9 papers
Statistical Learning of Contractive Dynamical Representations for Composite Adaptive Control
Min Kim, José Leonardo Brenes, Fred Hadaegh +1
We present a representation-learning framework for composite adaptive tracking control under dynamically coupled disturbances. The framework connects classical disturbance-accommod…
Geometric Fault Identification via Mirror Descent Learning
Mahdi Taheri, Haeyoon Han, Soon-Jo Chung +1
This paper develops a fault detection and identification (FDI) method for nonlinear control-affine systems under simultaneous actuator and sensor faults. We adopt a geometric appro…
Perron-Frobenius Contractive Operator Matching for Data-Driven Reachable Fault Identification and Recovery
Joshua D. Ibrahim, Mahdi Taheri, Soon-Jo Chung +1
This paper focuses on data-driven fault detection, identification, and recovery (FDIR) for nonlinear control-affine systems under actuator faults. We create a unified framework in…
Data-Driven Probabilistic Fault Detection and Identification via Density Flow Matching
Joshua D. Ibrahim, Mahdi Taheri, Soon-Jo Chung +1
Fault detection and identification (FDI) is critical for maintaining the safety and reliability of systems subject to actuator and sensor faults. In this paper, the problem of FDI…
ContractionPPO: Certified Reinforcement Learning via Differentiable Contraction Layers
Vrushabh Zinage, Narek Harutyunyan, Eric Verheyden +2
Legged locomotion in unstructured environments demands not only high-performance control policies but also formal guarantees to ensure robustness under perturbations. Control metho…
A Counterfactual Reasoning Framework for Fault Diagnosis in Robot Perception Systems
Haeyoon Han, Mahdi Taheri, Soon-Jo Chung +1
Perception systems provide a rich understanding of the environment for autonomous systems, shaping decisions in all downstream modules. Hence, accurate detection and isolation of f…
Closing the Loop Inside Neural Networks: Causality-Guided Layer Adaptation for Fault Recovery Control
Mahdi Taheri, Soon-Jo Chung, Fred Y. Hadaegh
This paper studies the problem of real-time fault recovery control for nonlinear control-affine systems subject to actuator loss of effectiveness faults and external disturbances.…
Array-Based Monte Carlo Tree Search
James Ragan, Fred Y. Hadaegh, Soon-Jo Chung
Monte Carlo Tree Search is a popular method for solving decision making problems. Faster implementations allow for more simulations within the same wall clock time, directly improv…
COFFEE: A Shadow-Resilient Real-Time Pose Estimator for Unknown Tumbling Asteroids using Sparse Neural Networks
Arion Zimmermann, Soon-Jo Chung, Fred Hadaegh
The accurate state estimation of unknown bodies in space is a critical challenge with applications ranging from the tracking of space debris to the shape estimation of small bodies…