A ship heading and speed control concept inherently satisfying actuator constraints

Sørensen, Mikkel Eske Nørgaard; Breivik, Morten; Eriksen, Bjørn-Olav Holtung

doi:10.1109/ccta.2017.8062483

Cited by 13 publications

(10 citation statements)

References 8 publications

(16 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Also, the cascaded control approach makes it possible to combine the controller with explicit constraint-handling algorithms such as e.g. the dynamic window algorithm [24], as preliminary suggested by the results in [25].…”

Section: F Discussionmentioning

confidence: 99%

Comparing Combinations of Linear and Nonlinear Feedback Terms for Ship Motion Control

2020

Self Cite

View full text Add to dashboard Cite

In this paper, combinations of linear and nonlinear feedback terms are investigated for 3 degrees-of-freedom pose and velocity control of ships. Nonlinear control algorithms that are found in the literature often have linear feedback terms, which result in nice globally exponential stability properties when assuming no actuator constraints. However, considering that all actuators have saturation constraints, such stability properties are not feasible in practice. Applying nonlinear feedback terms can be a step to handle such constraints. As a result, this paper explores nonlinear feedback terms for both the kinematic and kinetic control loops. Specifically, three controllers based on a cascaded backstepping control design are implemented and compared through simulations and model-scale experiments in an ocean basin. Stability properties and tuning rules for all the controllers are also provided. Interestingly, the use of nonlinear feedback terms gives the ability to constrain the feedback control inputs globally while simultaneously being able to change the convergence rates locally. The price to be paid is the introduction of additional tuning parameters. The three controller types are compared using performance metrics which consider both control accuracy and energy use. INDEX TERMS Ship motion control, Dynamic positioning, Cascaded backstepping control design, Nonlinear feedback terms, Tuning rules, Performance metrics, Experimental results.

show abstract

Section: F Discussionmentioning

confidence: 99%

Comparing Combinations of Linear and Nonlinear Feedback Terms for Ship Motion Control

2020

Self Cite

View full text Add to dashboard Cite

show abstract

“…In theory, independent and simultaneous acceleration in each degree of freedom allows it to navigate any trajectory in its state space. However, at high speeds, the bow thruster becomes less efficient, and the ship becomes underactuated ( Sørensen et al, 2017 ). Disabling the bow thruster input reduces the dimensionality of the action space while retaining sufficient and continuous control.…”

Section: Theorymentioning

confidence: 99%

Comparing Deep Reinforcement Learning Algorithms’ Ability to Safely Navigate Challenging Waters

et al. 2021

View full text Add to dashboard Cite

Reinforcement Learning (RL) controllers have proved to effectively tackle the dual objectives of path following and collision avoidance. However, finding which RL algorithm setup optimally trades off these two tasks is not necessarily easy. This work proposes a methodology to explore this that leverages analyzing the performance and task-specific behavioral characteristics for a range of RL algorithms applied to path-following and collision-avoidance for underactuated surface vehicles in environments of increasing complexity. Compared to the introduced RL algorithms, the results show that the Proximal Policy Optimization (PPO) algorithm exhibits superior robustness to changes in the environment complexity, the reward function, and when generalized to environments with a considerable domain gap from the training environment. Whereas the proposed reward function significantly improves the competing algorithms’ ability to solve the training environment, an unexpected consequence of the dimensionality reduction in the sensor suite, combined with the domain gap, is identified as the source of their impaired generalization performance.

show abstract

“…However, for the purpose of simplifying the RL agent's action space, we disregard the bow thruster in this study and allow only the aft thrusters and control surfaces to be applied by the RL agent as control signals. This omission is further motivated by the fact that bow thrusters have limited effectiveness at higher speeds [54]. Thus, the control vector can be modelled as…”

Section: ) Vessel Modelmentioning

confidence: 99%

COLREG-Compliant Collision Avoidance for Unmanned Surface Vehicle Using Deep Reinforcement Learning

et al. 2020

View full text Add to dashboard Cite

Path Following and Collision Avoidance, be it for unmanned surface vessels or other autonomous vehicles, are two fundamental guidance problems in robotics. For many decades, they have been subject to academic study, leading to a vast number of proposed approaches. However, they have mostly been treated as separate problems, and have typically relied on non-linear first-principles models with parameters that can only be determined experimentally. The rise of deep reinforcement learning in recent years suggests an alternative approach: end-to-end learning of the optimal guidance policy from scratch by means of a trial-and-error based approach. In this article, we explore the potential of Proximal Policy Optimization, a deep reinforcement learning algorithm with demonstrated state-of-the-art performance on Continuous Control tasks, when applied to the dual-objective problem of controlling an autonomous surface vehicle in a COLREGs compliant manner such that it follows an a priori known desired path while avoiding collisions with other vessels along the way. Based on high-fidelity elevation and AIS tracking data from the Trondheim Fjord, an inlet of the Norwegian sea, we evaluate the trained agent's performance in challenging, dynamic real-world scenarios where the ultimate success of the agent rests upon its ability to navigate nonuniform marine terrain while handling challenging, but realistic vessel encounters.

show abstract

A ship heading and speed control concept inherently satisfying actuator constraints

Cited by 13 publications

References 8 publications

Comparing Combinations of Linear and Nonlinear Feedback Terms for Ship Motion Control

Comparing Combinations of Linear and Nonlinear Feedback Terms for Ship Motion Control

Comparing Deep Reinforcement Learning Algorithms’ Ability to Safely Navigate Challenging Waters

COLREG-Compliant Collision Avoidance for Unmanned Surface Vehicle Using Deep Reinforcement Learning

Contact Info

Product

Resources

About