# Biomimetic Dual-Strategy Adaptive Differential Evolution for Joint Kinematic-Residual Calibration with a Neuro-Physical Hybrid Jacobian

## TL;DR

This paper introduces a new framework for improving the accuracy of industrial robots by combining evolutionary optimization and neural compensation, inspired by biological systems.

## Contribution

The Evo-NPH framework unifies rigid-body parameters and neural compensators in a co-evolving decision vector, inspired by brain-body co-adaptation.

## Key findings

- The proposed framework achieved a testing distance-residual RMSE of 0.62 mm on an ABB IRB 120 manipulator.
- RMSE was reduced by 86.75% compared to the uncalibrated baseline and 23.46% compared to the strongest published baseline.
- Dual-Strategy Adaptive Differential Evolution outperformed a sequential pipeline by 32.6% in joint optimization.

## Abstract

Improving absolute accuracy in industrial manipulators remains difficult because rigid-body kinematic calibration cannot fully represent configuration-dependent non-geometric effects. Drawing inspiration from biological brain–body co-adaptation, this study presents an Evolutionary Neuro-Physical Hybrid (Evo-NPH) framework in which rigid geometric parameters and neural compensator weights are treated as a single co-evolving decision vector. In the offline phase, a Dual-Strategy Adaptive Differential Evolution (DS-ADE) optimizer performs global joint identification using complementary exploration–exploitation behaviors and success-history inheritance, analogous to morphology-control co-evolution in biological systems. In the online phase, a Neuro-Physical Hybrid Jacobian (NPHJ) solver augments the analytical Jacobian with gradients from a Graph Kolmogorov–Arnold Network (GKAN), enabling sensorimotor-like real-time compensation on the learned physical manifold. Experiments on an ABB IRB 120 manipulator with 600 configurations (500 training, 100 testing) report a testing distance-residual RMSE of 0.62 mm, STD of 0.59 mm, and MAX of 0.83 mm. Relative to the uncalibrated baseline, RMSE is reduced by 86.75%; compared with the strongest published baseline, RMSE improves by 23.46%. Ablation results show that joint DS-ADE optimization outperforms a sequential pipeline by 32.6%, and the graph-structured KAN outperforms a parameter-matched MLP by 26.2%. Wilcoxon signed-rank tests (p<0.001) confirm statistical significance.