Learning-based vs model-free adaptive control of a MAV under wind gust
From MaRDI portal
Abstract: Navigation problems under unknown varying conditions are among the most important and well-studied problems in the control field. Classic model-based adaptive control methods can be applied only when a convenient model of the plant or environment is provided. Recent model-free adaptive control methods aim at removing this dependency by learning the physical characteristics of the plant and/or process directly from sensor feedback. Although there have been prior attempts at improving these techniques, it remains an open question as to whether it is possible to cope with real-world uncertainties in a control system that is fully based on either paradigm. We propose a conceptually simple learning-based approach composed of a full state feedback controller, tuned robustly by a deep reinforcement learning framework based on the Soft Actor-Critic algorithm. We compare it, in realistic simulations, to a model-free controller that uses the same deep reinforcement learning framework for the control of a micro aerial vehicle under wind gust. The results indicate the great potential of learning-based adaptive control methods in modern dynamical systems.
Recommendations
- Learning-based adaptive control with an accelerated iterative adaptive law
- Attitude reinforcement learning control of an unmanned helicopter with verification
- Adaptive fuzzy control for a quadrotor helicopter robust to wind buffeting
- An adaptive neural network approach to the tracking control of micro aerial vehicles in constrained space
- Novel Levenberg-Marquardt based learning algorithm for unmanned aerial vehicles
Cites work
- A comprehensive survey on safe reinforcement learning
- A simple dual control problem with an analytical solution
- adaptive controller for systems with unknown time-varying parameters and disturbances in the presence of non-zero trajectory initialization error
- Adaptive dual control. Theory and applications.
- Decision-Making in a Fuzzy Environment
- Failures of adaptive control theory and their resolution
- Gaussian processes for machine learning (GPML) toolbox
- scientific article; zbMATH DE number 3148886 (Why is no real title available?)
- scientific article; zbMATH DE number 5497005 (Why is no real title available?)
- Multi-parametric extremum seeking-based iterative feedback gains tuning for nonlinear control
- Real‐Time Optimization by Extremum‐Seeking Control
- Reinforcement learning. An introduction
- Self-tuning regulators for a class of multivariable systems
- Sliding modes in control and optimization. Transl. from the Russian
- Some Fundamental Control Theory II: Feedback Linearization of Single Input Nonlinear Systems
Cited in
(5)- A neuro-evolutionary approach to control surface segmentation for micro aerial vehicles
- Control policy learning design for vehicle urban positioning via BeiDou navigation
- Robust model‐free adaptive longitudinal flight control for a flapping wing micro air vehicle with wind disturbances
- A comparative analysis of reinforcement learning and adaptive control techniques for linear uncertain systems
- Online model-free reinforcement learning for the automatic control of a flexible wing aircraft
This page was built for publication: Learning-based vs model-free adaptive control of a MAV under wind gust
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2101765)
