The project is a realization of an automated smart carrom-playing robot that continuously analyses the board configuration using a vision feed and image processing and plays a series of best possible shots to complete a game. This leverages the knowledge of reinforcement learning in implementing strategic gameplay.
The automated smart carrom-playing robot project is a cutting-edge application of advanced machine learning techniques in a traditional tabletop game. The aim of the project is to develop an autonomous robot that can play carrom, a popular indoor game in South Asia, by continuously analyzing the board configuration using a vision feed and image processing. The robot uses reinforcement learning, a form of machine learning, to implement strategic gameplay.
The robot is equipped with a camera that is mounted on top of the carrom board, which captures images of the board configuration. These images are then mapped to a two-dimensional coordinate system to identify the centers of the carrom pieces and holes. This information is used to train a machine learning algorithm that determines the best play based on the game situation. The algorithm automatically determines the disk position, speed, and angle to hit an identified carrom piece.
The system also employs a real-time decision-making mechanism that analyzes the game's progress and recommends the best possible shots for the robot to take. This allows the robot to play a series of best possible shots to complete a game autonomously.
Overall, this project showcases Fcode Labs' expertise in advanced machine learning techniques and its application in real-world scenarios. The smart carrom-playing robot is an exciting development that has potential applications in various fields beyond gaming, such as industrial automation, robotics, and logistics.
The platform was awarded as the winner at E-Swabhimani by ICT Agency of Sri Lanka 2021