Joos Behncke

Papers

Total Citations

H-Index

About

Joos Behncke is a researcher working at the intersection of neuroscience, brain-computer interfaces (BCIs), and human-robot interaction, with a particular focus on how the human brain processes and responds to robotic behavior. His work explores the neural signatures associated with observing robot actions, seeking to decode meaningful brain signals that can inform smarter, safer robotic systems. Behncke's most notable contribution, his 2018 paper on decoding EEG signals using deep convolutional neural networks (cited 33 times), demonstrated that it is possible to identify whether a human observer perceives a robot's action as successful or erroneous — purely from their brain activity. This has significant implications for developing real-time robot error-correction systems driven by passive human neural feedback. His earlier 2017 work laid important groundwork by characterizing the brain responses that emerge when humans observe robot errors, helping establish the neurological basis for this line of inquiry. Together, these contributions advance the field of assistive robotics by proposing a novel pathway: using human neural observation signals to continuously monitor and correct robot performance. For students entering BCI or human-robot interaction research, Behncke's work represents a compelling example of how neuroscience and machine learning can converge to make assistive technology more responsive and reliable.