A Fast Initialization Method for Neural Network Controllers: A Case Study of Image-based Visual Servoing Control for the multicopter Interception
On the map: Deep reinforcement learning methods → RL theory and sample complexity
Abstract (arXiv)
Reinforcement learning-based controller design methods often require substantial data in the initial training phase. Moreover, the training process tends to exhibit strong randomness and slow convergence. It often requires considerable time or high computational resources. Another class of learning-based method incorporates Lyapunov stability theory to obtain a control policy with stability guarantees. However, these methods generally require an initially stable neural network control policy at the beginning of training. Evidently, a stable neural network controller can not only serve as an initial policy for reinforcement learning, allowing the training to focus on improving controller performance, but also act as an initial state for learning-based Lyapunov control methods. Although stable controllers can be designed using traditional control theory, designers still need to have a great deal of control design knowledge to address increasingly complicated control problems. The proposed neural network rapid initialization method in this paper achieves the initial training of the neural network control policy by constructing datasets that conform to the stability conditions based on the system model. Furthermore, using the image-based visual servoing control for multicopter interception as a case study, simulations and experiments were conducted to validate the effectiveness and practical performance of the proposed method. In the experiment, the trained control policy attains a final interception velocity of 15 m/s.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in RL theory and sample complexity, one of 15 directions in Deep reinforcement learning methods. Builds on 13 of its 22 references that are in the map. First posted on arXiv 23 Sep 2025.
Builds on
13 of 22 references.
References · 13
- 2018A Lyapunov-based Approach to Safe Reinforcement Learningcited by 297
- 2022Safe Control with Learned Certificates: A Survey of Neural Lyapunov, Barrier, and Contraction methodscited by 151
- 2019Lyapunov-based Safe Policy Optimization for Continuous Controlcited by 145
- 2020Neural Lyapunov Controlcited by 142
- 2021Safe Nonlinear Control Using Robust Neural Lyapunov-Barrier Functionscited by 94
- 2022Neural-Fly Enables Rapid Learning for Agile Flight in Strong Windscited by 85
- 2021Lyapunov-stable neural-network controlcited by 66
- 2020Actor-Critic Reinforcement Learning for Control with Stability Guaranteecited by 45
- 2021Stabilizing Neural Control Using Self-Learned Almost Lyapunov Criticscited by 35
- 2023Reinforcement Learning for Safe Robot Control using Control Lyapunov Barrier Functionscited by 13
- 2023Learning Stabilization Control from Observations by Learning Lyapunov-like Proxy Modelscited by 10
- 2022Control with Patterns: A D-learning Methodcited by 2
1 more
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2025Efficient Self-Supervised Neuro-Analytic Visual Servoing for Real-time Quadrotor Control
- 2026Stabilization Learning: A Paradigm Transition Bridging Control Theory and Machine Learning ↗
- 2026Learning to Fly: Stable Vision-Guided UAV Servoing with Compact Target-Centric Cues and Reinforcement Learning
- 2024Robust Optimal Safe and Stability Guaranteeing Reinforcement Learning Control for Quadcopter ↗
- 2024Stabilizing Dynamic Systems through Neural Network Learning: A Robust Approach ↗
- 2022Generating Stable and Collision-Free Policies through Lyapunov Function Learning
- 2022Learning Stable Dynamical Systems for Visual Servoing
- 2025Neural Lyapunov Function Approximation with Self-Supervised Reinforcement Learning