Human-robot interaction in precision agriculture: Sharing the workspace with service units

Abstract

Currently, Chile and Argentina experience serious challenges that affect their agricultural productivity. For example, in Chile, the loss of farmable field due to recent earthquakes, and volcanic eruptions as well as the loss of water reserves due to climate changes are affecting the agriculture. Additionally, both countries are facing a same problem: the loss of human labor force. Field workers are migrating from the farm to other fields in the industry which offer them more stable and more profitable jobs (like the mining industry in Chile, or car assembling lines in Argentina). In this adverse scenario, it becomes necessary to introduce and develop agricultural automation and sensing technologies for both primary (harvesting, seeding, fertilizing, spraying) and secondary tasks (grove supervision, weed detection, hauling, mowing). However, fully robotized farms are not yet a possibility since the transition from human labor force dependent farming to autonomous farming needs to be smooth and requires legal regulation not yet in discussion. In this paper, we summarize the state of the art in human-robot interaction in farmable fields, with emphasis in the current constrains associated with flexible automatization of farms in Argentina and Chile. In particular, we introduce the guidelines for designing a humanrobot interaction strategy for harvesting tasks, that could be used for other agricultural tasks.

Beyond the GUI in agriculture

“…Other works considered as borderline in this article focus on the use of interaction design techniques (such as usercentered design and the use of ethnographic methods) as tools to improve the inclusion of points of view, expectations and skill levels of farmers during the design of devices [1,6].…”

“…This feature is very valuable at least in two cases. It allows the operator to interact with the system while physically performing another task and when users have a low level of literacy (as is often the case in many phases of the agricultural cycle) it enable working with the system without the need to read or understand written instructions [1,6].…”

“…For example, one might think of the idea that agricultural sectors are naturally conservative and resistant to technological change. However, empirical studies have shown that innovation adoption decisions of rural societies are rooted in their awareness, cost and benefit factors and applicability of introduced technology rather than the myth of adherence to socio-cultural heritage [1,5].…”

“…Almost all works reviewed argued that since the end users are in a crucial role User Centered Design methods can enhance the innovation process, help to choose the technological level of the product and enhance its acceptability [6,12]. Works such as those by Readhead and her colleagues about farmer centered study of agro robots requirements or Brown ethnographic studio as input to design a computing solution for a vineyard [1,8] should be a course of action for further exploration.…”

“…Perhaps one of the main challenges for human machine control in agro robots is the level of complexity across multiple systems and human skills that they need to cope with the technology. At the same time that studies show farmers using use multiple machine interfaces for office administration, weather stations, moisture probes and tractor operation [1], others complain about low literacy or poorly skilled workers [2,6]. Multimodal, embodied interactions could be a good option to consider in those cases.…”