Michael Case
Papers
4
Total Citations
136
H-Index
4
About
Michael Case is a robotics researcher whose work centers on the perception and manipulation of deformable objects—a notoriously difficult challenge in the field. His most influential contribution, a 2014 paper on real-time pose estimation of deformable objects using a volumetric approach (69 citations), pioneered a method that reconstructs 3D models from low-cost depth sensors like the Kinect, enabling robots to recognize object poses by searching a database of simulated models. Building on this, his 2018 work on model-driven feedforward prediction (39 citations) introduced a framework to anticipate how deformable objects behave during manipulation, addressing the high-dimensional complexity of their state spaces. This approach has been cited as a key step toward more autonomous and reliable robotic handling of soft materials. Beyond manipulation, Case has also explored the use of autonomous maritime robotics for biological monitoring, as seen in his 2021 systematic review on tracking fish movements (22 citations). His research bridges fundamental robotics challenges with real-world applications in marine biology, demonstrating a versatile and impactful career.
Research Focus
Key Achievements
Top Papers
- 1Real-time pose estimation of deformable objects using a volumetric approach69 citations · 2014
- 2Model-Driven Feedforward Prediction for Manipulation of Deformable Objects39 citations · 2018
- 3
- 4