We propose Flumen, a method for learning flow functions of control systems in continuous time. The flow function is the natural concept of a solution operator for such systems. By restricting to classes of inputs typically used in practice, we show that the flow can be evaluated by computing trajectories of a discrete-time system, which motivates the structure of the employed architecture. We give an algorithm for the efficient simulation of trajectories, and show that, in comparison with direct numerical integration of the dynamics, our method is significantly faster for trajectory simulation and gradient computations, while retaining comparable accuracy. The approach extends to simulating families of systems depending on a parameter. We demonstrate the effectiveness of our method on parameter estimation problems using data from the Van der Pol oscillator with variable damping and a model of road traffic flow with 200 states. In the latter case, our method estimates the parameters 100 times faster than using traditional numerical integration methods, with minimal loss in accuracy. Our results show that flow function models are effective surrogate models for increasing the speed and reliability of model-based optimisation tasks.

We describe a recurrent neural network (RNN) based architecture to learn the flow function of a causal, time-invariant and continuous-time control system from trajectory data. By restricting the class of control inputs to piecewise constant functions, we show that learning the flow function is equivalent to learning the input-to-state map of a discrete-time dynamical system. This motivates the use of an RNN together with encoder and decoder networks which map the state of the system to the hidden state of the RNN and back. We show that the proposed architecture is able to approximate the flow function by exploiting the system's causality and time-invariance. The output of the learned flow function model can be queried at any time instant. We experimentally validate the proposed method using models of the Van der Pol and FitzHugh-Nagumo oscillators. In both cases, the results demonstrate that the architecture is able to closely reproduce the trajectories of these two systems. For the Van der Pol oscillator, we further show that the trained model generalises to the system's response with a prolonged prediction time horizon as well as control inputs outside the training distribution. For the FitzHugh-Nagumo oscillator, we show that the model accurately captures the input-dependent phenomena of excitability.

We propose a framework for surrogate modelling of spiking systems. These systems are often described by stiff differential equations with high-amplitude oscillations and multi-timescale dynamics, making surrogate models an attractive tool for system design and simulation. We parameterise the flow function of a spiking system using a recurrent neural network architecture, allowing for a direct continuous-time representation of the state trajectories. The spiking nature of the signals makes for a data-heavy and computationally hard training process; thus, we describe two methods to mitigate these difficulties. We demonstrate our framework on two conductance-based models of biological neurons, showing that we are able to train surrogate models which accurately replicate the spiking behaviour.

We propose RHYME-XT, an operator-learning framework for surrogate modeling of spatiotemporal control systems governed by input-affine nonlinear partial integro-differential equations (PIDEs) with localized rhythmic behavior. RHYME-XT uses a Galerkin projection to approximate the infinite-dimensional PIDE on a learned finite-dimensional subspace with spatial basis functions parameterized by a neural network. This yields a projected system of ODEs driven by projected inputs. Instead of integrating this non-autonomous system, we directly learn its flow map using an architecture for learning flow functions, avoiding costly computations while obtaining a continuous-time and discretization-invariant representation. Experiments on a neural field PIDE show that RHYME-XT outperforms a state-of-the-art neural operator and is able to transfer knowledge effectively across models trained on different datasets, through a fine-tuning process.

We consider the problem of approximating flow functions of continuous-time dynamical systems with inputs. It is well-known that continuous-time recurrent neural networks are universal approximators of this type of system. In this paper, we prove that an architecture based on discrete-time recurrent neural networks universally approximates flows of continuous-time dynamical systems with inputs. The required assumptions are shown to hold for systems whose dynamics are well-behaved ordinary differential equations and with practically relevant classes of input signals. This enables the use of off-the-shelf solutions for learning such flow functions in continuous-time from sampled trajectory data.

Spectral bias, the tendency of neural networks to learn low-frequency features first, is a well-known issue with many training algorithms for physics-informed neural networks (PINNs). To overcome this issue, we propose IFeF-PINN, an algorithm for iterative training of PINNs with Fourier-enhanced features. The key idea is to enrich the latent space using high-frequency components through Random Fourier Features. This creates a two-stage training problem: (i) estimate a basis in the feature space, and (ii) perform regression to determine the coefficients of the enhanced basis functions. For an underlying linear model, it is shown that the latter problem is convex, and we prove that the iterative training scheme converges. Furthermore, we empirically establish that Random Fourier Features enhance the expressive capacity of the network, enabling accurate approximation of high-frequency PDEs. Through extensive numerical evaluation on classical benchmark problems, the superior performance of our method over state-of-the-art algorithms is shown, and the improved approximation across the frequency domain is illustrated.

