Where Curiosity Meets
The Future of Making

Students design a multi-direction traffic control system that dynamically adjusts signal timing using real-time vehicle density input.

Core Learning: Sequential logic, timing algorithms, system automation.

A self-driving rover that follows a predefined path using IR sensor feedback, introducing students to real-world navigation principles.

Core Learning: Sensor feedback loops, proportional control, autonomous behaviour.

A rover that detects obstacles using ultrasonic sensing and intelligently changes direction without human intervention.

Core Learning: Autonomous decision-making, reactive AI agents, spatial sensing.

A smart solar panel prototype that aligns itself toward the highest light intensity using LDR sensors and servo-based control.

Core Learning: Analog sensing, optimisation logic, renewable energy systems.

Teams build and program Bluetooth-enabled rovers for real-time competition challenges and tactical missions.

Core Learning: Wireless communication, real-time control, teamwork under pressure.

A smart farming prototype that monitors soil moisture, temperature, and environmental conditions to automate irrigation decisions.

Core Learning: IoT sensing, environmental data analysis, decision-based automation.

A multi-sensor security prototype combining motion, vibration, and environmental detection for real-time alert systems.

Core Learning: Sensor fusion, event detection logic, system reliability engineering.

Students identify a real-world problem and build a complete intelligent system integrating sensors, automation logic, and control mechanisms.

Core Learning: End-to-end engineering design, computational thinking, system architecture.

Build a robot that detects obstacles using ultrasonic sensing and navigates independently without human control.

Learning Focus: Reactive intelligence, sensor feedback loops, decision logic.

Design and assemble the official Maker Dost Bot — a multi-sensor intelligent rover capable of navigation, alert signaling, and autonomous behavior.

Learning Focus: System integration, modular robotics architecture, multi-sensor coordination.

Develop a precision-controlled rover that follows a defined path using IR sensor feedback and speed tuning.

Learning Focus: Feedback control systems, proportional logic, autonomous vehicle concepts.

Train a computer vision model to recognize hand gestures and map them to real-time digital actions.

Learning Focus: Image-based AI, model training, real-time inference.

Create and train a custom AI model that identifies objects using live camera input.

Learning Focus: Supervised learning, dataset creation, model accuracy.

Explore human-centered AI by analyzing facial expressions and understanding how emotion recognition models work.

Learning Focus: Pre-trained models, inference systems, AI ethics.

Train models to recognize custom patterns and compare accuracy across different datasets.

Create intentionally biased datasets to observe how AI systems produce unfair or unreliable decisions.

Build a structured-data prediction model and explore feature selection, uncertainty, and real-world limits.

Develop a perception-based AI system that detects environmental patterns and triggers responses.

Design an intent-based AI assistant and evaluate system boundaries and failure cases.

Design and present a complete AI-powered solution — from problem definition to deployment logic.

Construct and calibrate a high-stability rover platform. Analyze torque, speed trade-offs, and system balance.

Integrate ultrasonic perception and deterministic reflex logic. Design escape strategies and analyze failure conditions.

Train and deploy a controlled AI vision model. Evaluate bias, lighting sensitivity, and reliability.

Connect perception to action. Implement fallback protocols and fail-safe architecture.

Live evaluation under variable conditions. Teams demonstrate autonomous performance in a dynamic arena.