AgBot II was a research prototype robot developed over the period 2013-2017 to demonstrate key capabilities such as navigation, vision-based weed detection, novel weed destruction, and automatic replenishment.
The robot was developed to help farmers deliver quality produce while ensuring long-term sustainability in a globally competitive sector.
The robot was equipped with cameras, sensors and software and designed to work in autonomous groups to navigate, detect and classify weeds and manage them either chemically or mechanically as well as apply fertilizer for site specific crop management.
It was designed to be transported as a flat pack and assembled like Ikea furniture and could carry 200 litres of herbicide as well as mechanical hoes. Agbot II also knew when it was tired and could find its way home to recharge when its battery was low.
Trials of the AgBot II prototype were carried out at the Queensland Government’s Redlands Research Station, with outstanding results including an overall success rate in weed detection and classification above 90%. The project ended in 2017 and has not yet been commercialised.
Lead Researcher: Dr Chris Lehnert