Cooperative Mapping, Localization, and Beam Management via Multi-Modal SLAM in ISAC Systems

2025-07-08

AI Summary

To address the challenges of robust radio map construction, high-precision multi-user localization, and interference-aware beam management in dynamic heterogeneous environments for 6G mmWave integrated sensing and communication (ISAC) systems, this paper proposes a multimodal Bayesian SLAM framework. It achieves error-aware tightly coupled localization by fusing visual, inertial measurement unit (IMU), and wireless signal data; constructs a global RF map and generates user-specific beam selection priors to jointly optimize communication and sensing. The key innovation lies in deeply embedding SLAM theory into the ISAC protocol stack, enabling unified modeling of joint sensing–communication decision-making. Simulation results demonstrate a 60% improvement in RF map accuracy, a 37.5% reduction in localization error, and significantly enhanced spectral efficiency and interference resilience over conventional methods in both indoor and outdoor scenarios.

Technology Category

• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Machine Learning: Multimodal Learning
• Computer Vision: Multi-modal Vision

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Location- and context-aware Web and WoT applications and services
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization

Abstract

Simultaneous localization and mapping (SLAM) plays a critical role in integrated sensing and communication (ISAC) systems for sixth-generation (6G) millimeter-wave (mmWave) networks, enabling environmental awareness and precise user equipment (UE) positioning. While cooperative multi-user SLAM has demonstrated potential in leveraging distributed sensing, its application within multi-modal ISAC systems remains limited, particularly in terms of theoretical modeling and communication-layer integration. This paper proposes a novel multi-modal SLAM framework that addresses these limitations through three key contributions. First, a Bayesian estimation framework is developed for cooperative multi-user SLAM, along with a two-stage algorithm for robust radio map construction under dynamic and heterogeneous sensing conditions. Second, a multi-modal localization strategy is introduced, fusing SLAM results with camera-based multi-object tracking and inertial measurement unit (IMU) data via an error-aware model, significantly improving UE localization in multi-user scenarios. Third, a sensing-aided beam management scheme is proposed, utilizing global radio maps and localization data to generate UE-specific prior information for beam selection, thereby reducing inter-user interference and enhancing downlink spectral efficiency. Simulation results demonstrate that the proposed system improves radio map accuracy by up to 60%, enhances localization accuracy by 37.5%, and significantly outperforms traditional methods in both indoor and outdoor environments.

Problem

• Enhance cooperative multi-user SLAM in ISAC systems
• Improve multi-modal localization with sensor fusion
• Optimize beam management using sensing data

Innovation

• Bayesian estimation for cooperative multi-user SLAM
• Multi-modal fusion with camera and IMU data
• Sensing-aided beam management using radio maps