SLAM Architectures for Resource Constrained Robotics with 6G Enabled Communication and Swarm Intelligence

Abstract

The rapid advancement of robotics and autonomous systems has intensified the need for efficient and scalable Simultaneous Localization and Mapping (SLAM) solutions, particularly for resource-constrained platforms such as micro-robots and edge devices. This study proposes a next-generation SLAM architecture that integrates lightweight deep learning models, 6G-enabled communication, and swarm intelligence to enhance collaborative perception and navigation. The framework is designed to minimize computational overhead while maintaining high localization accuracy through efficient feature extraction and distributed processing. By leveraging 6G communication, multiple robotic agents can share mapping information in real time, enabling cooperative loop closure detection and global map optimization. Swarm intelligence principles further enhance system scalability, adaptability, and fault tolerance by allowing decentralized decision-making among agents. Experimental evaluations demonstrate improved performance in terms of accuracy, communication efficiency, and energy consumption compared to conventional SLAM systems. The proposed approach provides a robust and scalable solution for nextgeneration autonomous robotics operating in complex and resource-limited environments.