Hao Shen
Papers
1
Total Citations
28
H-Index
1
About
Hao Shen is a robotics and artificial intelligence researcher whose work sits at the intersection of robot learning, generalization, and autonomous manipulation. His most recognized contribution, "Learning Category-Level Generalizable Object Manipulation Policy Via Generative Adversarial Self-Imitation Learning From Demonstrations" (2022), addresses one of the most pressing challenges in modern robotics: enabling robots to generalize manipulation skills across diverse object geometries within a category, rather than being constrained to specific instances. By combining generative adversarial learning with self-imitation from demonstrations, Shen's approach pushes beyond the limitations of traditional reinforcement learning frameworks, offering a pathway toward robots that can operate more flexibly in complex, real-world environments. This work has garnered 28 citations, reflecting meaningful uptake within the robotics and machine learning communities. Shen's research speaks directly to the need for intelligent, multi-functional robotic systems capable of handling the unpredictability of everyday tasks — a goal central to next-generation automation and human-robot interaction. His contributions offer both theoretical grounding and practical insight for researchers working on scalable, adaptable robot policies.
Research Focus
Key Achievements
Top Papers
- 1