Navigates collapsed buildings in a virtual environment, detects humans using vision, and plans the safest path. Combines CV, navigation (A*), and decision-making.

A robot that must reach a victim quickly through blocked paths and dynamic obstacles, balancing the fastest vs. safest route under time pressure.

A swarm of 3–5 robots that efficiently explore an area faster than a single robot with no overlap. Ideal for surveillance, cleaning, or search operations.

It is a touchless navigation system using Python and Mediapipe. It allows surgeons to control digital X-rays via hand gestures, maintaining a sterile environment by replacing mice with mid-air finger tracking.

This project is a computer vision application that translates real-time hand gestures into keyboard inputs. By leveraging a webcam, the system detects the user's hand movements and maps them to directional arrow keys, effectively allowing for hands-free control of games (like Subway Surfers) or navigation of digital interfaces.

This project is a real-time AI analyzer using MediaPipe and OpenCV to detect emotions and stress. It monitors facial micro-expressions, blink rates, and head movements through a futuristic dashboard interface.

Goes beyond basic lane following to make complex decisions like overtaking, stopping vs. slowing down, and handling edge cases using autonomy logic.

Detects crops and weeds, navigates a virtual farm, and simulates intelligent spraying or harvesting decisions.

A robot that moves safely through a dynamic crowd by predicting human motion and avoiding discomfort. Highly relevant for delivery robots in malls or airports.

an AI-powered project where a simulated robot uses 270-degree LiDAR and Reinforcement Learning to autonomously navigate mazes, optimizing real-world logistics like hospital delivery and warehouse automation.

An interactive simulator visualizing Pathfinding AI and Procedural Generation. It demonstrates how autonomous agents navigate complex environments using BFS, DFS, and heuristic-based logic to solve randomly generated, real-time mazes.

an AI-powered checkout system that uses vision-language models to instantly identify and count multiple grocery items simultaneously, automating the billing process through real-time visual recognition.

Navigates a hospital to deliver medicines while dynamically avoiding people. Can be enhanced with scheduling and priority logic.

AI controls the flow of multiple cars in an intersection (beyond basic traffic lights) to optimize wait times and reduce congestion.

An adaptive traffic control backend using Python, FastAPI, and YOLOv8. It detects vehicles and emergency responders in real-time, dynamically adjusting traffic signals to reduce congestion and prioritize safety on edge devices.

This project features an autonomous driving system leveraging YOLO (You Only Look Once) for real-time object detection. It identifies vehicles, pedestrians, and signs to ensure safe, intelligent navigation.

An interactive digital companion that blends high-fidelity rendering with conversational AI. Engage in real-time dialogue with a lifelike character designed to listen, respond, and animate.