8 citations · 28 across the 36 of their papers we have counts for
38 papers
Full-Covariance Smoothing of Bayesian Neural Networks for Online Adaptation
Oren Wright, Haoming Jing, Qiaoan Shen +3
A neural network's layers can be treated as time steps of a state-space model, turning Bayesian training into a smoothing problem: a forward pass propagates Gaussian moments throug…
Learning Fractional-Order Dynamics from a Single Trajectory
Xiaole Zhang, Ziyi Zhang, Zehao Zhao +4
Many real-world processes exhibit long-range dependence, where the current state depends on a slowly decaying trace of past states rather than on the most recent state alone. This…
Physics-informed Reinforcement Learning for Stochastic Reach-Avoid Analysis
Hikaru Hoshino, Yorie Nakahira
Stochastic reach-avoid analysis of controlled dynamical systems is an important tool for safety-critical control under uncertainty, in which the reach-avoid probability is characte…
Online Safety Filter for Deformable Object Manipulation with Horizon Agnostic Neural Operators
Jiaxing Li, Hanjiang Hu, Zhuoyuan Wang +2
Safety critical control of robotic manipulation tasks involving deformable media such as fluids, cloth, and soft objects remains challenging because existing learning based approac…
Fractional Risk Analysis of Stochastic Systems with Jumps and Memory
Yimeng Sun, Zhuoyuan Wang, Xiaole Zhang +4
Accurate risk assessment is essential for safety-critical autonomous and control systems under uncertainty. In many real-world settings, stochastic dynamics exhibit asymmetric jump…
OpInf-LLM: Parametric PDE Solving with LLMs via Operator Inference
Zhuoyuan Wang, Hanjiang Hu, Xiyu Deng +2
Solving diverse partial differential equations (PDEs) is fundamental in science and engineering. Large language models (LLMs) have demonstrated strong capabilities in code generati…
Online Adaptive Probabilistic Safety Certificate with Language Guidance
Zhuoyuan Wang, Xiyu Deng, Hikaru Hoshino +1
Achieving long-term safety in uncertain/extreme environments while accounting for human preferences remains a fundamental challenge for autonomous systems. Existing methods often t…
Safe Driving in Occluded Environments
Zhuoyuan Wang, Tongyao Jia, Pharuj Rajborirug +5
Ensuring safe autonomous driving in the presence of occlusions poses a significant challenge in its policy design. While existing model-driven control techniques based on set invar…
Multi-Level Multi-Fidelity Methods for Path Integral and Safe Control
Zhuoyuan Wang, Takashi Tanaka, Yongxin Chen +1
Sampling-based approaches are widely used in systems without analytic models to estimate risk or find optimal control. However, gathering sufficient data in such scenarios can be p…
Kalman Bayesian Transformer
Haoming Jing, Oren Wright, José M. F. Moura +1
Sequential fine-tuning of transformers is useful when new data arrive sequentially, especially with shifting distributions. Unlike batch learning, sequential learning demands that…
Neural Spline Operators for Risk Quantification in Stochastic Systems
Zhuoyuan Wang, Raffaele Romagnoli, Kamyar Azizzadenesheli +1
Accurately quantifying long-term risk probabilities in diverse stochastic systems is essential for safety-critical control. However, existing sampling-based and partial differentia…
Safety Certificate against Latent Variables with Partially Unidentifiable Dynamics
Haoming Jing, Yorie Nakahira
Many systems contain latent variables that make their dynamics partially unidentifiable or cause distribution shifts in the observed statistics between offline and online data. How…
Stabilizing Linear Systems under Partial Observability: Sample Complexity and Fundamental Limits
Ziyi Zhang, Yorie Nakahira, Guannan Qu
We study the problem of stabilizing an unknown partially observable linear time-invariant (LTI) system. For fully observable systems, leveraging an unstable/stable subspace decompo…
Physics-Informed Deep B-Spline Networks
Zhuoyuan Wang, Raffaele Romagnoli, Saviz Mowlavi +1
Physics-informed machine learning offers a promising framework for solving complex partial differential equations (PDEs) by integrating observational data with governing physical l…
Autonomous Drifting Based on Maximal Safety Probability Learning
Hikaru Hoshino, Jiaxing Li, Arnav Menon +2
This paper proposes a novel learning-based framework for autonomous driving based on the concept of maximal safety probability. Efficient learning requires rewards that are informa…
Predictive Control and Regret Analysis of Non-Stationary MDP with Look-ahead Information
Ziyi Zhang, Yorie Nakahira, Guannan Qu
Policy design in non-stationary Markov Decision Processes (MDPs) is inherently challenging due to the complexities introduced by time-varying system transition and reward, which ma…
Generalizable Physics-Informed Learning for Stochastic Safety-Critical Systems
Zhuoyuan Wang, Albert Chern, Yorie Nakahira
Accurate estimation of long-term risk is essential for the design and analysis of stochastic dynamical systems. Existing risk quantification methods typically rely on extensive dat…
Learning to Stabilize Unknown LTI Systems on a Single Trajectory under Stochastic Noise
Ziyi Zhang, Yorie Nakahira, Guannan Qu
We study the problem of learning to stabilize unknown noisy Linear Time-Invariant (LTI) systems on a single trajectory. It is well known in the literature that the learn-to-stabili…
Myopically Verifiable Probabilistic Certificates for Safe Control and Learning
Zhuoyuan Wang, Haoming Jing, Christian Kurniawan +2
This paper addresses the design of safety certificates for stochastic systems, with a focus on ensuring long-term safety through fast real-time control. In stochastic environments,…
Physics-informed RL for Maximal Safety Probability Estimation
Hikaru Hoshino, Yorie Nakahira
Accurate risk quantification and reachability analysis are crucial for safe control and learning, but sampling from rare events, risky states, or long-term trajectories can be proh…
An Analytic Solution to Covariance Propagation in Neural Networks
Oren Wright, Yorie Nakahira, José M. F. Moura
Uncertainty quantification of neural networks is critical to measuring the reliability and robustness of deep learning systems. However, this often involves costly or inaccurate sa…
Sample-Optimal Zero-Violation Safety For Continuous Control
Ritabrata Ray, Yorie Nakahira, Soummya Kar
In this paper, we study the problem of ensuring safety with a few shots of samples for partially unknown systems. We first characterize a fundamental limit when producing safe acti…
Context-aware LLM-based Safe Control Against Latent Risks
Xiyu Deng, Quan Khanh Luu, Anh Van Ho +1
Autonomous control systems face significant challenges in performing complex tasks in the presence of latent risks. To address this, we propose an integrated framework that combine…
Physics-Informed Representation and Learning: Control and Risk Quantification
Zhuoyuan Wang, Reece Keller, Xiyu Deng +3
Optimal and safety-critical control are fundamental problems for stochastic systems, and are widely considered in real-world scenarios such as robotic manipulation and autonomous d…