Cognitive modeling of waterborne traffic scenario incorporating COLREGs
CSTR:
Author:
Affiliation:

State Key Laboratory of Maritime Technology and Safety (Wuhan University of Technology), Wuhan 430063, China;National Engineering Research Center for Water Transport Safety (Wuhan University of Technology), Wuhan 430063, China;Sanya Science and Education Innovation Park, Wuhan University of Technology, Sanya 572000, Hainan, China

Clc Number:

U675

Fund Project:

  • Article
  • |
  • Figures
  • |
  • Metrics
  • |
  • Reference
  • |
  • Related
  • |
  • Cited by
  • |
  • Materials
  • |
  • Comments
    Abstract:

    To achieve semantic expression and reasoning of scenarios under the International Regulations for Preventing Collisions at Sea (COLREGs), enabling ships to understand and reason about waterborne traffic scenarios similarly to humans, a scenario cognition computing modeling method incorporating COLREGs is proposed. Based on the semantic description of waterborne traffic scenarios under COLREGs, this approach parses the scenarios into a comprehensive system of interactions among elements such as time, objects, attributes, relations, behaviors, and events, thereby constructing a conceptual model of waterborne traffic scenarios. It employs ontological modeling to structure the expression of the COLREGs scenario conceptual model. Through defining semantic computational operation functions and trigger sets, a COLREGs scenario cognition computing framework is established, leading to the proposal of a logic reasoning-based scenario cognition computing method. The model is validated with case studies using the environment of Xiamen Port and ship AIS data based on semantic extraction from scenarios. The results shows that, compared to data-driven model, the proposed model can describe and computationally process object attributes, ship behaviors, and traffic events in scenarios, and support the acquisition and querying of related knowledge of various elements within the scenario. The proposed scenario cognition modeling method is feasible and effective for enabling autonomous scenario cognition of ships under rule constraints.

    Reference
    Related
    Cited by
Get Citation
Related Videos

Article Metrics
  • Abstract:
  • PDF:
  • HTML:
  • Cited by:
History
  • Received:October 24,2023
  • Revised:
  • Adopted:
  • Online: October 19,2026
  • Published:
Article QR Code