The new Mamut autonomous robot from Cambridge Consultants gives growers a new tool to predict and optimize yield.

Designed specifically for the ag industry, Mamut captures data on plant health and yield at both the individual plant level and on a massive scale.

The artificial intelligence (AI) powered autonomous robotic platform comes equipped with a variety of sensors that enable the system to map and navigate its surroundings without GPS or fixed radio infrastructure. Cameras collect detailed crop data at the plant level as the robot travels. The system also has stereo cameras, LiDAR, an inertial measurement unit (IMU), a compass and wheel odometers. The on-board AI system fuses the multiple sensor data inputs. These technologies make it possible for Mamut to navigate through new environments in real time.

“Mamut is a practical application of AI, meeting a real and pressing need, particularly for growers of specialty crops where failure carries a high cost,” Head of Agritech Niall Mottram said, according to a news release. “AI systems are already being used to understand crop conditions, yield predictions and to enable weed identification, but our autonomous robotic platform can collect valuable and granular data below the canopy, where drones cannot see. This data enables farmers to treat each plant in their vineyard, orchard or field individually, and on the scale of massive industrial farming, optimizing yields and producing more output with less input.”

The robot has the ability to perform simultaneous localization and mapping (SLAM), enabling it to react and learn from unstructured routes in real time. The system was developed in navigation trials through a 12-acre corn maze at Skylark Garden Centre and at Mackle Apple’s orchard, both in Cambridgeshire, UK.