arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2512.14031cs.ROcs.AI
收藏

高效机器人技能学习用于建筑任务：评估分层强化学习与视觉-语言-动作VLA模型

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

Department of Civil Engineering, Stony Brook University（土木工程系，石溪大学）；Department of Civil and Environmental Engineering, Virginia Tech（土木与环境工程系，弗吉尼亚理工大学）；Department of Electrical and Computer Engineering, Virginia Tech（电气与计算机工程系，弗吉尼亚理工大学）

Zhaofeng Hu, Hongrui Yu, Vaidhyanathan Chandramouli, Ci-Jyun Liang

阅读 PDF
arXiv 页面 ↗HTML 原文 ↗

AI总结：

本研究比较了VLA模型和RL方法在建筑机器人技能学习中的效率与效果，发现VLA在泛化和少样本学习方面表现更优。

摘要：

本研究评估了两种领先的方案，用于教授建筑机器人新技能，以了解其在建筑自动化中的适用性：视觉-语言-动作（VLA）模型和强化学习（RL）方法。目标是理解任务表现和部署每种方法在实际作业中的实际努力。作者开发了两个遥控接口来控制机器人并收集所需演示，这两种方法都证明了有效，可用于训练机器人进行长时间跨度和灵巧任务。此外，作者进行了一种三阶段评估。首先，作者比较了多层感知器（MLP）策略与深度Q网络（DQN）模仿模型，以确定更强的RL基线，重点在于模型性能、泛化能力和抓取实验。其次，三种不同的VLA模型在两种不同的场景中进行训练并相互比较。第三，作者通过计算和样本效率指标以及多阶段面板安装任务的机器人实验，将选定的RL基线与VLA模型进行基准测试。VLA模型表现出强大的泛化能力和少量样本能力，在抓取阶段实现了60%和100%的成功率。相比之下，DQN可以变得稳健，但在调优过程中需要额外的噪声，这会增加工作量。总体而言，研究结果表明，VLA在改变任务时具有实际优势，通过减少编程工作量并以最少的数据实现有用的性能，而DQN在足够的调优工作量可接受时提供了一个可行的基线。

英文摘要：

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 both 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 conduct a three-stage evaluation. First, the authors compare a Multi-Layer 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 are trained in two different scenarios and compared with each other. Third, the authors benchmark the selected RL baseline against the VLA model using computational and sample-efficiency measures and then a robot experiment on a multi-stage panel installation task that includes transport and installation. The VLA model demonstrates strong generalization and few-shot capability, achieving 60% and 100% success in the pickup 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.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

↑