Capraru Updated — Richard

Earned his Bachelor of Engineering (B.Eng.) in Electrical and Electronic Engineering in 2021. During his tenure, he was named a Laidlaw Scholar and contributed to foundational radar signal processing datasets.

Dr. Capraru is a highly cited and active IEEE member whose collaborative projects have laid foundational benchmarks in radar and autonomous perception. Publication / Dataset Title Core Innovation / Focus

Presented at the prestigious IEEE/RSJ IROS Conference, detailing physical-grounded attacks in adverse environments.

Dr. Capraru’s academic path spans several of the world’s top engineering institutions:

Currently pursuing his doctoral studies at Nanyang Technological University. richard capraru

He explores the performance of LiDAR vision systems in self-driving cars during heavy rain. His work highlights how rain can be leveraged by attackers to create "ghost objects" or hide real obstacles with a reduced attack budget.

: He frequently collaborates with established figures in the field such as Matthew Ritchie Francesco Fioranelli

: He has co-authored work on frameworks for few-shot learning in millimeter-wave radar systems, aimed at making hand gesture recognition more efficient with minimal data. Safety-Critical AI : His recent work involves using Large Language Models (LLMs)

Improving how autonomous systems detect objects in challenging conditions like heavy rain. Cybersecurity in Robotics: Earned his Bachelor of Engineering (B

Richard Capraru is a researcher specializing in machine learning, robotics, and advanced sensing technologies, currently focusing on autonomous vehicle perception and radar-based interaction systems. Professional Profile

Learning from Failures: LLM-Guided Safety-Critical Scenario Recommendation for Self-Evolving Autonomous Driving Robustness of 3D Deep Learning in an Adversarial Setting

: Investigating how sensors like LiDAR perform in adverse weather, such as heavy rain, and how these conditions affect the reliability of autonomous navigation.

: He has co-authored papers on using deep learning, specifically convolutional neural networks (CNNs), to count and localize people using 60 GHz FMCW radar. This includes addressing the resilience of these models in dynamic environments. Radar Data Challenges : Capraru was a contributor to the Capraru is a highly cited and active IEEE

The foundation of Capraru’s success lies in his unique approach to organizational management. Rather than relying on traditional top-down hierarchies, he has long championed a culture of collaborative innovation. By empowering middle management and fostering a transparent communication style, Capraru has consistently transformed stagnant corporate structures into agile, high-performing entities. This human-centric approach to business is often cited as his primary differentiator, allowing him to retain top talent while hitting aggressive revenue targets.

Capraru’s journey into the field of electrical and electronic engineering began at University College London

– Presented at the prestigious IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2024).

As autonomous vehicles (AVs) shift from controlled environments to complex, unpredictable real-world deployments, Dr. Capraru’s research provides critical insights into how weather anomalies and malicious cyber-physical attacks compromise vehicle perception. Academic Background and International Trajectory

An End-to-end Framework for Few-shot Millimeter-wave Radar-based Hand Gesture Recognition Academic Collaborations Capraru frequently collaborates with experts such as Emil C. Lupu (Imperial College London), Boon Hee Soong Matthew A. Ritchie