# Ambient awareness for agricultural robotic vehicles

**Authors:** Giulio Reina, Annalisa Milella, Raphael Rouveure, Michael Nielsen, Rainer Worst, Morten R. Blas  
**arXiv:** [2104.05270](https://arxiv.org/abs/2104.05270)  
**Date:** 2021-04-12  
**Summary page:** https://www.summarizepaper.com/en/arxiv-id/2104.05270v1/

## Key points

- Robotic technology in agriculture is on the rise to improve productivity and competitiveness
- Environmental perception is critical for safe interaction with field workers and animals, obstacle detection, crop row guidance, surveying for variable rate applications, and situation awareness towards increased process automation
- The QUAD-AV project aims to develop a multi-sensory perception system that increases the ambient awareness of an agricultural vehicle operating in crop fields
- Onboard sensor technologies considered include stereovision, LIDAR, radar, and thermography
- A multi-sensory approach is necessary to increase accuracy and reliability when it comes to environmental perception for autonomous agricultural vehicles
- The QUAD-AV project proposes a solution by combining various sensors to create an ambient awareness system which can detect obstacles and differentiate between traversable and non-traversable areas autonomously
- This technology has great potential to revolutionize agriculture by improving productivity while ensuring safety for both workers and animals alike.

## Summary

The use of robotic technology in agriculture has been on the rise in recent years, with the aim of developing intelligent vehicles that can improve productivity and competitiveness. To address unsolved issues such as safe interaction with field workers and animals, obstacle detection in controlled traffic applications, crop row guidance, surveying for variable rate applications, and situation awareness towards increased process automation, accurate and robust environmental perception is a critical requirement. The Ambient Awareness for Autonomous Agricultural Vehicles (QUAD-AV) project aims to develop a multi-sensory perception system that increases the ambient awareness of an agricultural vehicle operating in crop fields. To achieve this objective, different onboard sensor technologies are considered including stereovision, LIDAR, radar, and thermography. Novel methods for their combination are proposed to automatically detect obstacles and discern traversable from non-traversable areas. Experimental results obtained in agricultural contexts demonstrate the effectiveness of the proposed methods. The authors of this study - Giulio Reina, Annalisa Milella, Raphael Rouveure, Michael Nielsen, Rainer Worst and Morten R. Blas - highlight that given the variety of conditions that may be encountered in the field no single sensor exists that can guarantee reliable results in every scenario. Therefore a multi-sensory approach is necessary to increase accuracy and reliability when it comes to environmental perception for autonomous agricultural vehicles. The QUAD-AV project proposes a solution by combining various sensors to create an ambient awareness system which can detect obstacles and differentiate between traversable and non-traversable areas autonomously. This technology has great potential to revolutionize agriculture by improving productivity while ensuring safety for both workers and animals alike.