Decentralised Collision Avoidance in a Semi-collaborative Multi-agent System

Hornauer, Sascha

doi:10.1007/978-3-642-40776-5_36

Cited by 5 publications

(8 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Its framework is given in Figure 1. (Fujii and Tanaka, 1971), (Goodwin, 1975), (Szlapczynski, 2006), (Wang et al, 2009) ship domain one-to-many centralised (Tsou and Hsueh, 2010), (Lazarowska, 2015) ant colony one-to-many centralised genetic algorithm one-to-many centralised (Lee et al, 2004) fuzzy theory one-to-many centralised (Lamb and Hunt, 1995;2000) probability one-to-many centralised (Szlapczynski, 2011; evolutionary algorithm many-to-many centralised (Hornauer, 2013), (Hornauer et al, 2015) Bayesian model many-to-many decentralised (Hu et al, 2008) negotiation one-to-one decentralised (Kim et al, 2014) local search many-to-many distributed (Kim et al, 2015) tabu search many-to-many distributed By the control procedure, a ship decides whether to proceed to the next position. If a ship does not have any target ship in the area within a certain distance from her current position and also has not yet arrived at her destination, she moves to the next position.…”

Section: I S T R I B U T E D S T O C H a S T I C S E A R C H A L G mentioning

confidence: 99%

See 1 more Smart Citation

Distributed Stochastic Search Algorithm for Multi-ship Encounter Situations

2017

View full text Add to dashboard Cite

Ship collision avoidance involves helping ships find routes that will best enable them to avoid a collision. When more than two ships encounter each other, the procedure becomes more complex since a slight change in course by one ship might affect the future decisions of the other ships. Two distributed algorithms have been developed in response to this problem: Distributed Local Search Algorithm (DLSA) and Distributed Tabu Search Algorithm (DTSA). Their common drawback is that it takes a relatively large number of messages for the ships to coordinate their actions. This could be fatal, especially in cases of emergency, where quick decisions should be made. In this paper, we introduce Distributed Stochastic Search Algorithm (DSSA), which allows each ship to change her intention in a stochastic manner immediately after receiving all of the intentions from the target ships. We also suggest a new cost function that considers both safety and efficiency in these distributed algorithms. We empirically show that DSSA requires many fewer messages for the benchmarks with four and 12 ships, and works properly for real data from the Automatic Identification System (AIS) in the Strait of Dover. K E Y W O R D S1. Ship collision avoidance.2. Distributed stochastic search algorithm. 3. Multiple ships control.

show abstract

Section: I S T R I B U T E D S T O C H a S T I C S E A R C H A L G mentioning

confidence: 99%

“…Hornauer (2013) and Hornauer et al (2015) proposed a decentralised trajectory optimisation algorithm to avoid collision between ships that are partly cooperating with each other. The movement for non-cooperative ships is computed by a Bayesian model using the data from AIS.…”

Section: Related Workmentioning

confidence: 99%

Distributed Stochastic Search Algorithm for Multi-ship Encounter Situations

2017

View full text Add to dashboard Cite

show abstract

“…The first papers on manoeuvers auto-negotiations, rejecting an axiom of having a central control point, emerged just recently. In papers (Hornauer, 2013; Hornauer and Hahn, 2013) a distributed system has been proposed in which ships negotiate their manoeuvers. The authors plan to base the optimization core on evolutionary sets of safe trajectories, following the paper (Szlapczynski, 2010).…”

Section: Literature Reviewmentioning

confidence: 99%

“…While this approach is natural for restricted harbor area, hardly it is possible for an encounter in open waters. Thus, recently a new idea of decentralized manoeuvers determination has emerged, as presented in (Hu et al, 2008;Hornauer, 2013;Hornauer and Hahn, 2013). It assumes that encountering ships communicate with each other without participation of any outer party and establish their further collision avoidance actions by means of negotiation.…”

Section: Introductionmentioning

confidence: 99%

Data Acquisition in a Manoeuver Auto-negotiation System

Szlapczynska

2015

TransNav

View full text Add to dashboard Cite

Typical approach to collision avoidance systems with artificial intelligence support is that such systems assume a central communication and management point (such as e.g. VTS station), usually located on shore. This approach is, however, not applicable in case of an open water encounter. Thus, recently a new approach towards collision avoidance has been proposed, assuming that all ships in the encounter, either restricted or open water, communicate with each other and negotiate their maneuvers, without involving any outer management or communication center. Usually the negotiation process is driven by the collision avoidance software and called auto-negotiation. This paper elaborates on data acquisition problem in case of the maneuver auto-negotiation. It focuses on shipsʹ initialization in the system and data gathering. http://www.transnav.eu the International Journal on Marine Navigation and Safety of Sea Transportation Volume 9 Number 3

show abstract

“…There have been many studies focusing on collision risk assessment [1][2][3][4][5]. The application of Integrated Bridge Systems incorporated on a ship and the corresponding new methods for determining safe ship trajectory [6][7][8] increase the safety of navigation.…”

Section: Introductionmentioning

confidence: 99%

A static position-adjustment method for the motion prediction of the Flexible Floating Collision-Prevention System

Chen

et al. 2018

Marine Structures

View full text Add to dashboard Cite

The Flexible Floating Collision-Prevention System (FFCPS), used to prevent collision between uncontrolled ships and non-navigational bridges, comprises cable chains, floating structures and mooring system. Its main working principle is to use the sliding of the mooring systems in the role of energy dissipation. It can convert the kinetic energy of the ship into internal energy, and thus achieve the effect of avoiding a ship collision. The force relationships between various components of the system and ensuing simplified numerical models are firstly established in order to study the movement of the FFCPS. Subsequently, using suitable assumptions, the method of position adjustment to approach equilibrium condition is introduced. This method is based on the concept of statically determinate equilibrium in each step. The feasibility of the method proposed in this paper is verified by comparing the calculated results with model test measurements and published reference predictions. From these comparisons it is concluded that this method can be used in the preliminary design stage of the FFCPS.

show abstract

Decentralised Collision Avoidance in a Semi-collaborative Multi-agent System

Cited by 5 publications

References 8 publications

Distributed Stochastic Search Algorithm for Multi-ship Encounter Situations

Distributed Stochastic Search Algorithm for Multi-ship Encounter Situations

Data Acquisition in a Manoeuver Auto-negotiation System

A static position-adjustment method for the motion prediction of the Flexible Floating Collision-Prevention System

Contact Info

Product

Resources

About