Autonomous Underwater Cognitive System for Adaptive Navigation: A SLAM-Integrated Cognitive Architecture
K. A. I. N Jayarathne, R. M. N. M. Rathnayaka, D. P. S. S. Peiris
TL;DR
The paper addresses autonomous deep-sea navigation in GPS-denied, dynamic environments. It proposes the Autonomous Underwater Cognitive System (AUCS), which couples SLAM with a Soar-based cognitive architecture to fuse perception, attention, planning, and learning. Key contributions include semantic mapping, adaptive sensor management, and memory-based learning that differentiate dynamic from static objects to improve long-term map consistency and autonomy. This approach has the potential to significantly enhance safety, reliability, and operational effectiveness for next-generation cognitive submersibles in deep-sea exploration.
Abstract
Deep-sea exploration poses significant challenges, including disorientation, communication loss, and navigational failures in dynamic underwater environments. This paper presents an Autonomous Underwater Cognitive System (AUCS) that integrates Simultaneous Localization and Mapping (SLAM) with a Soar-based cognitive architecture to enable adaptive navigation in complex oceanic conditions. The system fuses multi-sensor data from SONAR, LiDAR, IMU, and DVL with cognitive reasoning modules for perception, attention, planning, and learning. Unlike conventional SLAM systems, AUCS incorporates semantic understanding, adaptive sensor management, and memory-based learning to differentiate between dynamic and static objects, reducing false loop closures and enhancing long-term map consistency. The proposed architecture demonstrates a complete perception-cognition-action-learning loop, allowing autonomous underwater vehicles to sense, reason, and adapt intelligently. This work lays a foundation for next-generation cognitive submersible systems, improving safety, reliability, and autonomy in deep-sea exploration.