Jeffrey Fong
Papers
1
Total Citations
2
H-Index
1
About
Jeffrey Fong is a researcher at the forefront of robotics and artificial intelligence, with a primary focus on model-based reinforcement learning and non-prehensile manipulation. His work addresses one of the most challenging problems in robotics: enabling robots to manipulate objects without grasping them, using actions like pushing, sliding, or toppling. Fong’s key contribution lies in integrating Long Short-Term Memory (LSTM) networks into model-based reinforcement learning frameworks to capture the complex, switched nonlinear dynamics that govern physical interactions between robots and objects, as well as objects and their environments. His 2021 paper, "Model-Based Reinforcement Learning with LSTM Networks for Non-Prehensile Manipulation Planning," has garnered attention for its innovative approach to handling switching contact dynamics—a critical hurdle in real-world robotic tasks. Though early in his citation impact, Fong’s work is foundational for advancing autonomous systems in unstructured environments, such as warehouses or homes, where precise grasping is impractical. His research bridges deep learning and control theory, offering a scalable path toward more dexterous and adaptive robots.
Research Focus
Key Achievements
Top Papers
- 1