PyGemini: Unified Software Development towards Maritime Autonomy Systems

• URL: http://arxiv.org/abs/2506.06262v1
• Date: Fri, 06 Jun 2025 17:43:00 GMT
• Title: PyGemini: Unified Software Development towards Maritime Autonomy Systems
• Authors: Kjetil Vasstein, Christian Le, Simon Lervåg Breivik, Trygve Maukon Myhr, Annette Stahl, Edmund Førland Brekke,
• Abstract summary: PyGemini builds on the legacy of Autoferry Gemini to unify maritime autonomy development.<n>The framework functions as a stand-alone application, cloud-based service, or embedded library.<n>We demonstrate its versatility through a suite of maritime tools.
• Score: 2.088373411826489
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Ensuring the safety and certifiability of autonomous surface vessels (ASVs) requires robust decision-making systems, supported by extensive simulation, testing, and validation across a broad range of scenarios. However, the current landscape of maritime autonomy development is fragmented -- relying on disparate tools for communication, simulation, monitoring, and system integration -- which hampers interdisciplinary collaboration and inhibits the creation of compelling assurance cases, demanded by insurers and regulatory bodies. Furthermore, these disjointed tools often suffer from performance bottlenecks, vendor lock-in, and limited support for continuous integration workflows. To address these challenges, we introduce PyGemini, a permissively licensed, Python-native framework that builds on the legacy of Autoferry Gemini to unify maritime autonomy development. PyGemini introduces a novel Configuration-Driven Development (CDD) process that fuses Behavior-Driven Development (BDD), data-oriented design, and containerization to support modular, maintainable, and scalable software architectures. The framework functions as a stand-alone application, cloud-based service, or embedded library -- ensuring flexibility across research and operational contexts. We demonstrate its versatility through a suite of maritime tools -- including 3D content generation for simulation and monitoring, scenario generation for autonomy validation and training, and generative artificial intelligence pipelines for augmenting imagery -- thereby offering a scalable, maintainable, and performance-oriented foundation for future maritime robotics and autonomy research.

