Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Advanced techniques and applications of LiDAR Place Recognition in Agricultural Environments: A Comprehensive Survey

Judith Vilella-Cantos, Mónica Ballesta, David Valiente, María Flores, Luis Payá

TL;DR

This paper addresses the challenge of reliable localization for autonomous agricultural robots in unstructured, GNSS-denied fields. It surveys LiDAR-based place recognition (LPR) and related DL and handcrafted methods, contrasting them with vision-based approaches and highlighting the role of semantic cues. It reviews agricultural-specific datasets and evaluation metrics, and analyzes limitations, especially cross-season robustness and feature scarcity. The work underscores the need for specialized datasets, robust representations, and future research directions to enable practical field autonomy.

Abstract

An optimal solution to the localization problem is essential for developing autonomous robotic systems. Apart from autonomous vehicles, precision agriculture is one of the elds that can bene t most from these systems. Although LiDAR place recognition is a widely used technique in recent years to achieve accurate localization, it is mostly used in urban settings. However, the lack of distinctive features and the unstructured nature of agricultural environments make place recognition challenging. This work presents a comprehensive review of state-of-the-art the latest deep learning applications for agricultural environments and LPR techniques. We focus on the challenges that arise in these environments. We analyze the existing approaches, datasets, and metrics used to evaluate LPR system performance and discuss the limitations and future directions of research in this eld. This is the rst survey that focuses on LiDAR based localization in agricultural settings, with the aim of providing a thorough understanding and fostering further research in this specialized domain.

Advanced techniques and applications of LiDAR Place Recognition in Agricultural Environments: A Comprehensive Survey

TL;DR

This paper addresses the challenge of reliable localization for autonomous agricultural robots in unstructured, GNSS-denied fields. It surveys LiDAR-based place recognition (LPR) and related DL and handcrafted methods, contrasting them with vision-based approaches and highlighting the role of semantic cues. It reviews agricultural-specific datasets and evaluation metrics, and analyzes limitations, especially cross-season robustness and feature scarcity. The work underscores the need for specialized datasets, robust representations, and future research directions to enable practical field autonomy.

Abstract

An optimal solution to the localization problem is essential for developing autonomous robotic systems. Apart from autonomous vehicles, precision agriculture is one of the elds that can bene t most from these systems. Although LiDAR place recognition is a widely used technique in recent years to achieve accurate localization, it is mostly used in urban settings. However, the lack of distinctive features and the unstructured nature of agricultural environments make place recognition challenging. This work presents a comprehensive review of state-of-the-art the latest deep learning applications for agricultural environments and LPR techniques. We focus on the challenges that arise in these environments. We analyze the existing approaches, datasets, and metrics used to evaluate LPR system performance and discuss the limitations and future directions of research in this eld. This is the rst survey that focuses on LiDAR based localization in agricultural settings, with the aim of providing a thorough understanding and fostering further research in this specialized domain.
Paper Structure (33 sections, 10 equations, 9 figures, 4 tables)

This paper contains 33 sections, 10 equations, 9 figures, 4 tables.

Table of Contents

  1. Introduction
  2. Scope of the survey
  3. Organization of the survey
  4. Agricultural deep learning applications
  5. Fields of application
  6. Precision agriculture
  7. Autonomous agricultural vehicles
  8. Crop monitoring
  9. Phenotyping
  10. Pruning and spraying
  11. Localization in agricultural settings
  12. Vision-based methods
  13. LiDAR-based methods
  14. Semantic information
  15. Specific challenges
  16. ...and 18 more sections

Figures (9)

  • Figure 1: Evolution of trends related to precision agriculture. Source: Karunathilake et al. karunathilake2023path.
  • Figure 2: Autonomous agricultural vehicle operating in a orchard environment. Source: Washinton State University washington2023agricultural.
  • Figure 3: Example of 4D registration in the 3D phenotyping method proposed in chebrolu2021registration using LiDAR data from the Pheno4D dataset schunck2021pheno4d.
  • Figure 4: Autonomous pruning robot operating in a vineyard environment proposed by Williams et al. williams2023modelling.
  • Figure 5: Autonomous spraying robot operating in a tobacco field proposed by Nasir et al. nasir2023precision.
  • ...and 4 more figures