Utility of a commercial unmanned aerial vehicle for in-field localization of biomass bales

Baling is an accepted process for densifying and transporting herbaceous biomass. Prior to transporting bales to an outlet for utilization, producers often group or stack the bales at the edge of the field. This is a tedious and labor-intensive task. Also, bale retrieval is time-sensitive to avoid losing the dry matter or damaging crop regrowth. In this work we developed an unmanned aerial vehicle (UAV) system for operational mapping and surveying of fields with bales waiting for removal. To that end, a commercial UAV (Inspire 2 with Zenmuse XS4 camera) was utilized to determine bale locations via the onboard vision system and the low-accuracy Global Navigation Satellite System (GNSS). Also bale locations were estimated by ground survey utilizing an RTK-corrected GNSS signal, in order to determine the bale locating accuracy of the developed system. Seven fields were investigated, in which various number of bales had been produced (from 9 bales up to 58 bales) in corn stover and soybean stubble.Based on this work we were able to make the following observations. Field orthomosaic images generated with and without ground control points yielded localization accuracies that were practically similar. Hence, a localization error of less than 0.4 m was observed when aerial and ground surveys taking place in the same day. Results also showed that when flights occurred in the same day, the precision error was low (0.019–0.142 m for different fields). Different flight velocities and aircraft altitudes maintained an accuracy within practical limits of detecting bales while improving the field capacity up to 91% through the increase in flight velocity and 184% through doubling flight altitude. The results of this work could be used by both manned and robotic bale collectors for in-field navigation and bale retrieval.