mlsanityData to 14 Oct 2026

Bi-Level Reinforcement Learning Control for an Underactuated Blimp via Center-of-Mass Reconfiguration

arXiv 2605.01289 ↗First posted 2 May 2026cs.ROcited by 0

On the map: Deep reinforcement learning methods → RL for robot navigation and UAV control

Abstract (arXiv)

This paper investigates goal-directed tracking control of underactuated blimps with center-of-mass (CoM) reconfiguration. Unlike conventional overactuated blimp designs that rely on redundant actuation for simplified control, this paper focuses on a compact architecture consisting of two thrusters and a movable internal slider, aiming to improve energy efficiency and payload capacity. This hardware-efficient configuration introduces significant underactuation and strong nonlinear coupling between CoM dynamics and vehicle motion. To address these challenges, this paper proposes a bi-level reinforcement learning framework that explicitly decouples task-level CoM planning from continuous thrust control. The outer policy determines a target-dependent CoM configuration prior to flight, while the inner policy generates thrust commands to track straight-line references. To ensure stable learning, this paper introduces a two-stage learning strategy, supported by a convergence analysis of the resulting bi-level process. Extensive simulations and real-world experiments on a 27-goal evaluation set demonstrate that the proposed method consistently outperforms fixed-CoM baselines and PID-based controllers, achieving higher tracking accuracy, enhanced robustness, and reliable sim-to-real transfer.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in RL for robot navigation and UAV control, one of 15 directions in Deep reinforcement learning methods. Builds on 6 of its 38 references that are in the map. First posted on arXiv 2 May 2026.

Builds on

6 of 38 references.

References · 6

  1. 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,885
  2. 2024Task and Domain Adaptive Reinforcement Learning for Robot Controlcited by 4
  3. 2023Autonomous Blimp Control via H-infinity Robust Deep Residual Reinforcement Learningcited by 2
  4. 2024RGBlimp-Q: Robotic Gliding Blimp With Moving Mass Control Based on a Bird-Inspired Continuum Armcited by 2
  5. 2023RGBlimp: Robotic Gliding Blimp -- Design, Modeling, Development, and Aerodynamics Analysiscited by 1
  6. 2023SBlimp: Design, Model, and Translational Motion Control for a Swing-Blimpcited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Learning Robust Control Policies for Inverted Pose on Miniature Blimp Robots ↗
  2. 2026Path Planning and Reinforcement Learning-Driven Control of On-Orbit Free-Flying Multi-Arm Robots
  3. 2026Reinforcement Learning with Inner-loop Dynamics Estimator for Aerial Manipulation under Uncertainty
  4. 2026Prior Policy Guided Dual-Agent Coordinated Manipulation Planning of Spacecraft-Manipulator System ↗
  5. 2025Global End-Effector Pose Control of an Underactuated Aerial Manipulator via Reinforcement Learning
  6. 2025Deep Reinforcement Learning Policies for Underactuated Satellite Attitude Control
  7. 2024Whole-Body Control Through Narrow Gaps From Pixels To Action
  8. 2026Deep Reinforcement Learning for Spacecraft Attitude Control During Atmospheric Re-Entry