Agricultural Robots Classification based on Clustering by Features and Function

Robotic systems in agriculture (agrobots) have become popular in the last few years. They represent an opportunity to make food production more efficient, especially when coupled with technologies such as the Internet of Things and Big Data. Agrobots bring many advantages to farm operations: they can reduce human fatigue and work-related accidents. In contrast, their large-scale diffusion is today limited by a lack of clarity and exhaustiveness in the regulatory framework that is intrinsically tied with ethical and legal issues concerning the management of agrobots and information. Existing legislation places obligations, like machine registration and human supervision in operations, with several issues to be addressed. They concern, to name but a few, the legal responsibility, machine and human data management, privacy issues, and contractual limitations. In this context, obtaining a clear taxonomy of agrobots would facilitate addressing management and legal issues, opening up the possibility of setting specific policies and market strategies based on recurring characteristics and features. This study aims to pursue an exhaustive classification of the various types of agrobots available today. An observational survey method involved a web search of agrobots followed by contact by phone with agrobot producer company representatives resulted in a set of qualitative variables accounting for criteria describing the scope of agrobot operation. The study reports homogeneous groups (clusters) of agrobots characterized by minimum classification redundancy. This classification provides useful information for the refinement of ad-hoc legislative supports accounting for the various types of agrobots, the promotion of market segmentation practices by technological providers, and the creation of ad-hoc fleet management strategies in the farm context.