Daniel Butterfield
Papers
2
Total Citations
9
H-Index
2
About
Daniel Butterfield is pioneering the intersection of underwater robotics and legged robot perception, with a focus on advancing autonomy in challenging environments. His major contributions include the development of AcTag, the first opti-acoustic fiducial marker system designed for simultaneous use with imaging sonar and cameras underwater. This innovation enables robust localization and mapping in low-visibility aquatic settings—a critical capability for marine exploration and infrastructure inspection. In parallel, Butterfield introduced the Morphology-Informed Heterogeneous Graph Neural Network (MI-HGNN), a novel architecture that leverages robot morphology to enhance contact perception in legged robots. By structuring graph nodes and edges to mirror a robot’s joints and links, MI-HGNN achieves more accurate and physically grounded sensing. Though early in his career, his work has already garnered citations (7 for AcTag, 2 for MI-HGNN), reflecting growing interest from the robotics community. Butterfield’s research stands out for its creative fusion of sensing modalities and biologically inspired learning, positioning him as an emerging leader in field robotics and embodied AI.
Research Focus
Key Achievements
Top Papers
- 1
- 2