ROURKELA: Innovators at the National Institute of Technology-Rourkela (NIT-R) have secured patent for a robotic system designed to act as a friendly companion.
Using AI and Large Language Models (LLMs), the robot is capable of live conversation beyond pre-coded responses and can also respond to human emotions like happiness, neutral and upsetting in emphatic or comforting manner reading facial expressions.
The innovation largely focuses on creating seamless human-machine interaction by integrating verbal and non-verbal communication. The robotic system understands everyday language, follows verbal instructions, responds to questions and engages in real-time conversations.
The system can also detect simple gestures such as waving and raising a hand, and react appropriately. This ability makes the robot approachable for users regardless of age including children and elderly persons who mostly rely on natural gestures than spoken commands.
On the verbal communication front, the robotic system can greet users, provide instructions and reply using natural-sounding speech. The robot uses the Raspberry Pi system to process user inputs such as spoken commands or text-based queries. The LLM analyses the input, determines the context and produces an appropriate, human-like response. This output is then delivered through the robot’s speech system using Google Text-to-Speech.
Co-authored by associate professor in department of Computer Science and Engineering Anup Nandy, associate professor in Electrical Engineering Asim Kumar Naskar, research scholar Sougatamoy Biswas and MTech graduate Rahul Saw, the research findings have been published in the prestigious Computers and Electrical Engineering journal by Elsevier.
Nandy said, “The indigenously developed robotic system significantly aligns with the Government of India’s Make in India and Atmanirbhar Bharat initiatives.
In contrast to existing systems available globally, the NIT-R’s social robot introduces a uniquely integrated framework that combines gesture, emotion, speech and LLM-based conversational abilities within a cost-effective platform suitable for Indian contexts.”
The robot is equipped with a wheel-based platform and navigation system for easy movement. The built-in distance-sensing module allows it to avoid obstacles and ensure safe movement in a crowded setup. It has broad potential for use across various social settings including homes to assist and provide companionship to elderly individuals. In education space, the robot can provide students conversation-based explanations for complex topics, and can also be used in hospitals, workplaces and community facilities, creating a welcoming atmosphere and interacting naturally in a crowded setup.
The robot is expected to cost between `80,000 and `90,000 based on manufacturing scale and component optimisation. The research team plans to improve its interaction capabilities, conduct real-world pilot testing in schools, hospitals and community environments to further refine its performance.