Commercial farms of the future can be occupied by robots that identify, spraying and choose individual pieces of products from plants grapes, peppers and apples that are as green as the leaves, even if their objectives are that surround them.
Scientists in Israel and Europe closer to this goal is, experts say that the work has a number of potential benefits. Autonomous agricultural robot could protect against the harmful effects of hand human workers dealing with chemicals. And through a system of highly selective spraying robot could reduce a farm use of pesticides by up to 80 percent.
Robots could provide a timely supply of labour in many places, where there simply not enough non-hospital workers available on the right side times the cycle. In the meantime could attempts, to create robots that see to gather and learn can end up with widespread applications in medicine, video games, and much more.
And while scientists have worked to develop robots for agricultural work for more than 20 years, a new project takes a more cerebral approach. The goal is to see how people do and better on their work learn how they work and learn, to teach the computer.
"The technology is ready, and now we can begin to see it penetrates into the market," said Yael Edan, an engineer and robotics researcher at the Ben-Gurion University of the Negev in Israel. "I would say, robot definitely it out there in five years-maybe not on any farm, and not for each farmer may be." "I think, now is the time."
Modern commercial farms are already full of tractors with automated control and machines, the milk of cows, and down to the ground can. But a much more difficult task is wanted on individual fruits or vegetables. This is because the environment cannot be foreseen and is changing.
Each piece of produce, which means that a computer can be programmed is, for example, a unique shape, size, color and alignment, not just to a specific image search. Shade and light conditions change throughout the day and night, as well as a single object under various conditions makes different look. And green fruits and vegetables can similarly as the Green bushes or vines, which they grow up.
To the ability of a computer order within the relative chaos of an agricultural environment find promote, Edan's team, together with a consortium of European ladies and gentlemen, work on intelligent sensing systems. A strategy includes multi-spectral cameras, to analyze the wavelengths of light bouncing off of objects. The idea is, you will find a consistent pattern, which the robots would say if it is to see a pepper say, no matter whether this pepper right-side-up or was on the head.
Together with other sensors and programs a robot "Brain" want to create the researchers, who then learn from their mistakes and improve how it works.
"We will have an algorithm, simple forms will be displayed." And when food is partially covered by leaves, it will say: "OK, let us not use the algorithm for full-shape." But because we see only a part of the food, let us try the contour fill "" Edan said. What separates their teamwork from previous projects, said she is, that both properties of human vision and computer learn it contains.
So far, computers find easy between 80 and 85 percent of the fruits on a plant, the Group has found. But their benchmark is 90%, and many farmers say she would be used no robot, if it's a hit accuracy rate of 99 percent.
Once a robot identified its objectives, the engineers try also design to produce a grasping tool that is access to the right place and bring it with the right amount of strength. To this end, they will study human movements, and with an others can try to imitate what is as natural to the human hand.
As the project, which began in October last year, ramps up and starts lead to results, agricultural robot could contribute to farmers around the world, including in the United States, said Bernie Angel, an agricultural engineer at Purdue University in West Lafayette, Indiana
"In many cases are challenges to find work to do, some of the harvest of strawberries and other fruits and vegetables," angel said. "It is hard work." It is a factor of relevance, where you can wait a week. "You need much work for relatively short periods of time, which created real challenges for the storage of the employees in a sustainable manner."
"If you have the world's population at this point and the need to feed a growing population," he added, "We need to get more efficient harvesting and production of these crops."
没有评论:
发表评论