Sihua Zhang — accepted AI-conference papers

2026

SAD-Flower: Flow Matching for Safe, Admissible, and Dynamically Consistent Planning

Tzu-Yuan Huang, Armin Lederer, Dai-Jie Wu, Xiaobing Dai, Sihua Zhang, Hsiu-Chin Lin +3

ICML 2026poster

Flow matching (FM) has shown promising results in data-driven planning. However, it inherently lacks formal guarantees for ensuring state and action constraints, whose satisfaction is a fundamental and crucial requirement for the safety and admissibility of planned trajectories on various systems. M…

Cited by 0 Source ↗code ↗Scholar ↗

2025

Differential High Order Control Barrier Function-Based Safe Reinforcement Learning

Xiangyu Kong, Yuanqing Xia, Zhongqi Sun, Di-Hua Zhai, Yunshan Deng, Sihua Zhang

RA-L 2025

Safe reinforcement learning (RL) aims to learn policy while also ensuring the safety constraints. An increasingly common approach is to design a safety filter based on control barrier function (CBF) or high order control barrier function (HOCBF) for the RL policy. A quadratic programming (QP) is the

Cited by 2 Source ↗Scholar ↗