[Paper Review] Cognitive factors that affect the adoption of autonomous agriculture

S. Kate Devitt|arXiv (Cornell University)|Nov 28, 2021

Smart Agriculture and AI19 citations

TL;DR

This paper identifies cognitive factors—trust, situational awareness, cognitive load, and loss of farming knowledge—that hinder the adoption of robotic and autonomous agricultural technologies (RAATs). It proposes a human factors-informed framework for RAAT design, emphasizing autonomy level-specific interfaces and training to reduce cognitive strain and maintain farmer decision-making control.

ABSTRACT

Robotic and Autonomous Agricultural Technologies (RAAT) are increasingly available yet may fail to be adopted. This paper focusses specifically on cognitive factors that affect adoption including: inability to generate trust, loss of farming knowledge and reduced social cognition. It is recommended that agriculture develops its own framework for the performance and safety of RAAT drawing on human factors research in aerospace engineering including human inputs (individual variance in knowledge, skills, abilities, preferences, needs and traits), trust, situational awareness and cognitive load. The kinds of cognitive impacts depend on the RAATs level of autonomy, ie whether it has automatic, partial autonomy and autonomous functionality and stage of adoption, ie adoption, initial use or post-adoptive use. The more autonomous a system is, the less a human needs to know to operate it and the less the cognitive load, but it also means farmers have less situational awareness about on farm activities that in turn may affect strategic decision-making about their enterprise. Some cognitive factors may be hidden when RAAT is first adopted but play a greater role during prolonged or intense post-adoptive use. Systems with partial autonomy need intuitive user interfaces, engaging system information, and clear signaling to be trusted with low level tasks; and to compliment and augment high order decision-making on farm.

Motivation & Objective

• To identify key cognitive factors affecting farmer adoption of robotic and autonomous agricultural technologies (RAATs).
• To analyze how varying levels of autonomy (automatic, partial, fully autonomous) influence cognitive demands on farmers.
• To address the risk of reduced situational awareness and loss of farming knowledge due to over-reliance on automated systems.
• To propose a tailored human factors framework for RAAT performance and safety, drawing from aerospace engineering principles.
• To support sustainable adoption by aligning system design with human cognitive capabilities and limitations.

Proposed method

• Adapts human factors research from aerospace engineering to agricultural contexts, focusing on individual variance in knowledge, skills, and traits.
• Analyzes cognitive impacts across three autonomy levels: automatic, partial, and fully autonomous systems.
• Evaluates the role of trust, situational awareness, and cognitive load in adoption decisions during adoption, initial use, and post-adoptive use stages.
• Proposes design principles for intuitive user interfaces, clear system signaling, and information engagement to support trust and decision-making.
• Integrates findings into a proposed framework for RAAT performance and safety standards specific to agriculture.

Experimental results

Research questions

• RQ1 How do different levels of autonomy in RAATs affect farmers' cognitive load and situational awareness?
• RQ2 What role does trust play in the adoption and sustained use of autonomous agricultural systems?
• RQ3 How does the reduction of hands-on farming knowledge due to automation impact long-term decision-making on farms?
• RQ4 In what ways do cognitive factors become more pronounced during post-adoptive use compared to initial adoption?
• RQ5 How can human factors principles from aerospace be adapted to improve RAAT design and adoption in agriculture?

Key findings

• Higher autonomy in RAATs reduces the need for direct human operation but increases the risk of reduced situational awareness and strategic oversight.
• Cognitive factors such as trust and cognitive load are more influential during prolonged or intensive post-adoptive use than during initial adoption.
• Partial autonomy requires intuitive interfaces and clear system feedback to maintain farmer trust and support high-level decision-making.
• Loss of farming knowledge due to automation can impair long-term enterprise management, especially when system failures occur.
• Agriculture needs a dedicated framework for RAAT performance and safety, informed by human factors research, to address unique cognitive demands.
• The integration of human-centered design principles can mitigate cognitive strain and enhance sustainable adoption of autonomous agricultural technologies.