Joseph Park

Joseph Park

Auto-generated profile, based on publicly available information

Joseph Park

School of Mechanical Engineering Yonsei University Seoul South Korea

Research Focus & Metrics

Academic Career Length

1Year (2026-Present)

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

Representative Publications

View All Publications
20 January 2026 in arXiv
Verified
Preprint
Open access
PDF file
JCJunwoo Chang
Junwoo Chang
JPJoseph Park
Joseph Park
RHRoberto Horowitz
Roberto Horowitz
JLJongmin Lee
Jongmin Lee
JCJongeun Choi
Jongeun Choi
Unsupervised skill discovery aims to acquire behavior primitives that improve exploration and accelerate downstream task learning. However, existing approaches often ignore the geometric symmetries of physical environments, leading to redundant behaviors and sample inefficiency. To address this, we introduce Group-Invariant Skill Discovery (GISD), a framework that explicitly embeds group structure into the skill discovery objective. Our approach is grounded in a theoretical guarantee: we prove that in group-symmetric environments, the standard Wasserstein dependency measure admits a globally optimal solution comprised of an equivariant policy and a group-invariant scoring function. Motivated by this, we formulate the Group-Invariant Wasserstein dependency measure, which restricts the optimization to this symmetry-aware subspace without loss of optimality. Practically, we parameterize the scoring function using a group Fourier representation and define the intrinsic reward via the alignment of equivariant latent features, ensuring that the discovered skills generalize systematically under group transformations. Experiments on state-based and pixel-based locomotion benchmarks demonstrate that GISD achieves broader state-space coverage and improved efficiency in downstream task learning compared to a strong baseline.

4 November 2026 in International Journal of Control, Automation, and Systems
Verified
Journal Article
Open access
JPJoseph Park
Joseph Park
HLHaeseong Lee
Haeseong Lee
JPJaeheung Park
Jaeheung Park
Precise teleoperation in unstructured environments remains challenging, because human errors and system-inherent limitations such as control jittering can significantly degrade task success and operational efficiency. To address these limitations, this paper proposes a software-defined Context-Aware Virtual Fixture (CAVF) system that leverages the open-world understanding of a Vision-Language Model (VLM). The proposed system automatically generates motion guidance for the robot end-effector (EEF) to assist teleoperation, preserving critical task-relevant motion while suppressing unnecessary translation and rotation components. This framework enables the autonomous generation of context-aware, haptic-free assistance without relying on handcrafted rules or physical force-feedback devices. Quantitative experiments in both simulation and real-world environments demonstrate that the proposed system significantly improves success rates, reduces completion times, and enhances trajectory efficiency compared to conventional teleoperation.