Lettuce harvesting robot

Engineers have developed a robot that can harvest lettuces.

Harvesting is the only part of the lettuce life-cycle that is not automated, and it is back-breaking work. Whilst harvesting of other crops such as wheat and potatoes has for a long time been automated, lettuces have so far eluded automation for various reasons: firstly, lettuces are very easily damaged, and supermarkets have very high standards for what they will accept. Secondly, if you imagine looking at a field of lettuces, all you see is a sea of leaves, it is actually very difficult to pick out individual lettuces, even for humans. 

But now, engineers at Cambridge University have developed a robot which they believe is up to the task. At the end of a large robotic arm the robot has a square cage which is big enough to hold a football. The robot also has two cameras to see the lettuces.

When the robot goes to pick a lettuce it first lowers the cage over the lettuce. A soft gripper, covered in silicone, gently grabs the lettuce to avoid bruising it. Then a blade slices through the stalk of the lettuce, giving it a nice clean cut.

But before the robot picks the lettuce, it has to first find it in the confusing sea of leaves, and then decide whether the lettuce is good for harvesting. The robot has been trained to identify the lettuces using neural networks. A neural network is a computer system, which is inspired by the way the human brain works.

The robot classifies the lettuces into three categories: ready for harvesting, not yet ready, and diseased. “It’s very important not to pick a diseased lettuce” says Simon Birrell from Cambridge University “because if you do you can contaminate the [cage] and then when you move it to the next lettuce you run the risk of spreading whatever the infection is.” The immature lettuces can be harvested at a later date.

The team have tested the robot in the field - literally - in a field of lettuces. The robot sits on a rig, powered by a generator, and the wheels roll between the rows of lettuces. “The conditions are completely different from the lab” says Birrell, “all the fine-tuned calibration that you do in the lab is completely useless out in the field.”

In the tests the robots successfully located the lettuces 91% of the time and successfully classified them 82% of the time. At the moment the robot is about four times slower at picking lettuces than a human, but Simon reckons they can easily reduce this difference by changing to a stronger robotic arm. The current arm moves quite slowly because the cage is quite heavy.

Whilst the robot will be able to take over the physical demands of harvesting, there will still be a role for humans to play, in terms of monitoring and maintaining the robots.

But if you are worried about the robots taking over, Simon kindly pointed out that the cage was the perfect size for cutting off human heads! But he hasn’t tested this theory out.