Brandon Wagstaff
Papers
2
Total Citations
22
H-Index
2
About
Brandon Wagstaff’s research lies at the intersection of medical robotics and deep learning, with a focus on enabling intelligent, autonomous systems for real-world sensing and control. He is best known for pioneering work on ingestible capsule robots, where he developed an attention-based hierarchical deep learning framework to detect both the capsule’s pose and the state of its on-board sampling mechanism using ultrasound imaging. This contribution, published in 2022 and garnering 16 citations, addresses a critical bottleneck for non-invasive gastrointestinal diagnostics and intervention. In parallel, Wagstaff has advanced probabilistic regression for rotations—a fundamental challenge in vision-based motion estimation for augmented reality and robotics. His 2019 paper introduced a multi-headed network architecture combined with quaternion averaging to extract reliable uncertainty estimates from deep regression models, earning 6 citations. This work has implications for robust localization in dynamic environments. Wagstaff’s research is notable for bridging theoretical advances in representation learning with practical, high-impact applications in medical devices and autonomous systems, making him a rising voice in embodied AI and surgical robotics.
Research Focus
Key Achievements
Top Papers
- 1
- 2