Wi-Fi and satellite-based location techniques for intelligent agricultural machinery controlled by a human operator.

Slobodanka Tomic,Domagoj Drenjanac,Manuel Perez-Ruiz,Juan Agüera

doi:10.3390/s141019767

Slobodanka Tomic, Domagoj Drenjanac + Show 2 more

Open Access

https://doi.org/10.3390/s141019767

Copy DOI

Abstract

In the new agricultural scenarios, the interaction between autonomous tractors and a human operator is important when they jointly perform a task. Obtaining and exchanging accurate localization information between autonomous tractors and the human operator, working as a team, is a critical to maintaining safety, synchronization, and efficiency during the execution of a mission. An advanced localization system for both entities involved in the joint work, i.e., the autonomous tractors and the human operator, provides a basis for meeting the task requirements. In this paper, different localization techniques for a human operator and an autonomous tractor in a field environment were tested. First, we compared the localization performances of two global navigation satellite systems’ (GNSS) receivers carried by the human operator: (1) an internal GNSS receiver built into a handheld device; and (2) an external DGNSS receiver with centimeter-level accuracy. To investigate autonomous tractor localization, a real-time kinematic (RTK)-based localization system installed on autonomous tractor developed for agricultural applications was evaluated. Finally, a hybrid localization approach, which combines distance estimates obtained using a wireless scheme with the position of an autonomous tractor obtained using an RTK-GNSS system, is proposed. The hybrid solution is intended for user localization in unstructured environments in which the GNSS signal is obstructed. The hybrid localization approach has two components: (1) a localization algorithm based on the received signal strength indication (RSSI) from the wireless environment; and (2) the acquisition of the tractor RTK coordinates when the human operator is near the tractor. In five RSSI tests, the best result achieved was an average localization error of 4 m. In tests of real-time position correction between rows, RMS error of 2.4 cm demonstrated that the passes were straight, as was desired for the autonomous tractor. From these preliminary results, future work will address the use of autonomous tractor localization in the hybrid localization approach.

Highlights

With the advent of semiconductor technology and the associated development of embedded controls and sensing technologies, agricultural equipment manufacturers have focused on reducing the role of the human operator in the control loop
Due to the poor distance estimates produced by the use of radio signals for measuring the distance between nodes [8], we focus on the objective of providing a hybrid localization solution that combines distance estimates and real-time kinematic (RTK)
We analyzed existing localization techniques for mobile users and autonomous tractors collaborating in unstructured environments while performing complex agricultural tasks

Summary

Introduction

With the advent of semiconductor technology and the associated development of embedded controls and sensing technologies, agricultural equipment manufacturers have focused on reducing the role of the human operator in the control loop. Satellite-based localization approaches have become matured, and numerous applications in agriculture and forestry in developed countries have taken advantage of the centimeter-level accuracy and precision of global navigation satellite systems (GNSS) receivers. GNSS receivers are a key element in precision agriculture technologies (e.g., precision planting systems) and autonomous agricultural vehicles (e.g., system that integrate inertial sensors with GNSS capability for vehicle automation) because position information is a prerequisite for site-specific crop management [1,2]. To guarantee the achievement of high mission standards, autonomous vehicle control is combined with complementary human operator interaction. Two navigation approaches have become essential for intelligent vehicles systems: combining local information with global localization to enhance autonomous navigation and integrating inertial system information with real-time kinematic (RTK)-GNSS data for vehicle automation [2,5]

Objectives

Methods

Results

Conclusion