NemeSys: An Online Underwater Explorer with Goal-Driven Adaptive Autonomy

2025-07-16

AI Summary

To address the challenge of real-time mission reconfiguration for autonomous underwater vehicles (AUVs) in GPS-denied, low-bandwidth underwater environments, this paper proposes a buoy-assisted, semantics-driven online mission reconfiguration framework. Methodologically, it integrates optical-magneto-electric (OME) low-latency signaling, a distributed buoy relay network, semantic mission encoding, and an adaptive control architecture to enable tetherless, near-real-time semantic mission updates and interactive autonomous exploration. The key contribution lies in breaking away from conventional pre-programmed paradigms and overcoming the high-latency bottleneck of acoustic communication—marking the first integration of lightweight semantic parsing with physical-layer OME signaling for closed-loop dynamic mission execution underwater. Validated through analytical modeling, pool experiments, and open-sea trials, the system achieves mission replanning and response within seconds, significantly enhancing AUV adaptability and autonomy in complex marine environments.

Technology Category

• Planning, Routing, and Scheduling: Replanning and Plan Repair
• Multiagent Systems: Agent Communication
• Search and Optimization: Distributed Search

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Energy management for devices in mobile Web and WoT environments
• Search and Retrieval-Augmented AI: Vertical and domain-specific search
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Adaptive mission control and dynamic parameter reconfiguration are essential for autonomous underwater vehicles (AUVs) operating in GPS-denied, communication-limited marine environments. However, most current AUV platforms execute static, pre-programmed missions or rely on tethered connections and high-latency acoustic channels for mid-mission updates, significantly limiting their adaptability and responsiveness. In this paper, we introduce NemeSys, a novel AUV system designed to support real-time mission reconfiguration through compact optical and magnetoelectric (OME) signaling facilitated by floating buoys. We present the full system design, control architecture, and a semantic mission encoding framework that enables interactive exploration and task adaptation via low-bandwidth communication. The proposed system is validated through analytical modeling, controlled experimental evaluations, and open-water trials. Results confirm the feasibility of online mission adaptation and semantic task updates, highlighting NemeSys as an online AUV platform for goal-driven adaptive autonomy in dynamic and uncertain underwater environments.

Problem

• Enables real-time AUV mission reconfiguration in GPS-denied environments
• Reduces reliance on high-latency acoustic communication for AUV updates
• Supports adaptive autonomy via low-bandwidth optical/magnetoelectric signaling

Innovation

• Real-time mission reconfiguration via optical signaling
• Semantic mission encoding for low-bandwidth communication
• Goal-driven adaptive autonomy in dynamic environments