Domain-aware Control-oriented Neural Models for Autonomous Underwater Vehicles
This work addresses the bottleneck of time-consuming physics-based modeling for control design in safety-critical autonomous underwater vehicles, offering a hybrid solution that is incremental in nature.
The authors tackled the problem of modeling autonomous underwater vehicle dynamics by developing domain-aware neural models that combine physics knowledge with data-driven approaches, achieving improved prediction accuracy and generalization compared to purely data-driven methods in data-limited scenarios.
Conventional physics-based modeling is a time-consuming bottleneck in control design for complex nonlinear systems like autonomous underwater vehicles (AUVs). In contrast, purely data-driven models, though convenient and quick to obtain, require a large number of observations and lack operational guarantees for safety-critical systems. Data-driven models leveraging available partially characterized dynamics have potential to provide reliable systems models in a typical data-limited scenario for high value complex systems, thereby avoiding months of expensive expert modeling time. In this work we explore this middle-ground between expert-modeled and pure data-driven modeling. We present control-oriented parametric models with varying levels of domain-awareness that exploit known system structure and prior physics knowledge to create constrained deep neural dynamical system models. We employ universal differential equations to construct data-driven blackbox and graybox representations of the AUV dynamics. In addition, we explore a hybrid formulation that explicitly models the residual error related to imperfect graybox models. We compare the prediction performance of the learned models for different distributions of initial conditions and control inputs to assess their accuracy, generalization, and suitability for control.