4 papers
WRAP: Wasserstein-Robust Adaptive Plug-in for Robot Localization
Minhyuk Jang, Astghik Hakobyan, Jungjin Lee +2
Robotic localization under changing sensing conditions can suffer from biased errors and miscalibrated covariances. We present WRAP, an adapter-agnostic Wasserstein-robust plug-in…
Residual-Aware Distributionally Robust EKF: Absorbing Linearization Mismatch via Wasserstein Ambiguity
Minhyuk Jang, Jungjin Lee, Astghik Hakobyan +2
The extended Kalman filter (EKF) is a cornerstone of nonlinear state estimation, yet its performance is fundamentally limited by noise-model mismatch and linearization errors. We d…
KoopCast: Trajectory Forecasting via Koopman Operators
Jungjin Lee, Jaeuk Shin, Gihwan Kim +2
We present KoopCast, a lightweight yet efficient model for trajectory forecasting in general dynamic environments. Our approach leverages Koopman operator theory, which enables a l…
Egocentric Conformal Prediction for Safe and Efficient Navigation in Dynamic Cluttered Environments
Jaeuk Shin, Jungjin Lee, Insoon Yang
Conformal prediction (CP) has emerged as a powerful tool in robotics and control, thanks to its ability to calibrate complex, data-driven models with formal guarantees. However, in…