Intelligent sensing, planning, and control of a prototype robotic melon har
vester is described. The robot consists of a Cartesian manipulator mounted
on a mobile platform pulled by a tractor. Black and white image processing
is used to detect and locate the melons. Incorporation of knowledge-based r
ules adapted to the specific melon variety reduces false detections. Task,
motion and trajectory planning algorithms and their integration are describ
ed. The intelligent control system consists of a distributed blackboard sys
tem with autonomous modules for sensing, planning and control, Procedures f
or evaluating performance of the robot performing in an unstructured and ch
anging environment are described. The robot was tested in the field on two
different melon cultivars during two different seasons. Over 85% of the fru
it were successfully detected and picked.