Raz Halaly

Papers

Total Citations

H-Index

About

Raz Halaly is a leading researcher at the intersection of neuromorphic computing and autonomous systems, with a primary focus on brain-inspired control architectures for real-world robotics. His most impactful contribution is the development of a LiDAR-driven spiking neural network for collision avoidance in autonomous driving, a pioneering work that has garnered 24 citations since its 2021 publication. This research demonstrates how neuromorphic implementations can outperform conventional control paradigms by leveraging the temporal precision of event-based sensing and the energy efficiency of spiking neural networks. Halaly’s work addresses a critical bottleneck in autonomous vehicle safety—real-time obstacle detection and avoidance—by integrating low-level sensor data with high-level decision-making in a biologically plausible framework. His contributions are particularly notable for bridging the gap between theoretical neuromorphic computing and practical deployment in dynamic environments. By showing that brain-inspired algorithms can achieve superior performance in latency-sensitive tasks like collision avoidance, Halaly has opened new pathways for energy-efficient, real-time control in autonomous driving and robotics. His research continues to influence the growing field of neuromorphic engineering, offering a compelling alternative to traditional deep learning approaches for safety-critical applications.