Andrew R. Ferdinand
Papers
1
Total Citations
1
H-Index
1
About
Andrew R. Ferdinand is a robotics researcher whose work focuses on the intersection of geometric motion planning and machine learning, with a particular emphasis on multitask and transfer learning for articulated robots. His most notable contribution, the 2021 paper "Multitask and Transfer Learning of Geometric Robot Motion," addresses a critical inefficiency in robotics: the need to retrain models from scratch for each unique robot geometry, even when performing identical tasks. Ferdinand’s research pioneers methods for transferring learned swept volume predictors across structurally similar robots, enabling more efficient and scalable motion planning. By reducing the computational burden of training separate models, his work has significant implications for real-world applications where robot fleets with varying configurations must be rapidly deployed. While his citation count is still growing, Ferdinand’s early-career contributions demonstrate a clear vision for making robot learning more generalizable and resource-efficient. His research is particularly valuable for students and engineers working on adaptive robotics, offering a pathway toward more flexible and reusable AI-driven motion control systems.
Research Focus
Key Achievements
Top Papers
- 1Multitask and Transfer Learning of Geometric Robot Motion1 citations · 2021