Dr Satyavir Singh, Department of Electrical and Electronics Engineering, Dr Pankaj Bhalla, Department of Physics and two B.Tech. CSE students Aditya Kumar and Sachin Kumar, has designed a smart shopping trolley to ease the traditional shopping experience by eliminating long billing queues by utilising smart scanning technology. Their patent titled “AI-Enabled Smart Trolley System with Autonomous Navigation, Real-Time Billing, and IoT-Based Retail Analytics” with application no. 202541110198 A, has been published in the Indian Patent Office Journal.

Abstract

This research presents an AI-enabled Smart Shopping Trolley System designed to transform the conventional in-store shopping experience. The system integrates autonomous navigation, real-time product identification, automated billing, and IoT-based retail analytics into a single intelligent platform. Equipped with sensors such as ultrasonic, infrared, camera modules, and RFID readers, the trolley autonomously follows shoppers, detects items placed inside, generates a live bill, and securely transmits data to cloud servers. Additionally, the system provides retailers with actionable insights into customer movement, product demand, and inventory trends, enhancing operational efficiency while improving customer convenience.

Practical Implementation / Social Implications of the Research

Practical Implementation:

• Deployment in supermarkets, malls, and retail chains to reduce checkout time.
• Use as a self-billing system, minimizing dependence on manual counters.
• Integration with digital payments, mobile apps, and cloud platforms.
• Fleet deployment in large stores with centralized analytics dashboards.

Social Implications:

• Makes shopping accessible for elderly and differently-abled individuals.
• Reduces crowding and long queues, improving in-store safety.
• Encourages adoption of AI and IoT in everyday public spaces.
• Creates smarter retail ecosystems that compete effectively with online shopping.

Future Research Plans

• Enhancing AI-based navigation accuracy in crowded environments
• Integration of computer vision for barcode-less item recognition
• Improving battery efficiency and charging infrastructure
• Incorporating personalized recommendations using shopper behaviour data
• Large-scale pilot testing in real retail environments
• Publishing research outcomes in AI, IoT, and Smart Retail conferences/journals