Gesture Dependable Robotics ARM Movement: ROS and Machine Learning Perspective

Robotic arm simulation using the Robot Operating System (ROS) has emerged as a powerful tool for design, control strategy development, and human-robot interaction exploration. The proposed approach presented controlling of ROS framework based robotic ARM using gesture recognition. Multiple techniques are used for gesture recognition including hardware based and vision based. The proposed approach discusses camera-based gesture recognition as a method for human-robot interaction within ROS simulations. This approach involves capturing user gestures with a camera, employing machine learning models for gesture classification, and translating recognized gestures into control commands for the simulated robotic ARM. The proposed approach acknowledges the advantages of natural interaction, in-creased accessibility, and richer control information offered by gesture recognition, while also addressing challenges such as accuracy, gesture complexity, and real-time performance.