Page last updated at 11:02 GMT, Thursday, 11 March 2010

Down on the farm with the robots

By Mark Ward
Technology correspondent, BBC News

Autonomous tractor, Tony Stentz
Autonomous vehicles might soon be at work on many farms

Picking a cauliflower seems a very easy task, at least to anyone who has only ever encountered the brassica on a plate accompanied by meat and other vegetables.

But knowing the right moment to pick a cauliflower is tricky. Harvest it too soon or too late and supermarket chains might reject the whole crop for being too big or small.

There are also problems of finding labour willing to do the picking.

"It's a horrible job and there's not enough people doing it," said Dr Richard Dudley from the National Physical Laboratory (NPL), which is working on a robot to replace the human harvesters.

Human-based methods of picking cauliflowers involve about 15 people walking in front of a harvester checking cauliflowers to see if they are the right size, cutting them and then placing them in a hopper. All in a few seconds.

Cauliflower picking robot, NPL
Field tests of the cauliflower picking robot are under way

No wonder, then, that mistakes are made and the system is not very efficient.

"At the moment they do one pass and anything that's left is usually left to rot away," said Dr Dudley.

Dr Dudley and colleagues at NPL along with agricultural firm Vegetable Harvesting Systems (VHS) are working on robots that are as fast as humans at working out if a cauliflower is ready to be picked.

One prototype has a multi-axis arm and the other is equipped with a blade that simply cuts and gathers. Field trials of both are being carried out on a farm in Cambridgeshire.

For a robot equipped with the right sensors, far infra-red, terahertz and microwave, then working out if a cauliflower is ready to pick is easy.

"Once they reach a certain size you know they are ripe," said Dr Dudley.

Current prototypes will likely be attached to a harvester but future versions could patrol the fields themselves.

"They'll use GPS and imaging systems to see the crops and understand how they are growing," said Dr Dudley. "They can start monitoring, managing and predicting so you can maximise the yield per acre."

The robot cauliflower picker could be, he said, the harbinger of a new era in farming that makes far greater use of technology.

Hands off

"Agriculture is a great opportunity for automation like robotics," said Professor Tony Stentz of the Field Robotics Centre at Carnegie Mellon University.

Plowing, John Deere
Getting rows the right distance apart is tricky

"Fruits that grow on trees and vegetables that grow in a row, the idea is to farm those crops in a way that you want to pick the fruit and vegetables but you do not want to destroy the plant," he said. "That's a far more challenging task then using a combine to harvest corn."

So far, getting robots to be as cheap as human has proved difficult and has focussed interest on making more of the vehicles that are already in use on a farm.

"Take tractors," said Professor Stentz. "They pull an implement and with that they can plough, till and hoe. They can plant, spray chemicals and mow the weeds in between trees."

"There's an opportunity to improve all of that by automating and removing the driver," he said.

Making tractors and other machines autonomous would have many benefits, said Professor Stentz. Safety would be improved, he said, because farmers would spend less time around big machines and less time near the chemicals they spray.

An autonomous vehicle could also work at peak speed all the time, do without breaks and operate 24 hours a day.

Smart tractors studded with sensors would be able to monitor crops and selectively apply fertilisers or other chemicals, spot disease early on and gather data about a crop.

"You can watch them grow and report their size and number," said Professor Stentz. "You can predict when you are going to get the yield and how big it's going to be and you can plan your resources downstream."

Field fare

Key to all of this is improved location data.

Thousands of farms have used guidance systems over the past few years, said Mark James, of agricultural firm John Deere. Some guidance systems are GPS based and others simply help a farmer follow a straight line.

"If you are sitting in a cab for 10-12 hours then it's hard to work accurately by eye for any length of time," he said.

"Guidance systems can help steer the machine manually or steer it by itself to a high degree of accuracy all day long," said Mr James. "The benefit is that the rows are the right spacing."

That means, he said, less overlap of fertiliser and other chemicals cutting down on waste.

John Deere already sells hands-free tractors that can go up and down a field by themselves. Under development are tractors that are wirelessly linked to slave vehicles to handle the biggest farms.

John Deere is also looking at using location data produced by a combine harvester to guide a tractor pulling alongside to take away the crop it has harvested.

"Guidance systems are enablers," said Mr James. "Farmers buy them with one job in mind and then realise they can use it for lots more."



Print Sponsor


SEE ALSO
Can robots fight our battles?
08 Feb 10 |  Special Reports
Autonomous tech 'requires debate'
19 Aug 09 |  Technology
School wins prize for Lego robot
27 Jan 10 |  England
Harvest combines with technology
18 Aug 09 |  Nature
Military robot 'hops' over walls
15 Sep 09 |  Science & Environment
Robot plane sweeps over UK fields
08 Aug 08 |  Science & Environment
Robotic racers achieve milestone
09 Oct 05 |  Technology

RELATED INTERNET LINKS
The BBC is not responsible for the content of external internet sites


FEATURES, VIEWS, ANALYSIS
Has China's housing bubble burst?
How the world's oldest clove tree defied an empire
Why Royal Ballet principal Sergei Polunin quit

BBC iD

Sign in

BBC navigation

Copyright © 2016 BBC. The BBC is not responsible for the content of external sites. Read more.

This page is best viewed in an up-to-date web browser with style sheets (CSS) enabled. While you will be able to view the content of this page in your current browser, you will not be able to get the full visual experience. Please consider upgrading your browser software or enabling style sheets (CSS) if you are able to do so.

Americas Africa Europe Middle East South Asia Asia Pacific