Forum for Science, Industry and Business
Sponsored by:     Siemens  n-tv 
Search our Site:

Topic (optional):

 

Home Reports Agricultural and Forestry Science Content

Robot weeds fields

next article
16.09.2005

 


Weeding is a major problem for ecological growers since it is both expensive and time-consuming. New robot technology may have the solution. In a new dissertation, Björn Åstrand, from Halmstad University in Sweden, presents how weeds can be removed mechanically -with the fully automated robot Lukas.

In ecological cultivation, weeding is performed manually, entailing not only economic burdens for many growers but also logistic ones -it’s hard to find people willing to do this work, and many growers therefore have to limit their production.


“For an ecological grower of beets, weeding can cost about SEK 10,000 per hectare. With robot technology we estimate that these costs can be cut in half. In the long term this technology would also mean major environmental benefits by ultimately replacing chemical herbicides in traditional cultivation,” says Björn Åstrand, who works at the School of Information Science, Computer and Electrical Engineering at Halmstad University. He is formally a doctoral candidate at Chalmers University of Technology in Göteborg.

Together with associates at Halmstad University, he has developed and constructed a fully automated robot, named Lukas. The robot can automatically make its way around a field and remove weeds both between cultivation rows and in the rows, between plants. The method was developed for sugar beets, but it works in principle for all vegetables that are grown in rows, like lettuce, cauliflower, and carrots.

The robot functions with the aid of computerized image processing. An infrared camera is installed on the robot to read the rows. The images are processed using a specially developed computer program that in turn steers the robot’s wheels and weeding tool.

Within the rows, the robot distinguishes between crop and weeds with the aid of another camera, which takes color images, and a program that analyzes the color and form of the plants. This method works extremely well under certain conditions, but the system is susceptible to differences in the appearance of crops. The appearance can differ considerably within a field and can be influenced by factors such as rain, wind, and diseases.

“I have therefore developed another technique that also reads the cultivation patterns of crops. Since crops are planted at regular intervals, such as fifteen centimeters apart, the computer can determine what is a weed and what isn’t. By combining these different methods we achieve a robust technology,” he says.

There is some fine tuning to be done before the robot is ready to be marketed. One remaining challenge is how to deal with cases where crop and weed are so close together that they have become intertwined.

Lukas the Robot has been tested and developed in collaboration with ecological beet growers in the province of Halland.

Björn Åstrand publically defended his dissertation titled Vision-based perception for mechatronic weed control on September 8, 2005.

Ida Lövstål | Source: alphagalileo
Further information: www.hh.se

next article

More articles from Agricultural and Forestry Science:

nachricht Improved conditions for peasants fuelled agricultural revolution
08.02.2010 | University of Gothenburg

nachricht U of I faculty assist in evaluating US food security programs
05.02.2010 | University of Illinois at Urbana-Champaign

B2B Search

Product / Service
Company / Organisation

Latest News

Early Artificial Pancreas Trials Show Benefits for Kids, Teenagers with Diabetes While Sleeping Overnight

08.02.2010 | Studies and Analyses

Princeton scientist makes a leap in quantum computing

08.02.2010 | Information Technology

Sweet! -- sugar plays key role in cell division

08.02.2010 | Life Sciences

VideoLinks
More VideoLinks >>>

Event News

Asia-Pacific Symposium on Information and Telecommunication Technologies 2010 (APSITT 2010)

04.02.2010 | Event News

The Engineering Conference (EnCon 2010)

04.02.2010 | Event News

Homeland Security Science and Technology University Network Summit

01.02.2010 | Event News