Navigating route planning for multiple vehicles in multifield agriculture with a fast hybrid algorithm
Optimisation of route planning is becoming increasingly valuable aspect in agriculture. This study focuses on Agricultural Route Planning (ARP) in multifield areas (with a specific entrance point), incorporating several heterogeneous agricultural machines. The aim of this research is to improve the...
Saved in:
| Published in: | Computers and electronics in agriculture Vol. 212; p. 108021 |
|---|---|
| Main Authors: | , |
| Format: | Journal Article |
| Language: | English |
| Published: |
Elsevier B.V
01.09.2023
|
| Subjects: | |
| ISSN: | 0168-1699, 1872-7107 |
| Online Access: | Get full text |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Optimisation of route planning is becoming increasingly valuable aspect in agriculture. This study focuses on Agricultural Route Planning (ARP) in multifield areas (with a specific entrance point), incorporating several heterogeneous agricultural machines. The aim of this research is to improve the route planning of (semi-)autonomous machines by producing more efficient route plans. The problem sets of ARP contain both medium and large numbers of tracks consisting of irregular and rectangular fields. This research proposes a Fast Hybrid Algorithm (FHA) to address this problem. FHA incorporates various combinatorial operators into its structure. The experimental results demonstrate that, compared to Tabu Search, (Improved) Genetic Algorithm and Ant Colony Optimisation, FHA can reduce the distance travelled by an average of 16.21%. Furthermore, the efficiency of FHA is also reflected in its running time, which saves up to 54.23% compared to the other methods.
•A new and fast hybrid algorithm (FHA) is developed for agricultural route planning.•The problem includes multiple fields with barriers and heterogeneous machines.•FHA reduced runtime while maintaining a minimal nonworking distance in the field. |
|---|---|
| Bibliography: | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 23 |
| ISSN: | 0168-1699 1872-7107 |
| DOI: | 10.1016/j.compag.2023.108021 |