Max Robotics — Global Service Robot Directory + US Certification

About

Philipp Ruppel is a robotics researcher whose work spans dexterous manipulation, teleoperation, human-robot collaboration, and robot learning. He is perhaps best known for pioneering vision-based teleoperation systems for dexterous robotic hands, most notably through TeachNet (2019, 104 citations), a deep neural network architecture that translates depth images of human hands directly into robot joint angles without markers or wearable devices. This work, extended through subsequent systems like Transteleop and active vision-based approaches, has established Ruppel as a leading voice in markerless, intuitive robot control. Beyond teleoperation, Ruppel has made meaningful contributions to motion planning, developing cost-function frameworks for full-body and multi-goal manipulation tasks (2018, 43 citations), and to human-robot collaboration, proposing pipelines that integrate intention prediction, EEG-based vigilance monitoring, and trajectory forecasting to ensure both safety and efficiency in shared workspaces. His reinforcement learning research addresses real-world pushing and manipulation challenges by combining vision-proprioception models and simulation-trained adaptive systems. He has also contributed practical hardware innovations, including a low-cost modular tactile sensor array. With over 350 cumulative citations, Ruppel's research consistently bridges theoretical innovation and deployable robotic systems, making his work highly relevant for students and engineers advancing the frontier of intelligent, human-centered robotics.