What does this research mean for the field?

An adaptive safety controller integrating a deep neural network with a tuneable input-to-state safe high-order control barrier function improves safety performance in nonlinear systems with uncertainties compared to existing baselines. Novelty: ClaimNovelty.METHODOLOGICAL. Consensus alignment: ConsensusAlignment.NEUTRAL.

What question did this study set out to answer?

Design an adaptive safety controller for nonlinear systems to maintain rigorous safety guarantees despite operational uncertainties.

September 5, 2026International Journal of Systems Science

Safety-critical control of nonlinear systems using deep neural network-based control barrier functions

View Full Paper

Ask AI

Bookmark

Authors

YWYan Wei ZLZicong Lu XYXinyi Yu

Discussion

Member takes

Overview

Experimental validation demonstrates enhanced safety performance in a robotic manipulator, highlighting the utility of hybrid neural learning for real-time uncertainty compensation.

Key Points

Design an adaptive safety controller for nonlinear systems to maintain rigorous safety guarantees despite operational uncertainties.
Integrated a deep neural network with a tuneable input-to-state safe high-order control barrier function.
Trained the network online using an observer-driven hybrid learning strategy, updating hidden layers via stochastic gradient descent and output-layer weights via recursive least squares.
Validated safety and uncertainty compensation experimentally on a Franka Emika Panda robotic manipulator.
Established forward invariance of an extended safe operating set under dynamic uncertainty using Nagumo's theorem.
Demonstrated superior safety-critical control performance in robotic arm experiments compared to existing baseline methods.

Cite This Study

Wei et al. (2026) studied this question.

synapsesocial.com/papers/6a9bd3e16b95aff0620eb142 https://doi.org/10.1080/00207721.2026.2728145

View Full Paper

Ask AI

Bookmark

September 5, 2026International Journal of Systems Science

Safety-critical control of nonlinear systems using deep neural network-based control barrier functions

View Full Paper

Ask AI

Bookmark

Authors

YWYan Wei ZLZicong Lu XYXinyi Yu

Discussion

Member takes

Overview

Experimental validation demonstrates enhanced safety performance in a robotic manipulator, highlighting the utility of hybrid neural learning for real-time uncertainty compensation.

Key Points

Design an adaptive safety controller for nonlinear systems to maintain rigorous safety guarantees despite operational uncertainties.
Integrated a deep neural network with a tuneable input-to-state safe high-order control barrier function.
Trained the network online using an observer-driven hybrid learning strategy, updating hidden layers via stochastic gradient descent and output-layer weights via recursive least squares.
Validated safety and uncertainty compensation experimentally on a Franka Emika Panda robotic manipulator.
Established forward invariance of an extended safe operating set under dynamic uncertainty using Nagumo's theorem.
Demonstrated superior safety-critical control performance in robotic arm experiments compared to existing baseline methods.

Cite This Study

Wei et al. (2026) studied this question.

synapsesocial.com/papers/6a9bd3e16b95aff0620eb142 https://doi.org/10.1080/00207721.2026.2728145

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

View Full Paper

Ask AI

Bookmark