A novel intelligent collision avoidance algorithm based on deep reinforcement learning approach for USV

Editorial Material Multidisciplinary Sciences

Autonomous ships are on the horizon: here's what we need to know

Rudy R. Negenborn et al.

Summary: Ships and ports have the potential for unmanned operation, but the maritime industry must address practical, legal, and economic challenges beforehand.

NATURE (2023)

Add to Collection

Article Engineering, Civil

Deep Reinforcement Learning for Autonomous Driving: A Survey

B. Ravi Kiran et al.

Summary: This paper summarizes deep reinforcement learning algorithms, provides a taxonomy of automated driving tasks, discusses key computational challenges in real world deployment of autonomous driving agents, and explores adjacent domains as well as the role of simulators in training agents.

IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS (2022)

Add to Collection

Article Engineering, Marine

A dynamic collision avoidance solution scheme of unmanned surface vessels based on proactive velocity obstacle and set-based guidance

Wenming Wang et al.

Summary: This study introduces a proactive velocity obstacle (PVO) method and integrates it with the line of sight (LOS) algorithm to create a dynamic collision avoidance (DCA) solution for USVs. The proposed USV-DCA solution effectively avoids obstacles and complies with international collision prevention regulations at sea.

OCEAN ENGINEERING (2022)

Add to Collection

Article Engineering, Marine

COLREGs-abiding hybrid collision avoidance algorithm based on deep reinforcement learning for USVs

Xinli Xu et al.

Summary: An intelligent hybrid collision avoidance algorithm based on deep reinforcement learning is proposed in this paper to realize the autonomous collision avoidance of unmanned surface vehicles (USVs). The algorithm accurately judges the encounter situation and gives reasonable collision avoidance actions in a complex environment with dynamic and static obstacles.

OCEAN ENGINEERING (2022)

Add to Collection

Article Chemistry, Analytical

A Novel Reinforcement Learning Collision Avoidance Algorithm for USVs Based on Maneuvering Characteristics and COLREGs

Yunsheng Fan et al.

Summary: This paper investigates the problem of collision avoidance for unmanned surface vehicles (USVs) under the constraint of international regulations. A reinforcement learning collision avoidance algorithm that complies with USV maneuverability is proposed. The algorithm is tested in a marine simulation environment and shows a higher average reward.

SENSORS (2022)

Add to Collection

Article Multidisciplinary Sciences

Discovering faster matrix multiplication algorithms with reinforcement learning

Alhussein Fawzi et al.

Summary: Improving the efficiency of fundamental computations, such as matrix multiplication, is crucial for various fields, and machine learning can automate the discovery of efficient algorithms that surpass human-designed ones. AlphaTensor, based on deep reinforcement learning and AlphaZero, successfully discovered algorithms that outperform state-of-the-art ones. Its flexibility in accelerating algorithm discovery and optimization is showcased through different use-cases.

NATURE (2022)

Add to Collection

Article Engineering, Marine

APF-based intelligent navigation approach for USV in presence of mixed potential directions: Guidance and control design

Guoqing Zhang et al.

Summary: This paper investigates the real-time intelligent navigation approach for unmanned surface vehicles considering constraints of moving targets and obstacles. The proposed approach utilizes a dynamic virtual ship structure and artificial potential field technique to develop an intelligent guidance principle. Through improved repulsive potential field design, a reasonable obstacle avoidance capability is achieved. The robust neural path following control algorithm, based on minimal learning parameter and nonlinear disturbance observer techniques, is proposed to combine with the guidance method. Experimental results demonstrate the effectiveness of the proposed strategy in obstacle avoidance and dynamic tracking performance.

OCEAN ENGINEERING (2022)

Add to Collection

Article Engineering, Civil

A Formation Autonomous Navigation System for Unmanned Surface Vehicles With Distributed Control Strategy

Xiaojie Sun et al.

Summary: This study focuses on the formation autonomous navigation system (FANS) for unmanned surface vehicles (USVs), utilizing a leader-follower structure and distributed control strategy to provide autonomy within the system; the dynamic domain tunable fast marching square algorithm is used in the path planning subsystem, while the navigation control subsystem is based on finite control set model predictive control to quickly and safely guide and control the formation.

IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS (2021)

Add to Collection

Article Engineering, Ocean

Autonomous Collision Avoidance of Unmanned Surface Vehicles Based on Improved A Star And Minimum Course Alteration Algorithms

Cailei Liang et al.

Summary: The study improved the A star algorithm for automatic navigation by setting a safety distance, optimizing the planned route, and proposing the MCA algorithm, successfully avoiding various obstacles.

APPLIED OCEAN RESEARCH (2021)

Add to Collection

Article Engineering, Marine