No abstract

Models capable of capturing and reproducing the variability observed in experimental trials can be valuable for planning and control in the presence of uncertainty. This paper reports on a new data-driven methodology that extends deterministic models to a stochastic regime and offers probabilistic guarantees of model fidelity. From an acceptable deterministic model, a stochastic one is generated, capable of capturing and reproducing uncertain system–environment interactions at given levels of fidelity. The reported approach combines methodological elements from probabilistic model validation and randomized algorithms, to simultaneously quantify the fidelity of a model and tune the distribution of random parameters in the corresponding stochastic extension, in order to reproduce the variability observed experimentally in the physical process of interest. The approach can be applied to an array of physical processes, the models of which may come in different forms, including differential equations; we demonstrate this point by considering examples from the areas of miniature legged robots and aerial vehicles.

Dormant pruning of fruit trees is one of the most costly and labor‐intensive activities in specialty crop production. We present a system that solves the first step in the process of automated pruning: accurately measuring and modeling the fruit trees. Our system employs a laser sensor to collect observations of fruit trees from multiple perspectives, and it uses these observations to measure parameters needed for pruning. A split‐and‐merge clustering algorithm divides the collected data into three sets of points: trunk candidates, junction point candidates, and branches. The trunk candidates and junction point candidates are then further refined by a robust fitting algorithm that models as cylinders each segment of the trunk and primary branches. In this work, we focus on measuring the diameters of the primary branches and the trunk, which are important factors in dormant pruning and can be obtained directly from the cylindrical models. We show that the results are qualitatively satisfactory using synthetic and real data. Our experiments with three synthetic and three real apple trees of two different varieties showed that the system is able to identify the primary branches with an average accuracy of 98% and estimate their diameters with an average error of 0.6 cm. Although the current implementation of the system is too slow for large‐scale practical applications (it can measure approximately two trees per hour), our study shows that the proposed approach may serve as a fundamental building block of robotic pruners in the near future.

No abstract