Sample-Efficient Robot Skill Learning for Construction Tasks: Benchmarking Hierarchical Reinforcement Learning and Vision-Language-Action Model

Abstract

This study evaluates two leading approaches for teaching construction robots new skills to understand their applicability for construction automation: a vision-language-action (VLA) model and reinforcement learning (RL) methods. The goal is to understand task performance and the practical effort needed to deploy each approach on real jobs. The authors developed two teleoperation interfaces to control the robots and collect the demonstrations needed, both of which proved effective for training robots for long-horizon and dexterous tasks. In addition, the authors conducted a three-stage evaluation. First, the authors compared a multilayer perceptron (MLP) policy with a deep Q-network (DQN) imitation model to identify the stronger RL baseline, focusing on model performance, generalization, and a pick-up experiment. Second, three different VLA models were trained in two different scenarios and compared with each other. Third, the authors benchmarked the selected RL baseline against the VLA model using computational and sample-efficiency measures and then a robot experiment on a multistage panel installation task that included transport and installation. The VLA model demonstrates strong generalization and few-shot capability, achieving 60% and 100% success in the pick-up phase. In comparison, DQN can be made robust but needs additional noise during tuning, which increases the workload. Overall, the findings indicate that VLA offers practical advantages for changing tasks by reducing programming effort and enabling useful performance with minimal data, while DQN provides a viable baseline when sufficient tuning effort is acceptable.