Dafa Ren

Papers

Total Citations

H-Index

About

Dafa Ren is a rising robotics researcher whose work focuses on advancing robotic manipulation through deep reinforcement learning, particularly in grasping and pre-grasping strategies. Ren’s major contributions lie in developing intelligent frameworks that enable robots to handle cluttered environments and adapt to both goal-agnostic and goal-oriented tasks. In their highly cited 2023 paper, “Learning Bifunctional Push-Grasping Synergistic Strategy for Goal-Agnostic and Goal-Oriented Tasks” (14 citations), Ren introduced a unified approach that allows robots to seamlessly switch between clearing all objects in a workspace and targeting specific goal objects—a critical capability for real-world applications like warehouse automation and assistive robotics. Earlier, Ren’s 2021 work, “Fast-Learning Grasping and Pre-Grasping via Clutter Quantization and Q-map Masking” (10 citations), proposed the FLG framework, which uses clutter quantization and Q-map masking to accelerate learning of pre-grasping actions like pushing, enabling robots to efficiently scatter objects before grasping. Though early in their career, Ren’s innovative integration of goal flexibility and clutter management has already garnered attention, positioning them as a promising contributor to the field of intelligent robotic manipulation.