MobRT：一种面向移动操作中可扩展学习的基于数字孪生的框架
MobRT: A Digital Twin-Based Framework for Scalable Learning in Mobile Manipulation
AI总结：
针对移动操作机器人高质量演示数据难获取的问题，提出基于数字孪生的框架MobRT，可自主生成两类复杂全身任务的真实演示数据，实验证明其能有效提升策略泛化性与性能。
摘要：
机器人技术的近期进展很大程度上由模仿学习推动，而模仿学习严重依赖大规模、高质量的演示数据。然而，收集这类数据仍是一项重大挑战——对于移动操作机器人而言尤其如此，这类机器人必须在高维、动态且部分可观测的环境中协调基座移动与机械臂操作。因此，现有多数研究仍聚焦于更简单的桌面场景，使得移动操作领域的探索相对不足。为弥补这一差距，我们提出MobRT，这是一种基于数字孪生的框架，旨在模拟两类主要的复杂全身任务：与铰接式物体的交互（例如开门和开抽屉）以及移动基座拾放操作。MobRT通过整合虚拟运动学控制与全身运动规划，自主生成多样化且真实的演示数据，实现连贯且物理一致的执行效果。我们在多种基线算法上评估了MobRT生成数据的质量，构建了综合基准，并证明任务成功率与生成轨迹数量之间存在强相关性。结合模拟与真实世界演示的实验证实，我们的方法显著提升了策略的泛化能力与性能，在模拟和真实环境中均取得了鲁棒的结果。
英文摘要：
Recent advances in robotics have been largely driven by imitation learning, which depends critically on large-scale, high-quality demonstration data. However, collecting such data remains a significant challenge-particularly for mobile manipulators, which must coordinate base locomotion and arm manipulation in high-dimensional, dynamic, and partially observable environments. Consequently, most existing research remains focused on simpler tabletop scenarios, leaving mobile manipulation relatively underexplored. To bridge this gap, we present \textit{MobRT}, a digital twin-based framework designed to simulate two primary categories of complex, whole-body tasks: interaction with articulated objects (e.g., opening doors and drawers) and mobile-base pick-and-place operations. \textit{MobRT} autonomously generates diverse and realistic demonstrations through the integration of virtual kinematic control and whole-body motion planning, enabling coherent and physically consistent execution. We evaluate the quality of \textit{MobRT}-generated data across multiple baseline algorithms, establishing a comprehensive benchmark and demonstrating a strong correlation between task success and the number of generated trajectories. Experiments integrating both simulated and real-world demonstrations confirm that our approach markedly improves policy generalization and performance, achieving robust results in both simulated and real-world 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。
