Martin Rothbucher

Papers

Total Citations

H-Index

About

Martin Rothbucher's research sits at the intersection of human-robot interaction and spatial audio, with a particular focus on how machines can better perceive and interact with humans. His key contributions center on Head-Related Transfer Function (HRTF) personalization and sound localization for robotic systems. Rothbucher pioneered methods for measuring anthropometric data to tailor HRTFs to individual users, enabling more realistic 3D audio rendering in teleoperation scenarios. His work on dimensionality reduction in HRTFs using multiway array analysis provided efficient computational approaches for implementing spatial hearing in robots. Beyond audio, Rothbucher explored adaptive robotic behavior through reinforcement learning for gaze control, teaching robots to track active speakers in conversations using multimodal audio-visual data. His algorithm for HRTF-based localization and separation of multiple sound sources advanced robotic audition in noisy, real-world environments. While his citation counts (2-6 per paper) reflect focused technical contributions rather than broad impact, Rothbucher's work represents important steps toward integrating human-like sensing—vision, haptics, and audition—into robotic platforms for more natural human-robot collaboration.