Mung Chiang
Papers
2
Total Citations
69
H-Index
2
About
Mung Chiang is a pioneering researcher in robotics and human-robot interaction, with a focus on scalable robot learning from seamless human feedback. His major contributions center on developing frameworks that enable robots to learn from both explicit and implicit human interventions, bridging the gap between imitation learning and real-world task execution. His most cited work, "Learning from Interventions" (2020, 42 citations), introduces a novel approach that leverages human-robot interaction as a dual source of feedback, overcoming limitations of traditional off-policy demonstration methods. This work has been foundational in advancing robot adaptability in dynamic environments. His subsequent paper, "Expert Intervention Learning" (2021, 27 citations), further refines these techniques, demonstrating how robots can efficiently acquire complex behaviors through expert guidance. Chiang's research is notable for its practical impact on autonomous systems, with applications ranging from manufacturing to assistive robotics. His achievements include recognition for integrating human expertise into machine learning pipelines, making him a leading voice in the field of interactive robot learning.
Research Focus
Key Achievements
Top Papers
- 1
- 2Expert Intervention Learning27 citations · 2021