There is an increasing concern that the traditional approach of natural kiwifruit pollination by bees may not be sustainable. The alternatives are currently too costly for most growers due to high labor requirements or inefficient usage of expensive pollen. This paper presents a performance evaluation of a novel kiwifruit pollinating robot designed to provide a more efficient, reliable, and cost‐effective means of producing kiwifruit. The robot comprises a novel air‐assisted sprayer, a machine vision system employing convolution neural networks, and a flower targeting system for efficient and effective application of pollen to individual flowers. We show that this pollination system is capable of individually targeting and pollinating 79.5% of flowers at 3.5 km/hr while using comparable amounts of pollen to commercial Cambrian operators. Furthermore, flowers that were successfully pollinated at 1 km/hr grew into the first robotically pollinated kiwifruit which were comparable in quality to commercially grown kiwifruit. However, the overall fruit set was found to be well below commercial requirements and further work on increasing the overall yield is required.

Here we grow chemical gardens using a novel, quasi two-dimensional, experimental configuration. Buoyant calcium chloride solution is pumped onto the surface of sodium silicate solution. The solutions react to form a precipitation structure on the surface. Initially, an open channel forms that grows in a spiral. This transitions to radially spreading and branching fingers, which typically oscillate in transparency as they grow. The depth of the radial spreading, and the fractal dimension of the finger growth, are surprisingly robust, being insensitive to the pumping rate. The curvature of the channel membrane and the depth of the radially spreading solution can be explained in terms of the solution densities and the interfacial tension across the semipermeable membrane. These unusually beautiful structures provide new insights into the dynamics of precipitation structures and may lead to new technologies where structures are grown instead of assembled.

The growing popularity of kiwifruit orchards in New Zealand is increasing the already high demand for traditional pollinators (bees), with alternatives currently too costly for most growers due to high labour requirements or inefficient usage of expensive pollen. A novel pollinating robot has been previously described to provide a more efficient, reliable and cost-effective means of addressing this problem. However, the pollinator suffered from a low fruit-set rate of 40% overall, well below commercial requirements of 80% to 90%. This paper presents two new developments for that system: a new, off the shelf spray nozzle (SS1504) to increase the overall pollen delivery and an automated height controller to keep the spray manifolds at a consistent distance below the canopy while avoiding obstacles. Furthermore, we have designed and conducted a more controlled, real-world evaluation of the pollination system to compare both nozzle variants and measure the commercial viability of the pollination platform. Final results show that, operating from a mobile platform at 2.5 km h −1 , the new nozzle could consistently achieve a fruit-set rate only 16 ± 2% below the control samples in each test orchard (82 ± 2% and 72 ± 4% absolute). Pollen consumption remains high, however, with estimates of up to 4.6 kg ha−1 , thus preventing the system from being economically viable. While cost-effectiveness awaits substantial efficiency improvements, our work has demonstrated an automated pollinator that can produce commercial-grade kiwifruit.