Deep

Agency

                     Master Thesis  

                                                                           Stuttgart University

                                                 Year: 2023

​

Collab with S.Sardari and P.Zhang

 

Automating robotic assembly in architectural construction presents challenges due to the unpredictable nature of construction sites and the limited dexterity of robots. Consequently, human workers often have to  handle tasks that are manual and repetitive. Recent advancements in AI technologies demonstrate significant potential for enhancing the dexterity of robots. By integrating concepts from haptic teaching, deep reinforcement learning, and robotic assembly, this research examined methods to enhance robot’s performance for wood joint assembly tasks and autonomy in the construction field. The trained neural network is subsequently deployed to assemble lap joints of various sizes and angles that were not previously encountered by the agent. Human demonstrations are recorded on a real robot as successful experiences to improve the learning efficiency of the agent.

​