Learning to Build: Autonomous Robotic Assembly of Stable Structures Without Predefined Plans

TL;DR

This paper introduces an autonomous robotic assembly framework that constructs stable structures without predefined plans, using reinforcement learning to adapt to environmental uncertainties and variations during construction.

Contribution

The paper presents a novel RL-based framework for robotic assembly that operates without fixed blueprints, enabling flexible and adaptive construction in uncertain environments.

Findings

Successfully completed 15 diverse 2D block construction tasks

Demonstrated robustness to construction noise in real-world experiments

Showed adaptability to environmental variations during assembly

Abstract

This paper presents a novel autonomous robotic assembly framework for constructing stable structures without relying on predefined architectural blueprints. Instead of following fixed plans, construction tasks are defined through targets and obstacles, allowing the system to adapt more flexibly to environmental uncertainty and variations during the building process. A reinforcement learning (RL) policy, trained using deep Q-learning with successor features, serves as the decision-making component. As a proof of concept, we evaluate the approach on a benchmark of 15 2D robotic assembly tasks of discrete block construction. Experiments using a real-world closed-loop robotic setup demonstrate the feasibility of the method and its ability to handle construction noise. The results suggest that our framework offers a promising direction for more adaptable and robust robotic construction in real-world environments.