What does this research mean for the field?

A data-driven Nussbaum-RBF Sliding Mode Control (NRSMC) strategy achieves superior tracking accuracy and robustness for unmanned surface vehicle heading control compared to adaptive backstepping methods, without requiring precise mechanistic models. Novelty: ClaimNovelty.METHODOLOGICAL. Consensus alignment: ConsensusAlignment.NEUTRAL.

What question did this study set out to answer?

Develop a data-driven heading control strategy for unmanned surface vehicles to maintain stable tracking despite unknown hydrodynamics, environmental disturbances, and uncertain control coefficients.

September 8, 2026InformaticsOpen Access

Learning-Based Data-Driven Heading Control for Unmanned Surface Vehicles: A Nussbaum-RBF Sliding Mode Approach

View Full Paper

Ask AI

Bookmark

Authors

JZJianlin ZhouJiangsu University of Science and Technology YDYuhao DaiJiangsu University of Science and Technology WXWentao XueJiangsu University of Science and Technology

Discussion

Member takes

Implication

Simulation and experimental study demonstrates robust heading tracking in unmanned surface vehicles, indicating improved adaptability under unknown dynamics and disturbances.

Key Points

Develop a data-driven heading control strategy for unmanned surface vehicles to maintain stable tracking despite unknown hydrodynamics, environmental disturbances, and uncertain control coefficients.
Designed a Nussbaum-RBF sliding mode control (NRSMC) framework utilizing a radial basis function neural network to approximate unknown nonlinear vessel dynamics online.
Integrated a Nussbaum function to handle unknown control coefficients and applied a boundary layer technique to eliminate sliding mode chattering.
Conducted closed-loop Lyapunov stability proofs, comparative numerical simulations against Nussbaum-RBF Adaptive Backstepping Control (NRABC), and field trials on a physical vessel.
Lyapunov theoretical analysis verified closed-loop stability without needing prior knowledge of vessel hydrodynamic models or control gain signs.
Simulation benchmarks showed higher tracking precision and disturbance rejection for NRSMC compared with the NRABC method.
Field experiments confirmed the practical adaptability and trajectory tracking effectiveness of the data-driven controller under real-world water conditions.

Cite This Study

Zhou et al. (2026) studied this question.

synapsesocial.com/papers/6a9fd7ab58e84d0ff5b46813 https://doi.org/10.3390/informatics13090144

View Full Paper

Ask AI

Bookmark

Implication

Simulation and experimental study demonstrates robust heading tracking in unmanned surface vehicles, indicating improved adaptability under unknown dynamics and disturbances.

Learning-Based Data-Driven Heading Control for Unmanned Surface Vehicles: A Nussbaum-RBF Sliding Mode Approach

Discussion

Member takes

Implication

Key Points

Cite This Study

Learning-Based Data-Driven Heading Control for Unmanned Surface Vehicles: A Nussbaum-RBF Sliding Mode Approach

Discussion

Member takes

Implication

Key Points

Cite This Study

Also Consider

Also Consider