Papers
1
Total Citations
1
H-Index
1
About
Ming Ge is a robotics researcher whose work focuses on preference-based learning and human-robot interaction, particularly the challenge of aligning robot behaviors with human values. Their key contribution is the development of FARPLS (Feature-Augmented Robot Trajectory Preference Labeling System), a novel framework introduced in 2024 that assists human labelers in more effectively eliciting and articulating their preferences when comparing robot task trajectories. Traditional pairwise comparison systems often overwhelm labelers, making it difficult to identify subtle differences between trajectories. FARPLS addresses this by augmenting the labeling process with feature-based visualizations and structured guidance, enabling more accurate and efficient preference capture. This work sits at the intersection of machine learning, human factors, and robotics, with direct implications for improving how robots learn from human feedback. While still early in its citation trajectory, Ge’s research addresses a critical bottleneck in preference-based reinforcement learning—the quality and consistency of human-provided labels. Their approach promises to make robot learning systems more responsive to nuanced human preferences, advancing the goal of value-aligned autonomous systems.
Research Focus
Key Achievements
Top Papers
- 1