Self Model for Embodied Artificial Intelligence

This paper presents a systematic formulation of the Self Model for embodied artificial intelligence, aiming to provide the missing internal representation that enables an agent to understand its own body, capabilities, memories, and decision processes. Unlike existing approaches that address isolated aspects such as perception, prediction, or skill adaptation, we propose a unified computational framework that integrates body schema, forward and inverse models, perceptual memory mechanisms, and agency. This framework captures how an embodied agent represents its physical structure, predicts the consequences of its actions, selects policies, and accumulates experiences to form a coherent sense of self. We further introduce a six-level hierarchy (L0-L5) that characterizes the developmental stages of self model from non-self representation to full self awareness, providing the first operational taxonomy for evaluating self-awareness in embodied systems. A practical implementation is developed and validated in manipulation and navigation tasks, demonstrating improved prediction, adaptation, memory, and decision-making capabilities. Overall, this work establishes the conceptual foundation and technical pathway for building self model in embodied intelligence. It highlights their significance for achieving autonomy, robustness, long-horizon reasoning, and lifelong evolution in real-world environments.