Marinarium提供低成本可复现的水下与太空类比机器人实验平台。
Marinarium: A Modular Experimental Facility for Reproducible Maritime and Space-Analog Field Robotics
- 模块化设计整合水下/空中操作区与运动捕捉系统。
- 支持四类实证研究,验证了从仿真到现实的迁移效果。
- 适合需真实环境测试但预算有限的海洋与航天机器人研究者。
海洋与太空领域野外机器人研究受限于低成本低保真度仿真与昂贵海上实验之间的差距。带传感器的水池虽部分弥补这一缺口,但常存在感知能力弱、实验功能受限及与仿真工具集成差的问题。为此,我们提出Marinarium——一个模块化、独立运行的实验设施,作为仿真与实地部署之间的成本效益型中间测试平台。Marinarium结合了全仪器化的水下与空中作业空间、运动捕捉(MoCap)系统、可伸缩屋顶实现遮蔽与露天操作、在SMaRCSim中实现的数字孪生,以及与平面空间机器人实验室的直接集成,支持海洋与水下太空类比实验。我们展示了该设施的设计理念,并通过四项代表性研究验证其能力:(i) 基于数据的水下车辆动力学辨识;(ii) 异构多域机器人会合;(iii) 利用学习的动力学残差实现水下机器人仿真到现实的迁移;(iv) 使用水下模拟器对航天器自主性进行跨域验证。这些研究共同表明,Marinarium可实现多个野外机器人挑战的可复现、仪器化实验,而无需昂贵的海上部署或仅靠仿真难以实现的研究。
原文摘要 · Abstract (English)
Field robotics research in maritime and space domains is constrained by a persistent gap between low-cost, low-fidelity simulation and costly offshore experimentation. Instrumented water tanks partially bridge this gap but often provide limited sensing, restricted experimental capabilities, and weak integration with simulation tools. To address these limitations, we present Marinarium, a modular, standalone experimental facility that provides a cost-effective intermediate testbed between simulation and field deployment. Marinarium combines a fully instrumented underwater and aerial operational volume with motion capture (MoCap), a retractable roof enabling both sheltered and open-air operation, a digital twin implemented in SMaRCSim, and direct integration with a planar space robotics laboratory, enabling both maritime and underwater space-analog experimentation. We present the design rationale of the facility and validate its capabilities through four representative studies in field robotics: (i) data-driven system identification of underwater vehicle dynamics; (ii) heterogeneous multi-domain robotic rendezvous; (iii) sim-to-real transfer for underwater robotics using learned dynamics residuals; and (iv) cross-domain validation of spacecraft autonomy using underwater surrogates. Together, these studies demonstrate that Marinarium enables reproducible, instrumented experimentation across multiple field robotics challenges that would otherwise require costly offshore deployments or be impractical to investigate using simulation alone.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品;中文卡片由大模型生成,请以原文为准。