Richard: Capraru Work
Presented at the prestigious IEEE/RSJ IROS Conference, detailing physical-grounded attacks in adverse environments.
From his early academic foundations at University College London (UCL) to his current advanced research in Singapore, Capraru’s career path has been defined by a consistent focus on solving complex, real-world engineering challenges. He has made significant contributions to the development of radar databases, the analysis of adverse weather effects on sensors, and the creation of novel attack methodologies to expose security flaws. This article provides a comprehensive overview of his biography, career, research contributions, and the potential future impact of his work on the automotive and technology industries.
: Because autonomous vehicles are programmed to adapt to bad weather by filtering out minor signal anomalies, their defense mechanisms become less strict.
The goal is . We aren't just looking for blobs on a screen; we are teaching systems to distinguish between a pedestrian, a cyclist, and a rain-slicked road sign in real-time.
To counter this, he developed , a novel data minimization architecture designed to filter out malicious perturbations and secure real-time LiDAR streams against active manipulation. Key Research Publications and Data Contributions richard capraru
Richard Capraru's research in this field has been conducted alongside academic peers such as Emil Lupu, Jian-Gang Wang, and Boon Hee Soong.
Capraru’s career is not merely a chronological progression but a strategic layering of experiences that have shaped his unique perspective. His earliest publications, stemming from his undergraduate work at UCL, focused on practical engineering problems, such as using and creating shared databases for the research community. The "Dop-Net" project, a large, shareable database of radar micro-Doppler signatures, was a standout achievement from this period, demonstrating his early commitment to collaborative, open-source methods that accelerate scientific progress.
| Publication Title | Focus Area | Key Contribution | | :--- | :--- | :--- | | (2020) | Radar-based Gesture Recognition | Proved that low-cost Continuous Wave (CW) radar can match the gesture recognition accuracy of more complex systems. | | Dop-NET: a micro-Doppler radar data challenge (2020) | Radar Data & Machine Learning | Introduced a standard dataset to train machine learning algorithms for specific radar data. | | Exploring deep transfer learning interference classification... (2022) | Synthetic Data & SAR | Demonstrated that AI-generated synthetic radar data could be used to train other AI models effectively. | | Upsampling Data Challenge: Object-Aware Approach for 3D Object Detection in Rain (2023) | LiDAR & 3D Detection | Proposed a new data processing method to improve object detection for autonomous vehicles in rainy conditions. | | Rain-Reaper: Unmasking LiDAR-based Detector Vulnerabilities in Rain (2024, IROS) | LiDAR Security & Weather | Developed an attack that exploits rain’s physical properties to trick a LiDAR system into ignoring real obstacles. | | Leveraging Adverse Weather for Enhanced LiDAR Spoofing... (2026, IEEE Vehicular Technology Magazine ) | Autonomous Vehicle Security | Argued that weather isn't just a hindrance but can be strategically leveraged to design more sophisticated attacks on self-driving car sensors. |
If you want to focus deeper on a specific facet of his career, Analyze his like Dop-NET. This article provides a comprehensive overview of his
Under Capraru’s guidance, forward-thinking firms are deploying AI in three specific areas:
While LiDAR is known to be relatively robust to environmental interference, studies suggest that intensity and the number of detected points can be attenuated by rain. Capraru's research, such as "Leveraging Adverse Weather for Enhanced LiDAR Spoofing in Autonomous Driving," takes this further by exploring how these atmospheric impacts can be intentionally manipulated, rather than just observed as technical limitations. Key Collaborators
As the transportation industry edges closer to higher levels of vehicle autonomy, the security of perception models remains paramount. The ongoing research contributions of Richard Capraru ensure that future smart cars are built to withstand not only the unpredictability of human roads, but also the calculating nature of digital and physical threats.
When businesses discuss "digital transformation," they often think of buying software. has been a vocal critic of this "tech-first" approach. His blueprint for digital transformation follows a "People -> Process -> Tools" hierarchy. We aren't just looking for blobs on a
Unlike many industry pundits who focus solely on marketing or product development, Richard Capraru adopts a holistic approach. He looks at the organism of a business: the cash flow (blood), the team (muscle), the technology (nervous system), and the brand identity (skin). His work implies that for a business to live long, all these elements must harmonize.
Rain-Reaper: Unmasking LiDAR-Based Detector Vulnerabilities in Rain
Perhaps the most defining characteristic of Richard Capraru’s career is his focus on the intangible. In an industry often obsessed with the visual—how things look on a page or a screen—Capraru remains obsessed with how things work. He designs for the way light shifts at 4:00 PM, for the acoustics of a dinner party, for the privacy of a homeowner who wants to feel secluded without being shut away.
