Skip to main content
Knowledge4Policy
Knowledge for policy
Supporting policy with scientific evidence

We mobilise people and resources to create, curate, make sense of and use knowledge to inform policymaking across Europe.

  • Publication | 2025
Applications of robotics and extended reality in agriculture: A review

Highlights:

  • 210 research articles were analysed under the scope of robotics, extended reality, and human robot-interaction in agriculture.
  • Vegetable crops were the most widely used crop type in the research articles.
  • Operation-specific and wheeled robots were the most used robots according to type and locomotion.
  • Collision avoidance was the most frequently implemented safety feature in the studies.
  • Operations with high demand in accuracy, frequency or labour were connected with robots that were developed for a single operation.
  • End-effectors that were specialized in one operation were more preferable than generic end-effectors.

Abstract:

Agriculture is facing a labour shortage problem that affects global food safety and security. Robotic and extended reality (XR) technologies can prove to be potential solutions to this problem and help with the transition to Agriculture 5.0, although the latter is still at early stages of development. The aim of this study was to map and assess the way robotics and XR can mitigate labour shortage problem. PRISMA methodology was followed to identify relevant studies from the last five years, while frequency and correspondence analyses were used for identifying the corresponding trends. In total 210 relevant research studies were identified. These were analysed under the scope of crops, operations, robotics, XR and Human Robot Interaction (HRI). Vegetable crops (36%) followed by orchard crops (34%) were the most studied crop types. Additionally, the results presented that operation-specific robots were the most used robot type with use in 77 research articles while 140 research articles referred to wheeled robots. Also, the robots did not present any collaboration level with human in the most relevant studies. Collision avoidance was the most frequently implemented safety feature (31 out of 51 research articles) in the studies that included this type of information. Moreover, operations with high demand in accuracy, frequency or labour were connected with robots that were developed for a single operation. Thus, end-effectors that were specialized in one operation were more preferable than generic end-effectors. However, not all studies referred to all these topics, indicating a need for further investigation. Finally, future studies should further explore the use of Mixed Reality, safety, connectivity and data governance.