EUVIMEDOpdag EUVIMED
Open access · CC BY 4.0

Visual Safe Human-to-Humanoid Motion Imitation

Wenqi Cai, John Abanes, Nikolaos Evangeliou, Anthony Tzes

Big Data and Cognitive Computing · 2026-07-24 · 10 (8) · 246

DOI: 10.3390/bdcc10080246 ↗

At a glance

Journal article in Big Data and Cognitive Computing, published online on 2026-07-24. Written by Wenqi Cai and 3 co-authors. Cited 1 times so far (Crossref); 48 references. The full text is freely available (open access, CC BY 4.0). Funded by: NYUAD Center for AI and Robotics, Tamkeen, NYUAD Research Institute.

AbstractBibliografiske oplysningerCiteRelated studies

Abstract (original language)

Safe human-to-humanoid motion imitation is crucial for shared environments, where direct motion retargeting may induce self-collision or human–humanoid collision due to embodiment mismatch, kinematic limits, perception uncertainty, and human proximity. This paper presents an online vision-aided safe human-to-humanoid motion imitation framework that integrates skeleton-based upper-body pose estimation, joint-space retargeting, and capsule-based Control Barrier Function Quadratic Program (CBF-QP) safety filtering. Human skeletal observations are mapped to a reduced eight-degree-of-freedom (8-DoF) humanoid upper-body command, while the CBF-QP layer computes a safety-corrected target that minimally modifies the nominal imitation command subject to robot self-collision and human–humanoid collision constraints. The framework is evaluated via simulation and hardware experiments under representative self-collision and human–humanoid interaction episodes, complemented by a comparative benchmark against velocity damping and potential field baselines. Furthermore, this work introduces an evaluation protocol combining geometric safety, command deviation, and local-link similarity metrics to systematically characterize the safety–imitation trade-off governed by CBF parameters. The results demonstrate that, within the tested moderate-speed regime, the proposed framework substantially reduces geometric collision violations while balancing imitation fidelity with online computational feasibility, thereby providing a viable foundation for safe human-guided humanoid motion deployment.

Funding

  • NYUAD Center for AI and Robotics
  • Tamkeen
  • NYUAD Research Institute

Cite

APA

Cai, W., Abanes, J., Evangeliou, N., & Tzes, A. (2026). Visual Safe Human-to-Humanoid Motion Imitation. Big Data and Cognitive Computing, 10(8), 246. https://doi.org/10.3390/bdcc10080246

Vancouver

Cai W, Abanes J, Evangeliou N, Tzes A. Visual Safe Human-to-Humanoid Motion Imitation. Big Data and Cognitive Computing. 2026;10(8):246. doi:10.3390/bdcc10080246

BibTeX
@article{Cai2026,
  author = {Cai, Wenqi and Abanes, John and Evangeliou, Nikolaos and Tzes, Anthony},
  title = {Visual Safe Human-to-Humanoid Motion Imitation},
  journal = {Big Data and Cognitive Computing},
  year = {2026},
  volume = {10},
  number = {8},
  pages = {246},
  doi = {10.3390/bdcc10080246}
}
Start for free →