Meet the Bonirob, a car-sized, autonomous robot with ladar capabilities, satellite navigation, a high-impact smashing rod, and sophisticated video analysis capabilities: it’s here to tend to your carrots.
Teaching robots to do anything more than identically repetitive tasks is difficult: many strenuous, time-consuming labors are still human-run, despite being inefficient and unpleasant.
Currently, plant-scientists spend hundreds of man-hours in labs, analyzing plant after plant to ensure resistance to pests, fertilizer and water requirements, and yield: it can take up to ten years for a strain of crop to be ready for market. Further, some in-field crops must be hand-weeded.
Bonirob, equipped with high-quality video recording and analysis, is capable of object recognition, a particularly challenging task for robotics. When fed images of different species of plants, the robot can recognize new samples of these plants unassisted, and even learn from new data it collects.
“Algorithms analyze the photos taken by scanners and cameras. This automatic screening saves a lot of time and effort,” says Professor Amos Albert, robotics expert at Deepfield Robotics. “Over time, based on parameters such as leaf color, shape, and size, Bonirob learns how to differentiate more and more accurately between the plants…”
After identifying plants, Bonirob then collects data, and locates plants that are not wanted: weeds. Over time, it gets better at locating and differentiating between crops and weeds, and subsequently smashing the intrusions into the ground with a mechanical rod, removing the need for chemical pesticides.
While still in research phases, the robot shows promise. In September, the German Federal Minister of Food and Agriculture Christian Schmidt presented the agricultural robot with an award for innovation in horticulture. It won the Deutscher Innovationspreis Gartenbau in the “technology” category.