arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2306.10352cs.RO
收藏

履带机器人摆臂控制的深度强化学习

Deep Reinforcement Learning for Flipper Control of Tracked Robots

National University of Defense Technology(国防科技大学)

Hainan Pan, Bailiang Chen, Kaihong Huang, Junkai Ren, Xieyuanli Chen, Huimin Lu

AI总结:

本文提出基于深度强化学习的AT-D3QN网络,实现履带机器人摆臂的自主控制,通过新奖励函数训练并在仿真中验证,性能优于手动遥控。

摘要:

摆臂的自主控制在增强履带机器人在复杂环境中的智能操作方面发挥着重要作用。现有方法主要依赖手工设计的控制模型,而在本文中,我们提出了一种新方法,利用深度强化学习(DRL)技术实现复杂地形中的自主摆臂控制。具体而言,我们提出了一种名为AT-D3QN的新型DRL网络,该网络能够确保履带机器人安全且平滑的摆臂控制。它包含两个模块:一个特征提取与融合模块,用于提取并整合机器人与环境状态特征;以及一个深度Q学习控制生成模块,用于结合专家知识以获得平滑且高效的控制策略。为了训练该网络,我们提出了一种新颖的奖励函数,同时考虑了学习效率和通过平滑性。我们使用Pymunk物理引擎构建了一个仿真环境用于训练。随后,我们将训练好的模型直接应用于更逼真的Gazebo仿真中进行定量分析。所提方法持续的高性能验证了其相对于手动遥控操作的优越性。

英文摘要:

The autonomous control of flippers plays an important role in enhancing the intelligent operation of tracked robots within complex environments. While existing methods mainly rely on hand-crafted control models, in this paper, we introduce a novel approach that leverages deep reinforcement learning (DRL) techniques for autonomous flipper control in complex terrains. Specifically, we propose a new DRL network named AT-D3QN, which ensures safe and smooth flipper control for tracked robots. It comprises two modules, a feature extraction and fusion module for extracting and integrating robot and environment state features, and a deep Q-Learning control generation module for incorporating expert knowledge to obtain a smooth and efficient control strategy. To train the network, a novel reward function is proposed, considering both learning efficiency and passing smoothness. A simulation environment is constructed using the Pymunk physics engine for training. We then directly apply the trained model to a more realistic Gazebo simulation for quantitative analysis. The consistently high performance of the proposed approach validates its superiority over manual teleoperation.

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。

↑