Learning-Aided Control of Robotic Tether-Net with Maneuverable Nodes to Capture Large Space Debris

📄 arXiv: 2403.07125v1 📥 PDF

作者: Achira Boonrath, Feng Liu, Elenora M. Botta, Souma Chowdhury

分类: eess.SY

发布日期: 2024-03-11

备注: This paper was accepted for presentation in proceedings of IEEE International Conference on Robotics and Automation 2024

💡 一句话要点

提出基于学习辅助控制的可机动缆网系统以捕获大型太空垃圾

🎯 匹配领域: 支柱二：RL算法与架构 (RL & Architecture)

关键词: 太空垃圾清理 强化学习 去中心化控制 轨迹规划 机器人技术 机动单元 PID控制

📋 核心要点

  1. 核心问题：现有的太空垃圾捕获方法在机动性和适应性方面存在挑战，难以应对复杂的发射场景。
  2. 方法要点：论文提出了一种基于强化学习的去中心化控制策略，通过计算机学习优化机动单元的轨迹规划。
  3. 实验或效果：仿真实验结果显示，该方法在捕获成功率和燃料消耗方面均优于传统基线，尤其在垃圾位置偏离的情况下。

📝 摘要（中文）

可机动缆网系统从无人飞船发射，为主动清除大型太空垃圾提供了有前景的解决方案。成功捕获太空垃圾依赖于缆网系统的可靠机动能力。本文将此问题表示为一种分层去中心化的机器人轨迹规划与控制实现，并在两种不同的缆网系统中验证了该方法的有效性。采用强化学习设计集中轨迹规划器，根据目标垃圾的相对位置计算每个机动单元的最终瞄准位置。每个机动单元使用去中心化PID控制器跟随分配的轨迹，系统性能通过捕获成功率和整体燃料消耗进行评估。仿真实验表明，该方法在燃料成本上显著低于基线，尤其在垃圾位置偏离飞船的情况下。

🔬 方法详解

问题定义：本文旨在解决大型太空垃圾的捕获问题，现有方法在复杂发射场景下的机动性不足，导致捕获成功率低。

核心思路：通过引入强化学习，设计集中式轨迹规划器，计算机学习能够根据目标垃圾的相对位置优化机动单元的轨迹，从而提高捕获成功率。

技术框架：整体架构包括集中式轨迹规划和去中心化控制两个主要模块。集中式模块负责计算机动单元的最终瞄准位置，去中心化模块则通过PID控制器执行轨迹跟踪。

关键创新：最重要的创新在于将强化学习与去中心化控制相结合，形成了一种新的轨迹规划方法，显著提高了系统的适应性和捕获效率。

关键设计：采用了奖励塑形和代理模型来引导和加速强化学习过程，去中心化PID控制器则根据传感器反馈调整机动单元的推力向量，确保系统在噪声环境下的稳定性。

📊 实验亮点

实验结果表明，该方法在捕获成功率和燃料消耗方面显著优于传统基线，尤其在垃圾位置偏离的情况下，燃料成本降低幅度明显，展现出良好的实际应用潜力。

🎯 应用场景

该研究的潜在应用领域包括太空垃圾清理、卫星维护及轨道管理等。通过提高捕获效率和降低燃料消耗，能够为未来的太空任务提供更可持续的解决方案，减少太空环境的污染。

📄 摘要（原文）

Maneuverable tether-net systems launched from an unmanned spacecraft offer a promising solution for the active removal of large space debris. Guaranteeing the successful capture of such space debris is dependent on the ability to reliably maneuver the tether-net system -- a flexible, many-DoF (thus complex) system -- for a wide range of launch scenarios. Here, scenarios are defined by the relative location of the debris with respect to the chaser spacecraft. This paper represents and solves this problem as a hierarchically decentralized implementation of robotic trajectory planning and control and demonstrates the effectiveness of the approach when applied to two different tether-net systems, with 4 and 8 maneuverable units (MUs), respectively. Reinforcement learning (policy gradient) is used to design the centralized trajectory planner that, based on the relative location of the target debris at the launch of the net, computes the final aiming positions of each MU, from which their trajectory can be derived. Each MU then seeks to follow its assigned trajectory by using a decentralized PID controller that outputs the MU's thrust vector and is informed by noisy sensor feedback (for realism) of its relative location. System performance is assessed in terms of capture success and overall fuel consumption by the MUs. Reward shaping and surrogate models are used to respectively guide and speed up the RL process. Simulation-based experiments show that this approach allows the successful capture of debris at fuel costs that are notably lower than nominal baselines, including in scenarios where the debris is significantly off-centered compared to the approaching chaser spacecraft.