Gradient boosted trees are competition-winning, general-purpose, non-parametric regressors, which exploit sequential model fitting and gradient descent to minimize a specific loss function. The most popular implementations are tailored to univariate regression and classification tasks, precluding the possibility of capturing multivariate target cross-correlations and applying structured penalties to the predictions. In this paper, we present a computationally efficient algorithm for fitting multivariate boosted trees. We show that multivariate trees can outperform their univariate counterpart when the predictions are correlated. Furthermore, the algorithm allows to arbitrarily regularize the predictions, so that properties like smoothness, consistency and functional relations can be enforced. We present applications and numerical results related to forecasting and control.

We consider the problem of estimating the unobserved amount of photovoltaic (PV) generation and demand in a power distribution network starting from measurements of the aggregated power flow at the point of common coupling and local global horizontal irradiance (GHI). The estimation principle relies on modeling the PV generation as a function of the measured GHI, enabling the identification of PV production patterns in the aggregated power flow measurements. Four estimation algorithms are proposed: the first assumes that variability in the aggregated PV generation is given by variations of PV generation, the next two use a model of the demand to improve estimation performance, and the fourth assumes that, in a certain frequency range, the aggregated power flow is dominated by PV generation dynamics. These algorithms leverage irradiance transposition models to explore several azimuth/tilt configurations and explain PV generation patterns from multiple plants with nonuniform installation characteristics. Their estimation performance is compared and validated with measurements from a real-life setup including four houses with rooftop PV installations and battery systems for PV self-consumption.

The robust and efficient flight control of insects provide a powerful model system for autonomous microrobots. Conversely, robots offer a robust experimental platform on which to test biological hypotheses. This interaction of biology and robotics is an exciting but challenging task, because the vast disparities between both can lead to inaccurate or even misleading conclusions. In this paper, we present a biorobotic platform that can arbitrarily define the dynamic couplings between a fruit fly and a robot. The platform is used to explore the stability and emergent properties of the biorobotic couple. The fruit flypsilas wing kinematics are measured in real time and used to drive an autonomous robot. In turn, the robotpsilas sensory information is transformed back into visual feedback to the fly. Using different case studies, we explore how the choice of feedback influences the success of the biorobotic device. We discuss the meaning of such feedback in view of biomimetic implementations.