While working on CitizenSeeds, we had the idea to also put cameras on farms so people could remotely follow what is growing in the fields. During a discussion with a friend and market farmer, it became that what was much more useful for him was a tool to help him control the weeds in his field. He showed me videos of weeding machines with sensors that work "in-row", meaning, they also remove weeds in between plants in a row. So that became the starting point of the weeding robot: a practical tool for farmers and a tool to obtain data, such as image maps, to document what's happing in the field.
Instead of a design with several arms such as in the "in-row" designs, we decided to take an existing kit for CNC machines and put it on wheels. CNC machines can position a milling tool precisely on three axis and are used for cutting objects out of wood or metal. We replaced the milling machine with a "soil mixer" that perturbs small and germinating weeds. The CNC machine that we use is the X-Carve. (See also FarmBot and ecoRobotix for a similar idea.)
So now we have an interesting challenge: develop the computer vision and motion planning to control the "robot".
We will use this page to post the technical information.
Montoring and nurturing of crops is greatly helped with tools from computer vision. In particular, the following task are considered:
- Image fusion: gathering images from multiple locations and/or multiples captors, algorithms like stitching are helpful in building a consistent representation of these data.
- Image segmentation: the distinction between regions occupied by plants and those occupied by ground is critical to the operation of the wedding robot. Furthermore, we focus on algorithms that can provide segmentation at reasonale frame rate to have realtime operation.
- Image recognition: Not yet implemented.
Based on image analysis, a map of the robot workspace is built. Two possible ways to build the map are considered:
- Offline map construction
- Online map construction