Yifeng Lin

Papers

Total Citations

H-Index

About

Yifeng Lin’s research lies at the intersection of robotics, autonomous systems, and probabilistic modeling, with a central focus on quantifying and propagating uncertainty through complex decision-making pipelines. His most-cited work, “Propagating State Uncertainty Through Trajectory Forecasting” (2022, 20 citations), addresses a critical gap in autonomous navigation: how uncertainty from sensors, detection, tracking, and behavior prediction accumulates and distorts trajectory forecasts. By developing frameworks that treat uncertainty as a continuous, propagating signal rather than a static noise, Lin has advanced the reliability of robotic perception and planning in unpredictable environments. His contributions are particularly impactful for safety-critical applications like self-driving cars and drone swarms, where ignoring probabilistic dependencies can lead to catastrophic failures. Beyond this paper, Lin’s broader portfolio explores how probabilistic reasoning can be embedded into end-to-end autonomy stacks, bridging theory and practice. With a growing citation footprint and a reputation for tackling foundational challenges in robotics, Lin is shaping how next-generation autonomous systems reason about the unknown—making his work essential reading for students and researchers in robotics, control theory, and AI safety.