Premium
Classical Planning Model‐Based Approach to Automating Construction Planning on Earthwork Projects
Author(s) -
Li Duanshun,
Lu Ming
Publication year - 2019
Publication title -
computer‐aided civil and infrastructure engineering
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 2.773
H-Index - 82
eISSN - 1467-8667
pISSN - 1093-9687
DOI - 10.1111/mice.12420
Subject(s) - earthworks , automated planning and scheduling , testbed , planner , plan (archaeology) , computer science , robotics , site plan , project management , scheduling (production processes) , project planning , systems engineering , engineering , software engineering , artificial intelligence , robot , urban planning , regional planning , civil engineering , operations management , computer network , geotechnical engineering , archaeology , history
Extensive research in automated operation planning has led to significant advances in the area of robotics. Theories and methods resulting from robotics have yet to be adapted to enable automated project planning in construction engineering. Aiming to demonstrate the potential of implementing automated planning theory and methods in construction project planning, we developed an automated earthwork planner prototype following the principles and framework of classical planning model in computer science. As time is not explicitly represented, implementing classical planning model to perform optimization and planning simultaneously results in potential temporal–spatial conflicts (TSCs). The present research develops a two‐step approach to separate operations optimization and earthwork planning in typical rough grading projects. As such, TSCs encountered in existing mathematical programming based earthwork planning methods are resolved. To enable fully integrated and automated earthwork planning, the prototype system has been seamlessly integrated with project scheduling and operations simulation software for higher level analyses. To demonstrate advantages of the automated planning methodology, construction plans were independently produced by 14 graduate student teams on the same “testbed” project; results were evaluated and compared with the plan generated by the proposed system.