Papers
10
Total Citations
366
H-Index
8
About
Phillip Hyatt is a robotics researcher whose work sits at the intersection of soft robotics, model predictive control (MPC), and safe human-robot interaction. His research addresses one of the field's most pressing challenges: enabling compliant, pneumatically actuated robots to operate accurately and safely alongside humans in unstructured environments. Hyatt's most cited work, "A New Soft Robot Control Method" (2016, 119 citations), pioneered the application of MPC to pneumatically actuated humanoid robots, establishing a foundation for subsequent advances in the field. He has consistently pushed the boundaries of what soft robots can achieve through rigorous control theory, developing learned nonlinear models via deep neural networks (2019, 67 citations) and adaptive model reference predictive control strategies (2020, 36 citations). A recurring theme in his research is computational tractability: his work on GPU-accelerated nonlinear MPC and input parameterization techniques demonstrates a practical commitment to real-time applicability for high-degree-of-freedom systems. With over 350 cumulative citations, Hyatt's contributions have meaningfully shaped how researchers approach soft robot modeling, configuration estimation, and control, making his work essential reading for anyone exploring the future of safe, flexible robotic systems.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4
- 5Model Reference Predictive Adaptive Control for Large-Scale Soft Robots36 citations · 2020
- 6
- 7
- 8
- 9
- 10