Shehan Caldera

Papers

Total Citations

266

H-Index

About

Shehan Caldera is a researcher specializing in robotic perception, machine learning, and autonomous manipulation, with a particular focus on applying deep learning techniques to enable robots to interact intelligently with the physical world. His most influential contribution, "Review of Deep Learning Methods in Robotic Grasp Detection" (2018), has accumulated over 260 citations across multiple venues, establishing it as a foundational reference for researchers working at the intersection of computer vision and robotics. This comprehensive review systematically examines how deep learning architectures can be leveraged to allow robotic systems to visually identify and execute secure grasps on objects — a critical capability for developing truly general-purpose robots. Complementing this survey, his paper "Robotic Grasp Pose Detection Using Deep Learning" demonstrates practical implementation, proposing transfer learning with deep convolutional neural networks to improve grasp pose estimation performance. Caldera's work has meaningfully advanced the field by synthesizing fragmented research into accessible frameworks, helping guide both newcomers and experienced practitioners toward effective methodologies. His contributions continue to influence robotics research in areas including object manipulation, human-robot collaboration, and autonomous navigation systems.