Ben Purman

Papers

Total Citations

H-Index

About

Ben Purman’s research lies at the intersection of human-robot interaction and applied deep learning, with a focus on enabling intuitive, vision-based control systems. His most cited work, “Gesture Recognition for Robotic Control Using Deep Learning” (2017), demonstrates how convolutional neural networks can reliably interpret a small vocabulary of vehicle control gestures—such as move forward, turn left, and stop—directly from camera input. By tackling the challenge of real-time, non-contact command interfaces, Purman’s contribution helps pave the way for more natural human-robot collaboration in settings where traditional controllers are impractical. Though his citation count (7) reflects a focused, early-stage impact, the work is notable for its practical experimental design and clear proof-of-concept, making it a useful reference for researchers exploring lightweight gesture recognition pipelines. Purman’s approach emphasizes simplicity and robustness, offering a template for integrating deep learning into embedded robotic systems. For students and researchers entering the field, his study serves as a grounded example of how to bridge computer vision and robotics with constrained computational resources.