Automatic high-level motion sequencing methods for enabling multi-tasking construction robots

Abstract

Robots are expected to play an important role in future construction work. However, they are not yet widely adopted by the industry because it is difficult and expensive to program robots to conduct a variety of construction tasks. This paper presents a method for intuitively and flexibly teaching robots to perform various construction tasks through demonstrations. Robots are first programmed with basic skill primitives and then learn the sequencing of these primitive skills to perform different types of construction work under the guidance of human supervisors. The construction workflow and the interaction processes are enabled by a process-level digital twin system. Case studies with three assembly scenarios and a wooden frame construction experiment are used to present and verify the proposed method. The proposed approach enables automatic robot motion sequencing abilities through Learning from Demonstration and has the potential to enable the widespread adoption of robots on construction sites.