arXiv 2504.021612025-04-02cs.ROcs.CV

面向核退役中机器人巡检的偏好驱动主动3D场景表示

Preference-Driven Active 3D Scene Representation for Robotic Inspection in Nuclear Decommissioning

School of Computing Science, University of Glasgow（格拉斯哥大学计算科学学院）；University of Manchester（曼彻斯特大学）；James Watt School of Engineering, University of Glasgow（格拉斯哥大学詹姆斯·瓦特工程学院）

Zhen Meng, Kan Chen, Xiangmin Xu, Erwin Jose Lopez Pulgarin, Emma Li, Philip G. Zhao, David Flynn

备注：: This work has been submitted to IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) 2025

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

针对核退役巡检中视点选择忽略操作员目标的问题，提出一种基于RLHF的偏好驱动主动3D场景表示框架，通过专家输入重塑奖励函数优化路径规划，在提升场景表示的同时优化轨迹效率。

摘要：

主动3D场景表示在现代机器人应用中至关重要，包括远程巡检、操作和遥现。传统方法主要优化几何保真度或渲染精度，但往往忽略了操作员特定的目标，例如安全关键覆盖或任务驱动视点。这一局限性导致视点选择不佳，尤其是在核退役等受限环境中。为了弥补这一差距，我们引入了一种新颖的框架，将专家操作员偏好集成到主动3D场景表示流程中。具体而言，我们采用基于人类反馈的强化学习（RLHF）来指导机器人路径规划，根据专家输入重塑奖励函数。为了捕捉操作员特定的优先级，我们进行了交互式选择实验，以评估用户在3D场景表示中的偏好。我们使用UR3e机械臂在核退役场景中进行反应堆瓦片巡检，验证了我们的框架。与基线方法相比，我们的方法在优化轨迹效率的同时增强了场景表示。基于RLHF的策略始终优于随机选择，优先考虑任务关键细节。通过将显式3D几何建模与隐式人在回路优化相结合，这项工作为自适应、安全关键的机器人感知系统奠定了基础，为核退役、远程维护和其他高风险环境中增强自动化铺平了道路。

英文摘要：

Active 3D scene representation is pivotal in modern robotics applications, including remote inspection, manipulation, and telepresence. Traditional methods primarily optimize geometric fidelity or rendering accuracy, but often overlook operator-specific objectives, such as safety-critical coverage or task-driven viewpoints. This limitation leads to suboptimal viewpoint selection, particularly in constrained environments such as nuclear decommissioning. To bridge this gap, we introduce a novel framework that integrates expert operator preferences into the active 3D scene representation pipeline. Specifically, we employ Reinforcement Learning from Human Feedback (RLHF) to guide robotic path planning, reshaping the reward function based on expert input. To capture operator-specific priorities, we conduct interactive choice experiments that evaluate user preferences in 3D scene representation. We validate our framework using a UR3e robotic arm for reactor tile inspection in a nuclear decommissioning scenario. Compared to baseline methods, our approach enhances scene representation while optimizing trajectory efficiency. The RLHF-based policy consistently outperforms random selection, prioritizing task-critical details. By unifying explicit 3D geometric modeling with implicit human-in-the-loop optimization, this work establishes a foundation for adaptive, safety-critical robotic perception systems, paving the way for enhanced automation in nuclear decommissioning, remote maintenance, and other high-risk environments.

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。