Research on autonomous collision avoidance of merchant ship based on inverse reinforcement learning

Zheng, Mao; Xie, Shuguo; Chu, Xiumin; Zhu, Tianquan; Tian, Guohao

doi:10.1177/1729881420969081

Cited by 9 publications

(5 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the study of reinforcement learning, Zhao et al [18] introduced a collision avoidance algorithm based on deep reinforcement learning and demonstrated its superiority over the PID algorithm by providing examples. Zheng et al [19] proposed an inverse reinforcement learning collision avoidance algorithm based on cross entropy and projection. Chun et al [20] presented a deep reinforcement learning-based PPO (Proximal Policy Optimization) algorithm and compared it with the A-star algorithm to prove its superiority.…”

Section: Recent Advancesmentioning

confidence: 99%

Research progress and prospects of intelligent planning algorithms in navigation collision avoidance

Jing

2023

Third International Conference on Advanced Algorithms and Signal Image Processing (AASIP 2023)

View full text Add to dashboard Cite

With the development of the shipping industry, maritime transportation is preferred by more and more people, and ship collision is the first problem to be solved in intelligent navigation. Compared with collision avoidance algorithms for ground vehicles and air vehicles, there are still many problems to be solved in ship collision avoidance algorithms, among which the dynamic nature, safety, and complexity of environments will impact the development of reliable automatic collision avoidance algorithms. By analyzing the latest research on ship collision avoidance, the paper concludes that the current research mainly focuses on the rapidity, stability, and adaptability of various algorithms in complex situations, moreover, some suggestions and research directions are proposed for further research.

show abstract

Section: Recent Advancesmentioning

confidence: 99%

Research progress and prospects of intelligent planning algorithms in navigation collision avoidance

Jing

2023

Third International Conference on Advanced Algorithms and Signal Image Processing (AASIP 2023)

View full text Add to dashboard Cite

show abstract

“…As far as the authors' knowledge, few studies have been conducted to apply IRL for ship collision avoidance problems. Zheng et al [21] introduced the projection-based IRL method [22] and derived the policy imitating sample data which had been acquired from a ship maneuvering simulator. Here, it can be noted that the encounter situations were limited to simple cases (only one-on-one), and the results did not indicate why the system took its actions.…”

Section: Introductionmentioning

confidence: 99%

Investigation and Imitation of Human Captains’ Maneuver Using Inverse Reinforcement Learning

Higaki

Hashimoto

Yoshioka

2022

Preprint

View full text Add to dashboard Cite

Automatic collision avoidance is of significant importance to prevent maritime collisions. Although many studies have been conducted in recent years, autonomous system has not completely replaced human captains since it is still difficult to imitate their complicated decisions. Thus, the present paper tries to investigate and imitate experienced captains’ maneuver using maximum entropy inverse reinforcement learning (MaxEnt IRL). We firstly verify that MaxEnt IRL can reproduce appropriate reward function from demonstrative trajectories. Afterwards, we conduct an experiment on a simulator where well-experienced captains maneuver in congested sea and estimate reward from the trajectories. Searching the route which maximizes the obtained reward, finally, we demonstrate the optimized route can avoid collision against multiple ships in compliance with the International Regulations for Preventing Collisions at Sea (COLREGs).

show abstract

“…As far as the authors' knowledge, few studies have been conducted to apply IRL for ship collision avoidance problems. Zheng et al 21) introduced the projectionbased IRL method 22) and derived the policy imitating sample data which had been acquired from a ship maneuvering simulator. Here, it can be noted that the encounter situations were limited to simple cases (only one-on-one), and the results did not indicate why the system took its actions.…”

Section: Introductionmentioning

confidence: 99%

Investigation and Imitation of Human Captains' Maneuver Using Inverse Reinforcement Learning

Higaki

Hashimoto²,

Yoshioka

2022

J.JASNAOE

View full text Add to dashboard Cite

Automatic collision avoidance is of significant importance to prevent maritime collisions. Although many studies have been conducted in recent years, autonomous system has not completely replaced human captains since it is still difficult to imitate their complicated decisions. Thus, the present paper tries to investigate and imitate experienced captains' maneuver using maximum entropy inverse reinforcement learning (MaxEnt IRL). We firstly verify that MaxEnt IRL can reproduce appropriate reward function from demonstrative trajectories. Afterwards, we conduct an experiment on a simulator where well-experienced captains maneuver in congested sea and estimate reward from the trajectories. Searching the route which maximizes the obtained reward, finally, we demonstrate the optimized route can avoid collision against multiple ships in compliance with the International Regulations for Preventing Collisions at Sea (COLREGs).

show abstract

Research on autonomous collision avoidance of merchant ship based on inverse reinforcement learning

Cited by 9 publications

References 28 publications

Research progress and prospects of intelligent planning algorithms in navigation collision avoidance

Research progress and prospects of intelligent planning algorithms in navigation collision avoidance

Investigation and Imitation of Human Captains’ Maneuver Using Inverse Reinforcement Learning

Investigation and Imitation of Human Captains' Maneuver Using Inverse Reinforcement Learning

Contact Info

Product

Resources

About