A Decentralized Negotiation Protocol for Collaborative Collision Avoidance of Autonomous Surface Vehicles

Published: May 7, 2024

This study proposes a decentralized many-to-many negotiation protocol for collaborative collision avoidance of Autonomous Surface Vehicles (ASVs).The enables heterogeneous vehicles with different algorithms to negotiate in the same framework using asynchronous communication.To achieve fully decision-making, problem is modeled as Distributed Constraint Optimization Problem (DCOP) and solved Stochastic Search Algorithm (DSSA).Additionally, each vehicle adjusts its decision variables within range egocentric altruistic behaviors Monotonic Concession Protocol Fuzzy Logic.The proposed tested two reactive algorithms, considering some navigational rules (COLREG), verified both simulation field experiments.

Language: Английский

---

Research on Multi vessel Collision Avoidance Decision Considering China's Inland River Collision Avoidance Rules

Published: May 20, 2024

In order to quickly develop a multi ship collaborative collision avoidance plan in encounter scenarios, decision model is proposed accordance with the requirements of International Maritime Collision Avoidance Regulations, taking into account operations scenarios. Firstly, risk between ships determined by closest distance (DCPA) and time (TCPA). Secondly, objective function established based on rules, degree deviation, risk. Finally, prediction mechanism used calculate minimum value complete decision. The simulation results show that scenario multiple encounters, can achieve safe smaller steering frequency shorter col-lision time. provide reference for decision-making which helps im-prove efficiency

Language: Английский

---

A method for obtaining the starting set of formation based on IPSO

AIP Advances, Journal Year: 2024, Volume and Issue: 14(7)

Published: July 1, 2024

The formation of intelligent platforms is a multi-objective constraint problem. It necessary for the multi-agent to automatically generate path from initial position specified end point, and at same time meet constraints space collision avoidance on multi-target intersection agent’s motion ability, pursue shortest whole as much possible. In this paper, we propose an improved method obtaining starting set based particle swarm optimization. First, point defined, then optimization algorithm selected find best formation. Then turning performance platform studied, assembly route each agent designed by combining Dubins curve. simulation results show that proposed avoids between agents, shortens assembly, effectively ensures reliability route.

Language: Английский

---

Enhancing the Efficiency of Maritime Navigation Environmental Resource Management Based on Text Mining Techniques

Regional Studies in Marine Science, Journal Year: 2024, Volume and Issue: 81, P. 103988 - 103988

Published: Dec. 21, 2024

Language: Английский

---