Chao Chen

Laboratory of Motion Generation and Analysis (LMGA)

Department of Mechanical and Aerospace Engineering, Monash University, Australia

The increasingly severe labour shortage in the agriculture sector is driving a surging demand for robotic harvesting. Despite significant investment and advancements being made in the past two decades, autonomous harvesting robots have not yet achieved the level of productivity required to see widespread adoption. The excessive environmental complexity has made the robotic fruit harvesting task very challenging. In the field of apple harvesting, a number of orchards aim to transition to two-dimensional (2D) structured apple canopies such as fruiting walls to reduce the environmental complexity (improve accessibility and visibility of the target fruit). However, maintaining this standard of the canopy is labour-intensive, and an unsustainable practice for farmers in the long term who are already burdened with labour shortages. To address such challenge, we introduce the Monash Apple Retrieving System (MARS), a selective apple harvesting platform capable of navigating and harvesting apples in complex canopy environments without the need for canopy simplification. Featured with intelligent decision-making and adaptive fruit-robot interaction, MARS is able to perform elegant but firm apple harvesting in complex and unstructured canopies. Extensive trials were conducted over the 2021 and 2022 apple harvesting seasons in Australia, where MARS achieved a harvesting success rate of 70.7% and 71.4% against pink lady apples and smitten apples, respectively, with negligible damage to the fruit. The significance of these parameters is that it represents MARS’ performance under realistic conditions, where no attempts other than essential occluded leaves removal were made to modify the canopy to create idealistic conditions for robotic harvesting. These results are promising with huge potential for improvement, and by lowering strict canopy requirements for robotic harvesting, we can improve the accessibility of this technology to more farmers who are struggling with labour shortages around the world.