Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

KUNPENG: An Embodied Large Model for Intelligent Maritime

Naiyao Wang, Tongbang Jiang, Ye Wang, Shaoyang Qiu, Bo Zhang, Xinqiang Xie, Munan Li, Chunliu Wang, Yiyang Wang, Hongxiang Ren, Ruili Wang, Hongjun Shan, Hongbo Liu

TL;DR

Problem: Real-time decision-making in intelligent maritime under heterogeneous data. Approach: KUNPENG, the embodied large model for intelligent maritime, couples perception, brain-like cognition, autonomous decision, dual-path behavior, power optimization, and safe/emergency systems within a Perception-Cognition-Decision-Behavior loop and ego-motion imitation learning. Contributions: first embodiment of a large-model approach in intelligent maritime; a six-system architecture; ToM-based vessel interaction cognition; safety via credit-graph-based compliance; comprehensive maritime task performance. Significance: enhances safety, efficiency, and adaptability of autonomous ships within smart ocean networks and provides a data-driven, end-to-end framework for embodied maritime intelligence.

Abstract

Intelligent maritime, as an essential component of smart ocean construction, deeply integrates advanced artificial intelligence technology and data analysis methods, which covers multiple aspects such as smart vessels, route optimization, safe navigation, aiming to enhance the efficiency of ocean resource utilization and the intelligence of transportation networks. However, the complex and dynamic maritime environment, along with diverse and heterogeneous large-scale data sources, present challenges for real-time decision-making in intelligent maritime. In this paper, We propose KUNPENG, the first-ever embodied large model for intelligent maritime in the smart ocean construction, which consists of six systems. The model perceives multi-source heterogeneous data for the cognition of environmental interaction and make autonomous decision strategies, which are used for intelligent vessels to perform navigation behaviors under safety and emergency guarantees and continuously optimize power to achieve embodied intelligence in maritime. In comprehensive maritime task evaluations, KUNPENG has demonstrated excellent performance.

KUNPENG: An Embodied Large Model for Intelligent Maritime

TL;DR

Problem: Real-time decision-making in intelligent maritime under heterogeneous data. Approach: KUNPENG, the embodied large model for intelligent maritime, couples perception, brain-like cognition, autonomous decision, dual-path behavior, power optimization, and safe/emergency systems within a Perception-Cognition-Decision-Behavior loop and ego-motion imitation learning. Contributions: first embodiment of a large-model approach in intelligent maritime; a six-system architecture; ToM-based vessel interaction cognition; safety via credit-graph-based compliance; comprehensive maritime task performance. Significance: enhances safety, efficiency, and adaptability of autonomous ships within smart ocean networks and provides a data-driven, end-to-end framework for embodied maritime intelligence.

Abstract

Intelligent maritime, as an essential component of smart ocean construction, deeply integrates advanced artificial intelligence technology and data analysis methods, which covers multiple aspects such as smart vessels, route optimization, safe navigation, aiming to enhance the efficiency of ocean resource utilization and the intelligence of transportation networks. However, the complex and dynamic maritime environment, along with diverse and heterogeneous large-scale data sources, present challenges for real-time decision-making in intelligent maritime. In this paper, We propose KUNPENG, the first-ever embodied large model for intelligent maritime in the smart ocean construction, which consists of six systems. The model perceives multi-source heterogeneous data for the cognition of environmental interaction and make autonomous decision strategies, which are used for intelligent vessels to perform navigation behaviors under safety and emergency guarantees and continuously optimize power to achieve embodied intelligence in maritime. In comprehensive maritime task evaluations, KUNPENG has demonstrated excellent performance.
Paper Structure (14 sections, 3 figures)

This paper contains 14 sections, 3 figures.

Table of Contents

  1. Introduction
  2. Related Work
  3. General Large Models
  4. Embodied Large Models
  5. KUNPENG
  6. Workflow of the KUNPENG Model
  7. Main Systems
  8. Intelligent Perception
  9. Brain-like Cognition
  10. Autonomous Decision
  11. Dual-path Behavior
  12. Power Optimization
  13. Safe & Emergency
  14. Conclusions and Future Work

Figures (3)

  • Figure 1: Overall architecture of the KUNPENG embodied large model.
  • Figure 2: Intelligent maritime of the KUNPENG embodied large model, including Perception System, Cognition System, Decision System, Behavior System, Power System, and Safe & Emergency System.
  • Figure 3: Intelligent maritime of the KUNPENG embodied large model.