Papers
68
Total Citations
1,425
H-Index
19
About
Cornelius Weber is a prominent researcher at the intersection of human-robot interaction, deep learning, and autonomous robotics, whose work has shaped how machines perceive, learn from, and communicate with humans. His research spans lifelong machine learning, emotional recognition, interactive reinforcement learning, and socially assistive robotics — areas increasingly critical as robots move into domestic and healthcare environments. Weber's most influential contribution, his 2017 work on lifelong learning of human actions using self-organizing deep neural networks (133 citations), addresses a fundamental challenge in robotics: enabling systems to continuously acquire knowledge without forgetting prior experience. Complementing this, his research on self-organizing neural integration for human action recognition (80 citations) and multimodal emotional state recognition (83 citations) demonstrates his commitment to building robots capable of nuanced human understanding. His 2013 paper on socially assistive robots (106 citations) highlights his longstanding interest in extending independent living for vulnerable populations. More recently, Weber has embraced large language models for multimodal robotic perception, reflecting his ability to evolve with the field. With over 790 cumulative citations across his top works and contributions bridging neuroscience-inspired architectures with practical robotics, Weber represents a vital voice in designing robots that genuinely learn, adapt, and interact as collaborative partners.
Research Focus
Key Achievements
Top Papers
- 1Lifelong learning of human actions with deep neural network self-organization133 citations · 2017
- 2
- 3
- 4
- 5
- 6A Multichannel Convolutional Neural Network for Hand Posture Recognition77 citations · 2014
- 7
- 8
- 9
- 10