Max Robotics — Global Service Robot Directory + US Certification

About

Judith Kelner is a prominent researcher whose work spans human-robot interaction, deep learning for robotics, social robotics, and IoT-constrained computing. Her research has made significant contributions to the fields of robot pose estimation, human-robot collaboration safety, and child-computer interaction, establishing her as a versatile and impactful figure in applied computing and robotics. Among her most notable contributions is her work on resource-efficient deep learning for constrained devices, exemplified by FCN-Pose (2022, 20 citations), a pruned and quantized neural network enabling robot pose estimation on IoT hardware. Her research on human-robot collaboration safety — including collision detection and intelligent safety modeling using deep and machine learning techniques — has drawn considerable attention, collectively accumulating over 40 citations across three related works. Kelner has also explored the social dimensions of robotics, investigating how robot embodiment affects child education and co-editing influential work on social robots and their applications. Her earlier contributions to gesture-based robot control (2015) and extreme human-robot interfaces (2014) demonstrate a sustained interest in making human-robot interaction more intuitive and trustworthy. With publications spanning nearly a decade and a diverse, interdisciplinary portfolio, Kelner's work continues to shape how robots integrate safely and meaningfully into human environments.