\n<\/p>\n
What is and isn\u2019t a weed that needs to be eliminated in the field is determined by the eyes of the farmer \u2014 and now, increasingly, by a new AI model from Carbon Robotics.<\/p>\n
Seattle-based Carbon Robotics<\/a>, which builds the LaserWeeder \u2014 a robot fleet that uses lasers to kill weeds \u2014 announced a new AI model, the Large Plant Model (LPM), on Monday. This model recognizes plant species instantly and allows farmers to target new weeds without needing to retrain the robots.<\/p>\n The LPM is trained on more than 150 million photos and data points collected by the company\u2019s machines across the more than 100 farms in 15 countries where the robots currently operate. The model now powers Carbon AI, the AI system that serves as the brains inside the company\u2019s autonomous weed-killing robots.<\/p>\n Paul Mikesell, the founder and CEO of Carbon Robotics, told TechCrunch that prior to LPM, every time a new type of weed would show up on a farm \u2014 or even the same type of weed in different soil or with a slightly different appearance \u2014 the company would have to create new data labels to retrain its machines to recognize the plant.<\/p>\n This process took about 24 hours each time, Mikesell said. Now, LPM can learn a new weed instantly, even if it\u2019s never seen it before.<\/p>\n \u201cThe farmer can live in real time and say, \u2018Hey, this is a new weed. I want you to kill this,\u2019 and that was something that had never been done before,\u201d Mikesell said. \u201cThere\u2019s no new labeling or retraining because the Large Plant Model understands, at a much deeper level, what it\u2019s looking at and the type of plant.\u201d<\/p>\n Mikesell said that the company, which was founded in 2018, started developing this model shortly after it began shipping its first machines in 2022. Mikesell has years of experience building these types of neural networks from previous roles at Uber and working on Meta\u2019s Oculus virtual reality headsets.<\/p>\n Techcrunch event<\/p>\n \n\t\t\t\t\t\t\t\t\tBoston, MA<\/span> This new model will reach the company\u2019s existing systems through a software update. From there, farmers can tell the machine what to kill and what to protect by selecting photos that the machine has collected in the robot\u2019s user interface.<\/p>\n
\n\t\t\t\t\t\t\t\t\t\t\t\t\t|<\/span>
\n\t\t\t\t\t\t\t\t\t\t\t\t\tJune 23, 2026<\/span>\n\t\t\t\t\t\t\t<\/p>\n<\/p><\/div>\n<\/p><\/div>\n<\/div>\n