arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 2106.14130cs.AIcs.RO
收藏

基于深度强化学习的自主船舶连续控制

Continuous Control with Deep Reinforcement Learning for Autonomous Vessels

Memorial University of Newfoundland(纽芬兰纪念大学)

Nader Zare, Bruno Brandoli, Mahtab Sarvmaili, Amilcar Soares, Stan Matwin

摘要:

海上自主运输在世界经济全球化中发挥了至关重要的作用。深度强化学习(DRL)已被应用于自动路径规划,以模拟公海中的船舶避碰情况。直接从输入中学习复杂映射的端到端方法在不同环境中达到目标的泛化能力很差。在这项工作中,我们提出了一种新的策略,称为状态动作旋转,以提高代理的性能在看不见的情况下,通过旋转获得的经验(状态动作状态),并将它们保存在重放缓冲区。我们设计了基于深度确定性策略梯度、局部视图生成器和规划器的模型。我们的代理使用两个深度卷积神经网络来估计策略和动作-价值函数。拟议的模型在蒙特利尔和哈利法克斯等城市的真实地图上进行了详尽的训练和海上场景测试。实验结果表明,CVN上的状态-动作旋转一致地将到达目的地的速率(RATD)提高了11.96%,相对于具有计划器和局部视图的血管导航器(VNPLV),并且在不可见映射中实现了高达30.82%的卓越性能。当在新环境中进行测试时,我们提出的方法在鲁棒性方面表现出优势,支持了可以通过使用状态-动作旋转来实现泛化的想法。

英文摘要:

Maritime autonomous transportation has played a crucial role in the globalization of the world economy. Deep Reinforcement Learning (DRL) has been applied to automatic path planning to simulate vessel collision avoidance situations in open seas. End-to-end approaches that learn complex mappings directly from the input have poor generalization to reach the targets in different environments. In this work, we present a new strategy called state-action rotation to improve agent's performance in unseen situations by rotating the obtained experience (state-action-state) and preserving them in the replay buffer. We designed our model based on Deep Deterministic Policy Gradient, local view maker, and planner. Our agent uses two deep Convolutional Neural Networks to estimate the policy and action-value functions. The proposed model was exhaustively trained and tested in maritime scenarios with real maps from cities such as Montreal and Halifax. Experimental results show that the state-action rotation on top of the CVN consistently improves the rate of arrival to a destination (RATD) by up 11.96% with respect to the Vessel Navigator with Planner and Local View (VNPLV), as well as it achieves superior performance in unseen mappings by up 30.82%. Our proposed approach exhibits advantages in terms of robustness when tested in a new environment, supporting the idea that generalization can be achieved by using state-action rotation.

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。

↑