Task-unit based trajectory generation for excavators utilizing expert operator skills

Effective trajectory generation methods are crucial for the development of intelligent excavators. However, current methods face challenges in adapting to dynamic work environments and fulfilling task-specific requirements. This study proposes a trajectory generation method based on task-units. The trenching task is divided into five task-units by interviewing the expert operators, the data collected from the expert operators is further used for task-unit modeling. After that, the infrastructure of the task-units and the connectivity between the individual task-units are established. The advantages of Dynamical Movement Primitives (DMP) and Gaussian mixture models (GMM) are fused to model the trajectory generation of the task-unit. The trajectory reproduction capability of the model is further enhanced by the optimization of the Genetic Algorithm (GA). This method has the capability to generate various task trajectories by generalizing and combining task-units, making it highly applicable.