smart mobility applications. Autonomous driving system developed using computer vision techniques and AI algorithms. The system focuses on real-time lane detection and path planning by leveraging image processing, convolutional neural networks (CNNs), and behavior cloning to mimic human driving behavior. The methodology includes data acquisition using the Udacity self-driving car simulator, preprocessing of captured images, training a CNN model, and testing in a simulated environment. The system's performance is evaluated based on its ability to navigate autonomously in various simulated road scenarios, demonstrating lane-keeping accuracy and effective replication of human driving behavior. The project's industry relevance lies in its cost-efficient, camera-only approach, making it adaptable for ADAS, robotics, and smart mobility solutions."

Disclaimer: Curated by HT Syndication.