Haihui Gao

Haihui Gao

Auto-generated profile, based on publicly available information

Haihui Gao

Department of Mechanical Engineering, University of Pennsylvania, Philadelphia, PA, USA

Research Focus & Metrics

Academic Career Length

12Years (2015-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 September 2015
Verified
Conference Paper
Closed access
HGHaihui Gao
Haihui Gao
YPYong Peng
Yong Peng
KJKebin Jia
Kebin Jia
ZWZhe Wen
Zhe Wen
HLHanjing Li
Hanjing Li
More standardized, networked and intelligentized nature of industry 4.0 has intensified critical infrastructures cyberthreats. According to cyber-physical systems (CPS) layered architecture and security requirements in industry 4.0, a cyber-physical systems testbed based on cloud computing and software defined network (SDN), or CPSTCS is proposed. The CPSTCS uses a network testbed based on cloud computing and SDN to recreate the cyber elements of cyber-physical systems and real-world physical devices for the physical components. The CPSTCS helps assess cyberthreats against the cyber and physical dimensions of critical infrastructures.

15 May 2024 in IEEE Robotics and Automation Letters
Verified
Journal Article
Closed access
SSSunan Sun
Sunan Sun
HGHaihui Gao
Haihui Gao
TLTianyu Li
Tianyu Li
NFNadia Figueroa
Nadia Figueroa
The Linear Parameter Varying Dynamical System (LPV-DS) is an effective approach that learns stable, time-invariant motion policies using statistical modeling and semi-definite optimization to encode complex motions for reactive robot control. Despite its strengths, the LPV-DS learning approach faces challenges in achieving high model accuracy without compromising computational efficiency. To address this, we introduce the Directionality-Aware Mixture Model (DAMM), a novel statistical model that applies the Riemannian metric on the n-sphere to efficiently blend non-Euclidean directional data with Euclidean states. Additionally, we develop a hybrid Markov chain Monte Carlo technique that combines Gibbs Sampling with Split/Merge Proposal, allowing for parallel computation to speed up inference. Extensive empirical tests demonstrate that LPV-DS integrated with DAMM achieves higher reproduction accuracy, better computational efficiency, and near real-time/online learning compared to standard estimation methods on various datasets. Lastly, we demonstrate its suitability for incrementally learning multi-behavior policies in real-world robot experiments.