by Cotton is one of the most valuable crops grown in the US, with a harvest value of approximately US$7 billion per year. It is grown in a crescent of 17 states stretching from Virginia to California and is used in almost all types of clothing, as well as medical supplies and household items such as upholstery.
Cotton grows inside a hard, fibrous case called a boll. About 100 days after planting, the bolls ripen and split open, revealing thousands of fluffy white fibers inside. Each boll contains between 20 and 40 seeds with fibers attached to them, which is why the fruits of the cotton plant are called seed cotton.
Picking cotton by hand is a painstaking task, as it still is in some major producing countries. Workers have to stoop to reach the bolls and can injure their hands on hard, dry parts of the plants. To remove the seed cotton, they have to grab it and twist it to separate it from the boll without leaving any fiber behind.
Beginning in the 1930s, cotton farmers in the US transitioned from manual labor to large, heavy harvesters. Now the industry is entering a new phase that promises to be more efficient and precise.
I am an engineer with almost 20 years of research experience working on agricultural machinery. My current focus is on agricultural robotics and automation. During my Ph.D. at Mississippi State University, I worked with Alex Thomasson, who heads the agricultural and biological engineering department and the Institute for Agricultural Independence, to develop a robotic cotton picker that picks cotton with less damage to the product and the soil where it grows he.
Why use robotics?
Cotton farmers have economic, environmental and agricultural reasons for wanting a better harvesting option. Traditional mechanical harvesters can be up to 14 feet long and weigh more than 30 tons. They remove cotton effectively without harming the plants but can also cause problems.
One issue is prolonged fiber exposure. Cotton bolls do not all ripen at the same time; the first open boulders in the field may remain up to 50 days to be picked, until more bolls mature around them.
Another challenge is that the harvesting machines compact the soil as they roll over it. This makes it more difficult for water and fertilizers to penetrate to the roots of the plants. And the machines cost about US$1 million each but are only used for two or three months a year.
Robotics is a potential solution that farmers are already using for other crops, such as fruit and vegetables. Harvesting robots use cameras and sensors to detect when crops are ready for picking and can harvest them without damaging the plant.
For cotton, robotics offers more targeted picking of bolls that are ready to harvest. It produces better quality cotton fiber by picking seed cotton as soon as the bolls open, without leaving it exposed to the weather. The robot focuses on the seed cotton and avoids contact with other parts of the plant.
With robotic picking, cotton farmers do not need to use midges to remove leaves from the plants before harvest, which is now standard practice. And small, nimble robots don’t compact the soil as they move over it, so they help maintain soil health.
Her ‘handpicked’ bio inspiration
Our work focuses on designing a final effect for robotic cotton harvesting. An end effector is a robotic arm that enables the robot to interact with other objects. Ours is a three-finger version designed for sensitive and efficient cotton picking. It draws inspiration from nature, mimicking the hunting ability of a lizard.
Each finger is a 3D printed structure with a moving belt with a pin attached to it. The pins help the hand grasp and pull in the seed cotton. Like a lizard snapping prey with its sticky tongue, three fingers of our last survivor reach for the seed cotton. On contact, the cotton fibers adhere to the fingers of the machine, as much as an insect adheres to a lizard’s tongue.
Then, the hand quickly withdraws, like a lizard’s tongue. The latter continues to work to “swallow” the seed cotton, moving it out of the plant. As the cotton picker picks and moves seed cotton out of the plant, the final picker frequently touches parts of the cotton boll and the remaining seed cotton to pick as much as possible.
To pick cotton efficiently, our robot has to do three things: detect bolls that are ready for harvest, determine exactly where they are located in three-dimensional space and pick the cotton.
The robot uses a deep learning algorithm that we have trained to identify open bolls on cotton plants. It uses a stereoscopic camera to calculate their 3D spatial coordinates, which it transfers to the robotic arm. A control algorithm monitors each boll of cotton to ensure that the robot picks as much seed cotton as possible.
Test and results
So far, we have tested the robotic cotton harvester in the laboratory and in cotton fields. The detection system found 78% of the mature cotton bolls; calculate the 3D coordinate localization system for 70% of the detected bollards; and the picking system successfully removed 83% of these bolls. Overall, the robot picked about 50% of the cotton bolls within its reach.
Our cotton picker picked at a speed of 8.8 seconds per boll. If we can reduce this required time to 0.3 seconds and increase the efficiency of the robot to pick at least 90% of the cotton bolls it can reach, by optimizing the system and adding more arms on a robot, a fleet of 50 robots could harvest cotton. field as fast as a mechanical harvester, with a comparable yield.
To improve the overall performance of the robot, we plan to adopt better artificial intelligence algorithms, improve our system’s camera and add another level of movement to the robotic arm – for example, enabling the end effect to rotate – to perform to increase.
We see great potential for our robot in major cotton-producing countries such as China, India, Pakistan and Uzbekistan, where cotton is currently picked by hand, often by women and children and sometimes under abusive conditions. One way to make this technology available to small farmers in low-income countries is to make smaller, semi-autonomous robots that would need fewer sensors. Producing higher value cotton with less damage to plants and soil could improve life for the millions of people who earn their living growing this global crop.
This article is republished from The Conversation, a non-profit, independent news organization that brings you reliable facts and analysis to help you make sense of our complex world. It was written by: Hussein Gharakhani, Mississippi State University
Read more:
Hussein Gharakhani receives funding from Cotton Incorporated, a non-profit research and marketing company working to improve the demand and profitability of cotton.
