用于自主月球车对接的端到端视觉-语言-动作策略
End-to-End Vision-Language-Action Policies for Autonomous Lunar Rover Docking
AI总结：
本研究设计用于自主月球车对接的视觉-语言-动作策略，在高保真月球模拟中训练，闭环评估中其在训练未见过的感知干扰下表现与模块化基线相当，自适应时域执行可降低推理频率并限制危险接触率。
摘要：
月球表面导航面临极端光照对比度和部署时的感知干扰。长期以来，模块化导航流水线一直支持行星车导航，但测量误差会通过手工设计的组件传播，从而损害鲁棒性。端到端学习策略是导航的替代方法，它将观测直接映射到控制动作，无需中间组件。视觉-语言动作模型尤其在机器人和自动驾驶车辆研究中取得了重大突破，通过利用互联网规模的视觉-语言预训练，这些模型可利用其常识推理和视觉理解能力，在有限的特定任务数据下提供鲁棒的泛化能力。然而，其在月球表面作业中的适用性和性能尚未得到表征。本研究设计了一种用于自主月球车对接的视觉-语言-动作策略，并将其性能与模块化导航流水线进行了表征。我们开发了一个可扩展的训练框架，该框架在高保真月球模拟环境中生成感知安全的专家演示。在闭环评估中，我们的策略在训练期间未见过的感知干扰下，相对于模块化基线表现具有竞争力。为解决计算消耗与闭环安全性之间的权衡，该策略通过确定月球车在开环模式下可安全行驶的距离来调整其执行 horizon（执行时域）。在评估场景中，自适应时域执行降低了推理频率，同时相较于固定时域限制了危险接触率。
英文摘要：
Surface navigation on the Moon is subject to extreme illumination contrast and deployment-time perceptual disturbances. While modular navigation pipelines have long supported planetary rover navigation, robustness is compromised by measurement errors that propagate through hand-engineered components. End-to-end learned policies are an alternative approach to navigation, which maps observations directly to control actions without intermediate components. Vision-language-action models, in particular, have driven significant breakthroughs in robotics and autonomous vehicle research. By leveraging internet-scale vision-language pretraining, these models can be exploited for their commonsense reasoning and visual understanding to provide robust generalization with limited task-specific data. However, their applicability and performance have yet to be characterized for lunar surface operations. In this study, we design a vision-language-action policy for autonomous lunar rover docking and characterize its performance relative to a modular navigation pipeline. We develop a scalable training framework that generates safety-aware expert demonstrations in a high-fidelity lunar simulation environment. In closed-loop evaluations, our policy performs competitively relative to the modular baseline under perceptual disturbances unseen during training. To address the tradeoff between compute consumption and closed-loop safety, the policy adapts its execution horizon by determining how far the rover may safely travel in open loop. Adaptive-horizon execution reduces inference frequency while limiting hazard-contact rates relative to fixed horizons in the evaluated scenarios.
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。
