6G Research Center

MWC-Info

Mobile World Congress MWC Doha (25-26 November)

When LLMs meets immersive reality
Talk. Optimize. Immerse. Autonomously!
Optimize. Immerse. Autonomously!

Presented Aalto University,Finland, in collaboration with Khalifa University, UAE

Experience real-time semantic immersive streaming at MWC Doha 2025! Our end-to-end demo integrates 360° environmental sensing, LLM-powered 3D content generation, and immersive VR teleoperation, allowing users to explore remote environments visually and with tactile feedback.

Visitors can experience a live teleoperation of a 3D environment, with a digital twin that adapts and responds to user movements, creating a truly immersive encounter.

our system combines five key components:

1. VR User Interface

  • First-personVR control via HMD and joystick
  • Dualvisualization: 360° video + dynamically generated 3D scene

2. On-Board Computer & 360 Camera

  • Omnidirectional video capture and sensor telemetry (GPS, IMU, altimeter)
  • Image captioning through a Vision Language Model
  • Semantic annotations packaged in JSON and sent to the cloud

3. Cloud Server

  • Multi-agent LLM architecture:
    • LLM 1: Generates scene descriptions semantically
    • LLM 2: Converts descriptions into A-Frame-based 3D content for WebXR
  • Supports in-context learning and generates dynamic immersive 3D content

4. Edge Cloud Server

  • Low-latency delivery of 360° video and 3D content
  • Hosts WebXR interface and stores pre-generated content for fast rendering
  • Acts as MQTT broker for telemetry and haptic feedback

Visit Us at MWC Doha 2025

Discover how GenAI enables semantic immersive streaming. Explore VR teleoperation and interactive 3D worlds at our booth.

Arabic Autonomous Voice-to-Slice Operations

Showcasing an industry-first demo of AI-Powered autonomous private 5G. The demonstration shows how Arabic voice intent is transformed to validated network actions, all executed and enforced via O-RAN and AI-RAN compliant Telco APIs. Built as an industry–academia collaboration, the solution goes beyond simple transcription. It fuses reasoning-capable Large Language Models (LLMs) with telecom domain knowledge (local regulations, best practices, user behavior) to deliver decisions that are explainable, compliant, and production-ready.

Innovation

  • Autonomous Operations:an Arabic voice command is transformed into the right network configuration then validated and applied via O-RAN rApps.
  • Agentic Intelligence:BubbleRAN’s MX-AI framework with AI agents automating network operations using LLMs, SLMs, algorithms, and APIs. Task-specific agents orchestrated by higher-level agents to collaborate and resolve complex network operations.
  • Arabic-Native NetworksLLMs can power Arabic-language interaction with telecom networks. The system understands and reasons over Arabic user intents proving that network intelligence can now speak the language of its users.

Impact

  • Enable intelligent automation with zero-touch network management
  • Improved performance
  • Enhanced user experience in dynamic scenarios
  • Culturally aware approach to both operators and engineers

Intelligent RAN Optimization System Use Case : Cell Coverage and Performance

Deterministic Mathematical Optimization

  • Formal problem classification (e.g., Linear, Quadratic Programming).
  • Solving with proven mathematical solvers for verifiably optimal results.
  • Demonstrated for PRB % Allocation from formulation to execution.

LLM-Driven Optimization

  • End-to-end optimization performed by the LLM’s inherent reasoning.
  • Compatible with the mathematical pipeline following problem formalization.

Innovation

  • Mathematical:Classification and solving with mathematically-based algorithms.
  • Easy:Network optimization problem formulated though natural language input.
  • Improvement:AI agents capability to observe KPIs helps prediction of network behavior and optimization of configurations.
  • Immediately actionable:Demo shows ready-to-apply configuration changes in a standardized, automation-friendly format.

Impact

  • Network efficiency:Improved performance and load balancing
  • Lower OPEX:Enable intelligent automation with zero-touch network management
  • Use-case driven:Telco AI agents for network optimization available and personnalizable for your specific requirements