We had the pleasure of presenting our latest research at the 11th IEEE International Smart Cities Conference (ISC2 2025), themed “Resilient & Sustainable Smart Communities”, held in Patras, Greece.
Our paper, “A Holistic Perception System of Internal and External Monitoring for Ground Autonomous Vehicles: The AutoTRUST Paradigm,” showcased an AI-driven perception framework for autonomous vehicles that integrates three core layers:
- External monitoring: LiDAR-based super-resolution and semantic segmentation for accurate scene understanding.
- Internal monitoring: Multi-camera driver and occupant behavior analysis, including emotion recognition and air-quality sensing.
- Virtual assistant: An embedded Llama-3-powered module enabling context-aware, real-time in-vehicle interaction.
The complete system was validated on AviSense.AI and ALKE Vehicles platforms, demonstrating real-time performance and energy efficiency across both internal and external perception layers.
