SafeMind: A Risk-Aware Differentiable Control Framework for Adaptive and Safe Quadruped Locomotion
IEEE Access · 2026 · 14 · 50246-50269
DOI: 10.1109/access.2026.3679520 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Access, 2026. Verfasst von Zukun Zhang und 2 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 47 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Learning-based quadruped controllers achieve impressive agility but typically lack formal safety guarantees under model uncertainty, perception noise, and unstructured contact conditions. We introduce SafeMind, a differentiable stochastic safety-control framework that unifies probabilistic Control Barrier Functions with semantic context understanding and meta-adaptive risk calibration. SafeMind explicitly models epistemic and aleatoric uncertainty through a variance-aware barrier constraint embedded in a differentiable quadratic program, thereby preserving gradient flow for end-to-end training. A semantics-to-constraint encoder modulates safety margins using perceptual or language cues, while a meta-adaptive learner continuously adjusts risk sensitivity across environments. We provide theoretical conditions for probabilistic forward invariance, feasibility, and stability under stochastic dynamics. SafeMind is deployed on Unitree A1 and ANYmal C at 200 Hz and validated across 12 terrain types, dynamic obstacles, morphology perturbations, and semantically defined tasks. Experiments show that SafeMind reduces safety violations by 3– $10\times $ and energy consumption by 10–15% relative to state-of-the-art CBF, MPC, and hybrid RL baselines, while maintaining real-time control performance.
Zitieren
APA
Zhang, Z., Shu, K., & Mo, M. (2026). SafeMind: A Risk-Aware Differentiable Control Framework for Adaptive and Safe Quadruped Locomotion. IEEE Access, 14, 50246-50269. https://doi.org/10.1109/access.2026.3679520
Vancouver
Zhang Z, Shu K, Mo M. SafeMind: A Risk-Aware Differentiable Control Framework for Adaptive and Safe Quadruped Locomotion. IEEE Access. 2026;14:50246-50269. doi:10.1109/access.2026.3679520
BibTeX
@article{Zhang2026,
author = {Zhang, Zukun and Shu, Kai and Mo, Mingqiao},
title = {SafeMind: A Risk-Aware Differentiable Control Framework for Adaptive and Safe Quadruped Locomotion},
journal = {IEEE Access},
year = {2026},
volume = {14},
pages = {50246--50269},
doi = {10.1109/access.2026.3679520}
}
EUVIMED