LAUSR

In recent times, research on highly efficient construction has gained increasing popularity. During construction with hydraulic excavators, the sequence of excavation motions significantly affects the duration and precision of the work; therefore, it should be as efficient as possible. Because automation is still difficult, the ability improvement support system of nonskilled operators is required. However, currently, there exists no effective method for evaluating or planning the excavation motion sequence. This study proposes a method for evaluating excavation motion sequences based on a pattern recognition technique. First, the data array of hydraulic excavator motions is divided into unit excavation motions, characterized using a clustering method. Second, the patterns are divided into excavation phases with similar excavation motion patterns. Finally, the excavation motion sequence is evaluated by calculating the transition frequency between excavation phases. The result shows that the proposed approach can classify the skill level of the operator with accuracy of 0.8. Therefore, the frequency of excavation phase transitions can be used as a useful indicator for evaluating excavation motion sequences.