Neural Morphogenesis Algorithm (NMA) Benchmark Dataset: Simulation and Physical Validation

This dataset provides the complete experimental and simulation data supporting the study “Neural Morphogenesis Architecture for Self-Organizing Robotic Intelligence: A Developmental Control Framework.” It includes curated results from large-scale multi-agent simulations and physical soft-robotic experiments designed to evaluate the Neural Morphogenesis Algorithm (NMA) against state-of-the-art baseline controllers.

The dataset contains raw and aggregated metrics from repeated simulation runs across agent populations of 50, 100, and 200 units, as well as validation data from physical robotic prototypes and biohybrid interface experiments. Key performance indicators include informational entropy reduction, network modularity, energy efficiency ratio, morphological plasticity, cognitive stability, and bioelectronic signal latency.

In addition to performance metrics, the dataset documents ablation studies isolating the contributions of neural plasticity, morphogenetic regulation, and cognitive adaptation layers. Time-series data sampled over extended developmental cycles, hardware drift measurements, experimental parameters, and statistical summaries used in the article are also provided.

This resource is intended to support transparency, reproducibility, and independent verification of the reported results. All data are structured to facilitate replication of the experimental protocol, benchmarking against alternative control architectures, and further analysis of morphogenetic and developmental intelligence in robotic systems.