Emergent Role Differentiation in Morphable Soft-Body Robots: From Symmetry Locks to Environmental Differentiation

GPU-accelerated evolutionary framework for studying morphable soft-body robots that approach, combine, and locomote as merged entities using 400-particle spring-mass systems controlled by evolved neural networks. v3 updates (March 6, 2026): Experiment 7 (Sweet Spot): Systematic sweep of 7 mass ratios (1:1 to 10:1) reveals 3:1 as the optimal ratio maximizing Differentiation×Fitness (93.5). The correlation curve is non-monotonic, with a recovery at 7:1. Experiment 8 (Degrees of Freedom Trap): Adding a 4th NN output for dynamic mass redistribution causes a 256-point fitness collapse (+175 → −81) that persists even under curriculum learning ("Developmental Unlocking"). Experiment 9 (Environmental Differentiation): Asymmetric ground friction (0.1 vs 5.0) induces complete role differentiation (r=−0.032) in symmetric bodies at the highest fitness observed (+181). Demonstrates that specialization emerges at the body-environment interface. Key findings (8 principles): Symmetry Locks Theorem: Symmetric bodies cannot differentiate (r=0.742). Inertial Asymmetry Principle: Only mass asymmetry breaks synchronization (Mapping Inequivalence via F=ma). Transient Differentiation: Role specialization peaks early then is partially reabsorbed for efficiency. Reward Paradox: Multi-phase fitness can mask poor locomotion via reward hacking. Symmetry Optimality: Evolution chooses symmetric masses when free to evolve morphology. The Sweet Spot: Mass ratio 3:1 maximizes differentiation per unit fitness cost. Degrees of Freedom Trap: Adding control dimensions catastrophically expands the search space. Environmental Differentiation: Asymmetric environments induce differentiation in symmetric bodies at superior fitness. All experiments run on a single NVIDIA RTX 5080 Laptop GPU in under 3 hours total.