My lab’s research lies in the general area of mechanization, agricultural robotics, and automation for specialty crop production. We focus on developing methodologies and technologies that can be used to improve the efficiency and working conditions of human workers or replace labor in some tasks. Additionally, we work on ‘core’ robotic technologies, such as sensor-based safe, accurate, and robust autonomous navigation in orchards.
Robotic harvesting of fresh-market fruits has remained – for most crops – an elusive target for the past sixty years. The technical feasibility of robotic selective fruit picking was demonstrated – in principle – more than thirty years ago. However, low harvesting efficiency (% of marketable fruits harvested) and low picking speed (fruits per second harvested) continue to restrict the application of this approach. Our research investigates the use of robotic harvesters with many arms to increase harvesting speed. In particular, we explore alternative mechanical designs and the efficient and load-balancing distribution of work among arms to achieve high picking speeds.
Model-based design of mechanized orchard-harvesting systems
A significant obstacle towards improving current – or coming up with radically different – designs of mechanized fruit-harvesting systems is the lack of appropriate modeling tools. We are currently building model-based design tools to enable researchers and developers to investigate the interrelationships among orchard layout, tree canopy geometry and spatial fruit distribution, harvester design, and worker activities. Such tools can accelerate the development of next-generation orchard mechanization and automation systems.
Human-robot collaboration and multi-robot coordination
Robots cannot currently replace human perception and dexterity in many agricultural operations (e.g., harvesting, pruning). One alternative is to design advanced autonomous machines that work together with agricultural workers to improve labor efficiency and human factors. An essential challenge in this area is to develop mechanistic models of agricultural worker activities that robots can use to collaborate with them safely and efficiently. Another challenging issue is how autonomous agricultural vehicles can coordinate and collaborate to improve field and orchard logistics while guaranteeing human and equipment safety.