• Corpus ID: 211020892

Proportional integral derivative controller assisted reinforcement learning for path following by autonomous underwater vehicles

@article{Havenstrom2020ProportionalID,
  title={Proportional integral derivative controller assisted reinforcement learning for path following by autonomous underwater vehicles},
  author={Simen Theie Havenstrom and Camilla Sterud and Adil Rasheed and Omer San},
  journal={ArXiv},
  year={2020},
  volume={abs/2002.01022}
}
Control theory provides engineers with a multitude of tools to design controllers that manipulate the closed-loop behavior and stability of dynamical systems. These methods rely heavily on insights about the mathematical model governing the physical system. However, if a system is highly complex, it might be infeasible to produce a reliable mathematical model of the system. Without a model most of the theoretical tools to develop control laws break down. In these settings, machine learning… 

References

SHOWING 1-10 OF 46 REFERENCES
Path-Following Control of Autonomous Underwater Vehicles Subject to Velocity and Input Constraints via Neurodynamic Optimization
TLDR
A reference governor is proposed for computing optimal guidance signals within the velocity and input constraints and a projection neural network is employed for solving the optimization problem in real time.
Neural network based reinforcement learning control of autonomous underwater vehicles with control input saturation
TLDR
Simulation results show that the errors convergence to a adjustable neighborhood around zero, and optimization has been achieved in the sense of reinforcement learning.
Reinforcement Learning and Feedback Control: Using Natural Decision Methods to Design Optimal Adaptive Controllers
This article describes the use of principles of reinforcement learning to design feedback controllers for discrete- and continuous-time dynamical systems that combine features of adaptive control and
Output-Feedback Path-Following Control of Autonomous Underwater Vehicles Based on an Extended State Observer and Projection Neural Networks
TLDR
Simulation results substantiate the efficacy of the proposed method for output-feedback path-following of under-actuated autonomous underwater vehicles and prove that all error signals in the closed-loop system are uniformly and ultimately bounded.
Controller design for quadrotor UAVs using reinforcement learning
TLDR
A nonlinear autopilot for quadrotor UAVs based on feedback linearization is proposed and this controller is compared to an autopilot which has been learned by reinforcement learning using fitted value iteration with regard to design effort and performance.
Reinforcement learning for control: Performance, stability, and deep approximators
Autonomous underwater vehicle control using reinforcement learning policy search methods
TLDR
A high-level control system for solving the action selection problem of an autonomous robot, characterized by the use of reinforcement learning direct policy search methods (RLDPS) for learning the internal state/action mapping of some behaviors.
Deep reinforcement learning based optimal trajectory tracking control of autonomous underwater vehicle
TLDR
Based on theories and simulations, this algorithm is more accurate than traditional PID control in solving the trajectory tracking of AUV in complex curves to a certain precision.
Guidance Laws for Autonomous Underwater Vehicles
A mix between a monograph and an article collection, this PhD thesis considers the concept of guided motion control for marine vehicles, in particular focusing on underactuated marine surface
Nonlinear Path Following Control of an AUV
...
...