We consider the problem of traffic density reconstruction using measurements from probe vehicles (PVs) with a low penetration rate. In other words, the number of sensors is small compared to the number of vehicles on the road. The model used assumes noisy measurements and a partially unknown first-order model. All these considerations make the use of machine learning to reconstruct the state the only applicable solution. We first investigate how the identification and reconstruction processes can be merged and how a sparse dataset can still enable a good identification. Secondly, we propose a pre-training procedure that aids the hyperparameter tuning, preventing the gradient descent algorithm from getting stuck at saddle points. Examples using numerical simulations and the SUMO traffic simulator show that the reconstructions are close to the real density in all cases.

This paper proposes a method that uses satellite data to improve adaptive sampling missions. We find and track algal bloom fronts using an autonomous underwater vehicle (AUV) equipped with a sensor that measures the concentration of chlorophyll a. Chlorophyll a concentration indicates the presence of algal blooms. The proposed method learns the kernel parameters of a Gaussian process model using satellite images of chlorophyll a from previous days. The AUV estimates the chlorophyll a concentration online using locally collected data. The algal bloom front estimate is fed to the motion control algorithm. The performance of this method is evaluated through simulations using a real dataset of an algal bloom front in the Baltic. We consider a real-world scenario with sensor and localization noise and with a detailed AUV model.

We consider the problem of tracking moving algal bloom fronts using an unmanned surface vehicle (USV) equipped with a sensor that measures the concentration of chlorophyll a. Chlorophyll a is a green pigment found in plants, and its concentration is an indicator of phytoplankton abundance. Our algal bloom front tracking mission consists of three stages: deployment, data collection, and front tracking. At the deployment stage, a satellite collects an image of the sea from which the location of the front, the reference value for the concentration at this front and, consequently, the appropriate initial position for the USV are determined. At the data collection stage, the USV collects data points to estimate the local algal gradient as it crosses the front. Finally, at the front tracking stage, an adaptive algorithm based on recursive least squares fitting using recent past sensor measures is executed. We evaluate the performance of the algorithm and its sensitivity to measurement noise through MATLAB simulations. We also present an implementation of the algorithm on the DUNE onboard software platform for marine robots and validate it using simulations with satellite model forecasts from Baltic sea data.

Marine pollution incidents can have a huge impact on different ecosystems, with unpredictable short- and long-term consequences. Once the pollutant is detected, it is critical to quickly understand its characteristics so that authorities can lay out an adequate response. In parallel to the time- and cost-constrained traditional operational means, this paper suggests the use of AUVs for the sampling procedures of marine pollution incidents, to increase the speed and efficiency of operations. A new software architecture is developed, integrating trajectory optimization for AUVs into a software toolchain that allows human operators to plan, simulate, and control multiple vehicles deployments. A method to optimize AUVs deployment position and time is also presented. The overall architecture is simulated using high-resolution hydrodynamic data from the Ria de Aveiro lagoon and the adjacent coastal area, in Aveiro, Portugal. 

Consider a set of autonomous vehicles, each one with a preassigned task to start at a given region. Due to energy constraints, and in order to minimize the overall task completion time, these vehicles are deployed from a faster carrier vehicle. This paper develops a dynamic programming (DP) based solution for the problem of finding the optimal deployment location and time for each vehicle, and for a given sequence of deployments, so that the global mission duration is minimal. The problem is specialized for ocean-going vehicles operating under time-varying currents. The solution approach involves solving a sequence of optimal stopping problems that are transformed into a set variational inequalities through the application of the dynamic programming principle (DPP). The optimal trajectory for the carrier and the optimal deployment location and time for each vehicle to be deployed are obtained in feedback-form from the numerical solution of the variational inequalities. The solution is computed with our open source parallel implementation of the fast sweeping method. The approach is illustrated with two numerical examples.