Researched the intersection of computer vision and remote sensing via deep transfer learning architectures trained using Style Transfer Synthetic SAR datasets. Future Trajectory in Autonomous Safety
Presented at the prestigious IEEE/RSJ IROS Conference, detailing physical-grounded attacks in adverse environments.
From his early academic foundations at University College London (UCL) to his current advanced research in Singapore, Capraru’s career path has been defined by a consistent focus on solving complex, real-world engineering challenges. He has made significant contributions to the development of radar databases, the analysis of adverse weather effects on sensors, and the creation of novel attack methodologies to expose security flaws. This article provides a comprehensive overview of his biography, career, research contributions, and the potential future impact of his work on the automotive and technology industries.
: Because autonomous vehicles are programmed to adapt to bad weather by filtering out minor signal anomalies, their defense mechanisms become less strict.
The goal is . We aren't just looking for blobs on a screen; we are teaching systems to distinguish between a pedestrian, a cyclist, and a rain-slicked road sign in real-time.
To counter this, he developed , a novel data minimization architecture designed to filter out malicious perturbations and secure real-time LiDAR streams against active manipulation. Key Research Publications and Data Contributions
Richard Capraru's research in this field has been conducted alongside academic peers such as Emil Lupu, Jian-Gang Wang, and Boon Hee Soong.
Capraru’s career is not merely a chronological progression but a strategic layering of experiences that have shaped his unique perspective. His earliest publications, stemming from his undergraduate work at UCL, focused on practical engineering problems, such as using and creating shared databases for the research community. The "Dop-Net" project, a large, shareable database of radar micro-Doppler signatures, was a standout achievement from this period, demonstrating his early commitment to collaborative, open-source methods that accelerate scientific progress.
| Publication Title | Focus Area | Key Contribution | | :--- | :--- | :--- | | (2020) | Radar-based Gesture Recognition | Proved that low-cost Continuous Wave (CW) radar can match the gesture recognition accuracy of more complex systems. | | Dop-NET: a micro-Doppler radar data challenge (2020) | Radar Data & Machine Learning | Introduced a standard dataset to train machine learning algorithms for specific radar data. | | Exploring deep transfer learning interference classification... (2022) | Synthetic Data & SAR | Demonstrated that AI-generated synthetic radar data could be used to train other AI models effectively. | | Upsampling Data Challenge: Object-Aware Approach for 3D Object Detection in Rain (2023) | LiDAR & 3D Detection | Proposed a new data processing method to improve object detection for autonomous vehicles in rainy conditions. | | Rain-Reaper: Unmasking LiDAR-based Detector Vulnerabilities in Rain (2024, IROS) | LiDAR Security & Weather | Developed an attack that exploits rain’s physical properties to trick a LiDAR system into ignoring real obstacles. | | Leveraging Adverse Weather for Enhanced LiDAR Spoofing... (2026, IEEE Vehicular Technology Magazine ) | Autonomous Vehicle Security | Argued that weather isn't just a hindrance but can be strategically leveraged to design more sophisticated attacks on self-driving car sensors. |
If you want to focus deeper on a specific facet of his career, Analyze his like Dop-NET.
Under Capraru’s guidance, forward-thinking firms are deploying AI in three specific areas:
While LiDAR is known to be relatively robust to environmental interference, studies suggest that intensity and the number of detected points can be attenuated by rain. Capraru's research, such as "Leveraging Adverse Weather for Enhanced LiDAR Spoofing in Autonomous Driving," takes this further by exploring how these atmospheric impacts can be intentionally manipulated, rather than just observed as technical limitations. Key Collaborators
As the transportation industry edges closer to higher levels of vehicle autonomy, the security of perception models remains paramount. The ongoing research contributions of Richard Capraru ensure that future smart cars are built to withstand not only the unpredictability of human roads, but also the calculating nature of digital and physical threats.
When businesses discuss "digital transformation," they often think of buying software. has been a vocal critic of this "tech-first" approach. His blueprint for digital transformation follows a "People -> Process -> Tools" hierarchy.
Unlike many industry pundits who focus solely on marketing or product development, Richard Capraru adopts a holistic approach. He looks at the organism of a business: the cash flow (blood), the team (muscle), the technology (nervous system), and the brand identity (skin). His work implies that for a business to live long, all these elements must harmonize.
Rain-Reaper: Unmasking LiDAR-Based Detector Vulnerabilities in Rain
Perhaps the most defining characteristic of Richard Capraru’s career is his focus on the intangible. In an industry often obsessed with the visual—how things look on a page or a screen—Capraru remains obsessed with how things work. He designs for the way light shifts at 4:00 PM, for the acoustics of a dinner party, for the privacy of a homeowner who wants to feel secluded without being shut away.
Researched the intersection of computer vision and remote sensing via deep transfer learning architectures trained using Style Transfer Synthetic SAR datasets. Future Trajectory in Autonomous Safety
