Stability driven reinforcement learning for robotic construction

This project explores the use of reinforcement learning for autonomous robotic construction of stable structures without scaffolding. The focus lies on designing reward functions that effec- tively guide a robotic agent to connect two fixed points by placing blocks. Two metrics were de- veloped to e...

ver descrição completa

Detalhes bibliográficos
Autor: Garrobé Fonollosa, Marcel
Formato: tesis de maestría
Fecha de publicación:2025
País:España
Recursos:Universitat Politècnica de Catalunya (UPC)
Repositorio:UPCommons. Portal del coneixement obert de la UPC
Idioma:inglés
OAI Identifier:oai:upcommons.upc.edu:2117/445551
Acesso em linha:https://hdl.handle.net/2117/445551
Access Level:acceso abierto
Palavra-chave:Reinforcement learning
Autonomous robots
Aprenentatge per reforç
Robots autònoms
Àrees temàtiques de la UPC::Informàtica::Intel·ligència artificial
Descrição
Resumo:This project explores the use of reinforcement learning for autonomous robotic construction of stable structures without scaffolding. The focus lies on designing reward functions that effec- tively guide a robotic agent to connect two fixed points by placing blocks. Two metrics were de- veloped to evaluate structural stability: one based on the maximum vertical load each block can bear, and another based on the critical tilting angle before collapse. These metrics were used to shape more informative reward signals compared to traditional binary schemes. Results show that this approach improves learning efficiency and leads to the construction of more robust and reliable designs.