High-Altitude Balloon Station-Keeping with First Order Model Predictive Control
Myles Pasetsky, Jiawei Lin, Bradley Guo, Sarah Dean
高空气球(HABs)因其广泛的应用和低成本而在科学研究中很常见。 由于其非线性,不小的动力学和风场的部分可观测性,之前的工作主要依赖于无模型强化学习(RL)方法来设计近乎最优的站保持控制方案。 这些方法通常只与手工制作的后导方法进行比较,鉴于系统的复杂性和不确定的风预测,将基于模型的方法视为不切实际的。 我们通过开发一阶模型预测控制(FOMPC)来重新审视基于模型的控制对站保存的功效。 通过在 JAX 中实现风和气球动力学作为可微分函数,我们实现了基于梯度的轨迹优化,用于在线规划。 FOMPC优于最先进的RL政策,在半径内(TWR)上实现了24%的改善,而无需离线培训,尽管每个控制步骤的成本更高。 通过建模假设和控制因素的系统消融,我们表明在线规划在许多配置中是有效的,包括在简化的风和动力学模型下。
High-altitude balloons (HABs) are common in scientific research due to their wide range of applications and low cost. Because of their nonlinear, underactuated dynamics and the partial observability of wind fields, prior work has largely relied on model-free reinforcement learning (RL) methods to design near-optimal control schemes for station-keeping. These methods often compare only against hand-crafted heuristics, dismissing model-based approaches as impractical given the system complexity an...