High-Altitude Balloon Station-Keeping with First Order Model Predictive Control

TL;DR

This paper demonstrates that a first-order model predictive control approach can effectively perform station-keeping for high-altitude balloons, outperforming reinforcement learning methods without requiring offline training.

Contribution

The paper introduces a first-order model predictive control method for high-altitude balloon station-keeping, showing its effectiveness over RL approaches and enabling online planning with differentiable dynamics.

Findings

FOMPC achieves 24% better time-within-radius than RL.

Online planning with FOMPC is effective across various models.

Differentiable dynamics enable gradient-based trajectory optimization.

Abstract

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 and uncertain wind forecasts. We revisit this assumption about the efficacy of model-based control for station-keeping by developing First-Order Model Predictive Control (FOMPC). By implementing the wind and balloon dynamics as differentiable functions in JAX, we enable gradient-based trajectory optimization for online planning. FOMPC outperforms a state-of-the-art RL policy, achieving a 24% improvement in time-within-radius (TWR) without requiring offline training, though at the cost of greater online computation per control step. Through systematic ablations of modeling assumptions and control factors, we show that online planning is effective across many configurations, including under simplified wind and dynamics models.