Related papers

• An OpenSource CI/CD Pipeline for Variant-Rich Software-Defined Vehicles [0.0]
  Software-defined vehicles (SDVs) offer a wide range of connected functionalities, including enhanced driving behavior and fleet management.<n>These features are continuously updated via over-the-air (OTA) mechanisms.<n>This paper presents an open-source CI/CD pipeline tailored for SDVs.
  arXiv  Detail & Related papers  (2025-07-25T17:26:36Z)
• Amico: An Event-Driven Modular Framework for Persistent and Embedded Autonomy [7.117236435809274]
  We present Amico, a modular, event-driven framework for building autonomous agents optimized for embedded systems.<n>Amico supports reactive, persistent agents that operate efficiently across embedded platforms and browser environments via WebAssembly.
  arXiv  Detail & Related papers  (2025-07-19T07:21:09Z)
• State and Memory is All You Need for Robust and Reliable AI Agents [29.259008600842517]
  Large language models (LLMs) have enabled powerful advances in natural language understanding and generation.<n>Yet their application to complex, real-world scientific remain limited by challenges in memory, planning, and tool integration.<n>Here, we introduce SciBORG, a modular agentic framework that allows LLM-based agents to autonomously plan, reason, and achieve robust and reliable domain-specific task execution.
  arXiv  Detail & Related papers  (2025-06-30T02:02:35Z)
• Control Plane as a Tool: A Scalable Design Pattern for Agentic AI Systems [2.997108944111501]
  This paper conducts a comprehensive review of the types of agents, their modes of interaction with the environment, and the infrastructural and architectural challenges that emerge.<n>We propose a reusable design abstraction: the "Control Plane as a Tool" pattern.<n>This pattern allows developers to expose a single tool interface to an agent while encapsulating modular tool routing logic behind it.
  arXiv  Detail & Related papers  (2025-05-11T02:58:50Z)
• An LLM-enabled Multi-Agent Autonomous Mechatronics Design Framework [49.633199780510864]
  This work proposes a multi-agent autonomous mechatronics design framework, integrating expertise across mechanical design, optimization, electronics, and software engineering.<n> operating primarily through a language-driven workflow, the framework incorporates structured human feedback to ensure robust performance under real-world constraints.<n>A fully functional autonomous vessel was developed with optimized propulsion, cost-effective electronics, and advanced control.
  arXiv  Detail & Related papers  (2025-04-20T16:57:45Z)
• Extending Lifetime of Embedded Systems by WebAssembly-based Functional Extensions Including Drivers [46.538276603099916]
  We present Wasm-IO, a framework designed to facilitate peripheral I/O operations within WebAssembly (Wasm) containers.<n>We detail synchronous I/O and methods for embedding platform-independent peripheral configurations within Wasm binaries.
  arXiv  Detail & Related papers  (2025-03-10T17:22:00Z)
• MOSS: Enabling Code-Driven Evolution and Context Management for AI Agents [7.4159044558995335]
  We introduce MOSS (llM-oriented Operating System Simulation), a novel framework that integrates code generation with a dynamic context management system. At its core, the framework employs an Inversion of Control container in conjunction with decorators to enforce the least knowledge principle. We show how this framework can enhance the efficiency and capabilities of agent development and highlight its advantages in moving towards Turing-complete agents.
  arXiv  Detail & Related papers  (2024-09-24T14:30:21Z)
• Very Large-Scale Multi-Agent Simulation in AgentScope [112.98986800070581]
  We develop new features and components for AgentScope, a user-friendly multi-agent platform. We propose an actor-based distributed mechanism towards great scalability and high efficiency. We also provide a web-based interface for conveniently monitoring and managing a large number of agents.
  arXiv  Detail & Related papers  (2024-07-25T05:50:46Z)
• Internet of Agents: Weaving a Web of Heterogeneous Agents for Collaborative Intelligence [79.5316642687565]
  Existing multi-agent frameworks often struggle with integrating diverse capable third-party agents. We propose the Internet of Agents (IoA), a novel framework that addresses these limitations. IoA introduces an agent integration protocol, an instant-messaging-like architecture design, and dynamic mechanisms for agent teaming and conversation flow control.
  arXiv  Detail & Related papers  (2024-07-09T17:33:24Z)
• Integration of Mixture of Experts and Multimodal Generative AI in Internet of Vehicles: A Survey [82.84057882105931]
  Generative AI (GAI) can enhance the cognitive, reasoning, and planning capabilities of intelligent modules in the Internet of Vehicles (IoV) We present the fundamentals of GAI, MoE, and their interplay applications in IoV. We discuss the potential integration of MoE and GAI in IoV, including distributed perception and monitoring, collaborative decision-making and planning, and generative modeling and simulation.
  arXiv  Detail & Related papers  (2024-04-25T06:22:21Z)
• AgentScope: A Flexible yet Robust Multi-Agent Platform [66.64116117163755]
  AgentScope is a developer-centric multi-agent platform with message exchange as its core communication mechanism. The abundant syntactic tools, built-in agents and service functions, user-friendly interfaces for application demonstration and utility monitor, zero-code programming workstation, and automatic prompt tuning mechanism significantly lower the barriers to both development and deployment.
  arXiv  Detail & Related papers  (2024-02-21T04:11:28Z)
• A Self-Integration Testbed for Decentralized Socio-technical Systems [2.8360662552057323]
  This paper introduces a novel testbed architecture for decentralized socio-technical systems running on the Internet of Things. It is designed for a seamless reusability of application-independent decentralized services by an IoT application, and different IoT applications by the same decentralized service. Pressure and crash tests during continuous operations of several weeks, with more than 80K network joining and leaving of agents, 2.4M parameter changes, and 100M communicated messages, confirm the robustness and practicality of the testbed architecture.
  arXiv  Detail & Related papers  (2020-02-06T12:18:28Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.