Rafael de Lima
Papers
1
Total Citations
3
H-Index
1
About
Rafael de Lima is a robotics researcher whose work focuses on bridging the gap between deep reinforcement learning and real-world robotic manipulation. His primary research areas include visuomotor policy learning, end-to-end training of robotic systems, and the application of deep neural networks to complex manipulation tasks. De Lima’s most notable contribution is his pioneering work on implementing end-to-end training of deep visuomotor policies for the Baxter Research Robot, a platform widely used in robotics research. His 2019 paper on this topic, which has garnered 3 citations, addresses the critical challenge of training generalizable robotic manipulation models that require fewer training episodes—a significant bottleneck in the field. By demonstrating a practical framework for learning complex manipulation skills directly from visual inputs, de Lima has helped advance the feasibility of deploying reinforcement learning in real-world robotic systems. His work is particularly valuable for researchers and students exploring how to make deep learning-based control more sample-efficient and applicable to general tasks, contributing to the ongoing evolution of intelligent, autonomous robots.
Research Focus
Key Achievements
Top Papers
- 1