Research Analyzer
← Back ICRA 2026

Autonomous Balloon Based Adaptive Sliding Mode Control and Infinite-Horizon POMDP

Van Chung Nguyen, An Nguyen, Chuong Le, Gaurav Srikar, Thanh Nho Do, Hung La

PDF

AI summary

Key figure (auto-extracted from paper)
Combines adaptive altitude control with real-time wind estimation to enable autonomous balloon station-keeping under uncertainty.
Autonomous balloons Adaptive sliding mode control Infinite-horizon POMDP Real-time navigation Station-keeping Wind-optimal control

Problem

Existing balloon navigation methods rely on offline training, simulated validation, or simplified dynamics, failing to handle real-world thermodynamic and wind uncertainties in real time.

Approach

Integrates an adaptive sliding mode controller for robust altitude tracking with an infinite-horizon POMDP that continuously estimates wind direction and computes optimal navigation actions online.

Key results

  • Real-time wind estimation and robust altitude tracking via adaptive sliding mode control
  • Online POMDP framework for wind-optimal navigation without offline training
  • Lyapunov-proven stability against pressure, temperature, and wind disturbances
  • Validated through both simulation and real-world autonomous station-keeping experiments

Why it matters

Enables reliable, long-duration autonomous operations for aerial and underwater vehicles in complex, stratified flow environments.

Abstract

This paper presents a novel infinite-horizon Par- tially Observable Markov Decision Process (POMDP) frame- work with adaptive sliding mode control (ASMC) for au- tonomous navigation of the balloons. The proposed method integrates an altitude controller designed to account for thermo- dynamic and real-wind field constraints with an infinite-horizon POMDP for wind-optimal navigation. First, an adaptive sliding mode control is developed to ensure the balloon’s internal sta- bility under uncertainties in pressure, external wind fields, and temperature. Subsequently, a reference strategy is formulated using the infinite-horizon POMDP to exploit wind dynamics for station-keeping. The system estimates wind direction in real time and computes actions based on these observations. Experimental results demonstrate the framework’s ability to converge on efficient navigation policies while compensating for partial observability of wind dynamics. This approach is particularly suited for aerial or underwater vehicles operating in stratified flow environments, offering a computationally tractable solution for real-world deployment.

Index terms

Aerial Systems: Applications Planning under Uncertainty Robust/Adaptive Control

Related papers