Operator support system based on primitive static states in intelligent operated work machines

Intelligent functions that can autonomously identify the current work states and also provide informational or operational support to their operators are inevitably required for double-front construction machinery (DFCM), which has been developed for complicated tasks. In this study, which focuses on DFCM, we address the need for a new conceptual design of an operator support system. In particular, a state identification method strongly requires high reliability and robustness to address the complexity of the construction work environment and the variety of the operator's skill level. We, therefore, define primitive static states (PSS) that are determined using on–off information for the lever inputs and manipulator loads for each part of the grapple and front. We develop an intelligent system that provides a reduction of operational gain to make precise work easier and an indication of an enlarged image of the end-effector from a different viewpoint to assist depth perception based on PSS identification, and evaluate it using our newly developed simulator. Our experimental results show that the operator support system improves the work performance, including decreasing the operational time for completing a task, reducing the mental workload on the operators and the number of error operations.