Record Details

COLREGs-compliant dynamic collision avoidance algorithm based on deep deterministic policy gradient

NOPR - NISCAIR Online Periodicals Repository

View Archive Info
 
 
Field Value
 
Title COLREGs-compliant dynamic collision avoidance algorithm based on deep deterministic policy gradient
 
Creator Xu, X L
Zhou, X L
Cai, P
Chu, Z Z
 
Subject Collision avoidance
COLREGs
DDPG
Deep reinforcement learning
Unmanned surface vehicle
 
Description 978-987
In order to reduce collision avoidance accidents and improve the safety of ship navigation, a dynamic collision
avoidance algorithm based on deep reinforcement learning is proposed in this paper. In order to avoid the fuzziness and
uncertainty in the encounter process, the degree of risk is formulated to quantify the collision risk. International regulations
for preventing collisions at sea (COLREGs) are quantified reasonably. Considering the factors of collision, position, speed,
course and compliance with the COLREGs, the reward function of the algorithm is designed to ensure that the collision
avoidance decision is safe and effective and meet the requirements of the COLREGs. Based on DDPG algorithm, the sample
data processing mechanism is improved, the utilization rate of experience is improved, and the problems of long learning
time and unstable training are solved. The navigation and collision avoidance for multiple ships are simulated respectively.
The results show that this method can effectively avoid obstacle ships under the requirements of COLREGs, and it has good
real-time performance and safety.
 
Date 2022-03-14T09:50:04Z
2022-03-14T09:50:04Z
2021-11
 
Type Article
 
Identifier 2582-6727 (Online); 2582-6506 (Print)
http://nopr.niscair.res.in/handle/123456789/59319
 
Language en
 
Publisher NIScPR-CSIR, India
 
Source IJMS Vol.50(11) [November 2021]