Apple maturity discrimination and positioning system in an apple harvesting robot

Abstract

To obtain the spatial position and the maturity of apples, a system based on a multi‐spectral vision technique and a trigonometrical survey technique was designed. It comprised a 2D vision sensor and a microprocessor. The 2D vision sensor was constructed using two laser beams: a red laser beam (685 nm) and an infrared laser beam (830 nm). Beams were installed perpendicularly to one another, and they were united along the same optical axis using a cold filter. The united beam was transmitted into an apple through a full reflecting mirror and a swinging mirror; the reflected beam from the apple was focused onto the sensitive surface of a position sensitive device (PSD) through a focusing lens. The two output signals of the PSD were transmitted into a microprocessor after a set of processes including I/V conversion, amplification, filtering and demodulation. The microprocessor transmitted the output information of position and maturity to a manipulator through the RS 232 bus. To evaluate the performance of the system, some tests were performed.