Results 11 to 20 of about 10,103 (304)
No RL, No Simulation: Learning to Navigate without Navigating
CoRR, 2021 Most prior methods for learning navigation policies require access to simulation environments, as they need online policy interaction and rely on ground-truth maps for rewards. However, building simulators is expensive (requires manual effort for each and every scene) and creates challenges in transferring learned policies to robotic platforms in the ...
Meera Hahn +5 more
openaire +3 more sources
New Learning Methods for Marine Oil Spill Response Training [PDF]
TransNav, 2017 In Finland the Regional Fire and Rescue Services (RFRS) are responsible for near shore oil spill response and shoreline cleanup operations. In addition, they assist in other types of maritime incidents, such as search and rescue operations and fire ...
Justiina Halonen +2 more
doaj +1 more source
Benchmarking Projective Simulation in Navigation Problems
IEEE Access, 2018 Projective simulation (PS) is a model for intelligent agents with a deliberation capacity that is based on episodic memory. The model has been shown to provide a flexible framework for constructing reinforcement-learning agents, and it allows for quantum mechanical generalization, which leads to a speed-up in deliberation time.
Alexey A. Melnikov 0001 +2 more
openaire +4 more sources
Study on Manoeuvring Criteria for Safety Assessment in Shallow Water [PDF]
TransNav, 2017 The necessity of verifying manoeuvring mathematical models in shallow water for studying the safety of ships using a ship-handling simulator is pointed out in this report.
Shinya Nakamura
doaj +1 more source
Multi-Agent Maritime Traffic Simulator [PDF]
Modeling, Identification and ControlThis simulator is designed to support research on centralised game-theoretical algorithms for maritime traffic management. It supports an arbitrary number of vessels and land masses import.
Luka Grgicevic
doaj +1 more source
The Virtual Model of Deep Water Container Terminal T2 in Port Gdańsk [PDF]
TransNav, 2018 The level of education of seafarers currently depends among other things on the use of simulators in the training process. The reliability of the computer simulation depends on several factors such as own ship models or virtual training areas.
Piotr Zwolan, Krzysztof Czaplewski
doaj +1 more source
Automatic collision avoidance of ships [PDF]
, 2008 One of the key elements in automatic simulation of ship manoeuvring in confined waterways is route finding and collision avoidance. This paper presents a new practical method of automatic trajectory planning and collision avoidance based on an artificial
Han, D., Lee, B.S., Xue, Y.
core +1 more source
SIMULATION ASSESSMENT OF NEW GENERATION NAVIGATION STRATEGIES [PDF]
2018 Winter Simulation Conference (WSC), 2018 This research was funded by TRA2016-76914-C3-1-P of the Spanish R+D National Programs and by the Secretaria d’Universitats i Recerca de la Generalitat de Catalunya under 2017 SGR 1749.
Montero Mercadé, Lídia +5 more
openaire +2 more sources
Decoding Reinforcement Learning for Newcomers
IEEE Access, 2023 The Reinforcement Learning (RL) paradigm is showing promising results as a generic purpose framework for solving decision-making problems (e.g., robotics, games, finance). The aim of this work is to reduce the learning barriers and inspire young students,
Francisco S. Neves +4 more
doaj +1 more source
Generation of Electronic Nautical Chart Data for Assessment of Navigational Safety in Harbour and Waterway Design [PDF]
TransNav, 2010 Navigational simulator is widely applied in the assessment of Navigational Safety in the harbour and waterway design. According to the needs of ENC(Electronic Nautical Chart) data in the navigational assessment, this paper analyzes the source of ENC data,
Keping Guan +3 more
doaj