Vigorous research has been performed to accumulate biological and theoretical knowledge about neurodevelopmental disorders, including molecular, neural, computational, and behavioral characteristics, but these findings remain fragmentary and do not elucidate integrated mechanisms. An obstacle is the heterogeneity of developmental pathways causing clinical phenotypes. Additionally, in symptom formations, the primary causes and consequences of developmental learning processes are often indistinguishable. Here, we introduce a developmental neurorobotics approach for overcoming problems due to the dynamic, complex properties of neurodevelopmental disorders. Specifically, by constructing neurorobotic models with predictive processing mechanisms of learning, perception, and action, we can simulate formations of integrated causal relationships among neural, computational, and behavioral characteristics while considering developmental learning processes. This framework enables binding neurobiological hypotheses (excitation-inhibition imbalance, functional disconnection), computational accounts (unusual encoding of uncertainty), and clinical symptoms. Developmental neurorobotics approaches may serve as a complementary research framework for integrating fragmented knowledge and overcoming the heterogeneity of neurodevelopmental disorders.