English(EN) Cross-Platform Control for Autonomous Surface Vehicles via Adaptive Reinforcement Learning

自适应强化学习实现多样化自主航行器的零样本控制

作者 PulseAugur 编辑部 · [2 个来源] · 2026-07-02 11:04

研究人员开发了一种用于自主水面航行器轨迹跟踪的自适应强化学习方法。该方法允许在不同航行器上部署单一策略，无需事先调整，即使航行器特定动力学未知。该系统使用师生架构从交互历史中推断平台动力学，在真实世界实验中，与非自适应基线相比，位置平均绝对误差提高了高达58%。 AI

影响这项研究可以为各种平台的自主航行器实现更通用、更高效的控制系统。

排序理由详细介绍自主航行器新型控制方法的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]

AI 生成摘要 · Google Gemini · 来自 2 个来源。我们如何撰写摘要 →

报道来源 [2]

arXiv cs.LG TIER_1 English(EN) · Ruiheng Jiang, Thomas Bi, Raffaello D'Andrea, Aswin Ramachandran · 2026-07-03 04:00

Cross-Platform Control for Autonomous Surface Vehicles via Adaptive Reinforcement Learning

arXiv:2607.02037v1 Announce Type: cross Abstract: Autonomous surface vehicles vary widely in hydrodynamic and actuation characteristics, yet most controllers are designed for single-platform deployment. We present an adaptive reinforcement learning approach for trajectory trackin…
arXiv cs.LG TIER_1 English(EN) · Aswin Ramachandran · 2026-07-02 11:04

Cross-Platform Control for Autonomous Surface Vehicles via Adaptive Reinforcement Learning

Autonomous surface vehicles vary widely in hydrodynamic and actuation characteristics, yet most controllers are designed for single-platform deployment. We present an adaptive reinforcement learning approach for trajectory tracking that enables zero-shot cross-platform deployment…