scholarly journals An Approach to Solving of Collision Avoidance Problem Based on a New Concept : Circumstantial Judgment Neural Networks

1991 ◽  
Vol 85 (0) ◽  
pp. 1-8
Author(s):  
Masaaki INAISHI ◽  
Hayama IMAZU ◽  
Akio M. SUGISAKI
Keyword(s):  
Neural Networks ◽  
Collision Avoidance ◽  
Avoidance Problem

Automatic Control of Underway Replenishment Maneuvers in a Random Sea

1978 ◽  
Vol 22 (01) ◽  
pp. 20-28
Author(s):  
Reidar Alvestad
Keyword(s):  
Computer Simulation ◽  
Automatic Control ◽  
Collision Avoidance ◽  
Nonlinear Interaction ◽  
Interaction Forces ◽  
Random Seas ◽  
Close Proximity ◽  
Controller Performance ◽  
Hybrid Computer ◽  
Avoidance Problem

This paper describes a hybrid computer simulation of two ships performing replenishment operations in random seas. Such operations present collision hazards due to the nonlinear interaction forces and moments which result from close proximity maneuvering while underway. Maneuvers are simulated to demonstrate automatic controller performance during station-keeping, station-changing, and the approach and breakaway phases of typical underway replenishment (UNREP) operations. Results indicate that automatic control should be considered as a possible solution to the UNREP collision avoidance problem.

scholarly journals Model predictive ship collision avoidance based on Q-learning beetle swarm antenna search and neural networks

2019 ◽  
Vol 193 ◽  
pp. 106609 ◽  
Author(s):  
Shuo Xie ◽  
Vittorio Garofano ◽  
Xiumin Chu ◽  
Rudy R. Negenborn
Keyword(s):  
Neural Networks ◽  
Collision Avoidance ◽  
Q Learning ◽  
Ship Collision

scholarly journals Velocity Obstacle Approaches for Multi-Agent Collision Avoidance

2019 ◽  
Vol 07 (01) ◽  
pp. 55-64 ◽  
Author(s):  
James A. Douthwaite ◽  
Shiyu Zhao ◽  
Lyudmila S. Mihaylova
Keyword(s):  
Collision Avoidance ◽  
Critical Analysis ◽  
Monte Carlo Analysis ◽  
The Other ◽  
Multi Agent Systems ◽  
Agent Systems ◽  
Multi Agent ◽  
Velocity Obstacle ◽  
Scalable Computation ◽  
Avoidance Problem

This paper presents a critical analysis of some of the most promising approaches to geometric collision avoidance in multi-agent systems, namely, the velocity obstacle (VO), reciprocal velocity obstacle (RVO), hybrid-reciprocal velocity obstacle (HRVO) and optimal reciprocal collision avoidance (ORCA) approaches. Each approach is evaluated with respect to increasing agent populations and variable sensing assumptions. In implementing the localized avoidance problem, the author notes a problem of symmetry not considered in the literature. An intensive 1000-cycle Monte Carlo analysis is used to assess the performance of the selected algorithms in the presented conditions. The ORCA method is shown to yield the most scalable computation times and collision likelihood in the presented cases. The HRVO method is shown to be superior than the other methods in dealing with obstacle trajectory uncertainty for the purposes of collision avoidance. The respective features and limitations of each algorithm are discussed and presented through examples.

scholarly journals Ship-Collision Avoidance Decision-Making Learning of Unmanned Surface Vehicles with Automatic Identification System Data Based on Encoder—Decoder Automatic-Response Neural Networks

2020 ◽  
Vol 8 (10) ◽  
pp. 754
Author(s):  
Miao Gao ◽  
Guo-You Shi
Keyword(s):  
Neural Networks ◽  
Decision Making ◽  
Time Series ◽  
Collision Avoidance ◽  
Time Series Data ◽  
Series Data ◽  
Automatic Identification ◽  
Identification System ◽  
Automatic Response ◽  
Ship Collision

Intelligent unmanned surface vehicle (USV) collision avoidance is a complex inference problem based on current navigation status. This requires simultaneous processing of the input sequences and generation of the response sequences. The automatic identification system (AIS) encounter data mainly include the time-series data of two AIS sets, which exhibit a one-to-one mapping relation. Herein, an encoder–decoder automatic-response neural network is designed and implemented based on the sequence-to-sequence (Seq2Seq) structure to simultaneously process the two AIS encounter trajectory sequences. Furthermore, this model is combined with the bidirectional long short-term memory recurrent neural networks (Bi-LSTM RNN) to obtain a network framework for processing the time-series data to obtain ship-collision avoidance decisions based on big data. The encoder–decoder neural networks were trained based on the AIS data obtained in 2018 from Zhoushan Port to achieve ship collision avoidance decision-making learning. The results indicated that the encoder–decoder neural networks can be used to effectively formulate the sequence of the collision avoidance decision of the USV. Thus, this study significantly contributes to the increased efficiency and safety of maritime transportation. The proposed method can potentially be applied to the USV technology and intelligent collision-avoidance systems.

Collision avoidance for mobile robots based on artificial potential field and obstacle envelope modelling

2016 ◽  
Vol 36 (3) ◽  
pp. 318-332 ◽  
Author(s):  
Zhenyu Wu ◽  
Guang Hu ◽  
Lin Feng ◽  
Jiping Wu ◽  
Shenglan Liu
Keyword(s):  
Mobile Robot ◽  
Collision Avoidance ◽  
Potential Field ◽  
Dimensional Space ◽  
Three Dimensional ◽  
Artificial Potential Field ◽  
Content Type ◽  
Negative Pole ◽  
Avoidance Problem ◽  
Three Dimensional Space

Purpose This paper aims to investigate the collision avoidance problem for a mobile robot by constructing an artificial potential field (APF) based on geometrically modelling the obstacles with a new method named the obstacle envelope modelling (OEM). Design/methodology/approach The obstacles of arbitrary shapes are enveloped in OEM using the primitive, which is an ellipse in a two-dimensional plane or an ellipsoid in a three-dimensional space. As the surface details of obstacles are neglected elegantly in OEM, the workspace of a mobile robot is made simpler so as to increase the capability of APF in a clustered environment. Findings Further, a dipole is applied to the construction of APF produced by each obstacle, among which the positive pole pushes the robot away and the negative pole pulls the robot close. Originality/value As a whole, the dipole leads the robot to make a derivation around the obstacle smoothly, which greatly reduces the local minima and trajectory oscillations. Computer simulations are conducted to demonstrate the effectiveness of the proposed approach.

Sign in / Sign up

Export Citation Format

Share Document