Adaption of Mobile Robot Platform for Cotton Harvesting

Robots are becoming more integrated in the manufacturing industry. Though, most of the manufacturing environment are not as complicated as outdoor, recent advances on sensors and algorithm provide an interesting outlook on how robots will be working outdoor with humans. Commercial small unmanned ground vehicle (UGV) or mobile ground robots with navigation sensing modality provides a platform to increase farm management efficiency. The platform can be retrofitted with different manifolds that performs specific task, e.g. spraying, scouting (having multiple sensors), phenotyping, harvesting, etc. This paper will present a robot prototype which can be used for selective harvesting of cotton. In this paper, an autonomous map-based robot navigation will be presented including an initial results for selective harvesting experiment. A graphical user interface was created which allow the user to specify way points or segments on a field. These points/segments can be represented in different scenarios, e.g. locations of mature cotton bolls, locations of weeds, insects, etc. The robot will autonomously navigate to these segments and performs the task, in this paper selective harvesting of the cotton bolls. The robot was retrofitted with a vacuum-type system with a small storage bin. Performance test on navigation and the vacuum harvesting will be presented.