Ciarán Eising

Multimodal Fusion in Physical AI: Hardware-Aware Strategies for Robust Perception on Embedded Autonomous Driving Platforms

This survey addresses the fundamental challenge of deploying high-performance models for multimodal fusion in resource-constrained automotive environments, and organise state-of-the-art deep learning approaches into five paradigms—CNN-based, transformer-based, dense BEV-based, sparse-based, and hybrid—revealing trade-offs in accuracy, latency, and efficiency.