RobHortic: A Field Robot to Detect Pests and Diseases in Horticultural Crops by Proximal Sensing

RobHortic is a remote-controlled field robot that has been developed for inspecting the presence of pests and diseases in horticultural crops using proximal sensing. The robot is equipped with colour, multispectral, and hyperspectral (400–1000 nm) cameras, located looking at the ground (towards the plants). To prevent the negative influence of direct sunlight, the scene was illuminated by four halogen lamps and protected from natural light using a tarp. A GNSS (Global Navigation Satellite System) was used to geolocate the images of the field. All sensors were connected to an on-board industrial computer. The software developed specifically for this application captured the signal from an encoder, which was connected to the motor, to synchronise the acquisition of the images with the advance of the robot. Upon receiving the signal, the cameras are triggered, and the captured images are stored along with the GNSS data. The robot has been developed and tested over three campaigns in carrot fields for the detection of plants infected with ‘Candidatus Liberibacter solanacearum’. The first two years were spent creating and tuning the robot and sensors, and data capture and geolocation were tested. In the third year, tests were carried out to detect asymptomatic infected plants. As a reference, plants were analysed by molecular analysis using a specific real-time Polymerase Chain Reaction (PCR), to determine the presence of the target bacterium and compare the results with the data obtained by the robot. Both laboratory and field tests were done. The highest match was obtained using Partial Least Squares-Discriminant Analysis PLS-DA, with a 66.4% detection rate for images obtained in the laboratory and 59.8% for images obtained in the field.

Environment map generation in forest using field robot

We are developing an autonomous field robot to save labor in forest operation. About half of Japan's artificial forest area is already available as wood. However, trees are not harvested and forest resources are not effectively used, because the labor and costs are not sufficient. The employment rate of young people in forestry tends to decline, and the unmanaged forest area is expected to increase in the future. Therefore, in our laboratory we propose an autonomous field robot with all terrain vehicles (ATV) that focuses on the automation of work. The robot we are developing automates weeding and observation for all trees in the forest. In this research, we introduced Robot Operating System (ROS) developed in recent years to this robot. In addition, we observed trees by generating an environmental map in the forest using Simultaneous Localization and Mapping (SLAM).

Coverage Motion Planning Using Graph in Forest Environment in Field Robot

This paper addresses the problem of using a mobile, autonomous robot to manage a forest whose trees are destined for eventual harvesting. We have been focussing a eliminate weeding operation because it is one of the hard work in the forestry works. This research proposing the computation of trajectory capable of traversing in the entire forest. The method is based on a graph whose vertices are trees located in the forest. Trees located in the forest will be treated as vertices in a graph. In the first, the initial graph is made with considering the safety of the robot. Next, editing the initial graph to be Eulerian, and finally, the Hamiltonian circuit is obtained which could be used for trajectory. By our proposed method, the trajectory of which feasible route for traversing of the entire forest would be obtained. In the experiment, we show the result of the method applying to actual artificial forest.