Toward Intelligent and Affordable Humanoid Manipulation: A Lightweight 6-DOF Robotic Arm With Neural Inverse Kinematics and Optimized Control

Abstract

This study presents the design and intelligent control of a lightweight and low-cost 6-DOF humanoid robotic arm developed for assistive robotic applications. The manipulator is fabricated using 3D printing technology, achieving more than 60% weight reduction with structural performance evaluated using static finite-element analysis. A comprehensive modeling framework is established, including forward and inverse kinematics (IK), 3D workspace volume analysis, and trajectory planning within the MATLAB Simscape environment. System identification is performed for each joint, achieving model fit accuracies ranging from 90.34% to 97.07%. To address the highly nonlinear IK problem, a ResNet-style neural network (IKNet) employing unit-normalized trigonometric (sinq_i, cosq_i) output encoding and forward-kinematic position loss is trained for 100 epochs on a 2,000,000-sample dataset generated via uniform joint-space sampling, adhering to a 70/15/15 train/validation/test split. On a fixed random subset of 10,000 poses drawn from the 300,000-pose held-out test set, IKNet achieves a mean position error of 0.2954 mm and a P95 error of 0.7108 mm; the near-singular subset has a mean error of 0.4896 mm according to Yoshikawa’s manipulability index. On an unseen 100 × 100 mm square trajectory, IKNet yields a mean tracking error of 1.6464 mm and an inference time of 0.0308 ms per pose (32,499 Hz). For motion control, PID controllers are optimized using three metaheuristic algorithms: genetic algorithm (GA), particle swarm optimization (PSO), and Honey Badger algorithm (HBA). Simulation and hardware evaluations demonstrate the tracking and transient performance of the proposed control framework.