> Details

Basrur, Chaithanya [Author]; Singh, Arambam James [Author]; Sinha, Arunesh [Author]; Kumar, Akshat [Author]; Kumar, T. K. Satish [Author] ; Chaithanya Basrur and Arambam James Singh and Arunesh Sinha and Akshat Kumar and T. K. Satish Kumar [Contributor]

Trajectory Optimization for Safe Navigation in Maritime Traffic Using Historical Data

Reference
management

Bookmarks

Remove from
bookmarks

Share this on Whatsapp

Close

Bookmarks



You can manage bookmarks using lists, please log in to your user account for this.
  • Media type: Text; E-Article; Electronic Conference Proceeding
  • Title: Trajectory Optimization for Safe Navigation in Maritime Traffic Using Historical Data
  • Contributor: Basrur, Chaithanya [Author]; Singh, Arambam James [Author]; Sinha, Arunesh [Author]; Kumar, Akshat [Author]; Kumar, T. K. Satish [Author]
  • imprint: Schloss Dagstuhl – Leibniz-Zentrum für Informatik, 2022
  • Language: English
  • DOI: https://doi.org/10.4230/LIPIcs.CP.2022.5
  • Keywords: Multi-Agent Path Coordination ; Maritime Traffic Control
  • Origination:
  • Footnote: Diese Datenquelle enthält auch Bestandsnachweise, die nicht zu einem Volltext führen.
  • Description: Increasing maritime trade often results in congestion in busy ports, thereby necessitating planning methods to avoid close quarter risky situations among vessels. Rapid digitization and automation of port operations and vessel navigation provide unique opportunities for significantly improving navigation safety. Our key contributions are as follows. First, given a set of future candidate trajectories for vessels in a traffic hotspot zone, we develop a multiagent trajectory optimization method to choose trajectories that result in the best overall close quarter risk reduction. Our novel MILP-based optimization method is more than an order-of-magnitude faster than a standard MILP for this problem, and runs in near real-time. Second, although automation has improved in maritime operations, current vessel traffic systems (in our case study of a busy Asian port) predict only a single future trajectory of a vessel based on linear extrapolation. Therefore, using historical data we learn a generative model that predicts multiple possible future trajectories of each vessel in a given traffic hotspot, reflecting past vessel movement patterns, and integrate it with our trajectory optimizer. Third, we validate our trajectory optimization and generative model extensively using a real world maritime traffic dataset containing 6 million Automated Identification System (AIS) data records detailing vessel movements over 1.5 years from one of the world’s busiest ports, demonstrating effective risk reduction.
  • Access State: Open Access