Experimental Piano – Playing Robot Hand

The robotic and Artificial Intelligent (AI) have been introduced as a key factor for industry revolution4.0. Many industries such as manufacturing, agriculture, logistic and supply chain and so on, are transformed and applied robotic and AI in order to enhance the productivities and reduce cost. In addition, the automation system based on modern AI are highly adopted according to lacking of labors in ageing society era. The AI in creative work is very challenging, especially in music. This paper presents the experiments of making processing unit to understand music source separation, automatic music transcription and optical music recognition is our first experiments. Music source separation (MSS) is the separation of music into different sound sources (for example, vocal, drum, or piano). Automatic music transcription (AMT) is a transcription of instrument sound as a musical note. Optical music recognition (OMR) is a task that involves reading and interpreting music notes and creating a machine-readable version of the sheet music. From these three basic knowledges, our first prototype of a robotic hand is implemented successfully and is able to play piano from musical notes, songs and piano sound properly in real-time. The design and experimental results are explained in this paper.