Autonomous construction framework for crane control with enhanced soft actor–critic algorithm and real-time progress monitoring

With the shortage of skilled labors, there is an increasing demand for automation in the construction industry. This study presents an autonomous construction framework for crane control with enhanced soft actor–critic (SAC-E) algorithm and real-time progress monitoring. SAC-E is a novel reinforcement learning algorithm with superior learning speed and training stability for lifting path planning. In addition, robotic kinematics and a control algorithm are implemented to ensure that the crane can autonomously execute the lifting path. Last, novel hardware communication interfaces between robot operating system and building information modeling (BIM) are developed for real-time construction progress monitoring. The performance of the proposed framework was demonstrated using a robotized mobile crane to stack concrete retaining blocks. The results show that the proposed framework can be effectively used to execute the retaining block construction using the robotized mobile crane with real-time construction update in the BIM platform.