Automatic target recognition in agricultural harvesting robots is characterized by low detection rates and high false alarm rates due to the unstructured nature of both the environment and the objects. To improve detection human‐robot collaboration levels were defined and implemented. The collaboration level is defined as the level of system autonomy or the level at which the human operator (HO) interacts with the system. Experimental results on images taken in the field indicate that collaboration of HO and robot increases detection and reduces the time required for detection.