This paper explores the computational parallels between motor control and social interaction, proposing that motor control solutions can be extended to social interaction. It discusses the role of the motor system in action observation, imitation, and social interaction, suggesting that motor commands acting on the body can be equated with communicative signals acting on others. The paper outlines the sensorimotor and social interaction loops, emphasizing the challenges of motor control due to delays, noise, and nonlinearity. It introduces internal models for simulating sensorimotor transformations, which are crucial for predicting and controlling actions. The paper also discusses the use of multiple internal models for action production and imitation, highlighting the MOSAIC model's ability to handle different contexts. It further explores hierarchical control structures for intention extraction and communication, emphasizing the importance of similar computational structures for effective social interaction. The paper concludes that using the motor system in action understanding is an efficient mechanism for social interaction, supported by computational models like HMOSAIC. The study is supported by various funding sources and references to empirical studies in neuroscience.This paper explores the computational parallels between motor control and social interaction, proposing that motor control solutions can be extended to social interaction. It discusses the role of the motor system in action observation, imitation, and social interaction, suggesting that motor commands acting on the body can be equated with communicative signals acting on others. The paper outlines the sensorimotor and social interaction loops, emphasizing the challenges of motor control due to delays, noise, and nonlinearity. It introduces internal models for simulating sensorimotor transformations, which are crucial for predicting and controlling actions. The paper also discusses the use of multiple internal models for action production and imitation, highlighting the MOSAIC model's ability to handle different contexts. It further explores hierarchical control structures for intention extraction and communication, emphasizing the importance of similar computational structures for effective social interaction. The paper concludes that using the motor system in action understanding is an efficient mechanism for social interaction, supported by computational models like HMOSAIC. The study is supported by various funding sources and references to empirical studies in neuroscience.