Prediction and Optimization of Motion Trajectory of Hybrid Mechanism Based on Transformer

Abstract

To address error accumulation from multi-variable features and complex dynamic coupling in the motion trajectory prediction of hybrid mechanisms, this paper applies a Transformer-based prediction framework. The framework integrates a spatiotemporal attention mechanism and kinematic constraints to obtain precise and physically feasible predictions of component movement. Such trajectory modeling is also meaningful for advanced electromagnetic engineering, including antenna-positioning mechanisms, microwave inspection platforms, and robotic systems used in electromagnetic measurement. The method uses a Transformer core with a hierarchical spatiotemporal attention module to model time dependency and spatial coupling among joint angles, velocities, and torques, while refining multimodal dynamic behavior. A Dynamic Graph Convolutional Network captures the influence of topological changes on motion-transfer paths and reflects configuration-dependent joint interactions. By constructing a kinematic constraint loss function based on the Lagrangian equation, the model embeds dynamic priors and improves physical consistency. Experimental results show that the method achieves an RMSE of 1.42 mm and an MAE of 1.06 mm on the standard test set, reducing these errors by 63.3% and 64.1% compared with a traditional LSTM model. In a six-degreeof-freedom mechanism, the median prediction error of critical Joint 1 is controlled at 1.42 mm, supporting accurate motion prediction for constrained serial-reachable hybrid topologies.