Juan Del Aguila Ferrandis
Papers
1
Total Citations
15
H-Index
1
About
Juan Del Aguila Ferrandis is an emerging researcher at the intersection of robotics and machine learning, with a focused expertise in nonprehensile manipulation and reinforcement learning. His most recognized work addresses one of robotics' most persistent challenges: enabling robots to skillfully manipulate objects without grasping them — a deceptively complex problem involving underactuated systems, hybrid dynamics, and unpredictable frictional interactions. In his 2023 paper, "Nonprehensile Planar Manipulation through Reinforcement Learning with Multimodal Categorical Exploration," which has already garnered 15 citations, Del Aguila Ferrandis proposes novel reinforcement learning frameworks that incorporate multimodal categorical exploration strategies to develop robust robot controllers capable of dexterous pushing behaviors. This contribution is particularly significant because it tackles the inherent uncertainty arising from contact-rich, frictional environments — scenarios that have long resisted clean analytical solutions. By leveraging machine learning to navigate this complexity, his work pushes the boundaries of what autonomous robotic systems can achieve in unstructured settings. As a young researcher building a focused and technically rigorous body of work, Del Aguila Ferrandis represents a promising voice in the future of intelligent robot manipulation.
Research Focus
Key Achievements
Top Papers
- 1