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

2026-05-02 · Xiaorui Wang, Hongwu Wang, Yue Fan, Hao Cheng, Feitian Zhang 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.

📄 PDF Abstract BibTeX arXiv:2605.01289

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement Learning

Learning Robust Control Policies for Inverted Pose on Miniature Blimp Robots

2026-02-27 · Yuanlin Yang, Lin Hong, Fumin Zhang arxiv

The ability to achieve and maintain inverted poses is essential for unlocking the full agility of miniature blimp robots (MBRs). However, developing reliable inverted control strategies for MBRs remains challenging due t…

Task and Domain Adaptive Reinforcement Learning for Robot Control

2024-04-29 · Yu Tang Liu, Nilaksh Singh, Aamir Ahmad

Deep reinforcement learning (DRL) has shown remarkable success in simulation domains, yet its application in designing robot controllers remains limited, due to its single-task orientation and insufficient adaptability t…

Deep Reinforcement Learning reinforcement-learning Reinforcement Learning Transfer Learning

Autonomous Docking of Multi-Rotor UAVs on Blimps under the Influence of Wind Gusts

2025-11-24 · Pascal Goldschmid, Aamir Ahmad arxiv

Multi-rotor UAVs face limited flight time due to battery constraints. Autonomous docking on blimps with onboard battery recharging and data offloading offers a promising solution for extended UAV missions. However, the v…

Finetuning Deep Reinforcement Learning Policies with Evolutionary Strategies for Control of Underactuated Robots

2025-07-14 · Marco Calì, Alberto Sinigaglia, Niccolò Turcato, Ruggero Carli 외 arxiv

Deep Reinforcement Learning (RL) has emerged as a powerful method for addressing complex control problems, particularly those involving underactuated robotic systems. However, in some cases, policies may require refineme…

Reinforcement Learning

Trajectory Tracking of Underactuated Sea Vessels With Uncertain Dynamics: An Integral Reinforcement Learning Approach

2021-04-01 · Mohammed Abouheaf, Wail Gueaieb, Md. Suruz Miah, Davide Spinello

Underactuated systems like sea vessels have degrees of motion that are insufficiently matched by a set of independent actuation forces. In addition, the underlying trajectory-tracking control problems grow in complexity …

Reinforcement Learning (RL)