The bottom pressure and porosity of a rough rice layer piled in a grain tank are expected to be negatively correlated. Thus, we investigated the applicability of Janssen’s equation to the estimation of the bottom pressure, which can be an indicator of the porosity. Janssen’s equation accurately estimated the bottom pressure of a rough rice layer (moisture content: 14 %, 18 %, 25 %, 30 %) piled in a rectangular prism container with an RMSE of 0.04-0.13 kPa, indicating that Janssen’s equation is applicable to a grain tank of rectangular cross-sectional shape, but the porosity was dense and almost constant for each moisture content. Whether the abovementioned negative correlation prevails during harvest requires further investigation.

This study aims to develop a collision avoidance system that detects objects using a stereo camera for a robotic combine’s safe operation. Herein, two methods for object detection and distance estimation have been poposed. The first method is a combination of a deep learning-based object detection method, i.e., you look only once (YOLO), and a depth image, whereas the second relies on point cloud data, which are obtained from the stereo vision. Results show that both the detection methods achieved an F-measure of more than 0.95, however, YOLO-based method needs a high performance computer. Stereo vision system could be applied to real-time object detection and collision avoidance for a robotic combine, which can take actions, slow-down, and stop, according to the position of the detected obstacle.

We developed two different types of mowers for orchards based on walker mowers designed for inclines. We also evaluated the mowers’ ability to save labor and reduce workload while mowing around tree trunks in apple fields. On examination, the mower was developed with a caster improving work efficiency by 40 % (compared with a brush cutter). The mower was developed with a swingable, offset mechanism which improved performance two-fold. When these mowers are used, harmful working postures were lower compared with brush cutters.